Company

Explore resources related to company to help implement AI solutions for your business.

reddit

0

1

rezi_io•This week

I am the founder of a b2c saas - organically scaled to $2M ARR, 1.9M users. Started company when I was 22, moved to Korea, built it here over 9 years. Ask me anything

It's 12:05am on Saturday morning and I just had some coffee so I'd like to take this time to talk with the startup subreddit on my journey building a b2c saas company. Specifically on the topics of growth, product, investment/governance, or strategy. For what we are, we are the most popular AI resume builder these days - the story of the company is a bit unique since I started it as a college graduate, then moved to Korea, where I was able to turn the idea in a scaling startup via government programs and Korean VCs. These days our traction shows that we are doing a few things right. I'm happy to share any knowledge or experiences I've gained over this time! Metrics: ARR - 2M Users - 1.9M Employees - 10

#reddit#founder#saas

reddit

0

0

MudResponsible3029•This week

Enterprise folks how are you implementing AI in your company? Any success cases?

Curious to hear how you’re currently implementing AI company-wide? Use-cases, workflows, et al. We are on the path to adopting AI-enabled workflows across different departments, from sales and marketing to operations (eg. extracting data via IoT, generating reports, implementing custom AI chatbots, etc.) Also, we’re looking into custom AI solutions as opposed to going the generic route (OpenAi et al.) From what we’ve looked into, despite seemingly convenient, closed-source models (OpenAI and other competitors) lack certain capabilities that can quickly become a headache for enterprise adoption. Compliance, customization, fine-tuning, and systems integration, in particular, have all been a bottleneck with the ChatGPT's of the world. We’re looking into several custom AI solution providers that can meet our budget, compliance requirements, and timelines. Bigger firms (BCG, et al.) tend to charge a “reputational” premium and the onboarding process is an absolute nightmare from what I’ve heard. As an alternative, we're currently considering implementing custom AI solutions via multimodal. dev. Thoughts on this? Also how are you implementing AI in your company?

#reddit#enterprise#folks

reddit

0

1

mark1x12110•This week

How is ML/AI implemented in your company?

Hi, I am currently working as a full time SWE. I generally get to work with data/build solutions using data but I don't have any official ML/Data science title or background. Ideally, I'd like to be able to start making more intelligent decisions using that data and that's why I am interested on machine learning. Ideally, I'd like to write production systems that leverage models that I can build and understand end to end but after some research, I am not sure if such jobs exist today or if teams are usually split between modelling team (people that only train and analyze models) and SWE teams (people that take such models and focus on deploying them on production). My current company is using that model of development, so I might need to leave to be able to do what I want. I imagine startups work that way, but I am looking for some stability. Thanks!

#reddit#ml/ai#implemented

reddit

0

1

AssistanceOk2217•This week

How I Built A Simple ‘BPO’ Company, All AI Employees (All Local)

Disrupting the BPO Industry: My Journey Building a Fully Automated Company with AI Employees Full Article : https://medium.com/@learn-simplified/how-i-built-a-simple-bpo-company-all-ai-employees-all-local-631e48fa908a ​ https://preview.redd.it/htjo1mancl2d1.png?width=1586&format=png&auto=webp&s=7e77f4c66e5ca55a8b0ea6969c43a458503ad921 ● What Are We Doing Today? We are building a BPO (Business Process Outsourcing) call center for an imaginary electric company called "Aniket Very General Electric Company". We will create different departments staffed by AI agents who can chat (and eventually speak in next part) with customers to answer questions, handle complaints, or provide services. ● Why Should You Read This Article? Learning how to build AI agents that can do tasks in real setting, co ordinate w/ human, AI, providing technical support will be a highly valuable skill. ● How Are We Going to Build Our All AI Employees Company? ○ We will explain what BPO and call centers are. ○ Our AI company will have departments like Customer Service, Tech Support, Billing & Payments, Outage Management, and Onboarding Customers. ○ We will use Docker containers to run the Dify AI platform as the base. ○ The AI agents will use the LLaMA-3 language model from Meta AI. ○ We may use Groq's AI accelerator chip to make LLaMA-3 faster. ○ Each department will have a knowledge base of text files that the AI agents can reference. ● Let's Get Cooking! This section provides setup instructions for installing Docker, Ollama (for running LLaMA-3), and the Dify AI platform. It also outlines the different AI agents we will create for departments like Reception, Customer Service, Billing, Tech Support, etc. ● Let's Design our Organization ○ We explain how each department's AI agents will have their own knowledge base, like an employee handbook. ○ The knowledge bases will contain policies, procedures, and other key information. ○ The AI agents can quickly reference this information to provide accurate and knowledgeable responses. ● Let's Meet Our AI Employees ○ We chose the LLaMA-3 70B model as the base for all AI agents across departments. ○ We give the AI agents customized prompts to define their personalities and roles. ○ The knowledge bases act as training materials tailored to each department. ○ In the future, AI agents could have additional tools like ticket systems and integrations. ● Let's Run Our BPO Organization Now that the AI workforce and knowledge bases are ready, we can open our BPO company and have the AI agents start handling customer inquiries across different departments like billing, tech support, outages, and new connections. ● Debugging This section highlights the importance of debugging, showing traces of how the language model understands customer queries and retrieves relevant context from knowledge bases to provide good responses. ● Future Work ○ Scale up to handle more customers using cloud services or distributed computing. ○ Move AI agents and knowledge bases to the cloud for accessibility and maintenance. ○ Fine-tune language models for better performance in each department. ○ Use scalable vector databases for faster knowledge retrieval. ○ Enable voice interfaces and computer vision for more natural interactions. ○ Implement continuous learning so AI agents can expand their knowledge over time. The article demonstrates the potential of building an actual AI-powered company and raises thought-provoking questions about the role of humans, ethics, and using AI to create a better world. ​

#reddit#built#simple

reddit

0

1

Agreeable_Release549•This week

I create customized report on implementing AI in your company

I create personalized reports on how to implement cutting-edge AI technology, specifically GPT-4, in your company to optimize everyday tasks, workflows and boost employee efficiency. Here's the deal: 🎯 I'm looking for businesses with 10-200 employees. 🎯 Your company receives customized reports on implementing AI to stay ahead of the competition. 🎯 In exchange, I'm looking for testimonials from founders like you! Why should you care? ✅ Improve productivity and efficiency within your organization. ✅ No risk on your side If you're interested in receiving your personalized report, comment below or send me a message!

#reddit#create#customized

reddit

0

0.6

AlexSnakeKing•This week

[Discussion] When ML and Data Science are the death of a good company: A cautionary tale.

TD;LR: At Company A, Team X does advanced analytics using on-prem ERP tools and older programming languages. Their tools work very well and are designed based on very deep business and domain expertise. Team Y is a new and ambitious Data Science team that thinks they can replace Team X's tools with a bunch of R scripts and a custom built ML platform. Their models are simplistic, but more "fashionable" compared to the econometric models used by Team X, and team Y benefits from the ML/DS moniker so leadership is allowing Team Y to start a large scale overhaul of the analytics platform in question. Team Y doesn't have the experience for such a larger scale transformation, and is refusing to collaborate with team X. This project is very likely going to fail, and cause serious harm to the company as a whole financially and from a people perspective. I argue that this is not just because of bad leadership, but also because of various trends and mindsets in the DS community at large. Update (Jump to below the line for the original story): Several people in the comments are pointing out that this just a management failure, not something due to ML/DS, and that you can replace DS with any buzz tech and the story will still be relevant. My response: Of course, any failure at an organization level is ultimately a management failure one way or the other. Moreover, it is also the case that ML/DS when done correctly, will always improve a company's bottom line. There is no scenario where the proper ML solution, delivered at a reasonable cost and in a timely fashion, will somehow hurt the company's bottom line. My point is that in this case management is failing because of certain trends and practices that are specific to the ML/DS community, namely: The idea that DS teams should operate independently of tech and business orgs -- too much autonomy for DS teams The disregard for domain knowledge that seems prevalent nowadays thanks to the ML hype, that DS can be generalists and someone with good enough ML chops can solve any business problem. That wasn't the case when I first left academia for the industry in 2009 (back then nobody would even bother with a phone screen if you didn't have the right domain knowledge). Over reliance on resources who check all the ML hype related boxes (knows Python, R, Tensorflow, Shiny, etc..., has the right Coursera certifications, has blogged on the topic, etc...), but are lacking in depth of experience. DS interviews nowadays all seem to be: Can you tell me what a p-value is? What is elastic net regression? Show me how to fit a model in sklearn? How do you impute NAs in an R dataframe? Any smart person can look those up on Stackoverflow or Cross-Validated,.....Instead teams should be asking stuff like: why does portfolio optimization use QP not LP? How does a forecast influence a customer service level? When should a recommendation engine be content based and when should it use collaborative filtering? etc... (This is a true story, happening to the company I currently work for. Names, domains, algorithms, and roles have been shuffled around to protect my anonymity)  Company A has been around for several decades. It is not the biggest name in its domain, but it is a well respected one. Risk analysis and portfolio optimization have been a core of Company A's business since the 90s. They have a large team of 30 or so analysts who perform those tasks on a daily basis. These analysts use ERP solutions implemented for them by one the big ERP companies (SAP, Teradata, Oracle, JD Edwards,...) or one of the major tech consulting companies (Deloitte, Accenture, PWC, Capgemini, etc...) in collaboration with their own in house engineering team. The tools used are embarrassingly old school: Classic RDBMS running on on-prem servers or maybe even on mainframes, code written in COBOL, Fortran, weird proprietary stuff like ABAP or SPSS.....you get the picture. But the models and analytic functions were pretty sophisticated, and surprisingly cutting edge compared to the published academic literature. Most of all, they fit well with the company's enterprise ecosystem, and were honed based on years of deep domain knowledge.  They have a tech team of several engineers (poached from the aforementioned software and consulting companies) and product managers (who came from the experienced pools of analysts and managers who use the software, or poached from business rivals) maintaining and running this software. Their technology might be old school, but collectively, they know the domain and the company's overall architecture very, very well. They've guided the company through several large scale upgrades and migrations and they have a track record of delivering on time, without too much overhead. The few times they've stumbled, they knew how to pick themselves up very quickly. In fact within their industry niche, they have a reputation for their expertise, and have very good relations with the various vendors they've had to deal with. They were the launching pad of several successful ERP consulting careers.  Interestingly, despite dealing on a daily basis with statistical modeling and optimization algorithms, none of the analysts, engineers, or product managers involved describe themselves as data scientists or machine learning experts. It is mostly a cultural thing: Their expertise predates the Data Science/ML hype that started circa 2010, and they got most of their chops using proprietary enterprise tools instead of the open source tools popular nowadays. A few of them have formal statistical training, but most of them came from engineering or domain backgrounds and learned stats on the fly while doing their job. Call this team "Team X".  Sometime around the mid 2010s, Company A started having some serious anxiety issues: Although still doing very well for a company its size, overall economic and demographic trends were shrinking its customer base, and a couple of so called disruptors came up with a new app and business model that started seriously eating into their revenue. A suitable reaction to appease shareholders and Wall Street was necessary. The company already had a decent website and a pretty snazzy app, what more could be done? Leadership decided that it was high time that AI and ML become a core part of the company's business. An ambitious Manager, with no science or engineering background, but who had very briefly toyed with a recommender system a couple of years back, was chosen to build a data science team, call it team "Y" (he had a bachelor's in history from the local state college and worked for several years in the company's marketing org). Team "Y" consists mostly of internal hires who decided they wanted to be data scientists and completed a Coursera certification or a Galvanize boot camp, before being brought on to the team, along with a few of fresh Ph.D or M.Sc holders who didn't like academia and wanted to try their hand at an industry role. All of them were very bright people, they could write great Medium blog posts and give inspiring TED talks, but collectively they had very little real world industry experience. As is the fashion nowadays, this group was made part of a data science org that reported directly to the CEO and Board, bypassing the CIO and any tech or business VPs, since Company A wanted to claim the monikers "data driven" and "AI powered" in their upcoming shareholder meetings. In 3 or 4 years of existence, team Y produced a few Python and R scripts. Their architectural experience  consisted almost entirely in connecting Flask to S3 buckets or Redshift tables, with a couple of the more resourceful ones learning how to plug their models into Tableau or how to spin up a Kuberneties pod.  But they needn't worry: The aforementioned manager, who was now a director (and was also doing an online Masters to make up for his qualifications gap and bolster his chances of becoming VP soon - at least he now understands what L1 regularization is), was a master at playing corporate politics and self-promotion. No matter how few actionable insights team Y produced or how little code they deployed to production, he always had their back and made sure they had ample funding. In fact he now had grandiose plans for setting up an all-purpose machine learning platform that can be used to solve all of the company's data problems.  A couple of sharp minded members of team Y, upon googling their industry name along with the word "data science", realized that risk analysis was a prime candidate for being solved with Bayesian models, and there was already a nifty R package for doing just that, whose tutorial they went through on R-Bloggers.com. One of them had even submitted a Bayesian classifier Kernel for a competition on Kaggle (he was 203rd on the leaderboard), and was eager to put his new-found expertise to use on a real world problem. They pitched the idea to their director, who saw a perfect use case for his upcoming ML platform. They started work on it immediately, without bothering to check whether anybody at Company A was already doing risk analysis. Since their org was independent, they didn't really need to check with anybody else before they got funding for their initiative. Although it was basically a Naive Bayes classifier, the term ML was added to the project tile, to impress the board.  As they progressed with their work however, tensions started to build. They had asked the data warehousing and CA analytics teams to build pipelines for them, and word eventually got out to team X about their project. Team X was initially thrilled: They offered to collaborate whole heartedly, and would have loved to add an ML based feather to their already impressive cap. The product owners and analysts were totally onboard as well: They saw a chance to get in on the whole Data Science hype that they kept hearing about. But through some weird mix of arrogance and insecurity, team Y refused to collaborate with them or share any of their long term goals with them, even as they went to other parts of the company giving brown bag presentations and tutorials on the new model they created.  Team X got resentful: from what they saw of team Y's model, their approach was hopelessly naive and had little chances of scaling or being sustainable in production, and they knew exactly how to help with that. Deploying the model to production would have taken them a few days, given how comfortable they were with DevOps and continuous delivery (team Y had taken several months to figure out how to deploy a simple R script to production). And despite how old school their own tech was, team X were crafty enough to be able to plug it in to their existing architecture. Moreover, the output of the model was such that it didn't take into account how the business will consume it or how it was going to be fed to downstream systems, and the product owners could have gone a long way in making the model more amenable to adoption by the business stakeholders. But team Y wouldn't listen, and their leads brushed off any attempts at communication, let alone collaboration. The vibe that team Y was giving off was "We are the cutting edge ML team, you guys are the legacy server grunts. We don't need your opinion.", and they seemed to have a complete disregard for domain knowledge, or worse, they thought that all that domain knowledge consisted of was being able to grasp the definitions of a few business metrics.  Team X got frustrated and tried to express their concerns to leadership. But despite owning a vital link in Company A's business process, they were only \~50 people in a large 1000 strong technology and operations org, and they were several layers removed from the C-suite, so it was impossible for them to get their voices heard.  Meanwhile, the unstoppable director was doing what he did best: Playing corporate politics. Despite how little his team had actually delivered, he had convinced the board that all analysis and optimization tasks should now be migrated to his yet to be delivered ML platform. Since most leaders now knew that there was overlap between team Y and team X's objectives, his pitch was no longer that team Y was going to create a new insight, but that they were going to replace (or modernize) the legacy statistics based on-prem tools with more accurate cloud based ML tools. Never mind that there was no support in the academic literature for the idea that Naive Bayes works better than the Econometric approaches used by team X, let alone the additional wacky idea that Bayesian Optimization would definitely outperform the QP solvers that were running in production.  Unbeknownst to team X, the original Bayesian risk analysis project has now grown into a multimillion dollar major overhaul initiative, which included the eventual replacement of all of the tools and functions supported by team X along with the necessary migration to the cloud. The CIO and a couple of business VPs are on now board, and tech leadership is treating it as a done deal. An outside vendor, a startup who nobody had heard of, was contracted to help build the platform, since team Y has no engineering skills. The choice was deliberate, as calling on any of the established consulting or software companies would have eventually led leadership to the conclusion that team X was better suited for a transformation on this scale than team Y.  Team Y has no experience with any major ERP deployments, and no domain knowledge, yet they are being tasked with fundamentally changing the business process that is at the core of Company A's business. Their models actually perform worse than those deployed by team X, and their architecture is hopelessly simplistic, compared to what is necessary for running such a solution in production.  Ironically, using Bayesian thinking and based on all the evidence, the likelihood that team Y succeeds is close to 0%. At best, the project is going to end up being a write off of 50 million dollars or more. Once the !@#$!@hits the fan, a couple of executive heads are going to role, and dozens of people will get laid off. At worst, given how vital risk analysis and portfolio optimization is to Company A's revenue stream, the failure will eventually sink the whole company. It probably won't go bankrupt, but it will lose a significant portion of its business and work force. Failed ERP implementations can and do sink large companies: Just see what happened to National Grid US, SuperValu or Target Canada.  One might argue that this is more about corporate disfunction and bad leadership than about data science and AI. But I disagree. I think the core driver of this debacle is indeed the blind faith in Data Scientists, ML models and the promise of AI, and the overall culture of hype and self promotion that is very common among the ML crowd.  We haven't seen the end of this story: I sincerely hope that this ends well for the sake of my colleagues and all involved. Company A is a good company, and both its customers and its employees deserver better. But the chances of that happening are negligible given all the information available, and this failure will hit my company hard.

#reddit#[discussion]#data

reddit

0

0.6

AlexSnakeKing•This week

[Discussion] When ML and Data Science are the death of a good company: A cautionary tale.

TD;LR: At Company A, Team X does advanced analytics using on-prem ERP tools and older programming languages. Their tools work very well and are designed based on very deep business and domain expertise. Team Y is a new and ambitious Data Science team that thinks they can replace Team X's tools with a bunch of R scripts and a custom built ML platform. Their models are simplistic, but more "fashionable" compared to the econometric models used by Team X, and team Y benefits from the ML/DS moniker so leadership is allowing Team Y to start a large scale overhaul of the analytics platform in question. Team Y doesn't have the experience for such a larger scale transformation, and is refusing to collaborate with team X. This project is very likely going to fail, and cause serious harm to the company as a whole financially and from a people perspective. I argue that this is not just because of bad leadership, but also because of various trends and mindsets in the DS community at large. Update (Jump to below the line for the original story): Several people in the comments are pointing out that this just a management failure, not something due to ML/DS, and that you can replace DS with any buzz tech and the story will still be relevant. My response: Of course, any failure at an organization level is ultimately a management failure one way or the other. Moreover, it is also the case that ML/DS when done correctly, will always improve a company's bottom line. There is no scenario where the proper ML solution, delivered at a reasonable cost and in a timely fashion, will somehow hurt the company's bottom line. My point is that in this case management is failing because of certain trends and practices that are specific to the ML/DS community, namely: The idea that DS teams should operate independently of tech and business orgs -- too much autonomy for DS teams The disregard for domain knowledge that seems prevalent nowadays thanks to the ML hype, that DS can be generalists and someone with good enough ML chops can solve any business problem. That wasn't the case when I first left academia for the industry in 2009 (back then nobody would even bother with a phone screen if you didn't have the right domain knowledge). Over reliance on resources who check all the ML hype related boxes (knows Python, R, Tensorflow, Shiny, etc..., has the right Coursera certifications, has blogged on the topic, etc...), but are lacking in depth of experience. DS interviews nowadays all seem to be: Can you tell me what a p-value is? What is elastic net regression? Show me how to fit a model in sklearn? How do you impute NAs in an R dataframe? Any smart person can look those up on Stackoverflow or Cross-Validated,.....Instead teams should be asking stuff like: why does portfolio optimization use QP not LP? How does a forecast influence a customer service level? When should a recommendation engine be content based and when should it use collaborative filtering? etc... (This is a true story, happening to the company I currently work for. Names, domains, algorithms, and roles have been shuffled around to protect my anonymity)  Company A has been around for several decades. It is not the biggest name in its domain, but it is a well respected one. Risk analysis and portfolio optimization have been a core of Company A's business since the 90s. They have a large team of 30 or so analysts who perform those tasks on a daily basis. These analysts use ERP solutions implemented for them by one the big ERP companies (SAP, Teradata, Oracle, JD Edwards,...) or one of the major tech consulting companies (Deloitte, Accenture, PWC, Capgemini, etc...) in collaboration with their own in house engineering team. The tools used are embarrassingly old school: Classic RDBMS running on on-prem servers or maybe even on mainframes, code written in COBOL, Fortran, weird proprietary stuff like ABAP or SPSS.....you get the picture. But the models and analytic functions were pretty sophisticated, and surprisingly cutting edge compared to the published academic literature. Most of all, they fit well with the company's enterprise ecosystem, and were honed based on years of deep domain knowledge.  They have a tech team of several engineers (poached from the aforementioned software and consulting companies) and product managers (who came from the experienced pools of analysts and managers who use the software, or poached from business rivals) maintaining and running this software. Their technology might be old school, but collectively, they know the domain and the company's overall architecture very, very well. They've guided the company through several large scale upgrades and migrations and they have a track record of delivering on time, without too much overhead. The few times they've stumbled, they knew how to pick themselves up very quickly. In fact within their industry niche, they have a reputation for their expertise, and have very good relations with the various vendors they've had to deal with. They were the launching pad of several successful ERP consulting careers.  Interestingly, despite dealing on a daily basis with statistical modeling and optimization algorithms, none of the analysts, engineers, or product managers involved describe themselves as data scientists or machine learning experts. It is mostly a cultural thing: Their expertise predates the Data Science/ML hype that started circa 2010, and they got most of their chops using proprietary enterprise tools instead of the open source tools popular nowadays. A few of them have formal statistical training, but most of them came from engineering or domain backgrounds and learned stats on the fly while doing their job. Call this team "Team X".  Sometime around the mid 2010s, Company A started having some serious anxiety issues: Although still doing very well for a company its size, overall economic and demographic trends were shrinking its customer base, and a couple of so called disruptors came up with a new app and business model that started seriously eating into their revenue. A suitable reaction to appease shareholders and Wall Street was necessary. The company already had a decent website and a pretty snazzy app, what more could be done? Leadership decided that it was high time that AI and ML become a core part of the company's business. An ambitious Manager, with no science or engineering background, but who had very briefly toyed with a recommender system a couple of years back, was chosen to build a data science team, call it team "Y" (he had a bachelor's in history from the local state college and worked for several years in the company's marketing org). Team "Y" consists mostly of internal hires who decided they wanted to be data scientists and completed a Coursera certification or a Galvanize boot camp, before being brought on to the team, along with a few of fresh Ph.D or M.Sc holders who didn't like academia and wanted to try their hand at an industry role. All of them were very bright people, they could write great Medium blog posts and give inspiring TED talks, but collectively they had very little real world industry experience. As is the fashion nowadays, this group was made part of a data science org that reported directly to the CEO and Board, bypassing the CIO and any tech or business VPs, since Company A wanted to claim the monikers "data driven" and "AI powered" in their upcoming shareholder meetings. In 3 or 4 years of existence, team Y produced a few Python and R scripts. Their architectural experience  consisted almost entirely in connecting Flask to S3 buckets or Redshift tables, with a couple of the more resourceful ones learning how to plug their models into Tableau or how to spin up a Kuberneties pod.  But they needn't worry: The aforementioned manager, who was now a director (and was also doing an online Masters to make up for his qualifications gap and bolster his chances of becoming VP soon - at least he now understands what L1 regularization is), was a master at playing corporate politics and self-promotion. No matter how few actionable insights team Y produced or how little code they deployed to production, he always had their back and made sure they had ample funding. In fact he now had grandiose plans for setting up an all-purpose machine learning platform that can be used to solve all of the company's data problems.  A couple of sharp minded members of team Y, upon googling their industry name along with the word "data science", realized that risk analysis was a prime candidate for being solved with Bayesian models, and there was already a nifty R package for doing just that, whose tutorial they went through on R-Bloggers.com. One of them had even submitted a Bayesian classifier Kernel for a competition on Kaggle (he was 203rd on the leaderboard), and was eager to put his new-found expertise to use on a real world problem. They pitched the idea to their director, who saw a perfect use case for his upcoming ML platform. They started work on it immediately, without bothering to check whether anybody at Company A was already doing risk analysis. Since their org was independent, they didn't really need to check with anybody else before they got funding for their initiative. Although it was basically a Naive Bayes classifier, the term ML was added to the project tile, to impress the board.  As they progressed with their work however, tensions started to build. They had asked the data warehousing and CA analytics teams to build pipelines for them, and word eventually got out to team X about their project. Team X was initially thrilled: They offered to collaborate whole heartedly, and would have loved to add an ML based feather to their already impressive cap. The product owners and analysts were totally onboard as well: They saw a chance to get in on the whole Data Science hype that they kept hearing about. But through some weird mix of arrogance and insecurity, team Y refused to collaborate with them or share any of their long term goals with them, even as they went to other parts of the company giving brown bag presentations and tutorials on the new model they created.  Team X got resentful: from what they saw of team Y's model, their approach was hopelessly naive and had little chances of scaling or being sustainable in production, and they knew exactly how to help with that. Deploying the model to production would have taken them a few days, given how comfortable they were with DevOps and continuous delivery (team Y had taken several months to figure out how to deploy a simple R script to production). And despite how old school their own tech was, team X were crafty enough to be able to plug it in to their existing architecture. Moreover, the output of the model was such that it didn't take into account how the business will consume it or how it was going to be fed to downstream systems, and the product owners could have gone a long way in making the model more amenable to adoption by the business stakeholders. But team Y wouldn't listen, and their leads brushed off any attempts at communication, let alone collaboration. The vibe that team Y was giving off was "We are the cutting edge ML team, you guys are the legacy server grunts. We don't need your opinion.", and they seemed to have a complete disregard for domain knowledge, or worse, they thought that all that domain knowledge consisted of was being able to grasp the definitions of a few business metrics.  Team X got frustrated and tried to express their concerns to leadership. But despite owning a vital link in Company A's business process, they were only \~50 people in a large 1000 strong technology and operations org, and they were several layers removed from the C-suite, so it was impossible for them to get their voices heard.  Meanwhile, the unstoppable director was doing what he did best: Playing corporate politics. Despite how little his team had actually delivered, he had convinced the board that all analysis and optimization tasks should now be migrated to his yet to be delivered ML platform. Since most leaders now knew that there was overlap between team Y and team X's objectives, his pitch was no longer that team Y was going to create a new insight, but that they were going to replace (or modernize) the legacy statistics based on-prem tools with more accurate cloud based ML tools. Never mind that there was no support in the academic literature for the idea that Naive Bayes works better than the Econometric approaches used by team X, let alone the additional wacky idea that Bayesian Optimization would definitely outperform the QP solvers that were running in production.  Unbeknownst to team X, the original Bayesian risk analysis project has now grown into a multimillion dollar major overhaul initiative, which included the eventual replacement of all of the tools and functions supported by team X along with the necessary migration to the cloud. The CIO and a couple of business VPs are on now board, and tech leadership is treating it as a done deal. An outside vendor, a startup who nobody had heard of, was contracted to help build the platform, since team Y has no engineering skills. The choice was deliberate, as calling on any of the established consulting or software companies would have eventually led leadership to the conclusion that team X was better suited for a transformation on this scale than team Y.  Team Y has no experience with any major ERP deployments, and no domain knowledge, yet they are being tasked with fundamentally changing the business process that is at the core of Company A's business. Their models actually perform worse than those deployed by team X, and their architecture is hopelessly simplistic, compared to what is necessary for running such a solution in production.  Ironically, using Bayesian thinking and based on all the evidence, the likelihood that team Y succeeds is close to 0%. At best, the project is going to end up being a write off of 50 million dollars or more. Once the !@#$!@hits the fan, a couple of executive heads are going to role, and dozens of people will get laid off. At worst, given how vital risk analysis and portfolio optimization is to Company A's revenue stream, the failure will eventually sink the whole company. It probably won't go bankrupt, but it will lose a significant portion of its business and work force. Failed ERP implementations can and do sink large companies: Just see what happened to National Grid US, SuperValu or Target Canada.  One might argue that this is more about corporate disfunction and bad leadership than about data science and AI. But I disagree. I think the core driver of this debacle is indeed the blind faith in Data Scientists, ML models and the promise of AI, and the overall culture of hype and self promotion that is very common among the ML crowd.  We haven't seen the end of this story: I sincerely hope that this ends well for the sake of my colleagues and all involved. Company A is a good company, and both its customers and its employees deserver better. But the chances of that happening are negligible given all the information available, and this failure will hit my company hard.

#reddit#[discussion]#data

reddit

0

1

Efficient-Proof-1824•This week

[D] if your company is ingesting work emails and chats for AI/ML pipelines, is there concern around sensitive business info getting out?

Edit: to be more specific - around sensitive raw data/metadata being dumped in system logs and accidentally viewed by an insider Hi folks Firstly full disclosure I’m the CEO of DataFog (www.datafog.ai). This is NOT a sales pitch but rather an interest in hearing what the community thinks about the overall issue which I believe will ultimately be solved via an ML-based implementation. My contention is: Generative AI has catalyzed widespread practice of ingesting email and work chat content to power AI training and inference this introduces a risk of content concerning confidential corporate affairs\ that can pass most privacy filters This results in Raw data alluding to sensitive business events flowing in freely for easy accidental unauthorized access by an internal - like MLOps - user My second contention is that the current security tools may not offer adequate coverage for what will be an evolving ongoing need that run of the mill PII redactors can’t account for. Take this statement which might easily be found in the inbox of the C-Suite for one of these two companies under “CiscoAcqPR\_Draft.docx” or the like: Cisco offered $157 in cash for each share of Splunk, representing a 31% premium to the company's last closing price. I myself have run various merger docs and legal filings through some standard PII tools and all of them fail to redact mention of deal terms. ~~A model training on phrases like “ $157 in cash per share” could have negative downstream inferential consequences or~~ if viewed accidentally by someone internally without the right access privileges How’re you all thinking about this problem? Custom recognizers are a common option like what you see with Microsoft Presidio but I’ve heard from some that maintaining those can be a PITA. At big companies this has been solved through internal tooling. \*more than Personally Identifiable Information (PII), HIPAA, or customer transaction data. It’s about those emails the CEO has sent to the Board of Directors in the midst of a corporate crisis, or the email thread between the C-Suite regarding an upcoming Earnings Call, or the market-moving announcement in the works regarding a merger with a competitor. In other words, Non-PII content that still needs to be redacted.

#reddit#your#company

reddit

0

0.778

wutangsam•This week

12 months ago, I was unemployed. Last week my side hustle got acquired by a $500m fintech company

I’ve learned so much over the years from this subreddit. I thought I’d return the favour and share some of my own learnings. In November 2020 my best friend and I had an idea. “What if we could find out which stocks the Internet is talking about?” This formed the origins of Ticker Nerd. 9 months later we sold Ticker Nerd to Finder (an Australian fintech company valued at around $500m). In this post, I am going to lay out how we got there. How we came up with the idea First off, like other posts have covered - you don’t NEED a revolutionary or original idea to build a business. There are tonnes of “boring” businesses making over 7 figures a year e.g. law firms, marketing agencies, real estate companies etc. If you’re looking for an exact formula to come up with a great business idea I’m sorry, but it doesn’t exist. Finding new business opportunities is more of an art than a science. Although, there are ways you can make it easier to find inspiration. Below are the same resources I use for inspiration. I rarely ever come up with ideas without first searching one of the resources below for inspiration: Starter Story Twitter Startup Ideas My First Million Trends by the Hustle Trends VC To show how you how messy, random and unpredictable it can be to find an idea - let me explain how my co-founder and I came up with the idea for Ticker Nerd: We discovered a new product on Twitter called Exploding Topics. It was a newsletter that uses a bunch of software and algorithms to find trends that are growing quickly before they hit the mainstream. I had recently listened to a podcast episode from My First Million where they spoke about Motley Fool making hundreds of millions from their investment newsletters. We asked ourselves what if we could build a SaaS platform similar to Exploding Topics but it focused on stocks? We built a quick landing page using Carrd + Gumroad that explained what our new idea will do and included a payment option to get early access for $49. We called it Exploding Stock (lol). We shared it around a bunch of Facebook groups and subreddits. We made $1,000 in pre-sales within a couple days. My co-founder and I can’t code so we had to find a developer to build our idea. We interviewed a bunch of potential candidates. Meanwhile, I was trawling through Wall Street Bets and found a bunch of free tools that did roughly what we wanted to build. Instead of building another SaaS tool that did the same thing as these free tools we decided to pivot from our original idea. Our new idea = a paid newsletter that sends a weekly report that summarises 2 of the best stocks that are growing in interest on the Internet. We emailed everyone who pre-ordered access, telling them about the change and offered a full refund if they wanted. tl;dr: We essentially combined two existing businesses (Exploding Topics and Motley Fool) and made it way better. We validated the idea by finding out if people will actually pay money for it BEFORE we decided to build it. The idea we started out with changed over time. How to work out if your idea will actually make money It’s easy to get hung up on designing the logo or choosing the perfect domain name for your new idea. At this stage none of that matters. The most important thing is working out if people will pay money for it. This is where validation comes in. We usually validate ideas using Carrd. It lets you build a simple one page site without having to code. The Ticker Nerd site was actually built using a Carrd template. Here’s how you can do it yourself (at a high level): Create a Carrd pro account (yes it's a $49 one off payment but you’ll get way more value out of it). Buy a cheap template and send it to your Carrd account. You can build your own template but this will save you a lot of time. Once the template reaches your Carrd account, duplicate it. Leave the original so it can be duplicated for other ideas. Jump onto Canva (free) and create a logo using the free logos provided. Import your logo. Add copy to the page that explains your idea. Use the AIDA formula. Sign up to Gumroad (free) and create a pre-sale campaign. Create a discounted lifetime subscription or version of the product. This will be used pre-sales. Add the copy from the site into the pre-sale campaign on Gumroad. Add a ‘widget’ to Carrd and connect it to Gumroad using the existing easy integration feature. Purchase a domain name. Connect it to Carrd. Test the site works. Share your website Now the site is ready you can start promoting it in various places to see how the market reacts. An easy method is to find relevant subreddits using Anvaka (Github tool) or Subreddit Stats. The Anvaka tool provides a spider map of all the connected subreddits that users are active in. The highlighted ones are most relevant. You can post a thread in these subreddits that offer value or can generate discussion. For example: ‘I’m creating a tool that can write all your copy, would anyone actually use this?’ ‘What does everything think of using AI to get our copy written faster?’ ‘It’s time to scratch my own itch, I’m creating a tool that writes marketing copy using GPT-3. What are the biggest problems you face writing marketing copy? I’ll build a solution for it’ Reddit is pretty brutal these days so make sure the post is genuine and only drop your link in the comments or in the post if it seems natural. If people are interested they’ll ask for the link. Another great place to post is r/entrepreuerridealong and r/business_ideas. These subreddits expect people to share their ideas and you’ll likely make some sales straight off the bat. I also suggest posting in some Facebook groups (related to your idea) as well just for good measure. Assess the results If people are paying you for early access you can assume that it’s worth building your idea. The beauty of posting your idea on Reddit or in Facebook groups is you’ll quickly learn why people love/hate your idea. This can help you decide how to tweak the idea or if you should drop it and move on to the next one. How we got our first 100 customers (for free) By validating Ticker Nerd using subreddits and Facebook groups this gave us our first paying customers. But we knew this wouldn’t be sustainable. We sat down and brainstormed every organic strategy we could use to get traction as quickly as possible. The winner: a Product Hunt launch. A successful Product Hunt launch isn’t easy. You need: Someone that has a solid reputation and audience to “hunt” your product (essentially an endorsement). An aged Product Hunt account - you can’t post any products if your account is less than a week old. To be following relevant Product Hunt members - since they get notified when you launch a new product if they’re following you. Relationships with other builders and makers on Product Hunt that also have a solid reputation and following. Although, if you can pull it off you can get your idea in front of tens of thousands of people actively looking for new products. Over the next few weeks, I worked with my co-founder on connecting with different founders, indie hackers and entrepreneurs mainly via Twitter. We explained to them our plans for the Product Hunt launch and managed to get a small army of people ready to upvote our product on launch day. We were both nervous on the day of the launch. We told ourselves to have zero expectations. The worst that could happen was no one signed up and we were in the same position as we’re in now. Luckily, within a couple of hours Ticker Nerd was on the homepage of Product Hunt and in the top 10. The results were instant. After 24 hours we had around 200 people enter their payment details to sign up for our free trial. These signups were equal to around $5,800 in monthly recurring revenue. \-- I hope this post was useful! Drop any questions you have below and I’ll do my best to respond :)

#reddit#months#ago,

reddit

0

1

Millionaire_•This week

In 2018, I started an AI chatbot company...today, we have over 4000 paying customers and ChatGPT is changing EVERYTHING

Intro: 5 years ago, my co-founders and I ventured into the space of AI chatbots and started our first truly successful company. Never in a million years did I see myself in this business and we truly stumbled upon the opportunity by chance. Prior to that, we ran a successful lead generation business and questioned whether a simple ai chat product would increase our online conversions. Of the 3 co-founders, I was skeptical that it would, but the data was clear that we had something that really worked. We built a really simple MVP version of the product and gave it to some of our top lead buyers who saw even better conversion improvements on their own websites. In just a matter of weeks, a new business opportunity was born and a major pivot away from our lead generation business started. Our growth story: Startup growth is really interesting and in most cases, founders aren't really educated on what a typical growth curve looks like. While we hear about "hockey stick" growth curves, it's really atypical to actually see or experience this. From my experience, growth curves take place in a "stair curve". For example, you can scrap your way to a $100k run rate without much process or tracking. You can even get to $1 million ARR being super disorganized. As you start going beyond $1M ARR, things start to break and growth can flatten out while you put new processes and systems in place. Eventually you'll get to $2M or 3M with your new strategy and then things start breaking again. I've seen the process repeat itself and as you increase your ARR, the processes and systems become more difficult to work through...mainly because more people get involved and the product becomes more complex. When you do end up cracking the code in each step, the growth accelerates faster and faster before things start to break down and flatten out again. Without getting too much into the numbers, here were some of our initial levers for growth: Our first "stair" step was to leverage our existing customer base from our prior lead generation business. Having prior business relationships and a proven track record made it really simple to have conversations with people who already trusted us to try something new that we had to offer. Stair #2 was to build out a partner channel. Since our chat product involved a web developer or agency installing the chat on client sites, we partnered with these developers and agencies to leverage their already existing customer bases. We essentially piggy-backed off of their relationships and gave them a cut of the revenue. We built an internal partner tracking portal which took 6+ months, but it was well worth it. Stair #3 was our most expensive step, biggest headache, but added the most revenue. After COVID, we had and SDR/Account Executive sales team of roughly 30 people. It added revenue fast, but the payback periods were 12+ months so we had to cut back on this strategy after exhausting our universe of clients. Stair #4 involves a variety of paid advertisement strategies with product changes and the introduction of new onboarding features. We're in the middle of this stair and hope it's multiple years before things breakdown again. Don't give up I know it sounds really cliché, but the #1 indicator of success is doing the really boring stuff day in and day out and making incremental improvements. As the weeks, months, and years pass by, you will slowly gain domain expertise and start to see the gaps in the market that can set you apart from your competition. It's so hard for founders to stay focused and not get distracted so I would say it's equally as important to have co-founders who hold each other accountable on what your collective goals are. How GPT is changing everything I could write pages and pages about how GPT is going to change how the world operates, but I'll keep it specific to our business and chatbots. In 2021, we built an industry specific AI model that did a great job of classifying intents which allowed us to train future actions during a chat. It was a great advancement in our customer's industry at the time. With GPT integrated into our system, that training process that would take an employee hours to do, can be done in 5 minutes. The model is also cheaper than our own and more accurate. Because of these training improvements, we have been able to conduct research that is allowing us to leverage GPT models like no one else in the industry. This is both in the realm of chat and also training during onboarding. I really want to refrain from sharing our company, but if you are interested in seeing a model trained for your specific company or website, just PM me your link and I'll send you a free testing link with a model fully trained for your site to play around with. Where we are headed and the dangers of AI The level of advancement in AI is not terribly dangerous in its current state. I'm sure you've heard it before, but those who leverage the technology today will be the ones who get ahead. In the coming years, AI will inevitably replace a large percentage of human labor. This will be great for overall value creation and productivity for the world, but the argument that humans have always adapted and new jobs will be created is sadly not going to be as relevant in this case. As the possibility of AGI becomes a reality in the coming years or decades, productivity through AI will be off the charts. There is a major risk that human innovation and creative thinking will be completely stalled...human potential as we know it will be capped off and there will need to be major economic reform for displaced workers. This may not happen in the next 5 or 10 years, but you would be naïve not to believe the world we live in today will not be completely different in 20 to 30 years. Using AI to create deepfakes, fake voice agents, scam the unsuspecting, or exploit technical vulnerabilities are just a few other examples I could write about, but don't want to go into to much detail for obvious reasons. Concluding If you found the post interesting or you have any questions, please don't hesitate to ask. I'll do my best to answer whatever questions come from this! ​ \*EDIT: Wasn't expecting this sort of response. I posted this right before I went to sleep so I'll get to responding soon.

#reddit#2018,#started

reddit

0

0.778

wutangsam•This week

12 months ago, I was unemployed. Last week my side hustle got acquired by a $500m fintech company

I’ve learned so much over the years from this subreddit. I thought I’d return the favour and share some of my own learnings. In November 2020 my best friend and I had an idea. “What if we could find out which stocks the Internet is talking about?” This formed the origins of Ticker Nerd. 9 months later we sold Ticker Nerd to Finder (an Australian fintech company valued at around $500m). In this post, I am going to lay out how we got there. How we came up with the idea First off, like other posts have covered - you don’t NEED a revolutionary or original idea to build a business. There are tonnes of “boring” businesses making over 7 figures a year e.g. law firms, marketing agencies, real estate companies etc. If you’re looking for an exact formula to come up with a great business idea I’m sorry, but it doesn’t exist. Finding new business opportunities is more of an art than a science. Although, there are ways you can make it easier to find inspiration. Below are the same resources I use for inspiration. I rarely ever come up with ideas without first searching one of the resources below for inspiration: Starter Story Twitter Startup Ideas My First Million Trends by the Hustle Trends VC To show how you how messy, random and unpredictable it can be to find an idea - let me explain how my co-founder and I came up with the idea for Ticker Nerd: We discovered a new product on Twitter called Exploding Topics. It was a newsletter that uses a bunch of software and algorithms to find trends that are growing quickly before they hit the mainstream. I had recently listened to a podcast episode from My First Million where they spoke about Motley Fool making hundreds of millions from their investment newsletters. We asked ourselves what if we could build a SaaS platform similar to Exploding Topics but it focused on stocks? We built a quick landing page using Carrd + Gumroad that explained what our new idea will do and included a payment option to get early access for $49. We called it Exploding Stock (lol). We shared it around a bunch of Facebook groups and subreddits. We made $1,000 in pre-sales within a couple days. My co-founder and I can’t code so we had to find a developer to build our idea. We interviewed a bunch of potential candidates. Meanwhile, I was trawling through Wall Street Bets and found a bunch of free tools that did roughly what we wanted to build. Instead of building another SaaS tool that did the same thing as these free tools we decided to pivot from our original idea. Our new idea = a paid newsletter that sends a weekly report that summarises 2 of the best stocks that are growing in interest on the Internet. We emailed everyone who pre-ordered access, telling them about the change and offered a full refund if they wanted. tl;dr: We essentially combined two existing businesses (Exploding Topics and Motley Fool) and made it way better. We validated the idea by finding out if people will actually pay money for it BEFORE we decided to build it. The idea we started out with changed over time. How to work out if your idea will actually make money It’s easy to get hung up on designing the logo or choosing the perfect domain name for your new idea. At this stage none of that matters. The most important thing is working out if people will pay money for it. This is where validation comes in. We usually validate ideas using Carrd. It lets you build a simple one page site without having to code. The Ticker Nerd site was actually built using a Carrd template. Here’s how you can do it yourself (at a high level): Create a Carrd pro account (yes it's a $49 one off payment but you’ll get way more value out of it). Buy a cheap template and send it to your Carrd account. You can build your own template but this will save you a lot of time. Once the template reaches your Carrd account, duplicate it. Leave the original so it can be duplicated for other ideas. Jump onto Canva (free) and create a logo using the free logos provided. Import your logo. Add copy to the page that explains your idea. Use the AIDA formula. Sign up to Gumroad (free) and create a pre-sale campaign. Create a discounted lifetime subscription or version of the product. This will be used pre-sales. Add the copy from the site into the pre-sale campaign on Gumroad. Add a ‘widget’ to Carrd and connect it to Gumroad using the existing easy integration feature. Purchase a domain name. Connect it to Carrd. Test the site works. Share your website Now the site is ready you can start promoting it in various places to see how the market reacts. An easy method is to find relevant subreddits using Anvaka (Github tool) or Subreddit Stats. The Anvaka tool provides a spider map of all the connected subreddits that users are active in. The highlighted ones are most relevant. You can post a thread in these subreddits that offer value or can generate discussion. For example: ‘I’m creating a tool that can write all your copy, would anyone actually use this?’ ‘What does everything think of using AI to get our copy written faster?’ ‘It’s time to scratch my own itch, I’m creating a tool that writes marketing copy using GPT-3. What are the biggest problems you face writing marketing copy? I’ll build a solution for it’ Reddit is pretty brutal these days so make sure the post is genuine and only drop your link in the comments or in the post if it seems natural. If people are interested they’ll ask for the link. Another great place to post is r/entrepreuerridealong and r/business_ideas. These subreddits expect people to share their ideas and you’ll likely make some sales straight off the bat. I also suggest posting in some Facebook groups (related to your idea) as well just for good measure. Assess the results If people are paying you for early access you can assume that it’s worth building your idea. The beauty of posting your idea on Reddit or in Facebook groups is you’ll quickly learn why people love/hate your idea. This can help you decide how to tweak the idea or if you should drop it and move on to the next one. How we got our first 100 customers (for free) By validating Ticker Nerd using subreddits and Facebook groups this gave us our first paying customers. But we knew this wouldn’t be sustainable. We sat down and brainstormed every organic strategy we could use to get traction as quickly as possible. The winner: a Product Hunt launch. A successful Product Hunt launch isn’t easy. You need: Someone that has a solid reputation and audience to “hunt” your product (essentially an endorsement). An aged Product Hunt account - you can’t post any products if your account is less than a week old. To be following relevant Product Hunt members - since they get notified when you launch a new product if they’re following you. Relationships with other builders and makers on Product Hunt that also have a solid reputation and following. Although, if you can pull it off you can get your idea in front of tens of thousands of people actively looking for new products. Over the next few weeks, I worked with my co-founder on connecting with different founders, indie hackers and entrepreneurs mainly via Twitter. We explained to them our plans for the Product Hunt launch and managed to get a small army of people ready to upvote our product on launch day. We were both nervous on the day of the launch. We told ourselves to have zero expectations. The worst that could happen was no one signed up and we were in the same position as we’re in now. Luckily, within a couple of hours Ticker Nerd was on the homepage of Product Hunt and in the top 10. The results were instant. After 24 hours we had around 200 people enter their payment details to sign up for our free trial. These signups were equal to around $5,800 in monthly recurring revenue. \-- I hope this post was useful! Drop any questions you have below and I’ll do my best to respond :)

#reddit#months#ago,

reddit

0

0.75

Far-Amphibian3043•This week

Unmasking Fake Testimonials on a YC backed company

As developers, marketeers and builders, we often rely on trusted platforms to guide us in finding tools that meet our unique needs. Recently, I stumbled upon Overlap, a site marketed as a haven for collaboration tools. Its sleek interface and glowing testimonials initially convinced me I had found a gem. But as I dug deeper, I uncovered a jaw-dropping reality: their testimonials featured stock images, all of which were easily identified through a quick reverse image search. Even more shocking was the realization that Overlap is a Y Combinator-backed company—an organization renowned for nurturing some of the most innovative startups in the world. With significant funding at their disposal, the decision to cut corners with fake testimonials felt like a slap in the face to their user base. They could easily afford a robust testimonial platform, yet chose a path that undermined their credibility. As developers, marketeers and builders, we often rely on trusted platforms to guide us in finding tools that meet our unique needs. Recently, I stumbled upon Overlap, a site marketed as a haven for video AI tools. Its sleek interface and glowing testimonials initially convinced me I had found a gem. But as I dug deeper, I uncovered a jaw-dropping reality: their testimonials featured stock images, all of which were easily identified through a quick reverse image search. Even more shocking was the realization that Overlap is a Y Combinator-backed company—an organization renowned for nurturing some of the most innovative startups in the world. With significant funding at their disposal, the decision to cut corners with fake testimonials felt like a slap in the face to their user base. They could easily afford a robust testimonial platform, yet chose a path that undermined their credibility. A screenshot of Overlap's landing page https://preview.redd.it/zosmdl0v01ce1.png?width=1000&format=png&auto=webp&s=83ced4af92ca284486281f00b020f1f0114b4fcd This discovery was nothing short of a wake-up call. For a developer-focused website—an audience that prizes authenticity and technical precision above all else—faking testimonials with stock photos isn’t just misleading, it’s a catastrophic betrayal of trust. It left me questioning the integrity of their entire operation and serves as a stark reminder for businesses everywhere: your audience notices when you’re not authentic, and they won’t forgive it easily. Position of Fake Testimonials One of the stock images https://preview.redd.it/a7ugasrw01ce1.png?width=341&format=png&auto=webp&s=5261df741f1198a92e537f1e61640e7d6ec60a7f Lessons for Startup Founders and Developers This experience offers several critical lessons for startup founders and developers alike: Authenticity is Non-Negotiable: In a competitive market, trust and transparency can make or break your brand. Fake testimonials might provide a short-term boost, but the long-term damage to credibility far outweighs any temporary gains. Invest in Genuine Solutions: If you have the resources, like a Y Combinator-backed company, prioritize tools and practices that enhance authenticity. Platforms like RapidFeedback allow businesses to dynamically update reviews and manage feedback efficiently. Leverage Real User Feedback: Authentic testimonials not only build trust but also provide actionable insights into your product’s strengths and weaknesses. This feedback loop can be invaluable for refining and growing your business. Understand Your Audience: Developers value precision, integrity, and honesty. Catering to this audience requires a commitment to these principles in every aspect of your business. Let’s ensure that the tools we build and the businesses we run prioritize authenticity. In the long run, a commitment to transparency and user trust will always yield greater rewards than any shortcut could provide. Why Fake Testimonials Are a Problem Fake testimonials damage your brand in more ways than one: Loss of Credibility: Developers are a discerning audience. Trust is everything, and losing it can be catastrophic for your reputation. Hurt User Experience: Knowing a platform misrepresents itself makes users skeptical about its features and promises. Missed Opportunities: Genuine feedback can provide valuable insights for growth and improvement, which fake testimonials completely overlook. A Smarter Way: Authentic Testimonials with RapidFeedback This experience reminded me of why tools like RapidFeedback are invaluable. RapidFeedback helps businesses maintain authenticity by dynamically updating reviews and images in real time. Here’s why it stands out: Real-Time Updates: Reviews are fetched and displayed dynamically, ensuring they’re always up-to-date. Dashboard Management: Businesses can monitor and manage good vs. bad reviews from a centralized dashboard, enabling them to address concerns promptly. Authenticity Guaranteed: Dynamic updates ensure that testimonials reflect real users and their experiences, which builds trust and credibility. Lessons for Developers and Businesses If there’s one takeaway from my Overlap experience, it’s this: authenticity isn’t optional. Whether you’re building tools for developers or selling consumer products, your audience values transparency. Using tools like RapidFeedback ensures your business maintains trust while gaining actionable insights to grow. Let’s commit to prioritizing honesty in our work. Because in the end, authentic relationships with users are what truly drive success.

#reddit#unmasking#fake

reddit

0

1

Significant_Stable_7•This week

Best AI tools to help company productivity?

Hey guys! I recently did a big restructuring of my production company and moving away from smaller businesses ad’s and moving up to working with larger marketing agencies. My partner and I are brainstorming ways to automate or at least improve certain parts of our business as we also start to expand our team & to improve ease of labour as our turn around times tend to have to be pretty quick. The main things we’re looking to improve is in: • Sales/out reach strategy: we are constantly reaching out to new agencies in different parts of the world. I am already used to manually making a plan for each company we reach out to but it can be very time consuming. I don’t know if there is even a tool that could help with this haha. Even if it helps with pointers! • Organizing/visualizing spreadsheets: we deal with spreadsheets on what we spend per production and how we distribute our total budget per department. If there is anyway to ease the workflow for our managers and on top of that also allow us to expand easier without having to look for someone who is very efficient on excel or spending more time and money on the training. • Scheduling: We already have so much to organize day per day, im not sure if there is any tool or ai system that could help in regards to scheduling meetings, organizing priorities or even just deadlines for certain projects. Example: we need to schedule everything from pre production deadlines (meetings with talent, agency, and crew) production deadlines, & post production deadlines. I’m sure there is other small things I am missing but those are the three main things! There is just so many things i saw on the internet that are “ai powered” or “ai improved workflow” that all claim are the best or some just use chat gpt so its essentially all the same thing. I thought id ask on here to see if anyone has actually tried and could recommend some ai tools out there! Cheers,

#reddit#best#tools

reddit

0

1

TheHumanAnimal-•This week

Hello! Seeking essential advice regarding the desire to create an "AI". One that acts as a personal musical "Composer" in response to the individual users' emotional feedback. Company Name already created, as well as Trademark name for potential AI. However, I don't know where to start...

Title pretty much sums it up. With 0 background in computer science as well as no experience developing a company, I'm seeking professional advice (or personal) on the best approach to this potential business idea. Given the progression of Artificial Intelligence and its influence on the global population in modern day, I have now developed an interest in its potential. After creating a model for foundation, one which is relatively simple in nature, I took it upon to myself to embrace my lack of knowledge/interest in the science of AI and go directly to the source: ChatGPT. Unfortunately, I currently can't afford to engage with the "smartest model" of ChatGPT, but after discussing a plan of approach with the free OpenAI version, I was given a lot of valuable information that I most likely would have overwhelmed myself with independently. With that being said, I'm now looking to hear from individuals who have actual experience within the respective backgrounds. Any advice will help Questions: What does the development of an AI assistant require for foundation? Can it be built upon already established AI and will there require a level of knowledge regarding coding as well as the proper legal understanding of API usage? Should the focus be on app development or the AI tool specifically? What communities would you suggest, to seek individuals with the ability to bring an idea to fruition virtually? From a business perspective, given the lack of financial resources and significant model value, how would one communicate this idea to others to potentially become involved or invested? If I am asking the wrong question, feel free to advise. Any questions that require more information on the idea is welcomed.

#reddit#hello!#seeking

reddit

0

1

CoastOver6555•This week

Starting an Business Process Automation Company

I'm into working smarter because admittedly, I'm somewhat lazy. And because of that I came across a lot of tools that really boosts efficiency. I really find myself getting bored the same task iver and over again. That's how this idea was born. I feel like a lot of small businesses needs these tools to keep up with the times and also being more efficient. I'm not talking about AIs, I'm talking about no-code platforms that can connect/integrate other apps/services to one another using webhooks and APIs. What do you guys think about this?

#reddit#starting#business

reddit

0

1

totie2•This week

$1.2 MRR, should I do paid ads?

Hello, I launched a bootstrapped b2b SaaS end of last year and I've just hit 1.2k MRR. It's a 50-60% profit margin, so $600 are going to my pocket, I also do freelancing where most of my revenue comes from, that's about 3k monthly average. My project has essentially been stuck around this 1k MRR mark for months, I'm sticking to my strategy: Daily outreach on LinkedIn Weekly Post on LinkedIn (my company is a no code tool for building AI SEO & content workflows, so every week I share a new tool) Weekly Blog Post Reaching out to influencers/newsletter writers to see if they'd be willing to write about it. Now I'm thinking if I should set $500-$1000 monthly budget for paid ads, I'm primarily considering Google Ads and LinkedIn Ads. Essentially I'm wondering if 1.2k MRR a good point to start investing back into the company.

#reddit#$1.2#mrr,

reddit

0

1

DB010112•This week

Experienced Software Developer looking for startup to help. I will not promote

My passion for programming started at the age of 9 when I began playing video games. It was during this time that I first dived into programming, creating scripts for SA:MP (San Andreas Multiplayer) using the Pawn language. SA:MP is a modification for the popular game Grand Theft Auto: San Andreas, allowing players to experience multiplayer gameplay. My early experiences in programming were all about problem-solving—finding ways to enhance the game and improve the player experience. This was when I realized how satisfying it is to solve a problem through code, and that feeling has stayed with me throughout my career. I am a self-taught programmer, and everything I know today comes from my own initiative to learn and improve. After five years of working with local clients, I decided to expand my knowledge and started learning more widely applicable programming languages like Java and Python. I’ve always been the type of person who thrives on challenges. Whenever I encounter a problem, I don’t just look for a quick fix—I dive deep into researching and understanding the problem, and I find a solution that works in the long run. This is what drives me. The ability to solve problems, no matter how complex, and the satisfaction that comes with it is what fuels my passion for programming. My big break came when I had the opportunity to work at \\\\. There, I replaced two senior and two junior developers, which led to significant cost savings for the company. I completed all tasks ahead of schedule, focusing on Java-based applications that were multithreaded and communicated with embedded systems. This experience taught me how to work under pressure and how to manage and solve complex technical problems efficiently. Following my time at \\\\, I transitioned into freelance work as a FullStack Developer, working with technologies such as HTML, CSS, Bootstrap, JavaScript, Django, Spring, MySQL, and PostgreSQL. As a freelancer, I was responsible for finding solutions to a wide range of problems, often working independently and making decisions on the fly. I learned that self-reliance is key in this industry, and being resourceful is one of the most important qualities a developer can have. Later, I joined \\\\ elecom, where I worked on system integration with foreign teams, BPM process solutions, and the merging of complex systems in Oracle databases. I continued to solve challenges, often working with teams across borders and tackling technical obstacles that required creative and well-thought-out solutions. Eventually, I founded my own company, \\\\, where I focus on developing software solutions, Artificial Intelligence (AI), Cybersecurity, and Ethical Hacking. As an entrepreneur, I take pride in finding innovative solutions to problems, whether they come from clients or from technical obstacles I encounter along the way. I’ve also had the privilege of working with the Serbian Ministry of Defense and the police, handling sensitive projects that demand both technical expertise and trustworthiness. Being a self-taught programmer means that I have had to learn and adapt on my own, and I’ve learned to embrace challenges as opportunities for growth. I am constantly driven by the process of solving problems, and it is what keeps me engaged and fulfilled in my work. I am always open to new collaborations and am eager to take on new challenges that push my boundaries in technology, cybersecurity, and software development.

#reddit#experienced#software

reddit

0

0

JustZed32•This week

Technical founders - is "bulling" your way through learning right for a startup? [I will not promote]

Sup, This is a question for technical founders. \--a little backstory-- I am starting a company in AI field that creates something nobody has ever done before. 7 months in. \--- How most software companies are created - you have an improvement idea, then you have a thousand or so problems to solve to make that improvement happen, and for each one that you don't know, you go to Stackoverflow or ChatGPT to look for solutions for that problem. Which involves next-to-no upfront preparation because for vast majority of traditional software you can solve it on-the-go - "traditional" software is very easy compared to, say, mechanical, pharma or AI engineering. However, for more advanced disciplines - can you just "Google" it on-the-go? I'm a solo founder, and 8 months in, creating a foundational model, BECAUSE I did not know things upfront, I've wasted at least 3 months doing something which was mostly technically unviable in the first place. Out of 14000 lines of code that I've done (including tests), I had to scrap 10000 recently. Imagine the scale of it. Obviously I didn't even know how ML works when I've started. Major fuck-up. How do you operate in industries which you've done before? How do you determine that it's time to start creating you big technological leaps instead of continuing to learn? Cheers. Edit: No need to push me on business topics. I know how to create value very well. It's only a tech question, and I'm only asking because - well - to deliver my value, I need to do a lot of novel tech.

#reddit#technical#founders

reddit

0

1

stellarcitizen•This week

I fell into the builder's trap and need help getting out

Hi r/startups, First-time technical founder here. Two years ago, I decided to leave the 9-5 grind and build something meaningful. Now, I have (what I believe is) a brilliant technical solution but no clear business case. I’m seeking a cofounder with product and marketing expertise to help pivot my project into a viable business - or start a new one. Details below. About Me 36yo, born in Berlin and moved to San Francisco 8 years ago Master's in Software Engineering with 15 years of experience Worked with early-stage startups in Berlin and a venture studio in SF Spent the past years leading a team of 12 shipping enterprise software The tech I've built An AI engine that makes it easy for developers to automate their workflows. It works with code, issues, PRs and integrates with 3rd party systems like error trackers, wikis, ticketing systems, etc. It takes natural language instructions, fulfills them autonomously and responds with a result. The functionality is served as a platform, with an API and an SDK. On top of it, I've built a CLI and a web application with productivity tools for developers. Who and what I'm looking for My main goal is to leave my current job and build a company around a problem that matters to me, ideally with considerable equity. I’m looking for: A cofounder with product and marketing expertise who sees potential in my tech and can help turn it into a successful business—or someone with a strong business case who needs a technical founder. Mentorship from someone experienced in dev tool startups or as a successful solo founder. I’d love to learn from your journey and would be happy to offer my technical expertise or collaborate on projects in return. Happy to answer any questions or provide more details. Cheers!

#reddit#fell#into

reddit

0

0.6

wilschroter•This week

Anyone finding that they just don't NEED to add more Employees anymore? (I will not promote)

A friend of mine who was looking for work asked me if we were hiring and I responded "You know, it's weird but all of our growth goals don't seem to map back to hiring people anymore." This isn't about the economy or growth goals. It's a really fascinating shift in focus and costs for startups. My gut reaction is that I HATE the idea of not creating more jobs. In my career I've hired thousands of people, and I've always prided myself on job creation. We just sold a company that employed 200 people last year, and I'm proud of the work we were able to create. What's interesting is that I simply don't feel like we NEED to like we used to. As we're looking at all of our growth goals, for the first time I'm not assigning FTEs to them. Nearly everything we're doing is actually reducing the need for more humans, not adding them - and we're not even trying to reduce the need. Obviously the timing of AI has had a major impact. Product - Our team is shipping more code than ever before, and even our designers who have never touched code are shipping final code. If we doubled the size of the team, it would make no difference (this is a big deal considering the historical cost here). Marketing - So many aspects of our marketing are getting automated and streamlined, to the point where even a single FTE can create a massive amount of reach across channels. Support - Our Success team is able to effectively respond to tickets in a fraction of the time, which essentially doubles their capacity without adding any more staff. Management - With less staff we need less managers, which are a big expense, but it also means reporting and decisions are more streamlined, which is a positive. But it also means those positions simply don't get created like they used to. I think this is a big deal for the younger startups because it translates into needing less capital (or none!) which provides for more ownership and agency. Clearly we still need some folks to build out the core team, but that's very different than a massive staffing line item. Anyone else here finding the same trend? Opposite? I don't have a strong opinion either way, but I'd love to hear how other Founders are processing this.

#reddit#anyone#finding

reddit

0

1

xcitech•This week

What questions to ask to evaluate an offer from start up?

Hello! I am presently working working as a Data Scientist with a medium sized company. Last year my boss left the company to start his own. Very recently his non-solicitation clause expired, and he asked me to join his startup. While I know almost everything about the product idea, and the technical aspect of the startup - I have very less information on more critical points like funding, equity sharing, etc. He has made a verbal unofficial offer, and I have asked for a week to prepare my list of questions for him for me to be able to evaluate his offer. Since I have no knowledge of the startup scene, I would like some help regarding the questions I should put forward to him. Mentioned below are what I know so far and the offer: The company was started by two people, both working full time on it. I would be the third person on the team. The startup aims to introduce AI in a field which has lagged behind in the introduction of technology by at least 2 decades. The big players in this field are conservative, but now they are opening up towards embracing new technology. Personally I have confidence in their idea, and feel this will be a sustainable and profitable company. The offered salary is about 60% of what I make right now. The equity offered is 2%. I do not know the details of the funding they have received so far or the equity split. Any pointers in helping me frame my questions for the evaluation of the offer would be very helpful! Thank you

#reddit#questions#evaluate

reddit

0

1

juliannorton•This week

For anyone working on LLM / AI startups

My company (which I will not promote) wrote this blog post in compliance with rule #7 :) Introduction to fine-tuning Large Language Models, or LLMs, have become commonplace in the tech world. The number of applications that LLMs are revolutionizing is multiplying by the day — extraction use cases, chatbots, tools for creatives and engineers. In spite of this, at its core, the LLM is a multi-purpose neural network, dozens of layers deep, designed to simply predict one word after the next. It predicts words by performing billions of matrix multiplication steps based on so-called parameter weights, which are discovered during the model training process. Almost all open-source, open-weight models are trained on a massive amount of text from every conceivable genre and topic. How, then, do researchers and engineers create novel specialized applications? The answer is fine-tuning. In this post, we will demystify the process of fine-tuning and discuss the tradeoffs of other approaches to customizing an LLM. The history of fine-tuning In the ancient days of LLMs, by which we mean five years ago, the primary approaches to customizing an LLM was identical to the approaches to customizing any other deep learning model. A machine learning engineer would have two options: Retrain the entire LLM. This would mean discarding the trained weights and instead only using the open source model’s architecture to train it on a specialized dataset. As long as the amount and diversity of the specialized data is comparable to what the original model was trained on, this can be the ideal method of customizing a model. However, of course, this is a massive waste of resources due to the computational power required and the difficulty of collecting such a massive dataset. Even if an organization could provision enough GPUs, the cost of training modern-day models could cost up to $190 million. Retrain the last few layers of the LLM while keeping the rest of the weights frozen. This is a more efficient method in terms of time and computational power required because it significantly cuts down the number of parameters that need to be trained. However, for most tasks, this leads to subpar quality. Of course, almost everyone chooses to retrain the last few layers. And where there is only one option, the research community saw an opportunity to step in. Soon, the LLM space saw an enormous amount of activity in fine-tuning, which leads us to today. Modern approaches to fine-tuning Most fine-tuning approaches today are parameter-efficient. Deep neural networks are composed of matrices and vectors (generally called tensors), which are at their core arrays of floating point numbers. By training a small subset of these tensors, while the rest of the LLM’s weights are kept frozen, practitioners achieve good enough results without having to retrain the entire model. Generally, this method requires at least a hundred or so handcrafted examples of input-output pairs for fine-tuning. This is called supervised learning. The modern fine-tuning landscape involves an unsupervised learning step afterwards. Given a set of inputs, a practitioner gathers the various possible outputs from the LLM and casts votes among them. This preference data is then used to further train the LLM’s weights. Usually, this approach is used for LLM alignment and safety, which defends the application from malicious uses, outputs embarrassing to the organization, and prompt injection attacks. Fine-tuning’s relationship to prompt engineering A natural question arises: why fine-tune instead of crafting a well-considered system prompt? Wouldn’t that be easier and more efficient? The answer is no, it wouldn’t. Here’s why: Advanced techniques make prompt engineering obsolete: \[redacted\]'s product uses soft-prompting and other techniques to train the input layer itself. This obviates the need for prompt engineering entirely, which lets organizations avoid the time-consuming trial-and-error process to get the prompt just right. Prompt engineering has been a stopgap measure in the early days of LLM applications to convey the practitioner’s intent to the LLM. It is not the long-term solution for LLM application development. The system prompt is precious: the limited budget for system prompt length is better used for up-to-date information, e.g., Retrieval-Augmented Generation (RAG). Even as context windows increase in size with each new open-source model, the system prompt is the least efficient place to provide the LLM model with verbose instructions and examples. The longer the prompt, the slower the application: an LLM must attend to the entire system prompt for each token generated. This pain becomes more acute in the chatbot case, where the length of the conversation so far is also counted toward the system context. The longer the conversation, and the longer your beautifully-crafted system prompt, the slower the bot becomes. Even in cases where the model allows for system prompts that are millions of tokens long, doubling the size of the context will quadruple the latency. This means adding a few hundred words to the system prompt may result in several seconds of additional latency in production, making a chatbot impossible to use. Edge case handling: the number of edge cases that the system prompt would need to consider and emphasize to the LLM is too large. The instructions would have to be too nuanced and long to cover them all. However, fine-tuning on a dataset that considers these edge cases would be more straightforward. Do I need to fine-tune the LLM in my production application? Every LLM application in production must be fine-tuned often, not just once at the beginning. Why fine-tune? The world in which the application exists is constantly evolving. New prompt injection attacks are being discovered every day, new ways of embarrassing a chatbot are emerging constantly. This data can be used to further train an LLM model, which protects the application from new failure modes and reputational risk. Like any software, LLM models are constantly improving. Smarter and faster models are open-sourced all the time. For a new model to get deployed to production, it must first be finetuned on the specific dataset of the organization building the application. Fine-tuning does not add latency to LLM applications. Rather than a solution that sits in the middle of the LLM and the rest of the application, fine-tuning leverages the power of the LLM itself to increase the quality of the output. In fact, fine-tuning allows for shorter system prompts, which speeds up the average response generation time.

#reddit#anyone#working

reddit

0

0.5

AlmostARockstar•This week

Zero To One [Book Review]

If you don't feel like reading - check out the video here ##Introduction The more I read into Peter Thiel's background, the more ridiculous it seems.. He’s been involved in controversies over: Racism, Sexism, and, [Radical Right wing libertarianism.] (https://www.bloomberg.com/news/articles/2016-07-21/the-strange-politics-of-peter-thiel-trump-s-most-unlikely-supporter) He’s built a tech company that helps the NSA spy on the world. He supported Donald Trumps presidential campaign. He’s funding research on immortality And to top it off, he helped bankrupt online media company and blog network Gawker by funding Hulk Hogan’s sex tape lawsuit - after a report of his rumoured Homosexuality rattled his chain… Zero to One clearly reflects his unique attitude and doesn't pull any punches with a genuinely interesting point of view, that has clearly worked in the past, to the tune of almost 3 billion USD. But at times, his infatuation with the All American attitude is a little much…and, quite frankly, he’s not the kind of guy I could sit and have a pint with…without grinding my teeth anyway. The content is adapted from Blake Masters' lecture notes from Thiel's 2012 Stanford Course. This definitely helped keep the book concise and fast paced, at least compared to other books I’ve reviewed. The type of content is also quite varied, with a good spread from completely abstract theories — like the Technology vs. Globalisation concept, where the book get's it's title — to practical examples such as the analysis of personalities in chapter 14, "The Founders Paradox" covering Elvis Presley, Sean Parker, Lady Gaga and Bill Gates to name a few. ###Pros Monopolies To most people a monopoly is a negative thing. But while perfect competition can drive down costs and benefit the consumer - competition is bad for business. In fact, in Thiel's opinion, every startup should aim to be a monopoly or, as he puts it: Monopoly is the condition of every successful business. I like his honesty about it. While I’m not sure about the morality of encouraging monopolies at a large scale, I can see the benefit of thinking that way when developing a startup. When you're small, you can’t afford to compete. The best way to avoid competition is to build something nobody can compete with. The concept is summed up nicely at the end of chapter 3: Tolstoy opens Anna Karenina by observing: ‘All happy families are alike; each unhappy family is unhappy in its own way.’ Business is the opposite. All happy companies are different: each one earns a monopoly by solving a unique problem. All failed companies are the same: they failed to escape competition. Pareto The Pareto Law, which you might remember as the 80/20 rule in Tim Ferris’ The Four Hour Work Week, is often used synonymously with the power law of distribution, and shows up everywhere. Thiel refers to it in his section on The Power Law of Venture Capital. If Tim Ferris recommends identifying and removing the 20% of things that take 80% of your effort - Thiel recommends finding the 20% of investments that make 80% of your return. Anything else is a waste. Soberingly, he also suggests that the Pareto Law means: ...you should not necessarily start your own company, even if you are extraordinarily talented. But to me this seems more like a venture capitalists problem, than an entrepreneurs problem - Personally, I believe there’s far more benefit in starting up your own company that purely profit. ###Cons Man and machine? Content-wise, there is very little to dislike in this book. As long as you accept that the book is written specifically for startups - where anything short of exponential growth is considered a failure - it’s exceptionally on point. However, there are a couple sections dotted throughout the book where opinion and wild speculation began to creep in. Chapter 12 is a good example of this entitled: Man and Machine. It’s a short chapter, 12 pages in total, and Thiel essentially preaches and speculates about the impact of better technology and strong AI. I like to dog ear pages with interesting or useful content so I can come back later, but this entire chapter remains untouched. America, fuck yeah! It would be really difficult for a personality as pungent as Theil's to go entirely unnoticed in a book like this, and indeed it breaks through every now and then. I only had a feint idea of Thiel's personality before I read the book, but having read up on his background, I’m actually surprised the book achieves such a neutral, if pragmatic, tone. Pretty early on in the book however, we are introduced to Thiel's concept of Economic Optimism and quite frankly the whole of chapter 6 should have been printed on star spangled, red white and blue pages. I’m not necessarily against the egotistic American spirit but when Thiel writes, in relation to European Pessimism: the US treasury prints ‘in god we trust’ on the dollar; the ECB might as well print ‘kick the can down the road’ on the euro I can smell the bacon double cheese burgers, with those tiny little American flags from here. Ooh Rah! ###TL;DR (a.k.a: Conclusion) Overall, however, I really did enjoy this book and I can see myself coming back to it. Peter Thiel IS controversial, but he has also been undeniably successful with a career punctuated by bold business decisions. The ideas in the book reflect this mind set well. Yes, he backed Trump, be he also (sadly) backed the winner.

#reddit#zero#[book

reddit

0

1

uwalkirun•This week

Created the Shopify Alternative in a 3rd world country “I will not promote”

Built a Shopify alternative I’ve been a long-time follower of this subreddit and have always valued the insights shared here. Today, I’m reaching out to share our story and seek advice or guidance on potential next steps for our business. Four years ago, we set out to build a local e-commerce platform tailored to the unique challenges of operating in a third-world country where global solutions like Shopify fall short. Shopify, while a fantastic platform, doesn’t provide localized support or integrations here, and the costs of running a Shopify store are prohibitively high due to: The need for multiple apps to replicate basic functionality Expensive international support calls or long chat queues Higher payment gateway fees (no Shopify Pay) USD-only subscription payments, which incur additional bank conversion fees And more We built a solution that addresses these pain points, and today, we’re proud to have over 4,000 merchants on our platform, with 1,600+ paying customers. We’re processing over $1 million per month across 50,000+ orders, which translates to a significant impact in our local economy. As experienced founders, we’ve managed our financials meticulously, allowing us to thrive while many local competitors have shut down. However, scaling in our current economic climate has been challenging, and raising capital has proven to be incredibly tough. We’re exploring strategic options, including potential partnerships, acquisitions, or investments. For example, we believe our platform could be an attractive opportunity for a player like Shopify or another company looking to expand into emerging markets. I’m reaching out to this community to ask: Are there doors we haven’t knocked on? Are there opportunities or strategies we might be overlooking? Any advice, introductions, or insights would be immensely appreciated. Thank you for taking the time to read this, and I look forward to any feedback or ideas you might have! [post refined by AI]

#reddit#created#shopify

reddit

0

1

adriannelestrange•This week

I studied how 7 Founders found their first 100 customers for their businesses. Summarizing it here!

I am learning marketing, and so I combed through the internet to find specific advice that helped founders reach 100 users and not random Google answers. Here’s what I found: Llama Life by Marie Marie founder of Llama Life, a productivity app ($51.4K+ revenue) got her first 100 users using Snowballing effect. She shared great advice that I want to add here verbatim, “Need to think about what you have that you can leverage based on your current situation. eg..When you have no customers, think about where you can post to get the 1st customer eg Product Hunt. If you do well on PH, say you get #3 product of the day, then you post somewhere else saying ‘I got #3 product of the day’.. to get your next few customers. Maybe that post is on reddit with some learnings that you found. If the reddit post does well, then you might post it on Twitter, saying reddit did well and what learnings you got from that etc. or even if it doesn’t do well you can still post about it.” Another tip she shared is to build related products that get more viral than the product itself. These are small stand-alone sites that would appeal to the same target audience, but by nature, are more shareable. On these sites, you can mention your startup like: ‘brought to you by Llama Life’ and then provide a link to the main website if someone is interested. If one of those gets viral or ranks on Google, you’ll have a passive traffic source. Scraping bee by Pierre Pierre, founder of Scraping Bee, a web scraping tool has now reached $1.5M ARR. Pierre and his cofounder Kevin started with 10 Free Beta Users in 2019, and after 6 months asked them to take a paid subscription if they wanted to continue using the product. That’s how they got their first user within 50 minutes of that email. Then they listed it on dozens of startup directories but their core strategy was writing the best possible content for their target audience — Developers. 3 very successful pieces of content that worked were : A small tutorial on how to scrape single-page application An extensive general guide about web scraping without getting blocked A complete introduction to web scraping with Python They didn’t do content marketing for the sake of content marketing but deep-dived into the value they were providing their customer. One of these got 70K visits, and all this together got them to over 100 users. WePay by Bill Clerico Bill Clerico left his cushy corporate job to build WePay which was then acquired for $400M got his first users by using his app. He got his first users by using his app! The app was for group payments. So he hosted a Poker tournament at his house and collected payments only with his app. Then they hosted a barbecue for fraternity treasurers at San Jose State & helped them do their annual dues collection. Good old word-of-mouth marketing, that however, started with an event where they used what they made! RealWorld by Genevieve Genevieve — Founder and CEO of Realworld stands by the old-school advice of value giving. RealWorld is an app that helps GenZ navigate adulthood. So, before launching their direct-to-consumer platform, they had an educational course that they sold to college career centers and students. They already had a pipeline of adults who turned to Realworld for their adulting challenges. From there, she gained her first 100 followers. Saner dot ai by Austin Austin got 100 users from Reddit for his startup Saner.ai. Reddit hates advertising, and so his tips to market your startup on Reddit is to Write value-driven posts on your niche. Instead of writing posts, find posts where people are looking for solutions DM people facing problems that your SaaS solves. But instead of selling, ask about their problem to see if your product is a good fit Heartfelt posts about why you built it, aren’t gonna cut it To find posts and people, search Reddit with relevant keywords and join all the subreddits A Stock Portfolio Newsletter A financial investor got his first 100 paid newsletter subscribers for his stock portfolio newsletter. His tips : Don’t reinvent the wheel. Work what’s already working. He saw a company making $500M+ from stock picking newsletter, so decided to try that. Find the gaps in “already working” and leverage them. That newsletter did not have portfolios of advisors writing them. That was his USP. He added his own portfolio to his newsletter. Now to 100 users, he partnered with a guy running an investing website and getting good traffic. That guy got a cut of his revenue, in exchange. That one simple step got him to 100 users. Hypefury by Yannick and Samy Yannick and Samy from Hypefury, Twitter and Social Media Automation tool got their first beta testers and users from a paid community. They launched Hypefury there and asked if someone wanted to try it. A couple of people tried it and gave feedback. Samy conducted user interviews and product demos for them, And shared the reviews on Twitter. That alone, along with word-of-mouth marketing on Twitter got them their first 100 users. To conclude: Don’t reinvent the wheel, try what’s working. Find the gaps in what’s working, and leverage that. Instead of thinking about millions of customers, think about the first 10. Then first 100. Leverage what you have. Get the first 10 customers, then talk about this to get the next 100. Use your app. Find ways, events, and opportunities to use your app in front of people. And get them to use it. Write content not only for SEO but also to help people. It won’t work tomorrow, but it will work for years after it picks up. Leverage other sources of traffic by partnering up! Do things that don’t scale. I’m also doing SaaS marketing deep dives over 30 pieces of content. I'm posting here for the first time, so I'm not sure if it will stay or not, sorry if it doesn't. I've helped a SaaS grow from $19K to $100K MRR as a marketer in last 2 years, and now I wanna dive deep. Cheers! (1/30)

#reddit#studied#founders

reddit

0

1

Royal_Rest8409•This week

How a founder built a B2B AI startup to serve with 65+ global brands (including Fortune500 companies) (I will not promote)

AI Palette is an AI-driven platform that helps food and beverage companies predict emerging product trends. I had the opportunity recently to sit down with the founder to get his advice on building an AI-first startup, which he'll be going through in this post. (I will not promote) About AI Palette: Co-founders: >!2 (Somsubhra GanChoudhuri, Himanshu Upreti)!!100+!!$12.7M USD!!AI-powered predictive analytics for the CPG (Consumer Packaged Goods) industry!!Signed first paying customer in the first year!!65+ global brands, including Cargill, Diageo, Ajinomoto, Symrise, Mondelez, and L’Oréal, use AI Palette!!Every new product launched has secured a paying client within months!!Expanded into Beauty & Personal Care (BPC), onboarding one of India’s largest BPC companies within weeks!!Launched multiple new product lines in the last two years, creating a unified suite for brand innovation!Identify the pain points in your industry for ideas* When I was working in the flavour and fragrance industry, I noticed a major issue CPG companies faced: launching a product took at least one to two years. For instance, if a company decided today to launch a new juice, it wouldn’t hit the market until 2027. This long timeline made it difficult to stay relevant and on top of trends. Another big problem I noticed was that companies relied heavily on market research to determine what products to launch. While this might work for current consumer preferences, it was highly inefficient since the product wouldn’t actually reach the market for several years. By the time the product launched, the consumer trends had already shifted, making that research outdated. That’s where AI can play a crucial role. Instead of looking at what consumers like today, we realised that companies should use AI to predict what they will want next. This allows businesses to create products that are ahead of the curve. Right now, the failure rate for new product launches is alarmingly high, with 8 out of 10 products failing. By leveraging AI, companies can avoid wasting resources on products that won’t succeed, leading to better, more successful launches. Start by talking to as many industry experts as possible to identify the real problems When we first had the idea for AI Palette, it was just a hunch, a gut feeling—we had no idea whether people would actually pay for it. To validate the idea, we reached out to as many people as we could within the industry. Since our focus area was all about consumer insights, we spoke to professionals in the CPG sector, particularly those in the insights departments of CPG companies. Through these early conversations, we began to see a common pattern emerge and identified the exact problem we wanted to solve. Don’t tell people what you’re building—listen to their frustrations and challenges first. Going into these early customer conversations, our goal was to listen and understand their challenges without telling them what we were trying to build. This is crucial as it ensures that you can gather as much data about the problem to truly understand it and that you aren't biasing their answers by showing your solution. This process helped us in two key ways: First, it validated that there was a real problem in the industry through the number of people who spoke about experiencing the same problem. Second, it allowed us to understand the exact scale and depth of the problem—e.g., how much money companies were spending on consumer research, what kind of tools they were currently using, etc. Narrow down your focus to a small, actionable area to solve initially. Once we were certain that there was a clear problem worth solving, we didn’t try to tackle everything at once. As a small team of two people, we started by focusing on a specific area of the problem—something big enough to matter but small enough for us to handle. Then, we approached customers with a potential solution and asked them for feedback. We learnt that our solution seemed promising, but we wanted to validate it further. If customers are willing to pay you for the solution, it’s a strong validation signal for market demand. One of our early customer interviewees even asked us to deliver the solution, which we did manually at first. We used machine learning models to analyse the data and presented the results in a slide deck. They paid us for the work, which was a critical moment. It meant we had something with real potential, and we had customers willing to pay us before we had even built the full product. This was the key validation that we needed. By the time we were ready to build the product, we had already gathered crucial insights from our early customers. We understood the specific information they wanted and how they wanted the results to be presented. This input was invaluable in shaping the development of our final product. Building & Product Development Start with a simple concept/design to validate with customers before building When we realised the problem and solution, we began by designing the product, but not by jumping straight into coding. Instead, we created wireframes and user interfaces using tools like InVision and Figma. This allowed us to visually represent the product without the need for backend or frontend development at first. The goal was to showcase how the product would look and feel, helping potential customers understand its value before we even started building. We showed these designs to potential customers and asked for feedback. Would they want to buy this product? Would they pay for it? We didn’t dive into actual development until we found a customer willing to pay a significant amount for the solution. This approach helped us ensure we were on the right track and didn’t waste time or resources building something customers didn’t actually want. Deliver your solution using a manual consulting approach before developing an automated product Initially, we solved problems for customers in a more "consulting" manner, delivering insights manually. Recall how I mentioned that when one of our early customer interviewees asked us to deliver the solution, we initially did it manually by using machine learning models to analyse the data and presenting the results to them in a slide deck. This works for the initial stages of validating your solution, as you don't want to invest too much time into building a full-blown MVP before understanding the exact features and functionalities that your users want. However, after confirming that customers were willing to pay for what we provided, we moved forward with actual product development. This shift from a manual service to product development was key to scaling in a sustainable manner, as our building was guided by real-world feedback and insights rather than intuition. Let ongoing customer feedback drive iteration and the product roadmap Once we built the first version of the product, it was basic, solving only one problem. But as we worked closely with customers, they requested additional features and functionalities to make it more useful. As a result, we continued to evolve the product to handle more complex use cases, gradually developing new modules based on customer feedback. Product development is a continuous process. Our early customers pushed us to expand features and modules, from solving just 20% of their problems to tackling 50–60% of their needs. These demands shaped our product roadmap and guided the development of new features, ultimately resulting in a more complete solution. Revenue and user numbers are key metrics for assessing product-market fit. However, critical mass varies across industries Product-market fit (PMF) can often be gauged by looking at the size of your revenue and the number of customers you're serving. Once you've reached a certain critical mass of customers, you can usually tell that you're starting to hit product-market fit. However, this critical mass varies by industry and the type of customers you're targeting. For example, if you're building an app for a broad consumer market, you may need thousands of users. But for enterprise software, product-market fit may be reached with just a few dozen key customers. Compare customer engagement and retention with other available solutions on the market for product-market fit Revenue and the number of customers alone isn't always enough to determine if you're reaching product-market fit. The type of customer and the use case for your product also matter. The level of engagement with your product—how much time users are spending on the platform—is also an important metric to track. The more time they spend, the more likely it is that your product is meeting a crucial need. Another way to evaluate product-market fit is by assessing retention, i.e whether users are returning to your platform and relying on it consistently, as compared to other solutions available. That's another key indication that your solution is gaining traction in the market. Business Model & Monetisation Prioritise scalability Initially, we started with a consulting-type model where we tailor-made specific solutions for each customer use-case we encountered and delivered the CPG insights manually, but we soon realized that this wasn't scalable. The problem with consulting is that you need to do the same work repeatedly for every new project, which requires a large team to handle the workload. That is not how you sustain a high-growth startup. To solve this, we focused on building a product that would address the most common problems faced by our customers. Once built, this product could be sold to thousands of customers without significant overheads, making the business scalable. With this in mind, we decided on a SaaS (Software as a Service) business model. The benefit of SaaS is that once you create the software, you can sell it to many customers without adding extra overhead. This results in a business with higher margins, where the same product can serve many customers simultaneously, making it much more efficient than the consulting model. Adopt a predictable, simplistic business model for efficiency. Look to industry practices for guidance When it came to monetisation, we considered the needs of our CPG customers, who I knew from experience were already accustomed to paying annual subscriptions for sales databases and other software services. We decided to adopt the same model and charge our customers an annual upfront fee. This model worked well for our target market, aligning with industry standards and ensuring stable, recurring revenue. Moreover, our target CPG customers were already used to this business model and didn't have to choose from a huge variety of payment options, making closing sales a straightforward and efficient process. Marketing & Sales Educate the market to position yourself as a thought leader When we started, AI was not widely understood, especially in the CPG industry. We had to create awareness around both AI and its potential value. Our strategy focused on educating potential users and customers about AI, its relevance, and why they should invest in it. This education was crucial to the success of our marketing efforts. To establish credibility, we adopted a thought leadership approach. We wrote blogs on the importance of AI and how it could solve problems for CPG companies. We also participated in events and conferences to demonstrate our expertise in applying AI to the industry. This helped us build our brand and reputation as leaders in the AI space for CPG, and word-of-mouth spread as customers recognized us as the go-to company for AI solutions. It’s tempting for startups to offer products for free in the hopes of gaining early traction with customers, but this approach doesn't work in the long run. Free offerings don’t establish the value of your product, and customers may not take them seriously. You should always charge for pilots, even if the fee is minimal, to ensure that the customer is serious about potentially working with you, and that they are committed and engaged with the product. Pilots/POCs/Demos should aim to give a "flavour" of what you can deliver A paid pilot/POC trial also gives you the opportunity to provide a “flavour” of what your product can deliver, helping to build confidence and trust with the client. It allows customers to experience a detailed preview of what your product can do, which builds anticipation and desire for the full functionality. During this phase, ensure your product is built to give them a taste of the value you can provide, which sets the stage for a broader, more impactful adoption down the line. Fundraising & Financial Management Leverage PR to generate inbound interest from VCs When it comes to fundraising, our approach was fairly traditional—we reached out to VCs and used connections from existing investors to make introductions. However, looking back, one thing that really helped us build momentum during our fundraising process was getting featured in Tech in Asia. This wasn’t planned; it just so happened that Tech in Asia was doing a series on AI startups in Southeast Asia and they reached out to us for an article. During the interview, they asked if we were fundraising, and we mentioned that we were. As a result, several VCs we hadn’t yet contacted reached out to us. This inbound interest was incredibly valuable, and we found it far more effective than our outbound efforts. So, if you can, try to generate some PR attention—it can help create inbound interest from VCs, and that interest is typically much stronger and more promising than any outbound strategies because they've gone out of their way to reach out to you. Be well-prepared and deliberate about fundraising. Keep trying and don't lose heart When pitching to VCs, it’s crucial to be thoroughly prepared, as you typically only get one shot at making an impression. If you mess up, it’s unlikely they’ll give you a second chance. You need to have key metrics at your fingertips, especially if you're running a SaaS company. Be ready to answer questions like: What’s your retention rate? What are your projections for the year? How much will you close? What’s your average contract value? These numbers should be at the top of your mind. Additionally, fundraising should be treated as a structured process, not something you do on the side while juggling other tasks. When you start, create a clear plan: identify 20 VCs to reach out to each week. By planning ahead, you’ll maintain momentum and speed up the process. Fundraising can be exhausting and disheartening, especially when you face multiple rejections. Remember, you just need one investor to say yes to make it all worthwhile. When using funds, prioritise profitability and grow only when necessary. Don't rely on funding to survive. In the past, the common advice for startups was to raise money, burn through it quickly, and use it to boost revenue numbers, even if that meant operating at a loss. The idea was that profitability wasn’t the main focus, and the goal was to show rapid growth for the next funding round. However, times have changed, especially with the shift from “funding summer” to “funding winter.” My advice now is to aim for profitability as soon as possible and grow only when it's truly needed. For example, it’s tempting to hire a large team when you have substantial funds in the bank, but ask yourself: Do you really need 10 new hires, or could you get by with just four? Growing too quickly can lead to unnecessary expenses, so focus on reaching profitability as soon as possible, rather than just inflating your team or burn rate. The key takeaway is to spend your funds wisely and only when absolutely necessary to reach profitability. You want to avoid becoming dependent on future VC investments to keep your company afloat. Instead, prioritize reaching break-even as quickly as you can, so you're not reliant on external funding to survive in the long run. Team-Building & Leadership Look for complementary skill sets in co-founders When choosing a co-founder, it’s important to find someone with a complementary skill set, not just someone you’re close to. For example, I come from a business and commercial background, so I needed someone with technical expertise. That’s when I found my co-founder, Himanshu, who had experience in machine learning and AI. He was a great match because his technical knowledge complemented my business skills, and together we formed a strong team. It might seem natural to choose your best friend as your co-founder, but this can often lead to conflict. Chances are, you and your best friend share similar interests, skills, and backgrounds, which doesn’t bring diversity to the table. If both of you come from the same industry or have the same strengths, you may end up butting heads on how things should be done. Having diverse skill sets helps avoid this and fosters a more collaborative working relationship. Himanshu (left) and Somsubhra (right) co-founded AI Palette in 2018 Define roles clearly to prevent co-founder conflict To avoid conflict, it’s essential that your roles as co-founders are clearly defined from the beginning. If your co-founder and you have distinct responsibilities, there is no room for overlap or disagreement. This ensures that both of you can work without stepping on each other's toes, and there’s mutual respect for each other’s expertise. This is another reason as to why it helps to have a co-founder with a complementary skillset to yours. Not only is having similar industry backgrounds and skillsets not particularly useful when building out your startup, it's also more likely to lead to conflicts since you both have similar subject expertise. On the other hand, if your co-founder is an expert in something that you're not, you're less likely to argue with them about their decisions regarding that aspect of the business and vice versa when it comes to your decisions. Look for employees who are driven by your mission, not salary For early-stage startups, the first hires are crucial. These employees need to be highly motivated and excited about the mission. Since the salary will likely be low and the work demanding, they must be driven by something beyond just the paycheck. The right employees are the swash-buckling pirates and romantics, i.e those who are genuinely passionate about the startup’s vision and want to be part of something impactful beyond material gains. When employees are motivated by the mission, they are more likely to stick around and help take the startup to greater heights. A litmus test for hiring: Would you be excited to work with them on a Sunday? One of the most important rounds in the hiring process is the culture fit round. This is where you assess whether a candidate shares the same values as you and your team. A key question to ask yourself is: "Would I be excited to work with this person on a Sunday?" If there’s any doubt about your answer, it’s likely not a good fit. The idea is that you want employees who align with the company's culture and values and who you would enjoy collaborating with even outside of regular work hours. How we structure the team at AI Palette We have three broad functions in our organization. The first two are the big ones: Technical Team – This is the core of our product and technology. This team is responsible for product development and incorporating customer feedback into improving the technology Commercial Team – This includes sales, marketing, customer service, account managers, and so on, handling everything related to business growth and customer relations. General and Administrative Team – This smaller team supports functions like finance, HR, and administration. As with almost all businesses, we have teams that address the two core tasks of building (technical team) and selling (commercial team), but given the size we're at now, having the administrative team helps smoothen operations. Set broad goals but let your teams decide on execution What I've done is recruit highly skilled people who don't need me to micromanage them on a day-to-day basis. They're experts in their roles, and as Steve Jobs said, when you hire the right person, you don't have to tell them what to do—they understand the purpose and tell you what to do. So, my job as the CEO is to set the broader goals for them, review the plans they have to achieve those goals, and periodically check in on progress. For example, if our broad goal is to meet a certain revenue target, I break it down across teams: For the sales team, I’ll look at how they plan to hit that target—how many customers they need to sell to, how many salespeople they need, and what tactics and strategies they plan to use. For the technical team, I’ll evaluate our product offerings—whether they think we need to build new products to attract more customers, and whether they think it's scalable for the number of customers we plan to serve. This way, the entire organization's tasks are cascaded in alignment with our overarching goals, with me setting the direction and leaving the details of execution to the skilled team members that I hire.

#reddit#founder#built

reddit

0

1

avtges•This week

So, you want to be a CEO?

I used to post here occasionally with business advice. But it turns out most of you in this sub have a dream, but seemingly no execution. You want to be rich sure, but without understanding what it takes to be a founder, run a startup, create a team around an idea and a strategy, and push them to their limits without burning them out, to win in a market that's never heard of you - not to mention the pressures on your personal life. So, I'm going to post a new game called, "So, You Want to Be A CEO?" The game: Each week I will post a reasonably complex challenge that a startup founder has to overcome, between inception of the company until it goes bust or series A. You respond with your best course of action - that is, what would you do in the situation provided? YOU DON’T HAVE TO DO THE WORK! The rules: One response per person Your upvotes are your score for the week I will track them in the OP Scores are calculated on the Friday of that week You must answer the prompt completely, if you don't you lose half your points earned that week. ChatGPT is allowed, but it may not provide sufficient advice to win the game Prompt 1: "Boomerang" You are an HR executive turned entrepreneur. You have identified a significant issue: professionals over the age of 55 are struggling to re-enter the workforce and you also believe corporations are missing out on a wealth of institutional knowledge in retirement. You believe you can help solve this problem by creating Boomerang, a platform dedicated to empowering these individuals and corporate partners by connecting them with the best candidates aged 55 and older. Objective: Your goal is to validate your concept, develop a Minimum Viable Product (MVP), and balance your personal responsibilities while laying the foundation for Boomerang’s success. This Week's Key Challenges and Decisions: Market Research Challenge 1: You need to validate the market need for Boomerang. This involves understanding the pain points of older job seekers and potential employers. This will take 4 days (non-sequential) How do you get started? Developing an MVP Challenge 2: With limited resources, you need to create an MVP that effectively demonstrates Boomerang’s value. This will take 2 days. Can be combined with other challenges. How do you get started? Dealing with Personal Health Issues Challenge 3: Your doctor mentioned your bloodwork is irregular, but can't pinpoint the cause. They recommend you see a specialist before Friday. This will take 1 day. Give it a shot! There's no right answer, just answer what your plan to do and try to optimize the use of your time to the best of your ability. EDIT: Scoreboard (I realize now the top post generally gets the most upvotes, so I may change the points system): u/conscious_border3019 - 22 u/inBoulderForSummer - 4 u/that_whey-or-the-lee - 3 u/AgencySaas - 3 u/Gold-Ad-8211 - 2 u/93024662 - 2 u/DeusExBam - 2 u/njm19920 - 2 u/SilentEconomist9265 - 2 u/ai_servant - 2 u/Background-Term2759 - 2 u/Insane_squirrel - 2 u/kiss_thechef - 2 u/codeyman2 - 2 u/Xentoxus - 2 u/LongComplex4395 - 2

#reddit#want#ceo?

reddit

0

1

totie2•This week

$1.2 MRR, should I do paid ads?

Hello, I launched a bootstrapped b2b SaaS end of last year and I've just hit 1.2k MRR. It's a 50-60% profit margin, so $600 are going to my pocket, I also do freelancing where most of my revenue comes from, that's about 3k monthly average. My project has essentially been stuck around this 1k MRR mark for months, I'm sticking to my strategy: Daily outreach on LinkedIn Weekly Post on LinkedIn (my company is a no code tool for building AI SEO & content workflows, so every week I share a new tool) Weekly Blog Post Reaching out to influencers/newsletter writers to see if they'd be willing to write about it. Now I'm thinking if I should set $500-$1000 monthly budget for paid ads, I'm primarily considering Google Ads and LinkedIn Ads. Essentially I'm wondering if 1.2k MRR a good point to start investing back into the company.

#reddit#$1.2#mrr,

reddit

0

1

adriannelestrange•This week

I studied how 7 Founders found their first 100 customers for their businesses. Summarizing it here!

I am learning marketing, and so I combed through the internet to find specific advice that helped founders reach 100 users and not random Google answers. Here’s what I found: Llama Life by Marie Marie founder of Llama Life, a productivity app ($51.4K+ revenue) got her first 100 users using Snowballing effect. She shared great advice that I want to add here verbatim, “Need to think about what you have that you can leverage based on your current situation. eg..When you have no customers, think about where you can post to get the 1st customer eg Product Hunt. If you do well on PH, say you get #3 product of the day, then you post somewhere else saying ‘I got #3 product of the day’.. to get your next few customers. Maybe that post is on reddit with some learnings that you found. If the reddit post does well, then you might post it on Twitter, saying reddit did well and what learnings you got from that etc. or even if it doesn’t do well you can still post about it.” Another tip she shared is to build related products that get more viral than the product itself. These are small stand-alone sites that would appeal to the same target audience, but by nature, are more shareable. On these sites, you can mention your startup like: ‘brought to you by Llama Life’ and then provide a link to the main website if someone is interested. If one of those gets viral or ranks on Google, you’ll have a passive traffic source. Scraping bee by Pierre Pierre, founder of Scraping Bee, a web scraping tool has now reached $1.5M ARR. Pierre and his cofounder Kevin started with 10 Free Beta Users in 2019, and after 6 months asked them to take a paid subscription if they wanted to continue using the product. That’s how they got their first user within 50 minutes of that email. Then they listed it on dozens of startup directories but their core strategy was writing the best possible content for their target audience — Developers. 3 very successful pieces of content that worked were : A small tutorial on how to scrape single-page application An extensive general guide about web scraping without getting blocked A complete introduction to web scraping with Python They didn’t do content marketing for the sake of content marketing but deep-dived into the value they were providing their customer. One of these got 70K visits, and all this together got them to over 100 users. WePay by Bill Clerico Bill Clerico left his cushy corporate job to build WePay which was then acquired for $400M got his first users by using his app. He got his first users by using his app! The app was for group payments. So he hosted a Poker tournament at his house and collected payments only with his app. Then they hosted a barbecue for fraternity treasurers at San Jose State & helped them do their annual dues collection. Good old word-of-mouth marketing, that however, started with an event where they used what they made! RealWorld by Genevieve Genevieve — Founder and CEO of Realworld stands by the old-school advice of value giving. RealWorld is an app that helps GenZ navigate adulthood. So, before launching their direct-to-consumer platform, they had an educational course that they sold to college career centers and students. They already had a pipeline of adults who turned to Realworld for their adulting challenges. From there, she gained her first 100 followers. Saner dot ai by Austin Austin got 100 users from Reddit for his startup Saner.ai. Reddit hates advertising, and so his tips to market your startup on Reddit is to Write value-driven posts on your niche. Instead of writing posts, find posts where people are looking for solutions DM people facing problems that your SaaS solves. But instead of selling, ask about their problem to see if your product is a good fit Heartfelt posts about why you built it, aren’t gonna cut it To find posts and people, search Reddit with relevant keywords and join all the subreddits A Stock Portfolio Newsletter A financial investor got his first 100 paid newsletter subscribers for his stock portfolio newsletter. His tips : Don’t reinvent the wheel. Work what’s already working. He saw a company making $500M+ from stock picking newsletter, so decided to try that. Find the gaps in “already working” and leverage them. That newsletter did not have portfolios of advisors writing them. That was his USP. He added his own portfolio to his newsletter. Now to 100 users, he partnered with a guy running an investing website and getting good traffic. That guy got a cut of his revenue, in exchange. That one simple step got him to 100 users. Hypefury by Yannick and Samy Yannick and Samy from Hypefury, Twitter and Social Media Automation tool got their first beta testers and users from a paid community. They launched Hypefury there and asked if someone wanted to try it. A couple of people tried it and gave feedback. Samy conducted user interviews and product demos for them, And shared the reviews on Twitter. That alone, along with word-of-mouth marketing on Twitter got them their first 100 users. To conclude: Don’t reinvent the wheel, try what’s working. Find the gaps in what’s working, and leverage that. Instead of thinking about millions of customers, think about the first 10. Then first 100. Leverage what you have. Get the first 10 customers, then talk about this to get the next 100. Use your app. Find ways, events, and opportunities to use your app in front of people. And get them to use it. Write content not only for SEO but also to help people. It won’t work tomorrow, but it will work for years after it picks up. Leverage other sources of traffic by partnering up! Do things that don’t scale. I’m also doing SaaS marketing deep dives over 30 pieces of content. I'm posting here for the first time, so I'm not sure if it will stay or not, sorry if it doesn't. I've helped a SaaS grow from $19K to $100K MRR as a marketer in last 2 years, and now I wanna dive deep. Cheers! (1/30)

#reddit#studied#founders

reddit

0

1

masoodtalha•This week

What if one founder in every startup became an influencer in their space? Will they bring in more business? (I will not promote)

I quit my last startup literally a week ago and I am already starting something new. I raised $2.7 million for my last company. But I feel like that the distribution was not strong enough. Hence I failed. Now as a second time founder distribution is the first thing I am going to focus on. So I have started doing physical events. The first event is IRL in San Francisco. I am inviting the CEO of Product Hunt for a fireside. The event is about how Ai agent founders can launch on Product Hunt. I will also start making videos everyday until the event to promote myself as a influencer in the space of AI agents + Product launches. Then use this momentum and newly created distribution to launch my first Ai agent. Let's see if the strategy works. I will keep people here posted!

#reddit#founder#every

reddit

0

0.6

xoyourwife•This week

No revenue for 6 months, then signed $10k MRR in 2 weeks with a new strategy. Here’s what I changed.

This is my first company so I made A LOT of mistakes when starting out. I'll explain everything I did that worked so you don't have to waste your time either. For context, I built a SaaS tool that helps companies scale their new client outreach 10x (at human quality with AI) so they can secure more sales meetings. Pricing I started out pricing it way too low (1/10 as much as competitors) so that it'd be easier to get customers in the beginning. This is a HUGE mistake and wasted me a bunch of time. First, this low pricing meant that I was unable to pay for the tools I needed to make sure my product could be great. I was forced to use low-quality databases, AI models, sending infrastructure -- you name it. Second, my customers were less invested in the product, and I received less input from them to make the product better. None ended up converting from my free trial because my product sucked, and I couldn't even get good feedback from them. I decided to price my product much higher, which allowed me to use best-in class tools to make my product actually work well. Outreach Approach The only issue is that it's a lot harder to get people to pay $500/month than $50/month. I watched every single video on the internet about cold email for getting B2B clients and built up an outbound MACHINE for sending thousands of emails a day. I tried all the top recommended sales email formats and tricks (intro, painpoint, testimonial, CTA, etc). Nothing. I could send 1k emails and get a few out of office responses and a handful of 'F off' responses. I felt bad and decided I couldn't just spam the entire world and expect to make any progress. I decided I needed to take a step back and learn from people who'd succeeded before in sales. I started manually emailing CEOs/founders that fit my customer profile with personal messages asking for feedback on my product -- not even trying to sell them anything. Suddenly I was getting 4-6 meetings a day and just trying to learn from them (turns out people love helping others). And without even prompting, many of them said 'hey, I actually could use this for my own sales' and asked how they could start trying it out. That week I signed 5 clients between $500-$4k/month (depending how many contacts they want to reach). I then taught my product to do outreach the same way I did that worked (include company signals, make sure the person is a great match with web research, and DONT TALK SALESY). Now, 6 of my first 10 clients (still figuring out who it works for, lol) have converted from the free trial and successfully used it to book sales meetings. I'm definitely still learning, but this one change in my sales approach changed everything for me, so I wanted to share. If anyone has any other tips/advice that changed their business's sales, would love to hear!

#reddit#revenue#months,

reddit

0

0

smok1naces•This week

10,000 users in a month

Our team raised an angel fund and have been quietly iterating over the last year. We launched a month ago and have just about 10,000 users with a small amount of revenue. We are an AI company targeting consumers and beauty. Has anyone raised in the space who could shed some light on what worked/didn’t work for them? Our product is stickier than anyone on the team ever imagined.

#reddit#10,000#users

reddit

0

1

Ready_Papaya_7937•This week

For the Herd-Investor(Formerly Me)

Hey guys. my friend and I developed a model that looks over SEC filings and instead of just summarizing what they say like the existing “AI” solutions do(which are really just read-write programs), it infers and reads between the lines and analyzes what type of strategy the company is using(revenue recognition timing, the company's history,etc.) and many other factors. We used a different approach. Instead of basically making a GPT wrapper, we trained it from scratch based on not only summarizing filings but inferring on key information that is glossed over a lot. We plan to scale this into a model that accounts for not only filings, but recent news, public sentiment, and other factors. And instead of people having to upload files to get analyzed, we plan to automatically aggregate files on all public companies on the US markets and train the model on those to provide a one- stop shop financial search engine platform for retail investors to access digestable financial information(like an AlphaSense but for retail investors) because right now, the average retail investor has to access on average 5 services to get this info and then has to interpret the info as well. Obviously, the retail investor these days is also tied to a sense of community so plan to implement a moderated almost newletter like platform where verified creators can publish posts regarding their interests to further serve the retail investor. The gist is basically simplifying high-level finance to the point where the beginner investor can understand while preserving the technical value. Do you guys have any extra thoughts on this? I am trying to ask if you guys would actually pay for a service like this, and what it should additionally offer to make it more valuable to the average retail investor. Thanks again!

#reddit#herd-investor(formerly

reddit

0

1

trantrungtin•This week

I crawled 5000+ X account from AI companies.

Hi all, My work requires me to have an overview of the AI market so I wrote a script to crawl and keep track of all the X (Twitter) accounts that mention AI/LLM/SD or similar terms and look like a company/team. If someone asks how to scrape X, I just use some off-the-rack GitHub repo to implement the script, and X didn't detect the bot, or they are not enforcing the rule. I plan to also scrape these companies' websites to see what they are cooking but that is for later as it's a kinda big endeavor. Long story short, here is the result (in the first comment), hope it's somewhat helpful.

#reddit#crawled#5000+

reddit

0

1

tclzcja•This week

Equity vesting schedule as CTO - I will not promote

Hi everyone, in short I recently got an offer as CTO for a start-up with 17% equity vesting in 3 years. The product is like 6 months away from MVP but the co-founders had the core idea proved and figured out (it's an AI company), so my duty is to implement and deploy it. My question is that the first cliff is at the 13th month for 3%, which is definitely after the product is built. What if before the 13th month they just kick me off the bus? Should I ask for a 3% or sth at Day 0? Plus is that vesting schedule common (13th month, 25th month and 37th month) for tech start-up? Oh btw I'm getting paid with a very low almost 0 level until seed investment. Much appreciated for your input! I will not promote.

#reddit#equity#vesting

reddit

0

1

colbyn-wadman•This week

Content aggregation that acts as a middleman for content discovery via third-party marketplace & revenue sharing (i will not promote but I'm looking for fellow researchers)

High level I’m considering a content aggregation business model, but one that acts as an open marketplace where third party devs and where world class data scientists compete to build the best recommenders for different use cases. (E.g. the incentives can be ad revenue sharing or subscription based for niche professional markets.) The idea is to facilitate more bottom up innovation from third party data scientists. The platform itself just acts as the middleman. (Also something that strips out original ads and makes it easy to skip paid sponsorship sections would be great.)  I’ve seen startups building web crawlers and content aggregation systems for other AI startups. My proposal is better in the sense that third party devs are instead responsible for implementing whatever questionable hacks are necessarily to scrape platforms that don’t necessarily want to be scraped.  Personally, I’m more concerned about getting the right information than ever before, to this end I can’t rely on platform specific recommenders. The solution is more bottom up innovation in content promotion. More generally, if you’re also concerned about consuming game changing information that’s too easily missed: we need a platform that incentivizes bottom up innovation of content promotion. What we need is a platform that functions like a marketplace where third party devs and where world class data scientists compete to build the best recommenders for different use cases. Here’s some elevator pitches I’m considering:  Did you know that the magic behind YouTube is its recommendation engine? Now, imagine an open platform where independent engines compete to deliver the most personalized content feed—from news to local events—directly to you. Interested in rethinking how we find content? “In today’s fragmented digital landscape, a single platform no longer holds sway over content discovery. The Network Effect is dead: audiences are more mobile than ever; and big tech killed it. In such a fragmented landscape we’re building a bottom-up, decentralized marketplace for recommendation engines—a solution that taps into diverse revenue streams through subscriptions, ad revenue, and affiliate partnerships. Invest in the future of personalized content aggregation.” “Are you a developer passionate about algorithms and content discovery? Our open marketplace lets you build and monetize your own recommendation engine, competing to deliver the most engaging, personalized feeds. Join a revolution where your innovation can directly shape how the world finds content.” “Are you tired of being told what to watch or read by one mysterious algorithm? Imagine taking control—choosing from a marketplace of smart recommendation engines that curate content just for you. It’s a revolution in content discovery where you hold the power.” (As a Utahn this one is interesting because even mormons are talking about the dangers of “doom scrolling” though it’s seldom discussed in society at large.) As far as simple hooks I’m considering:  One platform to rule them all and in the darkness bind them.  Choose how you discover—content recommenders that work for you.  The area where recommender engines battle to win your feed. Request I would love to start prototyping this idea and see what else I can uncover from such preliminary research. But I want to get a couple other likeminded individuals onboard.  I'm the best when it comes to iOS/macOS development, but there's tons of backend work that needs to be done which I wouldn’t have the time for if i'm focused on the native clients. Who am I 'ideally' looking for?  I’ve heard of weird stats to the effect that if you scale up a population to billions of people, the number of life overlaps starts skyrocketing. Not just physical lookalikes, but people with eerily similar life paths, personalities, habits, and even thoughts — without ever knowing each other. Where are my clones? Such is whom I’m looking for in an ideal world.  Take a hunch  People nowadays have no concept of going out on a limb, taking a ‘hunch’, and backing their instincts. Everything has to be calculated, proven, and guaranteed before they make a move. In contrast consider the success of the Chinese DeepSeek project: According to Asianometry’s YouTube video on DeepSeek, their “memory-saving multi-head latent architecture” (whatever that means, just quoting the name) came about from a researchers ‘hunch’, which the company bet big on and the result was drastically improved performance on low end hardware…  Here in the west the idea of betting on a hunch is inconceivable. We have no balls to chase long term insights. My own instincts when it comes to software is such because I’ve wasted too much of my life on small scale projects. All I’m trying to do is attempt a more scaled up experiment based on some hunches with me and a few other likeminded individuals.  Just as the early oil prospectors didn’t have precise maps—just intuition and test drills. They had to drill, analyze the pressure, and adjust. The best oil fields weren’t found by foresight alone, but by adaptive exploration. The startup space itself is liken to the first prospectors who got the gold nuggets lying in the riverbed. In such an environment moving first has its advantages but nowadays I wish I could have all those shitty ‘engineers’ sent to their maker.  Today the reality is such that you’ve got to dig deep—where vast stores of wealth can be found—or go home, and those who dig into the depths cannot use mere forethought, for what lies beneath cannot be seen by the mind’s eye.  I will not promote but I'm looking for fellow research oriented minds.

#reddit#content#aggregation

reddit

0

0.333

minophen•This week

Lessons from 139 YC AI startups (S23)

YC's Demo Day was last week, and with it comes another deluge of AI companies. A record-breaking 139 startups were in some way related to AI or ML - up from 112 in the last batch. Here are 5 of my biggest takeaways: AI is (still) eating the world. It's remarkable how diverse the industries are - over two dozen verticals were represented, from materials science to social media to security. However, the top four categories were: AI Ops: Tooling and platforms to help companies deploy working AI models. We'll discuss more below, but AI Ops has become a huge category, primarily focused on LLMs and taming them for production use cases. Developer Tools: Apps, plugins, and SDKs making it easier to write code. There were plenty of examples of integrating third-party data, auto-generating code/tests, and working with agents/chatbots to build and debug code. Healthcare + Biotech: It seems like healthcare has a lot of room for automation, with companies working on note-taking, billing, training, and prescribing. And on the biotech side, there are some seriously cool companies building autonomous surgery robots and at-home cancer detection. Finance + Payments: Startups targeting banks, fintechs, and compliance departments. This was a wide range of companies, from automated collections to AI due diligence to "Copilot for bankers." Those four areas covered over half of the startups. The first two make sense: YC has always filtered for technical founders, and many are using AI to do what they know - improve the software developer workflow. But it's interesting to see healthcare and finance not far behind. Previously, I wrote: Large enterprises, healthcare, and government are not going to send sensitive data to OpenAI. This leaves a gap for startups to build on-premise, compliant \[LLMs\] for these verticals. And we're now seeing exactly that - LLMs focused on healthcare and finance and AI Ops companies targeting on-prem use cases. It also helps that one of the major selling points of generative AI right now is cost-cutting - an enticing use case for healthcare and finance. Copilots are king. In the last batch, a lot of startups positioned themselves as "ChatGPT for X," with a consumer focus. It seems the current trend, though, is "Copilot for X" - B2B AI assistants to help you do everything from KYC checks to corporate event planning to chip design to negotiate contracts. Nearly two dozen companies were working on some sort of artificial companion for businesses - and a couple for consumers. It's more evidence for the argument that AI will not outright replace workers - instead, existing workers will collaborate with AI to be more productive. And as AI becomes more mainstream, this trend of making specialized tools for specific industries or tasks will only grow. That being said - a Bing-style AI that lives in a sidebar and is only accessible via chat probably isn't the most useful form factor for AI. But until OpenAI, Microsoft, and Google change their approach (or until another company steps up), we'll probably see many more Copilots. AI Ops is becoming a key sector. "AI Ops" has been a term for only a few years. "LLM Ops" has existed for barely a year. And yet, so many companies are focused on training, fine-tuning, deploying, hosting, and post-processing LLMs it's quickly becoming a critical piece of the AI space. It's a vast industry that's sprung up seemingly overnight, and it was pretty interesting to see some of the problems being solved at the bleeding edge. For example: Adding context to language models with as few as ten samples. Pausing and moving training runs in real-time. Managing training data ownership and permissions. Faster vector databases. Fine-tuning models with synthetic data. But as much ~~hype~~ enthusiasm and opportunity as there might be, the size of the AI Ops space also shows how much work is needed to really productionalize LLMs and other models. There are still many open questions about reliability, privacy, observability, usability, and safety when it comes to using LLMs in the wild. Who owns the model? Does it matter? Nine months ago, anyone building an LLM company was doing one of three things: Training their own model from scratch. Fine-tuning a version of GPT-3. Building a wrapper around ChatGPT. Thanks to Meta, the open-source community, and the legions of competitors trying to catch up to OpenAI, there are now dozens of ways to integrate LLMs. However, I found it interesting how few B2B companies mentioned whether or not they trained their own model. If I had to guess, I'd say many are using ChatGPT or a fine-tuned version of Llama 2. But it raises an interesting question - if the AI provides value, does it matter if it's "just" ChatGPT behind the scenes? And once ChatGPT becomes fine-tuneable, when (if ever) will startups decide to ditch OpenAI and use their own model instead? "AI" isn't a silver bullet. At the end of the day, perhaps the biggest lesson is that "AI" isn't a magical cure-all - you still need to build a defensible company. At the beginning of the post-ChatGPT hype wave, it seemed like you just had to say "we're adding AI" to raise your next round or boost your stock price. But competition is extremely fierce. Even within this batch, there were multiple companies with nearly identical pitches, including: Solving customer support tickets. Negotiating sales contracts. Writing drafts of legal documents. Building no-code LLM workflows. On-prem LLM deployment. Automating trust and safety moderation. As it turns out, AI can be a competitive advantage, but it can't make up for a bad business. The most interesting (and likely valuable) companies are the ones that take boring industries and find non-obvious use cases for AI. In those cases, the key is having a team that can effectively distribute a product to users, with or without AI. Where we’re headed I'll be honest - 139 companies is a lot. In reviewing them all, there were points where it just felt completely overwhelming. But after taking a step back, seeing them all together paints an incredibly vivid picture of the current AI landscape: one that is diverse, rapidly evolving, and increasingly integrated into professional and personal tasks. These startups aren't just building AI for the sake of technology or academic research, but are trying to address real-world problems. Technology is always a double-edged sword - and some of the startups felt a little too dystopian for my taste - but I'm still hopeful about AI's ability to improve productivity and the human experience.

#reddit#lessons#startups

reddit

0

1

GPT-Rex•This week

Is my idea + progress good enough to raise pre-seed round? CRM for construction niches. Non-tech founder.

Is my startup idea and progress good enough to raise a pre-seed round? It’s a CRM with meaningful AI integrations for specific type of B2B construction companies. I only want to continue at my current pace if it’s realistic to start raising within the next 2 weeks. At first, I thought it was fine because simple companies still get on Y-comb such as hammr and Relate CRM , but now I’m not sure. Would love to get the community’s thoughts on this. I’ve been working on this for about a week. ​ Key Highlights (You can skip to longer section below) Product is CRM for B2B construction companies. The previous tech company I worked at used an in-house built CRM for their workflow, and I’m creating that solution and applying it to B2B construction companies that have similar workflows. No competitors I’ve found. I’m uniquely positioned to spearhead: B2B SaaS/tech sales + expertise in construction I’m a non-tech sales founder with experience in UI/UX. Will bring on CTO co-founder once I start raising as that would entice better talent Progress + Traction $400 MRR in pre-sales, can get to \~$800-1000 EOM Validated through customer interviews Created some Figma frames, product overview, user journeys, business plan Made a simple but meaningful AI tool that will be available to those that sign up for waitlist. Did this with GitHub + ChatGPT Landing page website going up this week followed by PPC campaign, email marketing, and outreach. My GF works in enterprise sales and she’ll help me generate more leads. ​ Long Version Background B2B SaaS/Tech sales. I worked at enterprise company as an Account Executive where I worked with funded startups and their development, UI/UX, and Product management teams. I have a general knowledge in all these - my best being UI/UX design as I can work with Figma well Domain expertise: my family has had a construction company since I was young. I have a large network because of this. Problem At my previous company, we had a custom in-house built CRM for our workflow. It worked okay, despite being maintained by multiple engineers costing hundreds of thousands a year. I’m creating a CRM that solves that, and applying it to construction industries that can make use of it. I have a great network here which makes it easy for me get sales quickly. Vision Building this CRM for construction niche will allow us to generate MRR fast. We will be first movers in bringing meaningful AI tools to construction, which is generating significant interest. This gives us the opportunity to build the foundational technology that can be adapted to a wider audience such as my previous company and others - think researchers, consultants, etc. Traction + Current Progress (1 week) Validated idea through user interviews and pre-sales. Currently have $400 MRR in pre-sales. I expect $800-1000 in a month if I continue at my pace. This is from doing typical B2B sales. I’ve set up a CRM for this. Created product overview, user journeys, wireframes and some Figma frames, business plan Created a simple but meaningful AI tool for the niche which will be available to those that sign up for the waitlist. Created with GitHub + ChatGPT Completing landing page website this week. Will start PPC ads (I’m experienced in this) after that to generate sign-ups. I’ll also start email marketing from lists I’ve scraped. Team Solo-founder, will bring on CTO co-founder once I start raising funds. I have promising candidates, but feel that I need to raise funds to really entice a good co-founder. I’m uniquely positioned to head this product; B2B sales having worked with many CRMs + construction expertise and network. That said, I’ve never actually done anything that* impressive besides being an AE at a known enterprise techy company (but not FAANG level). ​ I want to acknowledge that my progress might sound more impressive than it is - it's still just a CRM after all, and I'm non-technical. Should I keep going? Advice? I also have a great offer to lead sales at a profitable startup, but I could always do both if it was worth it. I’m feeling really uncertain for some reason :/ maybe it’s just burnout.

#reddit#idea#progress

reddit

0

1

Glittering-Koala-750•This week

Looking for a 3/4 Non-Technical Co-founders and 1 Technical co-founder

I have 3 startups that I would like to others to join. They are already up and running but I don't have the time to run all of them at once. Equity first then hopefully soon salary. Medical Recruitment in the UK - looking for Marketing and/or recruitment experience. You do not have to be in the UK and it can be alongside your current job. I already have 2000 nurses from overseas ready to come over. I have 2 pipelines involving education companies and IELTS training. Branding Company (UK and USA) - looking for marketers to push this company. This is in its infancy but I have a pool of 600 domain names along with a number of branding domains. I also have 2 trademarks pending in the UK. AI Saas - this is something I have been working on for a long time but cannot get off the ground myself. I would love the support of a technical co-founder but if I can get others to help it will be much faster. This software would also help support the other companies. This one is really just in my head and not reality yet but you never know. To clarify this is about people having fun, enjoying what they do and making money through this journey.

#reddit#looking#non-technical

reddit

0

0

GurOriginal3724•This week

Does this sound useful? [I will not promote]

My idea is an AI model that helps business owner make smart decisions no matter their size. (Mentor in your pocket) No more spending ours researching, Validating, planning, time wasting decision discussions etc 🕑Save Time > Saving Money💰 ⬇️Read for a better understanding⬇️ 1) give it context about your business( the more specific the better) 2) ask it a question. E.g "I need a marketing strategy that appeals to the X audience more " E.g "At the current rate is my business dying?" E.g "give me a step by step guide using the resources I have that can get my business up and running" 3) results aren't just pulled out of the air but are pulled from a database with answers and case studies to back up the answer. E.g "company Y had competition with company X in [2012] to get a larger market share so company Y...[The decisions that company made to get the result similar to the problem your facing]" This would even be friendly for people who wish to start a new business. •E.g prompt: "[ input idea] please validate my idea, does it suck?" Result could even be from a specific entrepreneur. E.g • "Alex Hormozi states that ... in the book $100M Offers. And it seems you are missing ... from his framework." Here is what you can do to [Desired result]. (You can specify which entrepreneur or the AI will select the most relevant one to you.)

#reddit#does#sound

reddit

0

1

avtges•This week

So, you want to be a CEO?

I used to post here occasionally with business advice. But it turns out most of you in this sub have a dream, but seemingly no execution. You want to be rich sure, but without understanding what it takes to be a founder, run a startup, create a team around an idea and a strategy, and push them to their limits without burning them out, to win in a market that's never heard of you - not to mention the pressures on your personal life. So, I'm going to post a new game called, "So, You Want to Be A CEO?" The game: Each week I will post a reasonably complex challenge that a startup founder has to overcome, between inception of the company until it goes bust or series A. You respond with your best course of action - that is, what would you do in the situation provided? YOU DON’T HAVE TO DO THE WORK! The rules: One response per person Your upvotes are your score for the week I will track them in the OP Scores are calculated on the Friday of that week You must answer the prompt completely, if you don't you lose half your points earned that week. ChatGPT is allowed, but it may not provide sufficient advice to win the game Prompt 1: "Boomerang" You are an HR executive turned entrepreneur. You have identified a significant issue: professionals over the age of 55 are struggling to re-enter the workforce and you also believe corporations are missing out on a wealth of institutional knowledge in retirement. You believe you can help solve this problem by creating Boomerang, a platform dedicated to empowering these individuals and corporate partners by connecting them with the best candidates aged 55 and older. Objective: Your goal is to validate your concept, develop a Minimum Viable Product (MVP), and balance your personal responsibilities while laying the foundation for Boomerang’s success. This Week's Key Challenges and Decisions: Market Research Challenge 1: You need to validate the market need for Boomerang. This involves understanding the pain points of older job seekers and potential employers. This will take 4 days (non-sequential) How do you get started? Developing an MVP Challenge 2: With limited resources, you need to create an MVP that effectively demonstrates Boomerang’s value. This will take 2 days. Can be combined with other challenges. How do you get started? Dealing with Personal Health Issues Challenge 3: Your doctor mentioned your bloodwork is irregular, but can't pinpoint the cause. They recommend you see a specialist before Friday. This will take 1 day. Give it a shot! There's no right answer, just answer what your plan to do and try to optimize the use of your time to the best of your ability. EDIT: Scoreboard (I realize now the top post generally gets the most upvotes, so I may change the points system): u/conscious_border3019 - 22 u/inBoulderForSummer - 4 u/that_whey-or-the-lee - 3 u/AgencySaas - 3 u/Gold-Ad-8211 - 2 u/93024662 - 2 u/DeusExBam - 2 u/njm19920 - 2 u/SilentEconomist9265 - 2 u/ai_servant - 2 u/Background-Term2759 - 2 u/Insane_squirrel - 2 u/kiss_thechef - 2 u/codeyman2 - 2 u/Xentoxus - 2 u/LongComplex4395 - 2

#reddit#want#ceo?

reddit

0

1

DB010112•This week

Experienced Software Developer looking for startup to help. I will not promote

My passion for programming started at the age of 9 when I began playing video games. It was during this time that I first dived into programming, creating scripts for SA:MP (San Andreas Multiplayer) using the Pawn language. SA:MP is a modification for the popular game Grand Theft Auto: San Andreas, allowing players to experience multiplayer gameplay. My early experiences in programming were all about problem-solving—finding ways to enhance the game and improve the player experience. This was when I realized how satisfying it is to solve a problem through code, and that feeling has stayed with me throughout my career. I am a self-taught programmer, and everything I know today comes from my own initiative to learn and improve. After five years of working with local clients, I decided to expand my knowledge and started learning more widely applicable programming languages like Java and Python. I’ve always been the type of person who thrives on challenges. Whenever I encounter a problem, I don’t just look for a quick fix—I dive deep into researching and understanding the problem, and I find a solution that works in the long run. This is what drives me. The ability to solve problems, no matter how complex, and the satisfaction that comes with it is what fuels my passion for programming. My big break came when I had the opportunity to work at \\\\. There, I replaced two senior and two junior developers, which led to significant cost savings for the company. I completed all tasks ahead of schedule, focusing on Java-based applications that were multithreaded and communicated with embedded systems. This experience taught me how to work under pressure and how to manage and solve complex technical problems efficiently. Following my time at \\\\, I transitioned into freelance work as a FullStack Developer, working with technologies such as HTML, CSS, Bootstrap, JavaScript, Django, Spring, MySQL, and PostgreSQL. As a freelancer, I was responsible for finding solutions to a wide range of problems, often working independently and making decisions on the fly. I learned that self-reliance is key in this industry, and being resourceful is one of the most important qualities a developer can have. Later, I joined \\\\ elecom, where I worked on system integration with foreign teams, BPM process solutions, and the merging of complex systems in Oracle databases. I continued to solve challenges, often working with teams across borders and tackling technical obstacles that required creative and well-thought-out solutions. Eventually, I founded my own company, \\\\, where I focus on developing software solutions, Artificial Intelligence (AI), Cybersecurity, and Ethical Hacking. As an entrepreneur, I take pride in finding innovative solutions to problems, whether they come from clients or from technical obstacles I encounter along the way. I’ve also had the privilege of working with the Serbian Ministry of Defense and the police, handling sensitive projects that demand both technical expertise and trustworthiness. Being a self-taught programmer means that I have had to learn and adapt on my own, and I’ve learned to embrace challenges as opportunities for growth. I am constantly driven by the process of solving problems, and it is what keeps me engaged and fulfilled in my work. I am always open to new collaborations and am eager to take on new challenges that push my boundaries in technology, cybersecurity, and software development.

#reddit#experienced#software

reddit

0

1

Able_Swimming_4909•This week

Why raise in 2025? - I will not promote

I will not promote Lately, I've been thinking about how AI tools are completely reshaping what it means to bootstrap a startup. It honestly feels like we're living through a golden age for entrepreneurs where you don't necessarily need venture capital to build something big or meaningful. At my company, we're a small team of just four people, bootstrapping our AI-focused startup. Thanks to AI-powered tools, we're able to keep our burn rate ridiculously low, quickly test new ideas, and scale our operations way faster than we ever expected. It’s honestly pretty incredible how accessible advanced technology has become, even compared to just a few years ago. Of course, bootstrapping definitely comes with its own share of headaches. For example, we've noticed that funded startups get significantly better access to cloud credits, advertising budgets, and enterprise-level tools. We do have access to some discounts and free resources, but it rarely compares to what funded startups enjoy. This can feel frustrating, especially when you know you're competing directly with businesses that have those extra advantages. Visibility is another major challenge we've noticed. Without big funding announcements or a well-connected investor backing us, getting attention from media or even early adopters can be tough. It's just harder to make a splash without someone else's endorsement. We've had to accept and work around creatively. That said, there's something genuinely empowering about staying bootstrapped, prioritizing profitability, and maintaining control over our vision. After speaking with several investors, we've become aware of how investors can significantly influence or even redirect the trajectory of a business. We've heard stories where investors gained enough leverage to replace the original founders or have killed perfectly profitable businesses that were not growing "fast enough", which certainly gave us pause. They can definitely be helpful but giving the control over the future of my business to someone else would definitely make me feel anxious. At this time, we simply don't feel raising external capital aligns with our current goals, but we're also aware that this could change in the future. For now, maintaining autonomy and staying close to our original vision remains a priority. I'm curious to hear from others here who've been through this. Have you successfully bootstrapped an AI a tech business? What obstacles did you encounter, and how did you overcome them? EDIT: To give you a bit of perspective, my company is a B2B SaaS in the finance industry based in Europe. We have received VC funding in the past but it was an exceptionally good deal and we don't plan to raise in the near future even-thought it may change if we see the need to help us scale. We have also raised a significant amount in soft funding. Right now, we are growing on our revenues, and we plan to continue this trajectory. Recently, one of our developers left, and although we are a small team, we noticed that it had little to no impact on our productivity.

#reddit#raise#2025?

reddit

0

1

MHC2010•This week

West coast vs east coast investor attitude towards digital health and AI start-up

I am a neurologist and co-founder of a start-up company automating the detection of stroke in the home. We have been fundraising for the last few months and have had the experience of west coast investors telling us to ask for way more and east coast investors suggesting we ask for less. Many west coast investors seem excited by the AI component while many east coast investors see this aspect as a technical risk/a negative. Is this consistent with other people's experience and where on the east coast is the best place to try to fund-raise if you happen to be a start-up in the digital health space (unfortunately we are located in Virginia)? Thanks.

#reddit#west#coast

reddit

0

1

Slight-Explanation29•This week

10y of product development, 2 bankruptcies, and 1 Exit — what next? [Extended Story]

10 years of obsessive pursuit from the bottom to impressive product-market fit and exit. Bootstrapping tech products as Software Developer and 3x Startup Founder (2 bankruptcies and 1 exit). Hi everyone, your motivation has inspired me to delve deeper into my story. So, as promised to some of you, I've expanded on it a bit more, along with my brief reflections. There are many founders, product creators, and proactive individuals, I’ve read many of your crazy stories and lessons so I decided to share mine and the lessons I learned from the bottom to impressive product-market fit and exit. I've spent almost the past 10 years building tech products as a Corporate Team Leader, Senior Software Developer, Online Course Creator, Programming Tutor, Head of Development/CTO, and 3x Startup Founder (2 bankruptcies, and 1 exit). And what next? good question... A brief summary of my journey: Chapter 1: Software Developer / Team Leader / Senior Software Developer I’ve always wanted to create products that win over users’ hearts, carry value, and influence users. Ever since my school days, I’ve loved the tech part of building digital products. At the beginning of school, I started hosting servers for games, blogs and internet forums, and other things that did not require much programming knowledge. My classmates and later even over 100 people played on servers that I hosted on my home PC. Later, as the only person in school, I passed the final exam in computer science. During my computer science studies, I started my first job as a software developer. It was crazy, I was spending 200–300 hours a month in the office attending also to daily classes. Yes, I didn’t have a life, but it truly was the fulfillment of my dreams. I was able to earn good money doing what I love, and I devoted fully myself to it. My key to effectively studying IT and growing my knowledge at rocket speed was learning day by day reading guides, building products to the portfolio, watching youtube channels and attending conferences, and even watching them online, even if I didn’t understand everything at the beginning. In one year we’ve been to every possible event within 400km. We were building healthcare products that were actually used in hospitals and medical facilities. It was a beautiful adventure and tons of knowledge I took from this place. That time I built my first product teams, hired many great people, and over the years became a senior developer and team leader. Even I convinced my study mates to apply to this company and we studied together and worked as well. Finally, there were 4 of us, when I left a friend of mine took over my position and still works there. If you’re reading this, I’m sending you a flood of love and appreciation. I joined as the 8th person, and after around 4 years, when I left hungry for change, there were already over 30 of us, now around 100. It was a good time, greetings to everyone. I finished my Master’s and Engineering degrees in Computer Science, and it was time for changes. Chapter 2: 1st time as a Co-founder — Marketplace In the meantime, there was also my first startup (a marketplace) with four of my friends. We all worked on the product, each of us spent thousands of hours, after hours, entire weekends… and I think finally over a year of work. As you might guess, we lacked the most important things: sales, marketing, and product-market fit. We thought users think like us. We all also worked commercially, so the work went very smoothly, but we didn’t know what we should do next with it… Finally, we didn’t have any customers, but you know what, I don’t regret it, a lot of learning things which I used many times later. The first attempts at validating the idea with the market and business activities. In the end, the product was Airbnb-sized. Landing pages, listings, user panels, customer panels, admin site, notifications, caches, queues, load balancing, and much more. We wanted to publish the fully ready product to the market. It was a marketplace, so if you can guess, we had to attract both sides to be valuable. “Marketplace” — You can imagine something like Uber, if you don’t have passengers it was difficult to convince taxi drivers, if you don’t have a large number of taxi drivers you cannot attract passengers. After a year of development, we were overloaded, and without business, marketing, sales knowledge, and budget. Chapter 3: Corp Team Lead / Programming Tutor / Programming Architecture Workshop Leader Working in a corporation, a totally different environment, an international fintech, another learning experience, large products, and workmates who were waiting for 5 pm to finish — it wasn’t for me. Very slow product development, huge hierarchy, being an ant at the bottom, and low impact on the final product. At that time I understood that being a software developer is not anything special and I compared my work to factory worker. Sorry for that. High rates have been pumped only by high demand. Friends of mine from another industry do more difficult things and have a bigger responsibility for lower rates. That’s how the market works. This lower responsibility time allowed for building the first online course after hours, my own course platform, individual teaching newbies programming, and my first huge success — my first B2C customers, and B2B clients for workshops. I pivoted to full focus on sales, marketing, funnels, advertisements, demand, understanding the market, etc. It was 10x easier than startups but allowed me to learn and validate my conceptions and ideas on an easier market and showed me that it’s much easier to locate their problem/need/want and create a service/product that responds to it than to convince people of your innovative ideas. It’s just supply and demand, such a simple and basic statement, in reality, is very deep and difficult to understand without personal experience. If you’re inexperienced and you think you understand, you don’t. To this day, I love to analyze this catchword in relation to various industries / services / products and rediscover it again and again... While writing this sentence, I’m wondering if I’m not obsessed. Chapter 4: Next try — 2nd time as a founder — Edtech Drawing upon my experiences in selling services, offering trainings, and teaching programming, I wanted to broaden my horizons, delve into various fields of knowledge, involve more teachers, and so on. We started with simple services in different fields of knowledge, mainly relying on teaching in the local area (without online lessons). As I had already gathered some knowledge and experience in marketing and sales, things were going well and were moving in the right direction. The number of teachers in various fields was growing, as was the number of students. I don’t remember the exact statistics anymore, but it was another significant achievement that brought me a lot of satisfaction and new experiences. As you know, I’m a technology lover and couldn’t bear to look at manual processes — I wanted to automate everything: lessons, payments, invoices, customer service, etc. That’s when I hired our first developers (if you’re reading this, I’m sending you a flood of love — we spent a lot of time together and I remember it as a very fruitful and great year) and we began the process of tool and automation development. After a year we had really extended tools for students, teachers, franchise owners, etc. We had really big goals, we wanted to climb higher and higher. Maybe I wouldn’t even fully call it Startup, as the client was paying for the lessons, not for the software. But it gave us positive income, bootstrap financing, and tool development for services provided. Scaling this model was not as costless as SaaS because customer satisfaction was mainly on the side of the teacher, not the quality of the product (software). Finally, we grew to nearly 10 people and dozens of teachers, with zero external funding, and almost $50k monthly revenue. We worked very hard, day and night, and by November 2019, we were packed with clients to the brim. And as you know, that’s when the pandemic hit. It turned everything upside down by 180 degrees. Probably no one was ready for it. With a drastic drop in revenues, society started to save. Tired from the previous months, we had to work even harder. We had to reduce the team, change the model, and save what we had built. We stopped the tool’s development and sales, and with the developers, we started supporting other product teams to not fire them in difficult times. The tool worked passively for the next two years, reducing incomes month by month. With a smaller team providing programming services, we had full stability and earned more than relying only on educational services. At the peak of the pandemic, I promised myself that it was the last digital product I built… Never say never… Chapter 5: Time for fintech — Senior Software Developer / Team Lead / Head of Development I worked for small startups and companies. Building products from scratch, having a significant impact on the product, and complete fulfillment. Thousands of hours and sacrifices. This article mainly talks about startups that I built, so I don’t want to list all the companies, products, and applications that I supported as a technology consultant. These were mainly start-ups with a couple of people up to around 100 people on board. Some of the products were just a rescue mission, others were building an entire tech team. I was fully involved in all of them with the hope that we would work together for a long time, but I wasn’t the only one who made mistakes when looking for a product-market fit. One thing I fully understood: You can’t spend 8–15 hours a day writing code, managing a tech team, and still be able to help build an audience. In marketing and sales, you need to be rested and very creative to bring results and achieve further results and goals. If you have too many responsibilities related to technology, it becomes ineffective. I noticed that when I have more free time, more time to think, and more time to bounce the ball against the wall, I come up with really working marketing/sales strategies and solutions. It’s impossible when you are focused on code all day. You must know that this chapter of my life was long and has continued until now. Chapter 6: 3rd time as a founder — sold Never say never… right?\\ It was a time when the crypto market was really high and it was really trending topic. You know that I love technology right? So I cannot miss the blockchain world. I had experience in blockchain topics by learning on my own and from startups where I worked before. I was involved in crypto communities and I noticed a “starving crowd”. People who did things manually and earned money(crypto) on it.I found potential for building a small product that solves a technological problem. I said a few years before that I don’t want to start from scratch. I decided to share my observations and possibilities with my good friend. He said, “If you gonna built it, I’m in”. I couldn’t stop thinking about it. I had thought and planned every aspect of marketing and sales. And you know what. On this huge mindmap “product” was only one block. 90% of the mindmap was focused on marketing and sales. Now, writing this article, I understood what path I went from my first startup to this one. In the first (described earlier) 90% was the product, but in the last one 90% was sales and marketing. Many years later, I did this approach automatically. What has changed in my head over the years and so many mistakes? At that time, the company for which I provided services was acquired. The next day I got a thank you for my hard work and all my accounts were blocked. Life… I was shocked. We were simply replaced by their trusted technology managers. They wanted to get full control. They acted a bit unkindly, but I knew that they had all my knowledge about the product in the documentation, because I’m used to drawing everything so that in the moment of my weakness (illness, whatever) the team could handle it. That’s what solid leaders do, right? After a time, I know that these are normal procedures in financial companies, the point is that under the influence of emotions, do not do anything inappropriate. I quickly forgot about it, that I was brutally fired. All that mattered was to bring my plan to life. And it has been started, 15–20 hours a day every day. You have to believe me, getting back into the game was incredibly satisfying for me. I didn’t even know that I would be so excited. Then we also noticed that someone was starting to think about the same product as me. So the race began a game against time and the market. I assume that if you have reached this point, you are interested in product-market fit, marketing, and sales, so let me explain my assumptions to you: Product: A very very small tool that allowed you to automate proper tracking and creation of on-chain transactions. Literally, the whole app for the user was located on only three subpages. Starving Crowd: We tapped into an underserved market. The crypto market primarily operates via communities on platforms like Discord, Reddit, Twitter, Telegram, and so on. Therefore, our main strategy was directly communicating with users and demonstrating our tool. This was essentially “free marketing” (excluding the time we invested), as we did not need to invest in ads, promotional materials, or convince people about the efficacy of our tool. The community could directly observe on-chain transactions executed by our algorithms, which were processed at an exceptionally fast rate. This was something they couldn’t accomplish manually, so whenever someone conducted transactions using our algorithm, it was immediately noticeable and stirred a curiosity within the community (how did they do that!). Tests: I conducted the initial tests of the application on myself — we had already invested significantly in developing the product, but I preferred risking my own resources over that of the users. I provided the tool access to my wallet, containing 0.3ETH, and went to sleep. Upon waking up, I discovered that the transactions were successful and my wallet had grown to 0.99ETH. My excitement knew no bounds, it felt like a windfall. But, of course, there was a fair chance I could have lost it too. It worked. As we progressed, some users achieved higher results, but it largely hinged on the parameters set by them. As you can surmise, the strategy was simple — buy low, sell high. There was considerable risk involved. Churn: For those versed in marketing, the significance of repeat visitors cannot be overstated. Access to our tool was granted only after email verification and a special technique that I’d prefer to keep confidential. And this was all provided for free. While we had zero followers on social media, we saw an explosion in our email subscriber base and amassed a substantial number of users and advocates. Revenue Generation: Our product quickly gained popularity as we were effectively helping users earn — an undeniable value proposition. Now, it was time to capitalize on our efforts. We introduced a subscription model charging $300 per week or $1,000 per month — seemingly high rates, but the demand was so intense that it wasn’t an issue. Being a subscriber meant you were prioritized in the queue, ensuring you were among the first to reap benefits — thus adding more “value”. Marketing: The quality of our product and its ability to continually engage users contributed to it achieving what can best be described as viral. It was both a source of pride and astonishment to witness users sharing charts and analyses derived from our tool in forum discussions. They weren’t actively promoting our product but rather using screenshots from our application to illustrate certain aspects of the crypto world. By that stage, we had already assembled a team to assist with marketing, and programming, and to provide round-the-clock helpdesk support. Unforgettable Time: Despite the hype, my focus remained steadfast on monitoring our servers, their capacity, and speed. Considering we had only been on the market for a few weeks, we were yet to implement alerts, server scaling, etc. Our active user base spanned from Japan to the West Coast of the United States. Primarily, our application was used daily during the evenings, but considering the variety of time zones, the only time I could afford to sleep was during the evening hours in Far Eastern Europe, where we had the least users. However, someone always needed to be on guard, and as such, my phone was constantly by my side. After all, we couldn’t afford to let our users down. We found ourselves working 20 hours a day, catering to thousands of users, enduring physical fatigue, engaging in talks with VCs, and participating in conferences. Sudden Downturn: Our pinnacle was abruptly interrupted by the war in Ukraine (next macroeconomic shot straight in the face, lucky guy), a precipitous drop in cryptocurrency value, and swiftly emerging competition. By this time, there were 5–8 comparable tools had infiltrated the market. It was a challenging period as we continually stumbled upon new rivals. They immediately embarked on swift fundraising endeavors — a strategy we overlooked, which in retrospect was a mistake. Although our product was superior, the competitors’ rapid advancement and our insufficient funds for expeditious scaling posed significant challenges. Nonetheless, we made a good decision. We sold the product (exit) to competitors. The revenue from “exit” compensated for all the losses, leaving us with enough rest. We were a small team without substantial budgets for rapid development, and the risk of forming new teams without money to survive for more than 1–2 months was irresponsible. You have to believe me that this decision consumed us sleepless nights. Finally, we sold it. They turned off our app but took algorithms and users. Whether you believe it or not, after several months of toiling day and night, experiencing burnout, growing weary of the topic, and gaining an extra 15 kg in weight, we finally found our freedom… The exit wasn’t incredibly profitable, but we knew they had outdone us. The exit covered all our expenses and granted us a well-deserved rest for the subsequent quarter. It was an insane ride. Despite the uncertainty, stress, struggles, and sleepless nights, the story and experience will remain etched in my memory for the rest of my life. Swift Takeaways: Comprehending User Needs: Do you fully understand the product-market fit? Is your offering just an accessory or does it truly satisfy the user’s needs? The Power of Viral Marketing: Take inspiration from giants like Snapchat, ChatGPT, and Clubhouse. While your product might not attain the same scale (but remember, never say never…), the closer your concept is to theirs, the easier your journey will be. If your user is motivated to text a friend saying, “Hey, check out how cool this is” (like sharing ChatGPT), then you’re on the best track. Really. Even if it doesn’t seem immediately evident, there could be a way to incorporate this into your product. Keep looking until you find it. Niche targeting — the more specific and tailored your product is to a certain audience, the easier your journey will be People love buying from people — establishing a personal brand and associating yourself with the product can make things easier. Value: Seek to understand why users engage with your product and keep returning. The more specific and critical the issue you’re aiming to solve, the easier your path will be. Consider your offerings in terms of products and services and focus on sales and marketing, regardless of personal sentiments. These are just a few points, I plan to elaborate on all of them in a separate article. Many products undergo years of development in search of market fit, refining the user experience, and more. And guess what? There’s absolutely nothing wrong with that. Each product and market follows its own rules. Many startups have extensive histories before they finally make their mark (for instance, OpenAI). This entire journey spanned maybe 6–8 months. I grasped and capitalized on the opportunity, but we understood from the start that establishing a startup carried a significant risk, and our crypto product was 10 times riskier. Was it worth it? Given my passion for product development — absolutely. Was it profitable? — No, considering the hours spent — we lose. Did it provide a stable, problem-free life — nope. Did this entire adventure offer a wealth of happiness, joy, and unforgettable experiences — definitely yes. One thing is certain — we’ve amassed substantial experience and it’s not over yet :) So, what lies ahead? Chapter 7: Reverting to the contractor, developing a product for a crypto StartupReturning to the past, we continue our journey… I had invested substantial time and passion into the tech rescue mission product. I came on board as the technical Team Leader of a startup that had garnered over $20M in seed round funding, affiliated with the realm of cryptocurrencies. The investors were individuals with extensive backgrounds in the crypto world. My role was primarily technical, and there was an abundance of work to tackle. I was fully immersed, and genuinely devoted to the role. I was striving for excellence, knowing that if we secured another round of financing, the startup would accelerate rapidly. As for the product and marketing, I was more of an observer. After all, there were marketing professionals with decades of experience on board. These were individuals recruited from large crypto-related firms. I had faith in them, kept an eye on their actions, and focused on my own responsibilities. However, the reality was far from satisfactory. On the last day, the principal investor for the Series A round withdrew. The board made the tough decision to shut down. It was a period of intense observation and gaining experience in product management. This was a very brief summary of the last 10 years. And what next? (Last) Chapter 8: To be announced — Product Owner / Product Consultant / Strategist / CTO After spending countless hours and days deliberating my next steps, one thing is clear: My aspiration is to continue traversing the path of software product development, with the hopeful anticipation that one day, I might ride the crest of the next big wave and ascend to the prestigious status of a unicorn company. I find myself drawn to the process of building products, exploring product-market fit, strategizing, engaging in software development, seeking out new opportunities, networking, attending conferences, and continuously challenging myself by understanding the market and its competitive landscape. Product Owner / Product Consultant / CTO / COO: I’m not entirely sure how to categorize this role, as I anticipate that it will largely depend on the product to which I will commit myself fully. My idea is to find one startup/company that wants to build a product / or already has a product, want to speed up, or simply doesn’t know what’s next. Alternatively, I could be a part of an established company with a rich business history, which intends to invest in digitization and technological advancements. The goal would be to enrich their customer experience by offering complementary digital products Rather than initiating a new venture from ground zero with the same team, I am receptive to new challenges. I am confident that my past experiences will prove highly beneficial for the founders of promising, burgeoning startups that already possess a product, or are in the initial phases of development. ‘Consultant’ — I reckon we interpret this term differently. My aim is to be completely absorbed in a single product, crafting funnels, niches, strategies, and all that is necessary to repeatedly achieve the ‘product-market fit’ and significant revenue. To me, ‘consultant’ resonates more akin to freelancing than being an employee. My current goal is to kickstart as a consultant and aide, dealing with facilitating startups in their journey from point A to B. Here are two theoretical scenarios to illustrate my approach: Scenario 1: (Starting from point A) You have a product but struggle with marketing, adoption, software, strategy, sales, fundraising, or something else. I conduct an analysis and develop a strategy to reach point B. I take on the “dirty work” and implement necessary changes, including potential pivots or shifts (going all-in) to guide the product to point B. The goal is to reach point B, which could involve achieving a higher valuation, expanding the user base, increasing sales, or generating monthly revenue, among other metrics. Scenario 2: (Starting from point A) You have a plan or idea but face challenges with marketing, adoption, strategy, software, sales, fundraising, or something else. I analyze the situation and devise a strategy to reach point B. I tackle the necessary tasks, build the team, and overcome obstacles to propel the product to point B. I have come across the view that finding the elusive product-market fit is the job of the founder, and it’s hard for me to disagree. However, I believe that my support and experiences can help save money, many failures, and most importantly, time. I have spent a great deal of time learning from my mistakes, enduring failure after failure, and even had no one to ask for support or opinion, which is why I offer my help. Saving even a couple of years, realistically speaking, seems like a value I’m eager to provide… I invite you to share your thoughts and insights on these scenarios :) Closing Remarks: I appreciate your time and effort in reaching this point. This has been my journey, and I wouldn’t change it for the world. I had an extraordinary adventure, and now I’m ready for the next exciting battle with the market and new software products. While my entire narrative is centered around startups, especially the ones I personally built, I’m planning to share more insights drawn from all of my experiences, not just those as a co-founder. If you’re currently developing your product or even just considering the idea, I urge you to reach out to me. Perhaps together, we can create something monumental :) Thank you for your time and insights. I eagerly look forward to engaging in discussions and hearing your viewpoints. Please remember to like and subscribe. Nothing motivates to write more than positive feedback :) Matt.

#reddit#product#development,

reddit

0

1

ayezee33•This week

Am I on the right track?

This might be a little long for the average reader. But i'll do my best to format it so it's skimmable. Context I left my SaaS company 2 months ago. I was employee number 4 and helped them grow to 8 figures. I had a seat at the executive table and equity in the business. Burnt out and wanted to start my own thing. I forgot how hard it is to go from 0 👉 1 📚 Two schools of thought Build a product that solves your pain point and find others with that pain point Perform customer discovery calls until you get signal and start building + follow up with them 🥇 First approach For the last 45 days I built the product I wished I had when leading a 10 person marketing/sales team for the SaaS I was previously at. It checked all the boxes, pulled data, automated specific steps, showed the conversion tracking, data, etc. I launched it as a beta to my close network and the crowd went MILD. 😒 After some follow up - I realized I built something that already kind of exists and it's hard to convince others (even those who personally know me) that it's different or better. Undiscouraged, I am going to go back to the drawing board and try approach #2 above and schedule some customer discovery calls. 🥈 Second approach After trying and failing to turn the marketing numbers around at my last role I am convicted of 4 brutal truths about digital marketing today Truth #1 – AI-generated content is flooding the internet and ANYONE can and will be creating content with AI. Truth #2 – Ranking for high-volume keywords is harder than ever and probably not worth it anymore. Truth #3 – AI-driven efficiency is non-negotiable. If you haven’t installed AI in your business - you are WAY behind. Truth #4 – Most businesses are thinking about AI completely wrong. Easy button vs quality stair step. I have some early thoughts on how I would like to solve this (backed by data and some user stories). But my main question and the entire point of this post is.... ⁉️ Questions Before I schedule these product discovery calls should I make it clear where I am convicted and find those who want to talk (agree or disagree) with the above. Or just keep that out of the mix and ask them my product discovery questions regardless? I am probably overthinking it - but I just hit up my personal network with a beta launch, feels silly to go back with product discovery questions for them. Is there a good place (besides reddit) to pay people for product discovery calls? A quick Google Search and it's unclear to me.

#reddit#right#track?

reddit

0

1

joepigeon•This week

36 startup ideas found by analyzing podcasts (problem, solution & source episode)

Hey, I've been a bit of a podcast nerd for a long time. Around a year ago I began experimenting with transcription of podcasts for a SaaS I was running. I realized pretty quickly that there's a lot of knowledge and value in podcast discussions that is for all intents and purposes entirely unsearchable or discoverable to most people. I ended up stopping work on that SaaS product (party for lack of product/market fit, and partly because podcasting was far more interesting), and focusing on the podcast technology full-time instead. I'm a long-time lurker and poster of r/startups and thought this would make for some interesting content and inspiration for folks. Given I'm in this space, have millions of transcripts, and transcribe thousands daily... I've been exploring fun ways to expose some of the interesting knowledge and conversations taking place that utilize our own data/API. I'm a big fan of the usual startup podcasts (My First Million, Greg Isenberg, etc. etc.) and so I built an automation that turns all of the startup ideas discussed into a weekly email digest. I always struggle to listen to as many episodes as I'd actually like to, so I thought I'd summarise the stuff I care about instead (startup opportunities being discussed). I thought it would be interesting to post some of the ideas extracted so far. They range from being completely whacky and blue sky, to pretty boring but realistic. A word of warning before anyone complains – this is a big mixture of tech, ai, non-tech, local services, etc. ideas: Some of the ideas are completely mundane, but realistic (e.g. local window cleaning service) Some of the ideas are completely insane, blue sky, but sound super interesting Here's the latest 36 ideas: |Idea Name|Problem|Solution|Source| |:-|:-|:-|:-| |SalesForce-as-a-Service - White Label Enterprise Sales Teams|White-label enterprise sales teams for B2B SaaS. Companies need sales but can't hire/train. Recruit retail sellers, train for tech, charge 30% of deals closed.|Create a white-label enterprise sales team by recruiting natural salespeople from retail and direct sales backgrounds (e.g. mall kiosks, cutco knives). Train them specifically in B2B SaaS sales techniques and processes. Offer this trained sales force to tech companies on a contract basis.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |TechButler - Mobile Device Maintenance Service|Mobile tech maintenance service. Clean/optimize devices, improve WiFi, basic support. $100/visit to homes. Target affluent neighborhoods.|Mobile tech support service providing in-home device cleaning, optimization, and setup. Focus on common issues like WiFi improvement, device maintenance, and basic tech support.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |MemoryBox - At-Home Video Digitization Service|Door-to-door VHS conversion service. Parents have boxes of old tapes. Pick up, digitize, deliver. $30/tape with minimum order. Going extinct.|Door-to-door VHS to digital conversion service that handles everything from pickup to digital delivery. Make it extremely convenient for customers to preserve their memories.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |Elite Match Ventures - Success-Based Luxury Matchmaking|High-end matchmaking for 50M+ net worth individuals. Only charge $1M+ when they get married. No upfront fees. Extensive vetting process.|Premium matchmaking service exclusively for ultra-high net worth individuals with a pure contingency fee model - only get paid ($1M+) upon successful marriage. Focus on quality over quantity with extensive vetting and personalized matching.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |LocalHost - Simple Small Business Websites|Simple WordPress sites for local businesses. $50/month includes hosting, updates, security. Target restaurants and shops. Recurring revenue play.|Simplified web hosting and WordPress management service targeting local small businesses. Focus on basic sites with standard templates, ongoing maintenance, and reliable support for a fixed monthly fee.|My First Million - "Life Hacks From The King of Introverts + 7 Business Ideas| |VoiceJournal AI - Voice-First Smart Journaling|Voice-to-text journaling app with AI insights. 8,100 monthly searches. $15/month subscription. Partners with journaling YouTubers.|AI-powered journaling app that combines voice recording, transcription, and intelligent insights. Users can speak their thoughts, which are automatically transcribed and analyzed for patterns, emotions, and actionable insights.|Where It Happens - "7 $1M+ AI startup ideas you can launch tomorrow with $0"| |AIGenAds - AI-Generated UGC Content Platform|AI platform turning product briefs into UGC-style video ads. Brands spending $500/video for human creators. Generate 100 variations for $99/month.|AI platform that generates UGC-style video ads using AI avatars and scripting. System would allow rapid generation of multiple ad variations at a fraction of the cost. Platform would use existing AI avatar technology combined with script generation to create authentic-looking testimonial-style content.|Where It Happens - "7 $1M+ AI startup ideas you can launch tomorrow with $0"| |InfographAI - Automated Infographic Generation Platform|AI turning blog posts into branded infographics. Marketers spending hours on design. $99/month unlimited generation.|AI-powered platform that automatically converts blog posts and articles into visually appealing infographics. System would analyze content, extract key points, and generate professional designs using predefined templates and brand colors.|Where It Happens - "7 $1M+ AI startup ideas you can launch tomorrow with $0"| |KidFinance - Children's Financial Education Entertainment|Children's media franchise teaching financial literacy. Former preschool teacher creating 'Dora for money'. Books, videos, merchandise potential.|Character-driven financial education content for kids, including books, videos, and potentially TV show. Focus on making money concepts fun and memorable.|The Side Hustle Show - "How a Free Challenge Turned Into a $500,000 a Year Business (Greatest Hits)"| |FinanceTasker - Daily Financial Task Challenge|Free 30-day financial challenge with daily action items. People overwhelmed by money management. Makes $500k/year through books, speaking, and premium membership.|A free 30-day financial challenge delivering one simple, actionable task per day via email. Each task includes detailed scripts and instructions. Participants join a Facebook community for support and accountability. The program focuses on quick wins to build momentum. Automated delivery allows scaling.|The Side Hustle Show - "How a Free Challenge Turned Into a $500,000 a Year Business (Greatest Hits)"| |FinanceAcademy - Expert Financial Training Platform|Premium financial education platform. $13/month for expert-led courses and live Q&As. 4000+ members generating $40k+/month.|Premium membership site with expert-led courses, live Q&As, and community support. Focus on specific topics like real estate investing, business creation, and advanced money management.|The Side Hustle Show - "How a Free Challenge Turned Into a $500,000 a Year Business (Greatest Hits)"| |SecurityFirst Compliance - Real Security + Compliance Platform|Security-first compliance platform built by hackers. Companies spending $50k+ on fake security. Making $7M/year showing why current solutions don't work.|A compliance platform built by security experts that combines mandatory compliance requirements with real security measures. The solution includes hands-on security testing, expert guidance, and a focus on actual threat prevention rather than just documentation. It merges traditional compliance workflows with practical security implementations.|In the Pit with Cody Schneider| |LinkedInbound - Automated Professional Visibility Engine|LinkedIn automation for inbound job offers. Professionals spending hours on manual outreach. $99/month per job seeker.|Automated system for creating visibility and generating inbound interest on LinkedIn through coordinated profile viewing and engagement. Uses multiple accounts to create visibility patterns that trigger curiosity and inbound messages.|In the Pit with Cody Schneider| |ConvoTracker - Community Discussion Monitoring Platform|Community discussion monitoring across Reddit, Twitter, HN. Companies missing sales opportunities. $499/month per brand tracked.|Comprehensive monitoring system that tracks competitor mentions and industry discussions across multiple platforms (Reddit, Twitter, Hacker News, etc.) with automated alerts and engagement suggestions.|In the Pit with Cody Schneider| |ContentAds Pro - Smart Display Ad Implementation|Display ad implementation service for content creators. Bloggers losing thousands in ad revenue monthly. Makes $3-5k per site setup plus ongoing optimization fees.|Implementation of professional display advertising through networks like Mediavine that specialize in optimizing ad placement and revenue while maintaining user experience. Include features like turning off ads for email subscribers and careful placement to minimize impact on core metrics.|The Side Hustle Show - "636: Is Business Coaching Worth It? A Look Inside the last 12 months of Side Hustle Nation"| |MoneyAppReviews - Professional Side Hustle App Testing|Professional testing service for money-making apps. People wasting time on low-paying apps. Makes $20k/month from affiliate commissions and ads.|Professional app testing service that systematically reviews money-making apps and creates detailed, honest reviews including actual earnings data, time investment, and practical tips.|The Side Hustle Show - "636: Is Business Coaching Worth It? A Look Inside the last 12 months of Side Hustle Nation"| |LightPro - Holiday Light Installation Service|Professional Christmas light installation service. Homeowners afraid of ladders. $500-2000 per house plus storage.|Professional Christmas light installation service targeting residential and commercial properties. Full-service offering including design, installation, maintenance, removal and storage. Focus on safety and premium aesthetic results.|The Side Hustle Show - "639: 30 Ways to Make Extra Money for the Holidays"| |FocusMatch - Research Participant Marketplace|Marketplace connecting companies to paid research participants. Companies spending weeks finding people. $50-150/hour per study.|Online platform connecting companies directly with paid research participants. Participants create detailed profiles and get matched to relevant studies. Companies get faster access to their target demographic while participants earn money sharing opinions.|The Side Hustle Show - "639: 30 Ways to Make Extra Money for the Holidays"| |SolarShine Pro - Specialized Solar Panel Cleaning Service|Solar panel cleaning service using specialized equipment. Panels lose 50% efficiency when dirty. $650 per job, automated scheduling generates $18k/month from repeat customers.|Professional solar panel cleaning service using specialized deionized water system and European cleaning equipment. Includes automated 6-month scheduling, professional liability coverage, and warranty-safe cleaning processes. Service is bundled with inspection and performance monitoring.|The UpFlip Podcast - "156. $18K/Month with This ONE Service — Niche Business Idea"| |ExteriorCare Complete - One-Stop Exterior Maintenance Service|One-stop exterior home cleaning service (solar, windows, gutters, bird proofing). Automated scheduling. $650 average ticket. 60% repeat customers on 6-month contracts.|All-in-one exterior cleaning service offering comprehensive maintenance packages including solar, windows, gutters, roof cleaning and bird proofing. Single point of contact, consistent quality, and automated scheduling for all services.|The UpFlip Podcast - "156. $18K/Month with This ONE Service — Niche Business Idea"| |ContentMorph - Automated Cross-Platform Content Adaptation|AI platform converting blog posts into platform-optimized social content. Marketing teams spending 5hrs/post on manual adaptation. $199/mo per brand with 50% margins.|An AI-powered platform that automatically transforms long-form content (blog posts, podcasts, videos) into platform-specific formats (Instagram reels, TikToks, tweets). The system would preserve brand voice while optimizing for each platform's unique requirements and best practices.|Entrepreneurs on Fire - "Digital Threads: The Entrepreneur Playbook for Digital-First Marketing with Neal Schaffer"| |MarketerMatch - Verified Digital Marketing Talent Marketplace|Marketplace for pre-vetted digital marketing specialists. Entrepreneurs spending 15hrs/week on marketing tasks. Platform takes 15% commission averaging $900/month per active client.|A specialized marketplace exclusively for digital marketing professionals, pre-vetted for specific skills (video editing, social media, SEO, etc.). Platform includes skill verification, portfolio review, and specialization matching.|Entrepreneurs on Fire - "Digital Threads: The Entrepreneur Playbook for Digital-First Marketing with Neal Schaffer"| |Tiger Window Cleaning - Premium Local Window Service|Local window cleaning service targeting homeowners. Traditional companies charging 2x market rate. Making $10k/month from $200 initial investment.|Local window cleaning service combining competitive pricing ($5/pane), excellent customer service, and quality guarantees. Uses modern tools like water-fed poles for efficiency. Implements systematic approach to customer communication and follow-up.|The Side Hustle Show - "630: How this College Student’s Side Hustle Brings in $10k a Month"| |RealViz3D - Real Estate Visualization Platform|3D visualization service turning architectural plans into photorealistic renderings for real estate agents. Agents struggling with unbuilt property sales. Making $30-40k/year per operator.|Professional 3D modeling and rendering service that creates photorealistic visualizations of properties before they're built or renovated. The service transforms architectural plans into immersive 3D representations that show lighting, textures, and realistic details. This helps potential buyers fully understand and connect with the space before it physically exists.|Side Hustle School - "#2861 - TBT: An Architect’s Side Hustle in 3D Real Estate Modeling"| |Somewhere - Global Talent Marketplace|Platform connecting US companies with vetted overseas talent. Tech roles costing $150k locally filled for 50% less. Grew from $15M to $52M valuation in 9 months.|Platform connecting US companies with pre-vetted overseas talent at significantly lower rates while maintaining high quality. Handles payments, contracts, and quality assurance to remove friction from global hiring.|My First Million - "I Lost Everything Twice… Then Made $26M In 18 Months| |GymLaunch - Rapid Gym Turnaround Service|Consultants flying to struggling gyms to implement proven member acquisition systems. Gym owners lacking sales expertise. Made $100k in first 21 days.|Expert consultants fly in to implement proven member acquisition systems, train staff, and rapidly fill gyms with new members. The service combines sales training, marketing automation, and proven conversion tactics to transform struggling gyms into profitable businesses within weeks.|My First Million - "I Lost Everything Twice… Then Made $26M In 18 Months| |PublishPlus - Publishing Backend Monetization|Backend monetization system for publishing companies. One-time customers becoming recurring revenue. Grew business from $2M to $110M revenue.|Add complementary backend products and services to increase customer lifetime value. Develop software tools and additional services that natural extend from initial publishing product. Focus on high-margin recurring revenue streams.|My First Million - "I Lost Everything Twice… Then Made $26M In 18 Months| |WelcomeBot - Automated Employee Onboarding Platform|Automated employee welcome platform. HR teams struggling with consistent onboarding. $99/month per 100 employees.|An automated onboarding platform that creates personalized welcome experiences through pre-recorded video messages, scheduled check-ins, and automated swag delivery. The platform would ensure consistent high-quality onboarding regardless of timing or location.|Entrepreneurs on Fire - "Free Training on Building Systems and Processes to Scale Your Business with Chris Ronzio: An EOFire Classic from 2021"| |ProcessBrain - Business Knowledge Documentation Platform|SaaS platform turning tribal knowledge into documented processes. Business owners spending hours training new hires. $199/month per company.|A software platform that makes it easy to document and delegate business processes and procedures. The platform would include templates, guided documentation flows, and tools to easily share and update procedures. It would help businesses create a comprehensive playbook of their operations.|Entrepreneurs on Fire - "Free Training on Building Systems and Processes to Scale Your Business with Chris Ronzio: An EOFire Classic from 2021"| |TradeMatch - Modern Manufacturing Job Marketplace|Modern job board making manufacturing sexy again. Factory jobs paying $40/hr but can't recruit. $500 per successful referral.|A specialized job marketplace and recruitment platform focused exclusively on modern manufacturing and trade jobs. The platform would combine TikTok-style content marketing, referral programs, and modern UX to make manufacturing jobs appealing to Gen Z and young workers. Would leverage existing $500 referral fees and industry demand.|My First Million - "He Sold His Company For $15M, Then Got A Job At McDonald’s"| |GroundLevel - Executive Immersion Program|Structured program putting CEOs in front-line jobs. Executives disconnected from workers. $25k per placement.|A structured program that places executives and founders in front-line jobs (retail, warehouse, service) for 2-4 weeks with documentation and learning framework. Similar to Scott Heiferman's McDonald's experience but productized.|My First Million - "He Sold His Company For $15M, Then Got A Job At McDonald’s"| |OneStepAhead - Micro-Mentorship Marketplace|Marketplace for 30-min mentorship calls with people one step ahead. Professionals seeking specific guidance. Takes 15% of session fees.|MicroMentor Marketplace - Platform connecting people with mentors who are just one step ahead in their journey for focused, affordable micro-mentorship sessions.|Entrepreneurs on Fire - "How to Create an Unbroken Business with Michael Unbroken: An EOFire Classic from 2021"| |VulnerableLeader - Leadership Authenticity Training Platform|Leadership vulnerability training platform. Leaders struggling with authentic communication. $2k/month per company subscription.|Leadership Vulnerability Platform - A digital training platform combining assessment tools, guided exercises, and peer support to help leaders develop authentic communication skills. The platform would include real-world scenarios, video coaching, and measurable metrics for tracking leadership growth through vulnerability.|Entrepreneurs on Fire - "How to Create an Unbroken Business with Michael Unbroken: An EOFire Classic from 2021"| |NetworkAI - Smart Network Intelligence Platform|AI analyzing your network to find hidden valuable connections. Professionals missing opportunities in existing contacts. $49/month per user.|AI Network Navigator - Smart tool that analyzes your professional network across platforms, identifies valuable hidden connections, and suggests specific actionable ways to leverage relationships for mutual benefit.|Entrepreneurs on Fire - "How to Create an Unbroken Business with Michael Unbroken: An EOFire Classic from 2021"| |Porch Pumpkins - Seasonal Decoration Service|Full-service porch pumpkin decoration. Homeowners spend $300-1350 per season. One operator making $1M in 8 weeks seasonal revenue.|Full-service seasonal porch decoration service focused on autumn/Halloween, including design, installation, maintenance, and removal. Offering premium curated pumpkin arrangements with various package tiers.|My First Million - "The guy who gets paid $80K/yr to do nothing"| |Silent Companion - Professional Presence Service|Professional silent companions for lonely people. Huge problem in Japan/globally. $68/session, $80k/year per companion. Non-sexual, just presence.|A professional companion service where individuals can rent a non-judgmental, quiet presence for various activities. The companion provides silent company without the pressure of conversation or social performance. They accompany clients to events, meals, or just sit quietly together.|My First Million - "The guy who gets paid $80K/yr to do nothing"| Hope this is useful. If anyone would like to ensure I include any particular podcasts or episodes etc. in future posts, very happy to do so. I'll generally send \~5 ideas per week in a short weekly digest format (you can see the format I'd usually use in here: podcastmarketwatch.beehiiv.com). I find it mindblowing that the latest models with large context windows make it even possible to analyze full transcripts at such scale. It's a very exciting time we're living through! Would love some feedback on this stuff, happy to iterate and improve the analysis/ideas... or create a new newsletter on a different topic if anyone would like. Cheers!

#reddit#startup#ideas

reddit

0

1

GrowthGet•This week

The Cold-Calling AI Project I'm Working On Just Got Some Angel Investment!

Hey y'all. The AI cold calling startup I've been working on for 3-4 months now just got a $2,500 angel investment, and we have 2 current customers, a credit card processing broker and a hospital equipment rental company based out of Texas. We have around $1,500 revenue so far, but we're having lots of trouble fulfilling the contracts because our tech just isn't "there" yet. I'm the Chief Tech Officer, and I'm also running some operations. The other main person in this is the CEO who has a strong sales background and came up with the idea. I've been working purely remotely, and it's great having some income because I'm stuck at home because I'm disabled, basically... ​ We're using 11labs, openai, google speech to text, and a sh\*tty online dialer right now to run the first MVP which runs locally on our "botrunners" computers, and we're developing a web app with django python + javascript react. Our plan is, after we get the webapp working better, to hire more botrunners for $3 per hour from countries like Phillipines and India, and we're going to try to track all the actions the botrunners take to be able to train the AI to run it fully automated. The biggest problem we're facing right now with the tech is reducing latency, it started at 27 seconds to get a response and I've been able to get it down to 6 seconds, but people are still hanging up. We're trying several ways to mitigate this, including having pre-rendered speech playing something like "Okay" or "As an artificial representative, I'm still learning to be quicker on the pickup. We appreciate your patience." One of the industries we want to target is international web development and digital marketing companies, and we want to use the bot to cold-call businesses to pitch them our services. The goal is to replace $30 an hour cold-callers from the USA with $3 per hour total-cost automation. Apparently the CEO was given a $5 million valuation from the strength of the MVP from a VC. Our investment so far was at a $300k valuation tho. It's exciting. Trying to get Twilio working to be able to make calls programmatically instead of using our hacky workaround. Let me know if you have any questions. I just wanted to share this awesome news!

#reddit#cold-calling#project

reddit

0

0.6

kyr0x0•This week

Online Reputation AI - Startup got stuck

Hi, I‘m one of 3 co-founders of a startup that built an AI-driven SaaS and App product this year. We‘re coming from an SaaS background, two of us senior developers (in the 3% of highest earning freelancers in Germany) and expert in our fields. The third is a seasoned sales strategist. We have a minor 4th co-founder (legal advisor). The company is self-funded, no investors. Our tech is owned by us, built by us and the product was already operational after a few months. We basically solve three data science/NLP issues in a generalized way: understand customer feedback to improve your business. Analyzes online review with context and explains it with a drill down, aggregation, charts (AI insights, timeframe reports); evidence driven, agentic LLM and ETL processes drive this. respond to customer feedback, half-automated, human in the loop, but AI supported. In the tone of your brand, any language. And context-aware, with your customer support signature etc. competitor analysis. Because we do 1 for you, we can do 1. for all of your competitors and compare the results, yielding insights like „oh, this happens to everyone in November to December, so I should focus on something else“ — etc. Now, after a huge sales effort we got only one paying customer. This customer is petty happy with the product. They tell us that they use our product daily, it‘s better than all the other solutions out there (better than TrustYou, etc.) However, after cold calling/emailing hundreds of leads, we almost always hear that „what we have is good enough“. Or that they don‘t have budget. I‘m the introverted tech part of the startup. I‘m good with algorithms. Give me any tech issue and I will solve it for you quickly and efficiently. I make stuff work. But with my startups I never had commercial luck. People always tell me about my stellar potential, because I can build things almost nobody else can. I come from a poor families background, worked my way up the very hard way. I just love tech and programming. I wrote a book for O’Reilly once. I‘m not doing bad economically, but I‘m probably not the best sales person. After founding a few startups with amazing tech, people using the products and loving them, but no commercial success, I truly question myself and if I‘m just unlucky with the fact that I‘m located in Europe, targeting the wrong industries, or are just unlucky somehow? I won‘t blame my co-founders here. They definitely did the best they could. I‘m just a bit resignated. I recently thought about valuing my own lifetime more and only building software for myself anymore. Basically not focusing on what problems other people face and trying to solve them, but solely focusing on what I enjoy doing most — e.g. coding algorithms for a music visualizer. Because in the end, my time is my most valuable resource. If I waste any second on something that isn‘t contributing to „my life“ and how I define success, then it would be a rather stupid deed? I don‘t want to derail too much here. I‘m confused and seeking for advice. Burn me if you like, but please be aware that you are talking to a broadly educated nerd.

#reddit#online#reputation

reddit

0

1

Royal_Rest8409•This week

How a founder built a B2B AI startup to serve with 65+ global brands (including Fortune500 companies) (I will not promote)

AI Palette is an AI-driven platform that helps food and beverage companies predict emerging product trends. I had the opportunity recently to sit down with the founder to get his advice on building an AI-first startup, which he'll be going through in this post. (I will not promote) About AI Palette: Co-founders: >!2 (Somsubhra GanChoudhuri, Himanshu Upreti)!!100+!!$12.7M USD!!AI-powered predictive analytics for the CPG (Consumer Packaged Goods) industry!!Signed first paying customer in the first year!!65+ global brands, including Cargill, Diageo, Ajinomoto, Symrise, Mondelez, and L’Oréal, use AI Palette!!Every new product launched has secured a paying client within months!!Expanded into Beauty & Personal Care (BPC), onboarding one of India’s largest BPC companies within weeks!!Launched multiple new product lines in the last two years, creating a unified suite for brand innovation!Identify the pain points in your industry for ideas* When I was working in the flavour and fragrance industry, I noticed a major issue CPG companies faced: launching a product took at least one to two years. For instance, if a company decided today to launch a new juice, it wouldn’t hit the market until 2027. This long timeline made it difficult to stay relevant and on top of trends. Another big problem I noticed was that companies relied heavily on market research to determine what products to launch. While this might work for current consumer preferences, it was highly inefficient since the product wouldn’t actually reach the market for several years. By the time the product launched, the consumer trends had already shifted, making that research outdated. That’s where AI can play a crucial role. Instead of looking at what consumers like today, we realised that companies should use AI to predict what they will want next. This allows businesses to create products that are ahead of the curve. Right now, the failure rate for new product launches is alarmingly high, with 8 out of 10 products failing. By leveraging AI, companies can avoid wasting resources on products that won’t succeed, leading to better, more successful launches. Start by talking to as many industry experts as possible to identify the real problems When we first had the idea for AI Palette, it was just a hunch, a gut feeling—we had no idea whether people would actually pay for it. To validate the idea, we reached out to as many people as we could within the industry. Since our focus area was all about consumer insights, we spoke to professionals in the CPG sector, particularly those in the insights departments of CPG companies. Through these early conversations, we began to see a common pattern emerge and identified the exact problem we wanted to solve. Don’t tell people what you’re building—listen to their frustrations and challenges first. Going into these early customer conversations, our goal was to listen and understand their challenges without telling them what we were trying to build. This is crucial as it ensures that you can gather as much data about the problem to truly understand it and that you aren't biasing their answers by showing your solution. This process helped us in two key ways: First, it validated that there was a real problem in the industry through the number of people who spoke about experiencing the same problem. Second, it allowed us to understand the exact scale and depth of the problem—e.g., how much money companies were spending on consumer research, what kind of tools they were currently using, etc. Narrow down your focus to a small, actionable area to solve initially. Once we were certain that there was a clear problem worth solving, we didn’t try to tackle everything at once. As a small team of two people, we started by focusing on a specific area of the problem—something big enough to matter but small enough for us to handle. Then, we approached customers with a potential solution and asked them for feedback. We learnt that our solution seemed promising, but we wanted to validate it further. If customers are willing to pay you for the solution, it’s a strong validation signal for market demand. One of our early customer interviewees even asked us to deliver the solution, which we did manually at first. We used machine learning models to analyse the data and presented the results in a slide deck. They paid us for the work, which was a critical moment. It meant we had something with real potential, and we had customers willing to pay us before we had even built the full product. This was the key validation that we needed. By the time we were ready to build the product, we had already gathered crucial insights from our early customers. We understood the specific information they wanted and how they wanted the results to be presented. This input was invaluable in shaping the development of our final product. Building & Product Development Start with a simple concept/design to validate with customers before building When we realised the problem and solution, we began by designing the product, but not by jumping straight into coding. Instead, we created wireframes and user interfaces using tools like InVision and Figma. This allowed us to visually represent the product without the need for backend or frontend development at first. The goal was to showcase how the product would look and feel, helping potential customers understand its value before we even started building. We showed these designs to potential customers and asked for feedback. Would they want to buy this product? Would they pay for it? We didn’t dive into actual development until we found a customer willing to pay a significant amount for the solution. This approach helped us ensure we were on the right track and didn’t waste time or resources building something customers didn’t actually want. Deliver your solution using a manual consulting approach before developing an automated product Initially, we solved problems for customers in a more "consulting" manner, delivering insights manually. Recall how I mentioned that when one of our early customer interviewees asked us to deliver the solution, we initially did it manually by using machine learning models to analyse the data and presenting the results to them in a slide deck. This works for the initial stages of validating your solution, as you don't want to invest too much time into building a full-blown MVP before understanding the exact features and functionalities that your users want. However, after confirming that customers were willing to pay for what we provided, we moved forward with actual product development. This shift from a manual service to product development was key to scaling in a sustainable manner, as our building was guided by real-world feedback and insights rather than intuition. Let ongoing customer feedback drive iteration and the product roadmap Once we built the first version of the product, it was basic, solving only one problem. But as we worked closely with customers, they requested additional features and functionalities to make it more useful. As a result, we continued to evolve the product to handle more complex use cases, gradually developing new modules based on customer feedback. Product development is a continuous process. Our early customers pushed us to expand features and modules, from solving just 20% of their problems to tackling 50–60% of their needs. These demands shaped our product roadmap and guided the development of new features, ultimately resulting in a more complete solution. Revenue and user numbers are key metrics for assessing product-market fit. However, critical mass varies across industries Product-market fit (PMF) can often be gauged by looking at the size of your revenue and the number of customers you're serving. Once you've reached a certain critical mass of customers, you can usually tell that you're starting to hit product-market fit. However, this critical mass varies by industry and the type of customers you're targeting. For example, if you're building an app for a broad consumer market, you may need thousands of users. But for enterprise software, product-market fit may be reached with just a few dozen key customers. Compare customer engagement and retention with other available solutions on the market for product-market fit Revenue and the number of customers alone isn't always enough to determine if you're reaching product-market fit. The type of customer and the use case for your product also matter. The level of engagement with your product—how much time users are spending on the platform—is also an important metric to track. The more time they spend, the more likely it is that your product is meeting a crucial need. Another way to evaluate product-market fit is by assessing retention, i.e whether users are returning to your platform and relying on it consistently, as compared to other solutions available. That's another key indication that your solution is gaining traction in the market. Business Model & Monetisation Prioritise scalability Initially, we started with a consulting-type model where we tailor-made specific solutions for each customer use-case we encountered and delivered the CPG insights manually, but we soon realized that this wasn't scalable. The problem with consulting is that you need to do the same work repeatedly for every new project, which requires a large team to handle the workload. That is not how you sustain a high-growth startup. To solve this, we focused on building a product that would address the most common problems faced by our customers. Once built, this product could be sold to thousands of customers without significant overheads, making the business scalable. With this in mind, we decided on a SaaS (Software as a Service) business model. The benefit of SaaS is that once you create the software, you can sell it to many customers without adding extra overhead. This results in a business with higher margins, where the same product can serve many customers simultaneously, making it much more efficient than the consulting model. Adopt a predictable, simplistic business model for efficiency. Look to industry practices for guidance When it came to monetisation, we considered the needs of our CPG customers, who I knew from experience were already accustomed to paying annual subscriptions for sales databases and other software services. We decided to adopt the same model and charge our customers an annual upfront fee. This model worked well for our target market, aligning with industry standards and ensuring stable, recurring revenue. Moreover, our target CPG customers were already used to this business model and didn't have to choose from a huge variety of payment options, making closing sales a straightforward and efficient process. Marketing & Sales Educate the market to position yourself as a thought leader When we started, AI was not widely understood, especially in the CPG industry. We had to create awareness around both AI and its potential value. Our strategy focused on educating potential users and customers about AI, its relevance, and why they should invest in it. This education was crucial to the success of our marketing efforts. To establish credibility, we adopted a thought leadership approach. We wrote blogs on the importance of AI and how it could solve problems for CPG companies. We also participated in events and conferences to demonstrate our expertise in applying AI to the industry. This helped us build our brand and reputation as leaders in the AI space for CPG, and word-of-mouth spread as customers recognized us as the go-to company for AI solutions. It’s tempting for startups to offer products for free in the hopes of gaining early traction with customers, but this approach doesn't work in the long run. Free offerings don’t establish the value of your product, and customers may not take them seriously. You should always charge for pilots, even if the fee is minimal, to ensure that the customer is serious about potentially working with you, and that they are committed and engaged with the product. Pilots/POCs/Demos should aim to give a "flavour" of what you can deliver A paid pilot/POC trial also gives you the opportunity to provide a “flavour” of what your product can deliver, helping to build confidence and trust with the client. It allows customers to experience a detailed preview of what your product can do, which builds anticipation and desire for the full functionality. During this phase, ensure your product is built to give them a taste of the value you can provide, which sets the stage for a broader, more impactful adoption down the line. Fundraising & Financial Management Leverage PR to generate inbound interest from VCs When it comes to fundraising, our approach was fairly traditional—we reached out to VCs and used connections from existing investors to make introductions. However, looking back, one thing that really helped us build momentum during our fundraising process was getting featured in Tech in Asia. This wasn’t planned; it just so happened that Tech in Asia was doing a series on AI startups in Southeast Asia and they reached out to us for an article. During the interview, they asked if we were fundraising, and we mentioned that we were. As a result, several VCs we hadn’t yet contacted reached out to us. This inbound interest was incredibly valuable, and we found it far more effective than our outbound efforts. So, if you can, try to generate some PR attention—it can help create inbound interest from VCs, and that interest is typically much stronger and more promising than any outbound strategies because they've gone out of their way to reach out to you. Be well-prepared and deliberate about fundraising. Keep trying and don't lose heart When pitching to VCs, it’s crucial to be thoroughly prepared, as you typically only get one shot at making an impression. If you mess up, it’s unlikely they’ll give you a second chance. You need to have key metrics at your fingertips, especially if you're running a SaaS company. Be ready to answer questions like: What’s your retention rate? What are your projections for the year? How much will you close? What’s your average contract value? These numbers should be at the top of your mind. Additionally, fundraising should be treated as a structured process, not something you do on the side while juggling other tasks. When you start, create a clear plan: identify 20 VCs to reach out to each week. By planning ahead, you’ll maintain momentum and speed up the process. Fundraising can be exhausting and disheartening, especially when you face multiple rejections. Remember, you just need one investor to say yes to make it all worthwhile. When using funds, prioritise profitability and grow only when necessary. Don't rely on funding to survive. In the past, the common advice for startups was to raise money, burn through it quickly, and use it to boost revenue numbers, even if that meant operating at a loss. The idea was that profitability wasn’t the main focus, and the goal was to show rapid growth for the next funding round. However, times have changed, especially with the shift from “funding summer” to “funding winter.” My advice now is to aim for profitability as soon as possible and grow only when it's truly needed. For example, it’s tempting to hire a large team when you have substantial funds in the bank, but ask yourself: Do you really need 10 new hires, or could you get by with just four? Growing too quickly can lead to unnecessary expenses, so focus on reaching profitability as soon as possible, rather than just inflating your team or burn rate. The key takeaway is to spend your funds wisely and only when absolutely necessary to reach profitability. You want to avoid becoming dependent on future VC investments to keep your company afloat. Instead, prioritize reaching break-even as quickly as you can, so you're not reliant on external funding to survive in the long run. Team-Building & Leadership Look for complementary skill sets in co-founders When choosing a co-founder, it’s important to find someone with a complementary skill set, not just someone you’re close to. For example, I come from a business and commercial background, so I needed someone with technical expertise. That’s when I found my co-founder, Himanshu, who had experience in machine learning and AI. He was a great match because his technical knowledge complemented my business skills, and together we formed a strong team. It might seem natural to choose your best friend as your co-founder, but this can often lead to conflict. Chances are, you and your best friend share similar interests, skills, and backgrounds, which doesn’t bring diversity to the table. If both of you come from the same industry or have the same strengths, you may end up butting heads on how things should be done. Having diverse skill sets helps avoid this and fosters a more collaborative working relationship. Himanshu (left) and Somsubhra (right) co-founded AI Palette in 2018 Define roles clearly to prevent co-founder conflict To avoid conflict, it’s essential that your roles as co-founders are clearly defined from the beginning. If your co-founder and you have distinct responsibilities, there is no room for overlap or disagreement. This ensures that both of you can work without stepping on each other's toes, and there’s mutual respect for each other’s expertise. This is another reason as to why it helps to have a co-founder with a complementary skillset to yours. Not only is having similar industry backgrounds and skillsets not particularly useful when building out your startup, it's also more likely to lead to conflicts since you both have similar subject expertise. On the other hand, if your co-founder is an expert in something that you're not, you're less likely to argue with them about their decisions regarding that aspect of the business and vice versa when it comes to your decisions. Look for employees who are driven by your mission, not salary For early-stage startups, the first hires are crucial. These employees need to be highly motivated and excited about the mission. Since the salary will likely be low and the work demanding, they must be driven by something beyond just the paycheck. The right employees are the swash-buckling pirates and romantics, i.e those who are genuinely passionate about the startup’s vision and want to be part of something impactful beyond material gains. When employees are motivated by the mission, they are more likely to stick around and help take the startup to greater heights. A litmus test for hiring: Would you be excited to work with them on a Sunday? One of the most important rounds in the hiring process is the culture fit round. This is where you assess whether a candidate shares the same values as you and your team. A key question to ask yourself is: "Would I be excited to work with this person on a Sunday?" If there’s any doubt about your answer, it’s likely not a good fit. The idea is that you want employees who align with the company's culture and values and who you would enjoy collaborating with even outside of regular work hours. How we structure the team at AI Palette We have three broad functions in our organization. The first two are the big ones: Technical Team – This is the core of our product and technology. This team is responsible for product development and incorporating customer feedback into improving the technology Commercial Team – This includes sales, marketing, customer service, account managers, and so on, handling everything related to business growth and customer relations. General and Administrative Team – This smaller team supports functions like finance, HR, and administration. As with almost all businesses, we have teams that address the two core tasks of building (technical team) and selling (commercial team), but given the size we're at now, having the administrative team helps smoothen operations. Set broad goals but let your teams decide on execution What I've done is recruit highly skilled people who don't need me to micromanage them on a day-to-day basis. They're experts in their roles, and as Steve Jobs said, when you hire the right person, you don't have to tell them what to do—they understand the purpose and tell you what to do. So, my job as the CEO is to set the broader goals for them, review the plans they have to achieve those goals, and periodically check in on progress. For example, if our broad goal is to meet a certain revenue target, I break it down across teams: For the sales team, I’ll look at how they plan to hit that target—how many customers they need to sell to, how many salespeople they need, and what tactics and strategies they plan to use. For the technical team, I’ll evaluate our product offerings—whether they think we need to build new products to attract more customers, and whether they think it's scalable for the number of customers we plan to serve. This way, the entire organization's tasks are cascaded in alignment with our overarching goals, with me setting the direction and leaving the details of execution to the skilled team members that I hire.

#reddit#founder#built

reddit

0

1

NoJob8068•This week

AI Might Be the Best Industry for Ambitious Lazy People i will not promote

Not here to promote, just talk about my experience with starting a new business. I'm not new to the game, so I was able to speed-run my new AI automation agency. I currently run a software company with a co-founder, and I recently decided to start a new AI and automation agency. I just had a private launch this week, and I already have a $2K client lined up, ready to buy, along with some other interested parties, as I have sales calls with them coming up. I found all of my leads after choosing a niche to focus on and using this tool I built that automatically scrapes IG data. My tool is “unique” because it automagically qualifies the leads with AI. It even has a custom frontend, and I used this tool as a case study to secure the client I have now, and I accomplished all of this in the span of about a week. Granted, I have a background in engineering, so picking up AI was easier for me, but anyone can do it. You can even use AI to learn AI. If you haven’t used AI in your business yet, I would strongly suggest getting into AI and automation. If you've been considering starting a business but don't know what business to start, take this as a sign to turn AI into a business. i will not promote

#reddit#might#best

reddit

0

1

EquivalentDecent5582•This week

Looking for an accountability partner as a solo founder. [I will not promote]

Hello! I am a technical founder focused on using AI solutions to drive automation. Recently had a co-founder split after working together for a couple month. We had a very good traction but I made a decision to leave because I believed we didn't have a solid foundational relationship that can be sustained for a long time. Had more of a co-worker style relationship. Took on the short-term pain to set myself up for a long term success. He was the one leading the sales and relation with the businesses, so we decided he will be leading the company moving forward and we split on very good terms. Back in the gulag now and starting from scratch. Took three days to reset and recover. When I tried to get back at things yesterday, my brain wasn't just having it. My stress activation got so high, i did like 4 wim hof breathing sessions and a 10 mile run to relieve the stress buildup. There is something about uncertainty and working without a lack of clear path that is super hard to process especially when you are solo. Currently I am working through my previous idea backlogs that I have built up and re-starting previous conversations. But my brain isn't giving me the dopamine hit from driving toward action as much as I used to. So any work that i do feels like a slogging through mud. I am looking to experiment with having an accountability partner, to make the initial ramp up easier. Thinking of doing the elon musk style "What have you done this week?" report that we can do to drive accountability and give that extra motivation. If you're navigating similar challenges as a solo founder and believe mutual accountability could accelerate our progress and growth, I'd love to connect. Let's help each other build momentum and stay motivated—drop a comment or DM if interested! I will not promote

#reddit#looking#accountability

reddit

0

1

GrowthGet•This week

The Cold-Calling AI Project I'm Working On Just Got Some Angel Investment!

Hey y'all. The AI cold calling startup I've been working on for 3-4 months now just got a $2,500 angel investment, and we have 2 current customers, a credit card processing broker and a hospital equipment rental company based out of Texas. We have around $1,500 revenue so far, but we're having lots of trouble fulfilling the contracts because our tech just isn't "there" yet. I'm the Chief Tech Officer, and I'm also running some operations. The other main person in this is the CEO who has a strong sales background and came up with the idea. I've been working purely remotely, and it's great having some income because I'm stuck at home because I'm disabled, basically... ​ We're using 11labs, openai, google speech to text, and a sh\*tty online dialer right now to run the first MVP which runs locally on our "botrunners" computers, and we're developing a web app with django python + javascript react. Our plan is, after we get the webapp working better, to hire more botrunners for $3 per hour from countries like Phillipines and India, and we're going to try to track all the actions the botrunners take to be able to train the AI to run it fully automated. The biggest problem we're facing right now with the tech is reducing latency, it started at 27 seconds to get a response and I've been able to get it down to 6 seconds, but people are still hanging up. We're trying several ways to mitigate this, including having pre-rendered speech playing something like "Okay" or "As an artificial representative, I'm still learning to be quicker on the pickup. We appreciate your patience." One of the industries we want to target is international web development and digital marketing companies, and we want to use the bot to cold-call businesses to pitch them our services. The goal is to replace $30 an hour cold-callers from the USA with $3 per hour total-cost automation. Apparently the CEO was given a $5 million valuation from the strength of the MVP from a VC. Our investment so far was at a $300k valuation tho. It's exciting. Trying to get Twilio working to be able to make calls programmatically instead of using our hacky workaround. Let me know if you have any questions. I just wanted to share this awesome news!

#reddit#cold-calling#project

reddit

0

1

stellarcitizen•This week

I fell into the builder's trap and need help getting out

Hi r/startups, First-time technical founder here. Two years ago, I decided to leave the 9-5 grind and build something meaningful. Now, I have (what I believe is) a brilliant technical solution but no clear business case. I’m seeking a cofounder with product and marketing expertise to help pivot my project into a viable business - or start a new one. Details below. About Me 36yo, born in Berlin and moved to San Francisco 8 years ago Master's in Software Engineering with 15 years of experience Worked with early-stage startups in Berlin and a venture studio in SF Spent the past years leading a team of 12 shipping enterprise software The tech I've built An AI engine that makes it easy for developers to automate their workflows. It works with code, issues, PRs and integrates with 3rd party systems like error trackers, wikis, ticketing systems, etc. It takes natural language instructions, fulfills them autonomously and responds with a result. The functionality is served as a platform, with an API and an SDK. On top of it, I've built a CLI and a web application with productivity tools for developers. Who and what I'm looking for My main goal is to leave my current job and build a company around a problem that matters to me, ideally with considerable equity. I’m looking for: A cofounder with product and marketing expertise who sees potential in my tech and can help turn it into a successful business—or someone with a strong business case who needs a technical founder. Mentorship from someone experienced in dev tool startups or as a successful solo founder. I’d love to learn from your journey and would be happy to offer my technical expertise or collaborate on projects in return. Happy to answer any questions or provide more details. Cheers!

#reddit#fell#into

reddit

0

1

stellarcitizen•This week

I fell into the builder's trap and need help getting out

Hi r/startups, First-time technical founder here. Two years ago, I decided to leave the 9-5 grind and build something meaningful. Now, I have (what I believe is) a brilliant technical solution but no clear business case. I’m seeking a cofounder with product and marketing expertise to help pivot my project into a viable business - or start a new one. Details below. About Me 36yo, born in Berlin and moved to San Francisco 8 years ago Master's in Software Engineering with 15 years of experience Worked with early-stage startups in Berlin and a venture studio in SF Spent the past years leading a team of 12 shipping enterprise software The tech I've built An AI engine that makes it easy for developers to automate their workflows. It works with code, issues, PRs and integrates with 3rd party systems like error trackers, wikis, ticketing systems, etc. It takes natural language instructions, fulfills them autonomously and responds with a result. The functionality is served as a platform, with an API and an SDK. On top of it, I've built a CLI and a web application with productivity tools for developers. Who and what I'm looking for My main goal is to leave my current job and build a company around a problem that matters to me, ideally with considerable equity. I’m looking for: A cofounder with product and marketing expertise who sees potential in my tech and can help turn it into a successful business—or someone with a strong business case who needs a technical founder. Mentorship from someone experienced in dev tool startups or as a successful solo founder. I’d love to learn from your journey and would be happy to offer my technical expertise or collaborate on projects in return. Happy to answer any questions or provide more details. Cheers!

#reddit#fell#into

reddit

0

1

Disastrous-Airport88•This week

From Running a $350M Startup to Failing Big and Rediscovering What Really Matters in Life ❤️

This is my story. I’ve always been a hustler. I don’t remember a time I wasn’t working since I was 14. Barely slept 4 hours a night, always busy—solving problems, putting out fires. After college (LLB and MBA), I was lost. I tried regular jobs but couldn’t get excited, and when I’m not excited, I spiral. But I knew entrepreneurship; I just didn’t realize it was an option for adults. Then, in 2017 a friend asked me to help with their startup. “Cool,” I thought. Finally, a place where I could solve problems all day. It was a small e-commerce idea, tackling an interesting angle. I worked 17-hour days, delivering on a bike, talking to customers, vendors, and even random people on the street. Things moved fast. We applied to Y Combinator, got in, and raised $18M before Demo Day even started. We grew 100% month-over-month. Then came another $40M, and I moved to NYC. Before I knew it, we had 1,000 employees and raised $80M more. I was COO, managing 17 direct reports (VPs of Ops, Finance, HR, Data, and more) and 800 indirect employees. On the surface, I was on top of the world. But in reality, I was at rock bottom. I couldn’t sleep, drowning in anxiety, and eventually ended up on antidepressants. Then 2022 hit. We needed to raise $100M, but we couldn’t. In three brutal months, we laid off 900 people. It was the darkest period of my life. I felt like I’d failed everyone—myself, investors, my company, and my team. I took a year off. Packed up the car with my wife and drove across Europe, staying in remote places, just trying to calm my nervous system. I couldn’t speak to anyone, felt ashamed, and battled deep depression. It took over a year, therapy, plant medicine, intense morning routines, and a workout regimen to get back on my feet, physically and mentally. Now, I’m on the other side. In the past 6 months, I’ve been regaining my mojo, with a new respect for who I am and why I’m here. I made peace with what I went through over those 7 years—the lessons, the people, the experiences. I started reconnecting with my community, giving back. Every week, I have conversations with young founders, offering direction, or even jumping in to help with their operations. It’s been a huge gift. I also began exploring side projects. I never knew how to code, but I’ve always had ideas. Recent advances in AI gave me the push I needed. I built my first app, as my first attempt at my true passion—consumer products for kids. Today, I feel wholesome about my journey. I hope others can see that too. ❤️ EDIT: Wow, I didn’t expect this post to resonate with so many people. A lot of you have DM’d me, and I’ll try to respond. Just a heads-up, though—I’m juggling consulting and new projects, so I can’t jump on too many calls. Since I’m not promoting anything, I won’t be funneling folks to my page, so forgive me if I don’t get back to everyone. Anyway, it’s amazing to connect with so many of you. I’d love to write more, so let me know what topics you’d be interested in!

#reddit#running#$350m

reddit

0

0

Masony817•This week

Raising sf venture in the south

So I currenlty run a tech startup in Chattanooga TN (between nashville and atlanta) and this city is very few and far between in tech or startup funding. I am planning on moving to SF someday but my girlfriend is still in school here for the next year and we can't quite afford to move to the bay area yet. My startup needs funding and there is little to no vc's in the area and if you can find someone interested in a deal then they want 30% or more of your company. How hard would it be to raise a 350k pre-seed (with 5-10 customers at 250/mo b2b ai powered smb call management) remotely?

#reddit#raising#venture

reddit

0

1

ItsRyeGuyy•This week

Honest thoughts on our startup

Hey y'all, we've recently started a marking push, overhauled the website, and our machine learning team has done drastic work to improve the reviews & auto pr descriptions. That being said, would love some candid feedback if you or your team members would consider using a tool like ours and if not, why not. Our company is Korbit AI and we do context based, AI code reviews and automated PR descriptions. While we have been getting more traction since some of the updates and larger companies are starting to sign up, I would really appreciate some honest opinions on why you \wouldn't\ try a tool like this in hopes we can use that info to alter marketing etc. This is not meant to be a promotion post, and legitimately looking to learn from other people rocking startups trying to build up a larger customer base etc. Any feedback is very much appreciated Thank you in advanced, Riley

#reddit#honest#thoughts

reddit

0

1

NoJob8068•This week

AI Might Be the Best Industry for Ambitious Lazy People i will not promote

Not here to promote, just talk about my experience with starting a new business. I'm not new to the game, so I was able to speed-run my new AI automation agency. I currently run a software company with a co-founder, and I recently decided to start a new AI and automation agency. I just had a private launch this week, and I already have a $2K client lined up, ready to buy, along with some other interested parties, as I have sales calls with them coming up. I found all of my leads after choosing a niche to focus on and using this tool I built that automatically scrapes IG data. My tool is “unique” because it automagically qualifies the leads with AI. It even has a custom frontend, and I used this tool as a case study to secure the client I have now, and I accomplished all of this in the span of about a week. Granted, I have a background in engineering, so picking up AI was easier for me, but anyone can do it. You can even use AI to learn AI. If you haven’t used AI in your business yet, I would strongly suggest getting into AI and automation. If you've been considering starting a business but don't know what business to start, take this as a sign to turn AI into a business. i will not promote

#reddit#might#best

reddit

0

1

adriannelestrange•This week

I studied how 7 Founders found their first 100 customers for their businesses. Summarizing it here!

I am learning marketing, and so I combed through the internet to find specific advice that helped founders reach 100 users and not random Google answers. Here’s what I found: Llama Life by Marie Marie founder of Llama Life, a productivity app ($51.4K+ revenue) got her first 100 users using Snowballing effect. She shared great advice that I want to add here verbatim, “Need to think about what you have that you can leverage based on your current situation. eg..When you have no customers, think about where you can post to get the 1st customer eg Product Hunt. If you do well on PH, say you get #3 product of the day, then you post somewhere else saying ‘I got #3 product of the day’.. to get your next few customers. Maybe that post is on reddit with some learnings that you found. If the reddit post does well, then you might post it on Twitter, saying reddit did well and what learnings you got from that etc. or even if it doesn’t do well you can still post about it.” Another tip she shared is to build related products that get more viral than the product itself. These are small stand-alone sites that would appeal to the same target audience, but by nature, are more shareable. On these sites, you can mention your startup like: ‘brought to you by Llama Life’ and then provide a link to the main website if someone is interested. If one of those gets viral or ranks on Google, you’ll have a passive traffic source. Scraping bee by Pierre Pierre, founder of Scraping Bee, a web scraping tool has now reached $1.5M ARR. Pierre and his cofounder Kevin started with 10 Free Beta Users in 2019, and after 6 months asked them to take a paid subscription if they wanted to continue using the product. That’s how they got their first user within 50 minutes of that email. Then they listed it on dozens of startup directories but their core strategy was writing the best possible content for their target audience — Developers. 3 very successful pieces of content that worked were : A small tutorial on how to scrape single-page application An extensive general guide about web scraping without getting blocked A complete introduction to web scraping with Python They didn’t do content marketing for the sake of content marketing but deep-dived into the value they were providing their customer. One of these got 70K visits, and all this together got them to over 100 users. WePay by Bill Clerico Bill Clerico left his cushy corporate job to build WePay which was then acquired for $400M got his first users by using his app. He got his first users by using his app! The app was for group payments. So he hosted a Poker tournament at his house and collected payments only with his app. Then they hosted a barbecue for fraternity treasurers at San Jose State & helped them do their annual dues collection. Good old word-of-mouth marketing, that however, started with an event where they used what they made! RealWorld by Genevieve Genevieve — Founder and CEO of Realworld stands by the old-school advice of value giving. RealWorld is an app that helps GenZ navigate adulthood. So, before launching their direct-to-consumer platform, they had an educational course that they sold to college career centers and students. They already had a pipeline of adults who turned to Realworld for their adulting challenges. From there, she gained her first 100 followers. Saner dot ai by Austin Austin got 100 users from Reddit for his startup Saner.ai. Reddit hates advertising, and so his tips to market your startup on Reddit is to Write value-driven posts on your niche. Instead of writing posts, find posts where people are looking for solutions DM people facing problems that your SaaS solves. But instead of selling, ask about their problem to see if your product is a good fit Heartfelt posts about why you built it, aren’t gonna cut it To find posts and people, search Reddit with relevant keywords and join all the subreddits A Stock Portfolio Newsletter A financial investor got his first 100 paid newsletter subscribers for his stock portfolio newsletter. His tips : Don’t reinvent the wheel. Work what’s already working. He saw a company making $500M+ from stock picking newsletter, so decided to try that. Find the gaps in “already working” and leverage them. That newsletter did not have portfolios of advisors writing them. That was his USP. He added his own portfolio to his newsletter. Now to 100 users, he partnered with a guy running an investing website and getting good traffic. That guy got a cut of his revenue, in exchange. That one simple step got him to 100 users. Hypefury by Yannick and Samy Yannick and Samy from Hypefury, Twitter and Social Media Automation tool got their first beta testers and users from a paid community. They launched Hypefury there and asked if someone wanted to try it. A couple of people tried it and gave feedback. Samy conducted user interviews and product demos for them, And shared the reviews on Twitter. That alone, along with word-of-mouth marketing on Twitter got them their first 100 users. To conclude: Don’t reinvent the wheel, try what’s working. Find the gaps in what’s working, and leverage that. Instead of thinking about millions of customers, think about the first 10. Then first 100. Leverage what you have. Get the first 10 customers, then talk about this to get the next 100. Use your app. Find ways, events, and opportunities to use your app in front of people. And get them to use it. Write content not only for SEO but also to help people. It won’t work tomorrow, but it will work for years after it picks up. Leverage other sources of traffic by partnering up! Do things that don’t scale. I’m also doing SaaS marketing deep dives over 30 pieces of content. I'm posting here for the first time, so I'm not sure if it will stay or not, sorry if it doesn't. I've helped a SaaS grow from $19K to $100K MRR as a marketer in last 2 years, and now I wanna dive deep. Cheers! (1/30)

#reddit#studied#founders

reddit

0

1

stellarcitizen•This week

I fell into the builder's trap and need help getting out

Hi r/startups, First-time technical founder here. Two years ago, I decided to leave the 9-5 grind and build something meaningful. Now, I have (what I believe is) a brilliant technical solution but no clear business case. I’m seeking a cofounder with product and marketing expertise to help pivot my project into a viable business - or start a new one. Details below. About Me 36yo, born in Berlin and moved to San Francisco 8 years ago Master's in Software Engineering with 15 years of experience Worked with early-stage startups in Berlin and a venture studio in SF Spent the past years leading a team of 12 shipping enterprise software The tech I've built An AI engine that makes it easy for developers to automate their workflows. It works with code, issues, PRs and integrates with 3rd party systems like error trackers, wikis, ticketing systems, etc. It takes natural language instructions, fulfills them autonomously and responds with a result. The functionality is served as a platform, with an API and an SDK. On top of it, I've built a CLI and a web application with productivity tools for developers. Who and what I'm looking for My main goal is to leave my current job and build a company around a problem that matters to me, ideally with considerable equity. I’m looking for: A cofounder with product and marketing expertise who sees potential in my tech and can help turn it into a successful business—or someone with a strong business case who needs a technical founder. Mentorship from someone experienced in dev tool startups or as a successful solo founder. I’d love to learn from your journey and would be happy to offer my technical expertise or collaborate on projects in return. Happy to answer any questions or provide more details. Cheers!

#reddit#fell#into

reddit

0

1

robbbb1029•This week

Job Board Website Idea

So I have a website planned out, and in most basic terms it will be a subscription to view a pool of job listings that cater to a specific industry so it cuts out the time of searching through every company's websites. I am looking for a no-code website building solution that would be best for integrating with an AI solution to scan websites for new job listings, categorize them into a pool, and list them on my website for subscribers to view. However, cost is a big thing for me at the start and I am looking to get it up and running at the lowest cost and hopefully not pay a big monthly subscription for it. Does anyone have any recommendations or ideas that could help?

#reddit#board#website

reddit

0

1

Training-Swan-6379•This week

Nuts and bolts AI implementation for small business

How can small businesses use AI to increase sales or decrease expenses without massive disruption? One way for us is using AI to process our email history to identify patterns and write personalized messages based on past correspondence. According to legal advice in which I have confidence, email that is personalized for each recipient (and meets other standards) does not need to be opt in. If you disagree - understood - but spam morality is not the topic here. Bottom line - obviously a game changer. Knowing phrases people have used before becoming clients - and all of the possible permutations of those phrases, and detecting where those phrases show up will make our sales and marketing many times more effective for a fraction of the cost. There's a reason big corps. record calls, and now small business can leverage the same technology. We are setting up a process that yields accurate, up to date, comprehensive data for our own business operations. Our clients - who are they and how has their demographic changed over time? To answer this question and for email personalization, we also need access to external data sources e.g. like accurate up to date company demographics. IMO - the leader in company data in the US? THEY SUCK. We found there is no magic fairy who is going to make good data appear for our AI. The process of applying our own proprietary knowledge to code and categorize the data is just as important, and obviously highly sensitive. How do we leverage the AI technologies of companies like Google and Microsoft (or anyone else) without being their bitch? Below is a list of some of the sources of my business's data: Data sources: PST/OST/Other Email data files Microsoft data from Windows/O365 Windows/Linux/Android/IOS application logs and other data Web server logs for the company website. SEO/Analytics Data Google data export Google voice/VOIP logs OneDrive/G drive Other Phone system/cell service logs Other SAAS and in-house application data. Facebook/social media data for company pages. QuickBooks/other accounting systems/business bank account logs POS/Credit card processing systems/PayPal, etc. OSINT to fill in the blanks

#reddit#nuts#bolts

reddit

0

1

Organic_Crab7397•This week

Seeking advice from every type of business owner - if you have a moment & an opinion please chime in.

Hello everyone. I haven't started selling yet and wanted to get some insight from the community I'm trying to serve (that makes the most sense to me). So over the past couple months I've gotten into AI & Automation. I got a HighLevel account and went to town learning new things. I learned how to make automations and workflows that make running a business easier (my dad has been letting me use his concrete business as a guinea pig). I also learned how to build and train AI Chat Assistants. I want to start a service based business that uses AI & workflows to automate some of the customer service tasks & lead generation for business. What I'm seeking advice about are as follows: NICHE SELECTION: Part of me thinks I shouldn't niche down in the beginning and just take whoever comes and niche down once I find an industry I'm comfortable with. Another side thinks I should choose one. What is your opinion on niche selection in the beginning? PRICING: I know that pricing largely depends on the value I bring to the client, but I've seen people doing the same or similar things as I want to do and charging vastly different prices. From $300- $2,000. While I think these solutions could absolutely help companies get and retain new business and reduce some of the workload of their staff -- I'm not comfortable charging a high price until I've got enough experience and data to justify that. ​ THESE ARE THE SERVICES I'M THINKING OF OFFERING: Customer Service Chat Assistant. This will be on the website as a "Live Chat". It also connects to Facebook Messenger & Google Business Chat. I'd train the chat assistant on everything related to the company; pertinent info (NAP, company mission, industry background), contact info, services / products / pricing, FAQs, current specials &/or discount codes (this can be changed monthly), how to handle upset clients, etc. It can also connect to a calendar like Google or Calendly so customers can make an appointment or schedule a call directly from the conversation. Missed Call Follow Up. If you're familiar with the platform HighLevel it's commonly called "Missed Call Text Back". The idea is that when a call is missed a text message is automatically fired to the prospect's phone saying something along the lines of "Hey this is \\\\\\ from \\\\\\\_. How can I help you?" and the business owner is alerted to the missed call via text notification. People have said they see a lot of success for their clients with this alone due to the instant follow up. I see a lot of people charging $300 /m. for this. My issues with this are: 1). The text fires automatically when the call is missed, but if the business owner isn't available to actually follow up and keep texting after the customer texts back, they will look inconsistent and bothersome. 2). Without context a prospect may wonder why you didn't answer when they called, but texted them instead. So my answer to these problems are #3. SMS Answering Service. It is essentially taking 2 + 1 and combining them. The missed call text goes out to the prospect, but with context on why they're being texted (because no one is available to take the call at the moment) and IF the prospect responds, a Customer Service Chat Assistant will take over the conversation with the goal of answering their questions and either getting them on the phone with the company via a call back OR helping them schedule an appointment. This offers a more consistent solution than just a text to the business owner / team & the prospect is contacted and helped (hopefully) before they have a chance to start calling a competitor. Lead Nurture / Lead Qualifying Sales Funnel. This one is more than just AI & automation. It's a full funnel. It can be for either Facebook or Google. The process is AD -> Landing Page -> AI Text Message Convo -> Booking/Schedule Call/ Appointment. Typically the ad will offer a lead magnet which they will claim on the LP by giving their information. After the form is submitted, they get a text message and begin a conversation with the AI. It can be trained to just walk them through a booking process, nurture a sale by answering questions and handling objections or to qualify leads. Lead qualification via text works well if you want to weed out who is serious versus who is curious. To be clear; I'd be making the ad, landing page & training the AI -- all parts of the funnel. For whichever service a few things are universal: \- All conversations; no matter what platform they're had on, all go to one inbox which is pretty helpful to see them all in one place. \- When scheduling / booking these can also collect payment. \- Tags can be added to keep track of how they came into the business and where they are in a sales pipeline. There are a lot of fun things I can do with these automations and I'm excited about learning more everyday. I'd really like to know what you think these services could be worth to a business. If you do reply please tell me what type of business you're in so I have an idea of what industries I should be looking towards. Thank you for any response I get as I know this was a long read! SN: I currently do digital marketing & web design as a freelancer.

#reddit#seeking#advice

reddit

0

0.778

No-Understanding5609•This week

The Birth of My First (and Hilariously Flawed) Voice Agent: A Tale of No-Code Chaos

Okay Reddit, buckle up. I'm about to tell you the saga of how I birthed my very first voice agent, a chaotic and frankly, slightly embarrassing journey involving Retell.ai, Make.com, and Zapier. Looking back, it's equal parts hilarious and traumatizing. The Naive Dream: Back then (it feels like ages ago!), I was convinced I could easily whip up a voice agent that would take restaurant orders over the phone. Elegant, efficient, and completely automated! I envisioned a world where my clients' restaurant never missed a beat, all thanks to my coding prowess... or rather, my no-code prowess. How wrong I was. The Gauntlet Begins: Retell.ai's Murky Depths Retell.ai was the starting point, the "voice" of my operation. Getting the phone number hooked up felt like a small victory, quickly overshadowed by the realization that their documentation was... well, let's just say it wasn't written for complete novices. I spent what felt like an eternity staring at API keys, convinced I'd entered them correctly, only to be greeted by cryptic error messages. The sheer frustration I felt wrestling with that initial setup is something I'll never forget. Make.com: From Pretty Picture to Painful Puzzle Then came Make.com, the orchestra conductor of my workflow. It looked so beautiful, so user-friendly! Drag and drop, visual modules... what could go wrong? Oh, so much could go wrong. Trying to decipher the JSON data stream from Retell was like trying to understand a foreign language I only knew a few words of. Mapping that data to a Google Sheet? A complete and utter disaster. I remember spending hours just trying to get the correct fields to populate, each failed attempt fueling my growing despair. Zapier: Briefly Considered, Quickly Dismissed I flirted with the idea of using Zapier instead, seduced by its simplicity. But its limitations became glaringly obvious when I tried to build the complex, multi-step process I needed. Make.com was the only real option, which meant diving headfirst into a whole new world of modules, triggers, and data transformations. The Infernal Testing Loop: The absolute WORST part of the entire process was the testing. Picture this: Calling the agent, rambling through a mock order, waiting for the workflow to execute, only to discover (yet another) error. Then, tweaking the scenario, pushing "save," and repeating the entire agonizing process. Each test call felt like a mini-marathon, a grueling race against time and my own dwindling patience. The AI's... Quirks: And then there was the AI itself. It was... let's just say it had a personality of its own. Sometimes, it perfectly understood my order. Other times, it decided I wanted to order 500 pizzas with extra anchovies. Debugging the AI's interpretation felt like negotiating with a stubborn toddler. Lessons Hard-Learned (And Forever Etched in My Memory): Start absurdly small: I tried to build a fully functional system right away. A HUGE mistake. If I could go back, I would have focused on just extracting one piece of information (like, say, just the quantity) and gotten that rock solid before adding anything else. JSON is your friend (or should be): Back then, JSON felt like alien code. Now, I have a slightly better grasp on it. Trust me, learn JSON. It will save you so much pain. Test like your sanity depends on it: Because it does. After every. Single. Change. Test the entire flow. It's tedious, but it's the only way to catch errors before they snowball into a catastrophe. Don't suffer in silence: I tried to be a lone wolf, figuring everything out myself. Big mistake. Retell.ai's forums and Make.com's documentation are goldmines. Use them! Embrace the struggle: This is the most important lesson. Building a voice agent, especially your first one, is hard. It's frustrating. It will test your limits. But don't give up. The feeling of finally making it work (even partially) is worth it. The Bot That (Barely) Lived: In the end, I did create a voice agent that could take orders and log them into a spreadsheet. It wasn't pretty. It was buggy. It occasionally ordered things that didn't make any sense. But it was mine. And it was the first step on a long and winding road. Looking back, I laugh (and cringe) at my naivety. But I also appreciate the lessons I learned and the sheer grit it took to bring my little AI Frankenstein to life. Anyone else have a similar "first bot" story? Let's hear them! Misery (and laughter) loves company. #RetellAI #Makecom #Zapier #FirstBot #NoCodeFail #VoiceAgentStruggles #StoryTime

#reddit#birth#first

reddit

0

1

EntryElectronic•This week

Seeking Your Feedback: SeedHustle and Your Small Business Journey✨

Hello, everyone, I'm one of the co-founder of SeedHustle, and I wanted to have an authentic discussion with you about our recent developments. SeedHustle is a project dear to us, with the aim of simplifying the often complex process of connecting startups with venture capitalists. 🌟 Why did we embark on this journey? Well, we've been in your shoes, experiencing the frustration of the never-ending search for the right VC partner and the challenges of establishing meaningful connections. This shared experience led to the creation of (https://seedhustle.ai/ ) . So, what's the deal with SeedHustle? It's our effort to streamline the process of finding the ideal VC match. You provide us with your company details, and our AI system goes to work, suggesting potential VCs and explaining why they might be a good fit based on their past investments and backgrounds. We also provide real-time data on their funds. We're currently in the private beta phase and want to extend an invitation to join our Discord community. It's a space where founders can share their stories and possibly make introductions to VCs. As founders who thrive on AI challenges, we believe this could be a game-changer. 👂 I'm here to have an open dialogue. Is there anything you'd like to discuss? Whether it's SeedHustle, our journey, or your own small business experiences, we're all ears. Here are a few conversation starters: \-Does SeedHustle align with your small business journey? \-Do you have any suggestions for how we can improve our platform? \-Is there anything about what we're doing that's unclear or not quite resonating with you? Your feedback is incredibly valuable to us, so please feel free to reach out. Thank you for being a part of this journey, and we hope to see you in our Discord community for a chat! 😊🚀

#reddit#seeking#your

reddit

0

1

thestoicdesigner•This week

Ai C-Level team

I've been exploring ways to run a company where I'm essentially the only internal team member, relying entirely on a suite of specialized AIs for executive roles, supported occasionally by external consultants for niche expertise. My goal is to stay lean, agile, and highly creative, especially in a fashion/tech brand context. Essentially, I'm building an AI-driven C-Level team, or what I like to call a "C-Level AI Wallet." Here's what I'm thinking for the key executive roles I'd need to cover with AI: CEO AI – Responsible for overall strategy, decision-making, trend analysis, and guiding the company's vision. I'd probably lean on something advanced like Gemini, GPT-4, or similar models, fine-tuned with market-specific data. COO AI (Operations): I'd need tools that streamline and automate logistics, supply chain management, and day-to-day operations (think something along the lines of Zapier AI integrations or Make). CMO AI (Marketing & Content): For branding, content creation, digital marketing, and consumer insights, I'd use Jasper or Copy.ai, combined with predictive analytics tools like Google Vertex AI to understand trends better. Additionally, for generating engaging visual and multimedia content, tools like Midjourney, DALL·E, Adobe Firefly, and Runway ML would be perfect. CFO AI (Financial Management): For financial management, cash flow control, and investment decisions, I'd probably leverage AI tools like Bloomberg GPT, combined with AI-powered forecasting platforms. CHRO AI (Human Resources & Culture): Although the internal team is minimal (just myself!), I'd still rely on AI for tasks like project management, freelancer hiring, and performance tracking—tools like HireVue AI, Motion, or even Notion's AI could be beneficial here. CSO AI (Sustainability & Compliance): Since sustainability and ethical sourcing are critical, I'd integrate ESG-focused AI tools to ensure transparency and responsible sourcing. My idea is that, with the right AI tools seamlessly integrated, I can manage the strategic vision and creative direction personally, leveraging external consultants only when necessary. This setup would ideally allow me to operate as a one-person internal team supported by a robust "wallet" of AI executives. Has anyone tried a similar approach? What AI tools would you recommend for a truly lean, innovative brand structure? I'm very curious about your experiences or suggestions—let me know your thoughts!

#reddit#c-level#team

reddit

0

0

Affectionate-Row2454•This week

What are some B2B sales strategies for an AI startup?

Hey folks, need some advice on how I can book meetings with clients to sell a software that I've built. I'm a Software engineer working at a Fortune 500 company. After grinding on the side for a few months now, I've now built a software product to really automate manual every day tasks using LLMs. Its going to be sold to B2B sales teams, and I think my initial market would be mid-market/small companies. Here's a demo that I recently recorded if you are interested: https://www.youtube.com/watch?v=CPTCHBnItkI Let me know what you guys think of it? I’d really appreciate any advice.

#reddit#some#sales

reddit

0

1

yamaggie•This week

Struggling with Cold Start for Our AI PowerPoint Tool - Seeking Platform and Strategy Suggestions!

Hello everyone, I'm one of the co-founders of a new AI-generated PowerPoint company, and I handle the marketing side of things. Our product is currently in the cold start phase, and we’re facing some challenges in gaining traction. We've already tried some influencer marketing, but the results have been underwhelming. We're looking for advice on the best platforms and strategies to effectively launch our product and reach our target audience. Here’s a bit more about our product: AI-Powered: Our tool leverages AI to help users quickly create professional PowerPoint presentations by simply entering their desired topic. User-Friendly: The process is streamlined to save users time and effort, making it ideal for professionals, educators, and students. Given our current situation, we would greatly appreciate any suggestions on: Platforms: Which platforms have you found most effective for cold starts, especially for tech or AI products? Strategies: What marketing strategies or tactics have worked for you in the early stages? Any tips on refining our influencer marketing approach or alternative methods to consider? Partnerships: Are there any specific types of partnerships or collaborations that you’ve found beneficial for similar products? Thank you in advance for your insights and advice. We're eager to learn from this community and hopefully turn things around for our launch. Best, Maggie

#reddit#struggling#cold

reddit

0

1

WillieGarzaYT•This week

Struggling with Emotions Automating Jobs

Hey everyone, I run a small logistics company alongside my father that I recently began taking a more active role in. Many of the \~50 employees are quite behind on the tech side of things and therefore are lacking serious productivity, lots of pen and paper still. As part of my efforts to streamline things I worked with an automation/ai company that took a look at our processes and helped us implement some new tech, however I’m struggling emotionally with the outcome. ​ Unfortunately we no longer need several of our staff anymore, particularly those that handled tasks like our data entry, text customer service, invoicing, and dispatchers. It’s never fun letting anyone go, but I’m worried about some of the implications for our culture and other employees… ​ In a perfect world I’d love to keep these 4-5 full-time staff members on the team and train them to do other roles, but frankly after calculating it out and running the numbers we’re better off just reducing staff and taking the significant cost savings for now, and reallocating resources. ​ My question: How to toe this delicate line to do right by our staff that we respect and care about, while also keeping our business up to date with modern tech? I am leaning towards generous exit packages and providing support helping them find new jobs, but still don’t quite feel right.

#reddit#struggling#emotions

reddit

0

1

Training-Swan-6379•This week

Nuts and bolts AI implementation for small business

How can small businesses use AI to increase sales or decrease expenses without massive disruption? One way for us is using AI to process our email history to identify patterns and write personalized messages based on past correspondence. According to legal advice in which I have confidence, email that is personalized for each recipient (and meets other standards) does not need to be opt in. If you disagree - understood - but spam morality is not the topic here. Bottom line - obviously a game changer. Knowing phrases people have used before becoming clients - and all of the possible permutations of those phrases, and detecting where those phrases show up will make our sales and marketing many times more effective for a fraction of the cost. There's a reason big corps. record calls, and now small business can leverage the same technology. We are setting up a process that yields accurate, up to date, comprehensive data for our own business operations. Our clients - who are they and how has their demographic changed over time? To answer this question and for email personalization, we also need access to external data sources e.g. like accurate up to date company demographics. IMO - the leader in company data in the US? THEY SUCK. We found there is no magic fairy who is going to make good data appear for our AI. The process of applying our own proprietary knowledge to code and categorize the data is just as important, and obviously highly sensitive. How do we leverage the AI technologies of companies like Google and Microsoft (or anyone else) without being their bitch? Below is a list of some of the sources of my business's data: Data sources: PST/OST/Other Email data files Microsoft data from Windows/O365 Windows/Linux/Android/IOS application logs and other data Web server logs for the company website. SEO/Analytics Data Google data export Google voice/VOIP logs OneDrive/G drive Other Phone system/cell service logs Other SAAS and in-house application data. Facebook/social media data for company pages. QuickBooks/other accounting systems/business bank account logs POS/Credit card processing systems/PayPal, etc. OSINT to fill in the blanks

#reddit#nuts#bolts

reddit

0

0.333

lazymentors•This week

80+ Social Media Updates Related to Business Marketing That Occurred in last 5 months

Tiktok expanded its caption limits from 100 to 500 Characters. Reddit Updates Search tools, Now you can search User Comments. “Comment search is here”. Pinterest Announces New Partnership with WooCommerce to Expand Product Listings. Google’s launched ‘multisearch’ feature that lets you search using text and image at the same time. Etsy sellers went on strike after platform increases transaction fees. Reddit launched $1 million fund to support various projects going on platform. Instagram is updating its ranking algorithm to put more focus on Original Content LinkedIn Added New tools In creator mode: improved content analytics and Updates profile video Options. Tiktok launched its own gif library “Effect House”. Instagram Updates Reels editing tools adding reordering clips feature. Google Search got a new label to direct people to original news sources YouTube launches new Profile Rings for Stories and Live. Snapchat launched YouTube Link stickers to make video sharing easier! Messenger adds new shortcuts, including a slack like @everyone feature. Pinterest Expands it’s Creator funds program to help more Underrepresented creators. Reddit brings back r/place after 5 years. Google Adds New Seller Performance Badges, New Pricing Insights for eCommerce Brands. Meta and Google agrees to New Data Transfer agreement to keep Instagram and Facebook running in EU. Twitter tests New Interactive Ad types to boost its promotional Appeal. Instagram removed In-stream Ads from its Advertising Options. Tiktok launched new program “CAP” to help creative agencies reach its audience. Twitch shuts down its desktop app. Meta launched the ability to add “share to Reels” feature to third Party Apps. TikTok Adds New ‘Background Player’ Option for Live-Streams. Twitter rolls out ALT badge and improved image description. Fast, A Checkout Startup with $15 billion valuation shuts down after spending all the funds raised in 2021. Wordpress announced new pricing with more traffic and storage limits after receiving backlash from the community. Sales force upgrades marketing field services and sales tools with AI. Dropbox shop launches in open beta to allow creators to sell digital content. Tiktok is the most downloaded app in Quarter 1 of 2022. WhatsApp announced launch of ‘Communities’ - more structured group chats with admin controls. Tiktok expands testing a private dislike button for comments. Twitter acquired “Openback” A notification app to improve timeline and relevance of push notifications YouTube and Tiktok added New options for Automated Captions, Improving Accessibility. A new social media App “Be Real” is trending across the internet grabbing Gen-Zs attention to try the app. WhatsApp got permission to expand payment services to its Indian user base of 100 Million. YouTube Shorts now allows creators to splice in long-form videos. You can use long form video audios and clips for YT shorts. New Snapchat feature ‘Dynamic Stories’ uses a publisher’s RSS feed to automatically create Stories posts. Zoom launches AI-powered features aimed at sales teams. Tiktok started testing who viewed your profile feature. Ogilvy Announced they will no longer work with who edit their bodies and faces for ads. If you don’t know “Oglivy” is the most successful advertising agency of the decade. YouTube Launches New ‘Search Insights’ for all creators. Snapchat Added 13 million new users in Q1 2022 more than both Twitter and Facebook. Google is Introduced new options to reject tracking cookies in Europe after receiving fines from violating EU data laws. Sony & Microsoft are planning to integrate Ads into their gaming platforms Xbox and PlayStation. YouTube Adds new Shorts Shelf to Trending Tab to show Top Shorts in an alternative section. Instagram started testing a reels template feature which enables creators to copy formats from other reels. Google Tests “What People Are Saying” Search Results. Twitter Launches New Test of Promotions for Third Party Tools Within the App. Instagram is changing how hashtags work by experimenting removing Recents tab from hashtags section. Google Adds New Publisher Verification Badges to Extension Listings in the Google Web Store Amazon AWS launches $30M accelerator program aimed at minority founders. Meta launched more fundraising options for Instagram Reels in 30 countries. Brave Search and DuckDuckGo will no longer support Google AMP due to privacy issues. Instagram is working on a pinned post feature and will officially launch in next few months. Meta: You can now add Music to your Facebook comments Twitter tests new closed caption button to switch on captions in Video Clip Elon Musk Bought Twitter $44 Billion and Company is set to go private. Google now lets you request the removal of personal contact information from search results YouTube reveals that Ads between YT Shorts are being tested with selective brands. LinkedInis rolling out a new website link feature. Google Reduces Visibility Of Business Edits With Color Changes To Profile Updates. Instagram expands testing of 90 second Reels. Microsoft Advertising now offers incentive features like cash-back and adding stock images from your website. Facebook & Pinterest are growing again despite all the hype around slow growth of both platform in last quarter. Google Added 9 new Ad policies to prevent misleading ads taking place. Tiktok Introduces Third-party cookies to its Pixel. (like Facebook Pixel) Twitter reportedly overcounted number of daily active users for last 3 years. Google launched Media CDN to compete on content delivery. YouTube expands Thank You Monetisation tool to all eligible creators. Twitch is looking to expand their cut from streamers earnings from 30 to 50% and also thinks of boosting Ads. Snapchat launches a $230 flying drone camera and new e-commerce integrations in Snap Summit 2022. YouTube Expands its ‘Pre-Publish Checks’ Tool to the Mobile App Google Search Console’s URL parameter tool is officially removed for a time period. Twitter creators can now get paid through Cryptocurrency on Twitter with Stripe. Jellysmack- One of the Influencer marketing agency acquires YouTube analytics tool Google & Microsoft Ads brought more revenue in last quarter- 22% Gains! WhatsApp is working on a paid subscription for multi-phone and tablet chatting. Instagram users now spend 20% of their time in the reels section. Google tests new Color for clicked search results by you. Now Clicked results are in Purple. Twitter: Elon plans to remove employees and focus more on influencers for twitter’s growth + new monetisation ideas were shared. YouTube revenue falls as more users spend time on shorts tab than consuming long form content. Drop 👋 to receive June Updates!

#reddit#social#media

reddit

0

1

superhyooman•This week

Automated/AI Bookkeeping

Hi all, I'm having trouble deciding between 3 different bookkeeping companies for my small business. All 3 are modern, onlince based with good banking integration, and varying levels of AI/automation involved to cut costs and streamline the work. The companies are: Bench Fincent Digits I'm currently using Bench, and am overall happy with the service, but since my contract period is up and I have the opportunity to switch, I'm doing some due diligence. Would really appreciate any reviews based on personal experience for these options! Or if theres another company I should consider as well.

#reddit#automated/ai#bookkeeping

reddit

0

1

JohACNH•This week

Looking to streamline and update family business

Hey r/smallbusiness, I’ve been working at my family’s business for six years now—joined right after college—and I’ve realized that we’re long overdue for an overhaul. I handle advertising sales, and while the business itself is solid, the way we operate is extremely outdated. Without revealing too much, we print about 180 publications, and businesses pay to have their ads featured. As a sales rep, my job includes: Renewing current advertisers Finding new customers and making sales Collecting artwork for ads Gathering billing info Laying out the ad grid with all advertisers The Problem: Everything is still done with pen and paper. We use carbon copy paper to record business details, billing info, and ad costs. One copy goes to the graphic designers, the other to billing. The billing team manually enters everything into QuickBooks, prints invoices, stuffs envelopes, and mails them out. We recently got new software that lets us send invoices via email and text through QuickBooks, which is a step in the right direction, but it’s just a small fix to a much bigger problem. What I Want to Change: Move everything onto an app or website—no more paper. Digitally layout the ad grid instead of doing it manually. (For graphics team) Collect billing info online instead of writing it down. (Obviously to get paid faster and reduce wasted labor) Automate renewal emails instead of calling every single customer. (Save time) Find more efficient ways to generate leads for new business. (Work smarter not harder) Honestly, the company still runs like my grandma set it up in the '90s, and it’s overwhelming trying to figure out where to start. If anyone has been through something similar or has advice on modernizing a business, I’d love to hear your thoughts! Happy to provide more details if needed. I’ve explored some CRMs and AI tools, but I’m sure someone here has better insights or more experience with this than I do. There are other parts of the business that need improvement, but I believe this would be a big step in the right direction. Thanks in advance!

#reddit#looking#streamline

reddit

0

1

Organic_Crab7397•This week

Seeking advice from every type of business owner - if you have a moment & an opinion please chime in.

Hello everyone. I haven't started selling yet and wanted to get some insight from the community I'm trying to serve (that makes the most sense to me). So over the past couple months I've gotten into AI & Automation. I got a HighLevel account and went to town learning new things. I learned how to make automations and workflows that make running a business easier (my dad has been letting me use his concrete business as a guinea pig). I also learned how to build and train AI Chat Assistants. I want to start a service based business that uses AI & workflows to automate some of the customer service tasks & lead generation for business. What I'm seeking advice about are as follows: NICHE SELECTION: Part of me thinks I shouldn't niche down in the beginning and just take whoever comes and niche down once I find an industry I'm comfortable with. Another side thinks I should choose one. What is your opinion on niche selection in the beginning? PRICING: I know that pricing largely depends on the value I bring to the client, but I've seen people doing the same or similar things as I want to do and charging vastly different prices. From $300- $2,000. While I think these solutions could absolutely help companies get and retain new business and reduce some of the workload of their staff -- I'm not comfortable charging a high price until I've got enough experience and data to justify that. ​ THESE ARE THE SERVICES I'M THINKING OF OFFERING: Customer Service Chat Assistant. This will be on the website as a "Live Chat". It also connects to Facebook Messenger & Google Business Chat. I'd train the chat assistant on everything related to the company; pertinent info (NAP, company mission, industry background), contact info, services / products / pricing, FAQs, current specials &/or discount codes (this can be changed monthly), how to handle upset clients, etc. It can also connect to a calendar like Google or Calendly so customers can make an appointment or schedule a call directly from the conversation. Missed Call Follow Up. If you're familiar with the platform HighLevel it's commonly called "Missed Call Text Back". The idea is that when a call is missed a text message is automatically fired to the prospect's phone saying something along the lines of "Hey this is \\\\\\ from \\\\\\\_. How can I help you?" and the business owner is alerted to the missed call via text notification. People have said they see a lot of success for their clients with this alone due to the instant follow up. I see a lot of people charging $300 /m. for this. My issues with this are: 1). The text fires automatically when the call is missed, but if the business owner isn't available to actually follow up and keep texting after the customer texts back, they will look inconsistent and bothersome. 2). Without context a prospect may wonder why you didn't answer when they called, but texted them instead. So my answer to these problems are #3. SMS Answering Service. It is essentially taking 2 + 1 and combining them. The missed call text goes out to the prospect, but with context on why they're being texted (because no one is available to take the call at the moment) and IF the prospect responds, a Customer Service Chat Assistant will take over the conversation with the goal of answering their questions and either getting them on the phone with the company via a call back OR helping them schedule an appointment. This offers a more consistent solution than just a text to the business owner / team & the prospect is contacted and helped (hopefully) before they have a chance to start calling a competitor. Lead Nurture / Lead Qualifying Sales Funnel. This one is more than just AI & automation. It's a full funnel. It can be for either Facebook or Google. The process is AD -> Landing Page -> AI Text Message Convo -> Booking/Schedule Call/ Appointment. Typically the ad will offer a lead magnet which they will claim on the LP by giving their information. After the form is submitted, they get a text message and begin a conversation with the AI. It can be trained to just walk them through a booking process, nurture a sale by answering questions and handling objections or to qualify leads. Lead qualification via text works well if you want to weed out who is serious versus who is curious. To be clear; I'd be making the ad, landing page & training the AI -- all parts of the funnel. For whichever service a few things are universal: \- All conversations; no matter what platform they're had on, all go to one inbox which is pretty helpful to see them all in one place. \- When scheduling / booking these can also collect payment. \- Tags can be added to keep track of how they came into the business and where they are in a sales pipeline. There are a lot of fun things I can do with these automations and I'm excited about learning more everyday. I'd really like to know what you think these services could be worth to a business. If you do reply please tell me what type of business you're in so I have an idea of what industries I should be looking towards. Thank you for any response I get as I know this was a long read! SN: I currently do digital marketing & web design as a freelancer.

#reddit#seeking#advice

reddit

0

1

sarveshpandey89•This week

Seeking Feedback on My Business Idea – SaaS + Lead Generation for Small Businesses

Edit: TL;DR I’m Sarvesh, a digital marketer with 10 years of experience in paid ads. After losing my job last year, I started freelancing and discovered how much small businesses struggle with getting reviews (Google, Yelp, TrustPilot, etc.). My Business Idea – SaaS + Paid Ads Free Plan: Businesses can track & reply to reviews across 40+ platforms in one dashboard. Paid Plan ($99/month): Automates review collection, AI-powered responses, social media posting, and spam detection. Custom Plan: Paid ads to generate leads, offered only to businesses on my paid plan for 3+ months. Goal: SaaS platform attracts users → Some upgrade to paid plan → Best clients get lead-generation help → More leads → More reviews → More organic customers → A profitable business cycle. Need Feedback: Does this idea have potential? How can I get my first beta users? Any features I should add/remove? Would love your thoughts—thanks for reading! 😊 TL: Hi everyone, I’m Sarvesh, and I’m in the process of starting my own business. Since my target audience is small businesses, I’d love to get some input, advice, or critiques from this community. A Little About Me I’ve spent the last 10 years working in paid advertising, helping medium and large businesses generate leads through Facebook and Google Ads. I also have experience running e-commerce campaigns. You can check out my background on LinkedIn: LinkedIn Profile Last year, my second daughter was born, and around the same time, my company shut down all its offices (India & UK), leaving me without a job. I decided to take a break and spend time with my wife and newborn, something I regretted not doing with my first child. By November, I started job hunting again, but in the meantime, I got some freelance work through Reddit, helping small businesses with ads for the first time. For context, in my previous jobs, I managed ad campaigns with daily budgets of £4K–£8K. Working with small businesses was a new challenge, but to my surprise, I was able to generate solid leads for beauty salons, hair salons, and nail salons, helping them grow. What stood out to me was how much impact my work had—unlike my corporate job, where I was just another person in the system, here I felt truly valued. That feeling led me to explore starting my own business. The Problem I Noticed While working with small businesses, I realized that online reviews (Google, Yelp, Trustpilot, etc.) are critical for them, yet many struggle to get them. Customers often don’t leave reviews, and employees are either too shy or don’t prioritize asking for them. This gave me an idea—to build a system that helps businesses get more genuine Google reviews from customers. I developed the system but struggled to find businesses willing to test it, even for free. My target audience is U.S. small businesses, but since I’m based in India, cold emails and Reddit outreach didn’t get much traction. My Business Idea – SaaS + Custom Plans I’m now thinking of pivoting my business model into a SaaS platform with optional paid upgrades. Here’s how it would work: Free Plan (Review Tracking & Management) Businesses can track their reviews across 40+ platforms (Google, Yelp, Facebook, Trustpilot, TripAdvisor, etc.) in one dashboard. They can reply to reviews manually from a single place instead of switching between platforms. This will be completely free forever. Paid Plan ($99/month, Plus SMS/Email Costs) For businesses that struggle to get reviews, they can upgrade to a paid plan that includes: Automated Review Requests – Automatically send review requests via SMS & email. Website Widget – Showcase 4- and 5-star reviews dynamically. Social Media Automation – Automatically post positive reviews on Facebook/Instagram. AI-Powered Responses – AI can reply to reviews automatically. Spam Detection – The system will notify businesses of suspicious reviews (but won’t take direct action). Custom Plan (Lead Generation via Paid Ads) I will personally manage paid ad campaigns to generate leads. Pricing depends on the niche, budget, and contract duration. Money-Back Guarantee – If I don’t deliver results, I refund the month’s fee. Small businesses can’t afford wasted ad spend, and I want to ensure I provide real value. Limited spots per month to maintain quality and avoid burnout. How Everything Ties Together The SaaS platform serves as a lead generation tool for my custom plans: Businesses use the free plan to track their reviews. Some upgrade to the paid plan to automate and improve reviews. A select few, after 3 months on the paid plan, can join my custom plan for paid ads to generate more leads. More leads → More reviews → Better Google Maps ranking → More organic customers → A more profitable business. Would Love Your Feedback! What do you think about this approach? Do you see potential for this business to take off? Any features I should add or remove? Any suggestions on how I can get my first beta users to test the SaaS platform? What about pricing? Do you think $99 is good pricing? I know this is a long post, but I really appreciate anyone taking the time to read and share their thoughts. Thanks in advance!

#reddit#seeking#feedback

reddit

0

0

SillyDogsAreFunny•This week

No

No I don't need SEO No I don't need a new website because the one my full-time employees who have graduated with CS degrees made is "unoptimized" No I don't need social media growth services No I don't need an agency to run my ads that are perfectly fine on there own No I don't need help "traversing this digital landscape" No I don't need an AI appointment setter No I don't need an AI bot to set appointments No I don't need you to generate me leads for my already thriving \marketing\ company No I don't need a "growth operator" No I don't need workflow automations No I don't need to "nurture my google reviews" No, you're not a digital marketing expert Holy fuck ​

#reddit

reddit

0

1

Malachiian•This week

ChatGPT for business automation (incredible new AI)

Hey fellow small business owners! I'm curious to know how you would use ChatGPT or other AI automation tools to improve your business. For those who are not aware, recently a new chat AI was made available to the public by OpenAI, called ChatGPT. (same company that did Dall-E) In a tweet Elon Musk wrote that "ChatGPT is scary good. We are not far from dangerously strong AI." It allows anyone (regardless of tech skill) to simply type commands and it will spit out answers. It can also create actual working code. For example most tasks you do in a browser can be automated with a Python script, but it takes time and coding knowledge to create. With ChatGPT you can just tell it what you want and it will create the code! The impact for businesses is insane: 1) Your entire customer service can be easily replaced by chat bots and probably soon by AI that can speak over the phone (google showcased this in 2018, it already exists). 2) you can have the AI automate your sales process, creating a 1-on-1 conversations, at scale. It can probably also improve and optimize it's closing rate over time as it learns more about your customers. 3) It can be used to train your staff. It's really good for 1on1 instruction and teaching because it will go a the students pace and answer questions (compare that to the usual PowerPoint presentation people use) 4) Since it can create code to automate most tasks a human can do in a browser, you can create for example bots that take customer orders and automatically import them to whatever shipping system you use, send customers tracking info etc. (a lot of this stuff is done with software and APIs, but now anyone can create their own, custom solutions) I feel like we hit an inflection point in 2022 with AI and now we are beginning to see some really useful stuff coming out. Am I crazy or are we about to see a massive shift in how we do things?

#reddit#chatgpt#business

reddit

0

1

thestoicdesigner•This week

Ai C-Level team

I've been exploring ways to run a company where I'm essentially the only internal team member, relying entirely on a suite of specialized AIs for executive roles, supported occasionally by external consultants for niche expertise. My goal is to stay lean, agile, and highly creative, especially in a fashion/tech brand context. Essentially, I'm building an AI-driven C-Level team, or what I like to call a "C-Level AI Wallet." Here's what I'm thinking for the key executive roles I'd need to cover with AI: CEO AI – Responsible for overall strategy, decision-making, trend analysis, and guiding the company's vision. I'd probably lean on something advanced like Gemini, GPT-4, or similar models, fine-tuned with market-specific data. COO AI (Operations): I'd need tools that streamline and automate logistics, supply chain management, and day-to-day operations (think something along the lines of Zapier AI integrations or Make). CMO AI (Marketing & Content): For branding, content creation, digital marketing, and consumer insights, I'd use Jasper or Copy.ai, combined with predictive analytics tools like Google Vertex AI to understand trends better. Additionally, for generating engaging visual and multimedia content, tools like Midjourney, DALL·E, Adobe Firefly, and Runway ML would be perfect. CFO AI (Financial Management): For financial management, cash flow control, and investment decisions, I'd probably leverage AI tools like Bloomberg GPT, combined with AI-powered forecasting platforms. CHRO AI (Human Resources & Culture): Although the internal team is minimal (just myself!), I'd still rely on AI for tasks like project management, freelancer hiring, and performance tracking—tools like HireVue AI, Motion, or even Notion's AI could be beneficial here. CSO AI (Sustainability & Compliance): Since sustainability and ethical sourcing are critical, I'd integrate ESG-focused AI tools to ensure transparency and responsible sourcing. My idea is that, with the right AI tools seamlessly integrated, I can manage the strategic vision and creative direction personally, leveraging external consultants only when necessary. This setup would ideally allow me to operate as a one-person internal team supported by a robust "wallet" of AI executives. Has anyone tried a similar approach? What AI tools would you recommend for a truly lean, innovative brand structure? I'm very curious about your experiences or suggestions—let me know your thoughts!

#reddit#c-level#team

reddit

0

0

Otherwise_Reserve268•This week

Is anyone using and getting reliable results from AI for social media, and automating some tasks in the business?

Hi, We are currently paying £600/month for a social media company to do a pretty meh job at promoting us, by just doing some posts on our socials I am just wondering if anyone has used AI to help with this and if so what do you use. I've looked at Blaze but I'm put off by their marketing and then Sintra looks interesting but hoping for some feedback from people that have used it, or any others!

#reddit#anyone#getting

reddit

0

0

Otherwise_Reserve268•This week

Is anyone using and getting reliable results from AI for social media, and automating some tasks in the business?

Hi, We are currently paying £600/month for a social media company to do a pretty meh job at promoting us, by just doing some posts on our socials I am just wondering if anyone has used AI to help with this and if so what do you use. I've looked at Blaze but I'm put off by their marketing and then Sintra looks interesting but hoping for some feedback from people that have used it, or any others!

#reddit#anyone#getting

reddit

0

0

AlexDataKnowl•This week

Feedback request: Virtual Receptionist - Phone Answering Service

Hi everyone! We develop an AI solution for the Enterprise segment, aimed at managing and automating interactions with Customers (e.g. self-service customer support via telephone) I do not refer in any way to company names, products, etc... to avoid any ambiguity or distraction. ➡️ My post is aimed at exploring the point of view of an SMB regarding the problem of managing interactions with customers, for example in managing telephone calls. ⭐In particular, what do you think of traditional virtual receptionist and phone answering services? The underlying issue is valuing every call, or interaction in general. ⭐A missed or poorly managed call can be a lost opportunity (a sale, a service) or even worse, a lost customer. But often outsourcing the service also means relying on people in a call center who manage your business in parallel with many others, and you cannot be an expert in everything. Therefore, the outsourced agents will be competent on 10, 15 points. This often results in little use for the caller, which does not resolve the issue for which he called. AI is making giant strides, as is speech synthesis and speech recognition. 🚀 What do you think if you were to use AI as a virtual receptionist, or in general for call management for your business? ⭐ Points in favor? What is the most critical aspect? Typical cases: Provide information Customer service Appointment made Order management ...other? The purpose of this post is to provide food for constructive reflection, combining different visions.

#reddit#feedback#request:

reddit

0

1

adamwfletcher•This week

Looking for feedback on small business communities

Hi folks - I'm working on a new company (I've built and sold two developer tools companies), and instead of building some AI tech I want to build small business communities to help SMB owners. Both my parents ran their own small businesses and I spent my youth working behind a register. I'd love to hear about your experiences interacting with your SMB neighbors, online or off - here's a survey link: https://marketstreet.cc/survey \- and once we get enough results I'll post here with any insights.

#reddit#looking#feedback

reddit

0

1

Malachiian•This week

ChatGPT for business automation (incredible new AI)

Hey fellow small business owners! I'm curious to know how you would use ChatGPT or other AI automation tools to improve your business. For those who are not aware, recently a new chat AI was made available to the public by OpenAI, called ChatGPT. (same company that did Dall-E) In a tweet Elon Musk wrote that "ChatGPT is scary good. We are not far from dangerously strong AI." It allows anyone (regardless of tech skill) to simply type commands and it will spit out answers. It can also create actual working code. For example most tasks you do in a browser can be automated with a Python script, but it takes time and coding knowledge to create. With ChatGPT you can just tell it what you want and it will create the code! The impact for businesses is insane: 1) Your entire customer service can be easily replaced by chat bots and probably soon by AI that can speak over the phone (google showcased this in 2018, it already exists). 2) you can have the AI automate your sales process, creating a 1-on-1 conversations, at scale. It can probably also improve and optimize it's closing rate over time as it learns more about your customers. 3) It can be used to train your staff. It's really good for 1on1 instruction and teaching because it will go a the students pace and answer questions (compare that to the usual PowerPoint presentation people use) 4) Since it can create code to automate most tasks a human can do in a browser, you can create for example bots that take customer orders and automatically import them to whatever shipping system you use, send customers tracking info etc. (a lot of this stuff is done with software and APIs, but now anyone can create their own, custom solutions) I feel like we hit an inflection point in 2022 with AI and now we are beginning to see some really useful stuff coming out. Am I crazy or are we about to see a massive shift in how we do things?

#reddit#chatgpt#business

reddit

0

1

__god_bless_you_•This week

I Accidentally Made My Mom Redundant at Her Office Job

At my tech job, AI assistants have boosted productivity so much we’ve almost stopped hiring. It made me wonder: why isn’t AI used more in small businesses? My mom works in the office of a small local manufacturing company, handling repetitive tasks like inputting orders into their ERP system. After shadowing her for a half day, I built an AI program that automates most of her work. Now she has so much free time, she’s watching Netflix at the office lol I’m thinking of quitting my job and starting my own small local business, offering this as a service to other small businesses in the era, but before I jump on it and quit my current job, I’d love to know if this is a more common issue. My main question are: What’s the most repetitive/time-consuming (computer) tasks you wish you could automate? If possible, could you break it down step by step with a lot of boring details ? 😅 Any hacks or tools you've found to make things easier so far? And maybe what else I should think on that I am missing before quitting my job and starting my own business?

#reddit#accidentally#made

reddit

0

1

axetobe_ML•This week

Neural Networks you can try to implement from scratch (for beginners)

I was reading a tweet talking about how useful it is to implement neural networks from scratch. How it allowed for a greater understanding of the topic. The author said he found it more useful than other people explaining the concept to him. While I disagree with the author’s opinion that it stops the need for explanations. It certainly does help the understanding of one’s model. I recommend giving it a go. In the blog post, I will suggest which models you should try to implement from scratch using NumPy or your favourite library. Also, I will link to some accompanying resources. Simple Feedforward Network This is the most famous example because it’s so simple. But allows you to learn so much. I heard about this idea from Andrew Trask. It also helped me think about implementing networks from scratch in general. In the Feedforward network, you will be using NumPy. As you won't need Pytorch or TensorFlow. To do the heavy-lifting for complex calculations. You can simply create a Numpy Array for training and testing data. You can also create a nonlinear function using Numpy. Then work out the error rate between the layer’s guess and real data. Resource for this task: https://iamtrask.github.io/2015/07/12/basic-python-network/ Follow this tutorial. It does a much better job of explaining how to do this in NumPy. With code examples to follow. Feedforward Network with Gradient Descent This is an extension of the network above. In this network, we allow the model to optimise its weights. This can also be done in NumPy. Resource for this task: https://iamtrask.github.io/2015/07/27/python-network-part2/ A follow-on from the previous article. Pytorch version of Perceptrons and Multi-layered Perceptrons. Here will go up a level by using a library. Examples I'm using will be done in Pytorch. But you can use whatever library you prefer. When implementing these networks, you learn how much a library does the work for you. Recourses for the task: https://medium.com/@tomgrek/building-your-first-neural-net-from-scratch-with-pytorch-56b0e9c84d54 https://becominghuman.ai/pytorch-from-first-principles-part-ii-d37529c57a62 K Means Clustering Yes, this does not count as a neural network. But a traditional machine learning algorithm is still very useful. As this is non deep learning algorithm it should be easier to understand. This can be done just using NumPy or Pandas depending on the implementation. Recourse for this task: https://www.machinelearningplus.com/predictive-modeling/k-means-clustering/ http://madhugnadig.com/articles/machine-learning/2017/03/04/implementing-k-means-clustering-from-scratch-in-python.html https://gdcoder.com/implementation-of-k-means-from-scratch-in-python-9-lines/ There are quite a few choices to choose from. So pick whatever implementation helps you understand the concepts better. These networks or models should be simple enough that you won't get lost trying to implement them. But still, help learn a few stuff along the way. \- If you found this post useful, then check out my mailing list where I write more stuff like this.

#reddit#neural#networks

reddit

0

1

Difficult-Race-1188•This week

Month of August in AI

🔍 Inside this Issue: 🤖 Latest Breakthroughs: This month it’s all about Agents, LangChain RAG, and LLMs evaluation challenges.* 🌐 AI Monthly News: Discover how these stories are revolutionizing industries and impacting everyday life: EU AI Act, California’s Controversial SB1047 AI regulation act, Drama at OpenAI, and possible funding at OpenAI by Nvidia and Apple.* 📚 Editor’s Special: This covers the interesting talks, lectures, and articles we came across recently. Follow me on Twitter and LinkedIn at RealAIGuys and AIGuysEditor to get insight on new AI developments. Please don't forget to subscribe to our Newsletter: https://medium.com/aiguys/newsletter Latest Breakthroughs Are Agents just simple rules? Are Agents just enhanced reasoning? The answer is yes and no. Yes, in the sense that agents have simple rules and can sometimes enhance reasoning capabilities compared to a single prompt. But No in the sense that agents can have a much more diverse functionality like using specific tools, summarizing, or even following a particular style. In this blog, we look into how to set up these agents in a hierarchal manner just like running a small team of Authors, researchers, and supervisors. How To Build Hierarchical Multi-Agent Systems? TextGrad. It is a powerful framework performing automatic “differentiation” via text. It backpropagates textual feedback provided by LLMs to improve individual components of a compound AI system. In this framework, LLMs provide rich, general, natural language suggestions to optimize variables in computation graphs, ranging from code snippets to molecular structures. TextGrad showed effectiveness and generality across various applications, from question-answering and molecule optimization to radiotherapy treatment planning. TextGrad: Improving Prompting Using AutoGrad The addition of RAG to LLMs was an excellent idea. It helped the LLMs to become more specific and individualized. Adding new components to any system leads to more interactions and its own sets of problems. Adding RAG to LLMs leads to several problems such as how to retrieve the best content, what type of prompt to write, and many more. In this blog, we are going to combine the LangChain RAG with DSPy. We deep dive into how to evaluate the RAG pipeline quantitatively using RAGAs and how to create a system where instead of manually tweaking prompts, we let the system figure out the best prompt. How To Build LangChain RAG With DSPy? As the field of natural language processing (NLP) advances, the evaluation of large language models (LLMs) like GPT-4 becomes increasingly important and complex. Traditional metrics such as accuracy are often inadequate for assessing these models’ performance because they fail to capture the nuances of human language. In this article, we will explore why evaluating LLMs is challenging and discuss effective methods like BLEU and ROUGE for a more comprehensive evaluation. The Challenges of Evaluating Large Language Models AI Monthly News AI Act enters into force On 1 August 2024, the European Artificial Intelligence Act (AI Act) enters into force. The Act aims to foster responsible artificial intelligence development and deployment in the EU. The AI Act introduces a uniform framework across all EU countries, based on a forward-looking definition of AI and a risk-based approach: Minimal risk: most AI systems such as spam filters and AI-enabled video games face no obligation under the AI Act, but companies can voluntarily adopt additional codes of conduct. Specific transparency risk: systems like chatbots must clearly inform users that they are interacting with a machine, while certain AI-generated content must be labelled as such. High risk: high-risk AI systems such as AI-based medical software or AI systems used for recruitment must comply with strict requirements, including risk-mitigation systems, high-quality of data sets, clear user information, human oversight, etc. Unacceptable risk: for example, AI systems that allow “social scoring” by governments or companies are considered a clear threat to people’s fundamental rights and are therefore banned. EU announcement: Click here https://preview.redd.it/nwyzfzgm4cmd1.png?width=828&format=png&auto=webp&s=c873db37ca0dadd5b510bea70ac9f633b96aaea4 California AI bill SB-1047 sparks fierce debate, Senator likens it to ‘Jets vs. Sharks’ feud Key Aspects of SB-1047: Regulation Scope: Targets “frontier” AI models, defined by their immense computational training requirements (over 10²⁶ operations) or significant financial investment (>$100 million). Compliance Requirements: Developers must implement safety protocols, including the ability to immediately shut down, cybersecurity measures, and risk assessments, before model deployment. Whistleblower Protections: Encourages reporting of non-compliance or risks by offering protection against retaliation. Safety Incident Reporting: Mandates reporting AI safety incidents within 72 hours to a newly established Frontier Model Division. Certification: Developers need to certify compliance, potentially under penalty of perjury in earlier drafts, though amendments might have altered this. Pros: Safety First: Prioritizes the prevention of catastrophic harms by enforcing rigorous safety standards, potentially safeguarding against AI misuse or malfunction. Incentivizes Responsible Development: By setting high standards for AI model training, the company encourages developers to think critically about the implications of their creations. Public Trust: Enhances public confidence in AI by ensuring transparency and accountability in the development process. Cons: Innovation Stagnation: Critics argue it might stifle innovation, especially in open-source AI, due to the high costs and regulatory burdens of compliance. Ambiguity: Some definitions and requirements might be too specific or broad, leading to legal challenges or unintended consequences. Global Competitiveness: There’s concern that such regulations could push AI development outside California or the U.S., benefiting other nations without similar restrictions. Implementation Challenges: The practicalities of enforcing such regulations, especially the “positive safety determination,” could be complex and contentious. News Article: Click here Open Letter: Click here https://preview.redd.it/ib96d7nk4cmd1.png?width=828&format=png&auto=webp&s=0ed5913b5dae72e203c8592393e469d9130ed689 MORE OpenAI drama OpenAI co-founder John Schulman has left the company to join rival AI startup Anthropic, while OpenAI president and co-founder Greg Brockman is taking an extended leave until the end of the year. Schulman, who played a key role in creating the AI-powered chatbot platform ChatGPT and led OpenAI’s alignment science efforts, stated his move was driven by a desire to focus more on AI alignment and hands-on technical work. Peter Deng, a product manager who joined OpenAI last year, has also left the company. With these departures, only three of OpenAI’s original 11 founders remain: CEO Sam Altman, Brockman, and Wojciech Zaremba, lead of language and code generation. News Article: Click here https://preview.redd.it/0vdjc18j4cmd1.png?width=828&format=png&auto=webp&s=e9de604c26aed3e47b50df3bdf114ef61f967080 Apple and Nvidia may invest in OpenAI Apple, which is planning to integrate ChatGPT into iOS, is in talks to invest. Soon after, Bloomberg also reported that Apple is in talks but added that Nvidia “has discussed” joining the funding round as well. The round is reportedly being led by Thrive Capital and would value OpenAI at more than $100 billion. News Article: Click here https://preview.redd.it/ude6jguh4cmd1.png?width=828&format=png&auto=webp&s=3603cbca0dbb1be3e6d0efcf06c3a698428bbdd6 Editor’s Special The AI Bubble: Will It Burst, and What Comes After?: Click here Eric Schmidt Full Controversial Interview on AI Revolution (Former Google CEO): Click here AI isn’t gonna keep improving Click here General Intelligence: Define it, measure it, build it: Click here

#reddit#month#august

reddit

0

0.714

level6-killjoy•This week

GPT Weekly - 19the June Edition - OpenAI's function calling, Meta's free LLM, EU Regulation and more.

This is a recap covering the major news from last week. 🔥Top 3 news - OpenAI’s updates, Meta’s upcoming free LLM and EU Regulation 🗞️Interesting reads include PSA about protecting your keys, The GPT ouroboros, Reddit - OpenAI’s moat, and more.. 🧑‍🎓Learning includes a Step-by-step guide from a non-technical founder who launched his MVP, Chatbot for your Gdrive and more 🔥Top 3 AI news in the past week OpenAI: New Pricing, Models, & Functions OpenAI has been on a roll. Last week we saw the release of OpenAI best practice on using GPT. This week we saw some amazing updates. Three major buckets were: First, the price decreases for both embeddings and GPT-3.5 tokens. Second, new models for gpt-4 and gpt-3.5. A new longer context model for gpt-3.5. Third, a new function calling capability. Why is it important? Previously, the output from OpenAI was all text. So, calling an external API from GPT was quite difficult. You had to parse the text data and things were often incorrect. Langchain created the Agents and Tools feature to tackle this problem. It was still unreliable and prone to issues. Now you get native support to generate a fixed format output. You can use the output to generate functional calls and also pass functions which need to be called. For example, if your app has multiple API endpoints then you can use GPT to generate the API calls with parameters. You can also pass the endpoints as function calls to ensure the correct function is executed. This functionality can further be used to generate structured data (JSON) out of GPT. So, you can generate data from GPT and load it into your backend. What’s next? This functionality allows turning natural language responses into structured data. This can be used to create “intelligent” backends using LLMs. We might see implementations in no-code tools to allow more robust and natural-language tools for non-technical folks. The structured data process goes both ways. You can also feed structured data into GPT for better responses. This feature also has its share of issues. Function calling suffers from the same prompt injection issues. Malicious actors can pass malicious code in function or the responses. For example, creation of queries using functions might contain malicious code to delete data. Without proper user validation this code will be executed automatically and delete data. So, using LLM as the back-end layer needs proper security implementation. Meta's LLM: Commercial Use Ahead Llama has been a boon for the open source community. Many of the open source models rely on Llama. The issue is that Llama is research-only and cannot be used commercially. So, no one can use it to build any product. Meta is now working on the next version of the model. This model will be available for commercial use. This is in stark contrast to both OpenAI and Google. Both safe-guarde their models and make it available through API. Why is it important? Certain industries cannot use LLM APIs because of strict restrictions on data privacy. These companies would want to run their own instance of a foundational model. A commercially available foundational model is also going to help people who want to keep their “API call” costs next to 0. A commercially available free-for-all model will also help push the open source community further. Just like Llama. What’s next? Sam Altman has said OpenAI didn’t release GPT-3 as open-source because they didn’t think people would be able to run it. Now OpenAI is working on an open-source model. This is going to be weaker than GPT-4. Let the battle of LLMs begin. EU's Proposed Legislation and Its Impact on AI Usage The EU parliament voted to move ahead with the E.U. AI Act. This act aims to ensure consumer protection against the dangers of AI. Why is it important? OpenAI and Sam Altman want regulations for models. They have proposed a IAEA-type of agency to stop the proliferation of LLM models. As per OpenAI, all models should be regulated and monitored. The suggestion of a license based regulation has led to significant backlash. Many people have called it “regulatory capture” - with the aim of shutting down competing LLMs. Licensing based regulations might not really be effective. The EU is approaching regulation from a different angle. It doesn’t focus on how models are developed. Rather focuses on how AI will/can be used. They have broken down use cases into 4 categories - unacceptable (prohibited), high, medium and low risk. For example, Building a Pre-Crime software,on%20crimes%20not%20yet%20committed.) to predict crimes? Building a Social credit system? Unacceptable. Using tools to influence elections or recommendation algorithms? High (Highly regulated). Using generative AI tools to create text or images on news sites? Medium (Add label that the content is AI generated) AI providers also need to disclose their training source. To me this sounds like good legislation. What do you guys think? But, OpenAI has warned that EU regulations might force them to pull out completely. What’s next? The disclosure requirements might help various publishing companies. AI and media companies are in talks to pay for training data. Google has been leading the charge. Additionally, OpenAI and Deepmind will open their models for safety and research purposes to the UK government. 🗞️10 AI news highlights and interesting reads PSA: If you are using Repl to write code, you might want to check your OpenAI API keys. If you have left them embedded then people can pirate and steal the keys. LLMs rely on human annotation or human feedback to learn. And one way to generate human annotation is crowdsourcing. But what if the crowdsource human annotators use LLMs? Research shows 33-46% workers used LLMs. So, basically we go from Human -> AI -> Human -> AI. The AI ouroboros. Researchers also say generated data to train models might cause serious issue. All the talks about moats \- Reddit might be OpenAI’s \future\ moat. Given the amount of complaints about how Google search experience has deteriorated during the blackout, this might be true? Doctors are using ChatGPT but not to diagnose.Rather to be more empathetic. We discussed this just a month ago. And guess where the data for this study came from? Reddit AskDocs. Moat FTW?! Beatles to make a comeback…using Generative AI. SnapFusion - Text to Image diffusion on mobile phones. Large context lengths are important for better GPT experience. The secret sauce for 100k context length. There is a lot of bad AI research out there. Some border on snake oil. Most AI “research” should be double checked and challenged. A new research on huggingface said that GPT-4 can ace MIT curriculum. Now someone is replicating the results and say that GPT-4 can’t beat MIT. Are we seeing peak AI? Especially when people from Deepmind and Meta are involved? Mistral AI raised $113 million in seed round with no product. Some might say this funding is for the team and the team is really solid. The issue though is whether the valuation is justified when OpenAI and Google already have a head start. The AI Hype Wall of Shame. \- Collection of articles which mislead people about AI in various aspects. 🧑‍🎓3 Learning Resources Building and Launching a company using GPT-4 with prompts. (The author didn’t know how to code but created and launched the MVP in a month). Chatbot for your Gdrive - https://www.haihai.ai/gpt-gdrive/ Building ChatGPT plugin using Supabase - https://supabase.com/blog/building-chatgpt-plugins-template That’s it folks. Thank you for reading and have a great week ahead. If you are interested in a focused weekly recap delivered to your inbox on Mondays you can subscribe here. It is FREE!

#reddit#weekly#19the

reddit

0

1

daniel-data•This week

Study Plan for Learning Data Science Over the Next 12 Months [D]

In this thread, I address a study plan for 2021. In case you're interested, I wrote a whole article about this topic: Study Plan for Learning Data Science Over the Next 12 Months Let me know your thoughts on this. ​ https://preview.redd.it/emg20nzhet661.png?width=1170&format=png&auto=webp&s=cf09e4dc5e82ba2fd7b57c706ba2873be57fe8de We are ending 2020 and it is time to make plans for next year, and one of the most important plans and questions we must ask is what do we want to study?, what do we want to enhance?, what changes do we want to make?, and what is the direction we are going to take (or continue) in our professional careers?. Many of you will be starting on the road to becoming a data scientist, in fact you may be evaluating it, since you have heard a lot about it, but you have some doubts, for example about the amount of job offers that may exist in this area, doubts about the technology itself, and about the path you should follow, considering the wide range of options to learn. I’m a believer that we should learn from various sources, from various mentors, and from various formats. By sources I mean the various virtual platforms and face-to-face options that exist to study. By mentors I mean that it is always a good idea to learn from different points of view and learning from different teachers/mentors, and by formats I mean the choices between books, videos, classes, and other formats where the information is contained. When we extract information from all these sources we reinforce the knowledge learned, but we always need a guide, and this post aims to give you some practical insights and strategies in this regard. To decide on sources, mentors and formats it is up to you to choose. It depends on your preferences and ease of learning: for example, some people are better at learning from books, while others prefer to learn from videos. Some prefer to study on platforms that are practical (following online code), and others prefer traditional platforms: like those at universities (Master’s Degree, PHDs or MOOCs). Others prefer to pay for quality content, while others prefer to look only for free material. That’s why I won’t give a specific recommendation in this post, but I’ll give you the whole picture: a study plan. To start you should consider the time you’ll spend studying and the depth of learning you want to achieve, because if you find yourself without a job you could be available full time to study, which is a huge advantage. On the other hand, if you are working, you’ll have less time and you’ll have to discipline yourself to be able to have the time available in the evenings, mornings or weekends. Ultimately, the important thing is to meet the goal of learning and perhaps dedicating your career to this exciting area! We will divide the year into quarters as follows First Quarter: Learning the Basics Second Quarter: Upgrading the Level: Intermediate Knowledge Third Quarter: A Real World Project — A Full-stack Project Fourth Quarter: Seeking Opportunities While Maintaining Practice First Quarter: Learning the Basics ​ https://preview.redd.it/u7t9bthket661.png?width=998&format=png&auto=webp&s=4ad29cb43618e7acf793259243aa5a60a8535f0a If you want to be more rigorous you can have start and end dates for this period of study of the bases. It could be something like: From January 1 to March 30, 2021 as deadline. During this period you will study the following: A programming language that you can apply to data science: Python or R. We recommend Python due to the simple fact that approximately 80% of data science job offers ask for knowledge in Python. That same percentage is maintained with respect to the real projects you will find implemented in production. And we add the fact that Python is multipurpose, so you won’t “waste” your time if at some point you decide to focus on web development, for example, or desktop development. This would be the first topic to study in the first months of the year. Familiarize yourself with statistics and mathematics. There is a big debate in the data science community about whether we need this foundation or not. I will write a post later on about this, but the reality is that you DO need it, but ONLY the basics (at least in the beginning). And I want to clarify this point before continuing. We could say that data science is divided in two big fields: Research on one side and putting Machine Learning algorithms into production on the other side. If you later decide to focus on Research then you are going to need mathematics and statistics in depth (very in depth). If you are going to go for the practical part, the libraries will help you deal with most of it, under the hood. It should be noted that most job offers are in the practical part. For both cases, and in this first stage you will only need the basics of: Statistics (with Python and NumPy) Descriptive statistics Inferential Statistics Hypothesis testing Probability Mathematics (with Python and NumPy) Linear Algebra (For example: SVD) Multivariate Calculus Calculus (For example: gradient descent) Note: We recommend that you study Python first before seeing statistics and mathematics, because the challenge is to implement these statistical and mathematical bases with Python. Don’t look for theoretical tutorials that show only slides or statistical and/or mathematical examples in Excel/Matlab/Octave/SAS and other different to Python or R, it gets very boring and impractical! You should choose a course, program or book that teaches these concepts in a practical way and using Python. Remember that Python is what we finally use, so you need to choose well. This advice is key so you don’t give up on this part, as it will be the most dense and difficult. If you have these basics in the first three months, you will be ready to make a leap in your learning for the next three months. Second Quarter: Upgrading the Level: Intermediate Knowledge ​ https://preview.redd.it/y1y55vynet661.png?width=669&format=png&auto=webp&s=bd3e12bb112943025c39a8975faf4d64514df275 If you want to be more rigorous you can have start and end dates for this period of study at the intermediate level. It could be something like: From April 1 to June 30, 2021 as deadline. Now that you have a good foundation in programming, statistics and mathematics, it is time to move forward and learn about the great advantages that Python has for applying data analysis. For this stage you will be focused on: Data science Python stack Python has the following libraries that you should study, know and practice at this stage Pandas: for working with tabular data and make in-depth analysis Matplotlib and Seaborn: for data visualization Pandas is the in-facto library for data analysis, it is one of the most important (if not the most important) and powerful tools you should know and master during your career as a data scientist. Pandas will make it much easier for you to manipulate, cleanse and organize your data. Feature Engineering Many times people don’t go deep into Feature Engineering, but if you want to have Machine Learning models that make good predictions and improve your scores, spending some time on this subject is invaluable! Feature engineering is the process of using domain knowledge to extract features from raw data using data mining techniques. These features can be used to improve the performance of machine learning algorithms. Feature engineering can be considered as applied machine learning itself. To achieve the goal of good feature engineering you must know the different techniques that exist, so it is a good idea to at least study the main ones. Basic Models of Machine Learning At the end of this stage you will start with the study of Machine Learning. This is perhaps the most awaited moment! This is where you start to learn about the different algorithms you can use, which particular problems you can solve and how you can apply them in real life. The Python library we recommend you to start experimenting with ML is: scikit-learn. However it is a good idea that you can find tutorials where they explain the implementation of the algorithms (at least the simplest ones) from scratch with Python, since the library could be a “Black Box” and you might not understand what is happening under the hood. If you learn how to implement them with Python, you can have a more solid foundation. If you implement the algorithms with Python (without a library), you will put into practice everything seen in the statistics, mathematics and Pandas part. These are some recommendations of the algorithms that you should at least know in this initial stage Supervised learning Simple Linear Regression Multiple Linear Regression K-nearest neighbors (KNN) Logistic Regression Decision Trees Random Forest Unsupervised Learning K-Means PCA Bonus: if you have the time and you are within the time ranges, you can study these others Gradient Boosting Algorithms GBM XGBoost LightGBM CatBoost Note: do not spend more than the 3 months stipulated for this stage. Because you will be falling behind and not complying with the study plan. We all have shortcomings at this stage, it is normal, go ahead and then you can resume some concepts that did not understand in detail. The important thing is to have the basic knowledge and move forward! If at least you succeed to study the mentioned algorithms of supervised and unsupervised learning, you will have a very clear idea of what you will be able to do in the future. So don’t worry about covering everything, remember that it is a process, and ideally you should have some clearly established times so that you don’t get frustrated and feel you are advancing. So far, here comes your “theoretical” study of the basics of data science. Now we’ll continue with the practical part! Third Quarter: A Real World Project — A Full-stack Project ​ https://preview.redd.it/vrn783vqet661.png?width=678&format=png&auto=webp&s=664061b3d33b34979b74b10b9f8a3d0f7b8b99ee If you want to be more rigorous you can have start and end dates for this period of study at the intermediate level. It could be something like: From July 1 to September 30, 2021 as deadline. Now that you have a good foundation in programming, statistics, mathematics, data analysis and machine learning algorithms, it is time to move forward and put into practice all this knowledge. Many of these suggestions may sound out of the box, but believe me they will make a big difference in your career as a data scientist. The first thing is to create your web presence: Create a Github (or GitLab) account, and learn Git*. Being able to manage different versions of your code is important, you should have version control over them, not to mention that having an active Github account is very valuable in demonstrating your true skills. On Github, you can also set up your Jupyter Notebooks and make them public, so you can show off your skills as well. This is mine for example: https://github.com/danielmoralesp Learn the basics of web programming*. The advantage is that you already have Python as a skill, so you can learn Flask to create a simple web page. Or you can use a template engine like Github Pages, Ghost or Wordpress itself and create your online portfolio. Buy a domain with your name*. Something like myname.com, myname.co, myname.dev, etc. This is invaluable so you can have your CV online and update it with your projects. There you can make a big difference, showing your projects, your Jupyter Notebooks and showing that you have the practical skills to execute projects in this area. There are many front-end templates for you to purchase for free or for payment, and give it a more personalized and pleasant look. Don’t use free sub-domains of Wordpress, Github or Wix, it looks very unprofessional, make your own. Here is mine for example: https://www.danielmorales.dev/ Choose a project you are passionate about and create a Machine Learning model around it. The final goal of this third quarter is to create ONE project, that you are passionate about, and that is UNIQUE among others. It turns out that there are many typical projects in the community, such as predicting the Titanic Survivors, or predicting the price of Houses in Boston. Those kinds of projects are good for learning, but not for showing off as your UNIQUE projects. If you are passionate about sports, try predicting the soccer results of your local league. If you are passionate about finance, try predicting your country’s stock market prices. If you are passionate about marketing, try to find someone who has an e-commerce and implement a product recommendation algorithm and upload it to production. If you are passionate about business: make a predictor of the best business ideas for 2021 :) As you can see, you are limited by your passions and your imagination. In fact, those are the two keys for you to do this project: Passion and Imagination. However don’t expect to make money from it, you are in a learning stage, you need that algorithm to be deployed in production, make an API in Flask with it, and explain in your website how you did it and how people can access it. This is the moment to shine, and at the same time it’s the moment of the greatest learning. You will most likely face obstacles, if your algorithm gives 60% of Accuracy after a huge optimization effort, it doesn’t matter, finish the whole process, deploy it to production, try to get a friend or family member to use it, and that will be the goal achieved for this stage: Make a Full-stack Machine Learning project. By full-stack I mean that you did all the following steps: You got the data from somewhere (scrapping, open data or API) You did a data analysis You cleaned and transformed the data You created Machine Learning Models You deployed the best model to production for other people to use. This does not mean that this whole process is what you will always do in your daily job, but it does mean that you will know every part of the pipeline that is needed for a data science project for a company. You will have a unique perspective! Fourth Quarter: Seeking Opportunities While Maintaining Practice ​ https://preview.redd.it/qd0osystet661.png?width=1056&format=png&auto=webp&s=2da456b15985b2793041256f5e45bca99a23b51a If you want to be more rigorous you can have start and end dates for this period of study at the final level. It could be something like: From October 1 to December 31, 2021 as deadline. Now you have theoretical and practical knowledge. You have implemented a model in production. The next step depends on you and your personality. Let’s say you are an entrepreneur, and you have the vision to create something new from something you discovered or saw an opportunity to do business with this discipline, so it’s time to start planning how to do it. If that’s the case, obviously this post won’t cover that process, but you should know what the steps might be (or start figuring them out). But if you are one of those who want to get a job as a data scientist, here is my advice. Getting a job as a data scientist “You’re not going to get a job as fast as you think, if you keep thinking the same way”.Author It turns out that all people who start out as data scientists imagine themselves working for the big companies in their country or region. Or even remote. It turns out that if you aspire to work for a large company like data scientist you will be frustrated by the years of experience they ask for (3 or more years) and the skills they request. Large companies don’t hire Juniors (or very few do), precisely because they are already large companies. They have the financial muscle to demand experience and skills and can pay a commensurate salary (although this is not always the case). The point is that if you focus there you’re going to get frustrated! Here we must return to the following advise: “You need creativity to get a job in data science”. Like everything else in life we have to start at different steps, in this case, from the beginning. Here are the scenarios If you are working in a company and in a non-engineering role you must demonstrate your new skills to the company you are working for*. If you are working in the customer service area, you should apply it to your work, and do for example, detailed analysis of your calls, conversion rates, store data and make predictions about it! If you can have data from your colleagues, you could try to predict their sales! This may sound funny, but it’s about how creatively you can apply data science to your current work and how to show your bosses how valuable it is and EVANGELIZE them about the benefits of implementation. You’ll be noticed and they could certainly create a new data related department or job. And you already have the knowledge and experience. The key word here is Evangelize. Many companies and entrepreneurs are just beginning to see the power of this discipline, and it is your task to nurture that reality. If you are working in an area related to engineering, but that is not data science*. Here the same applies as the previous example, but you have some advantages, and that is that you could access the company’s data, and you could use it for the benefit of the company, making analyses and/or predictions about it, and again EVANGELIZING your bosses your new skills and the benefits of data science. If you are unemployed (or do not want, or do not feel comfortable following the two examples above)*, you can start looking outside, and what I recommend is that you look for technology companies and / or startups where they are just forming the first teams and are paying some salary, or even have options shares of the company. Obviously here the salaries will not be exorbitant, and the working hours could be longer, but remember that you are in the learning and practice stage (just in the first step), so you can not demand too much, you must land your expectations and fit that reality, and stop pretending to be paid $ 10,000 a month at this stage. But, depending of your country $1.000 USD could be something very interesting to start this new career. Remember, you are a Junior at this stage. The conclusion is: don’t waste your time looking at and/or applying to offers from big companies, because you will get frustrated. Be creative, and look for opportunities in smaller or newly created companies. Learning never stops While you are in that process of looking for a job or an opportunity, which could take half of your time (50% looking for opportunities, 50% staying in practice), you have to keep learning, you should advance to concepts such as Deep Learning, Data Engineer or other topics that you feel were left loose from the past stages or focus on the topics that you are passionate about within this group of disciplines in data science. At the same time you can choose a second project, and spend some time running it from end-to-end, and thus increase your portfolio and your experience. If this is the case, try to find a completely different project: if the first one was done with Machine Learning, let this second one be done with Deep learning. If the first one was deployed to a web page, that this second one is deployed to a mobile platform. Remember, creativity is the key! Conclusion We are at an ideal time to plan for 2021, and if this is the path you want to take, start looking for the platforms and media you want to study on. Get to work and don’t miss this opportunity to become a data scientist in 2021! Note: we are building a private community in Slack of data scientist, if you want to join us write to the email: support@datasource.ai I hope you enjoyed this reading! you can follow me on twitter or linkedin Thank you for reading!

#reddit#study#plan

reddit

0

1

Brilliant_Fishing110•This week

Randomly asked ChatGPT and Claude for a 4 year roadmap for an ML Engineer

Title, Is it actually a good plan ?? If no, why not ?? \\🚀 4-Year Roadmap to Becoming a High-Earning ML Engineer & Entrepreneur\\ \\(With Smartwork & Realistic 60-70% Execution Feasibility)\\ \\🟢 Year 1: Strong Foundation & Initial Projects (0-12 Months)\\ 🎯 \\Goal: Master Python & ML Fundamentals\\ \\🔹 1-4 Months (Python & Math Strengthening)\\ ✅ Python Mastery \- Daily LeetCode Easy problems (minimum 2) \- Build automation projects \- NumPy & Pandas mastery \- DSA fundamentals ✅ Mathematics Foundation \- Linear Algebra basics \- Statistics fundamentals \- Basic calculus concepts ✅ First Mini-Hackathon Participation \- Join beginner-friendly hackathons \- Focus on Python-based challenges \- Team up with other beginners 💡 \\Smart Move:\\ \- Join Discord/Slack hackathon communities \- Practice collaborative coding \- Build network with fellow participants \\🔹 5-8 Months (ML Foundations)\\ ✅ Machine Learning Basics \- Supervised Learning \- Model evaluation \- Feature engineering \- scikit-learn projects ✅ Participate in 2-3 ML Hackathons \- Kaggle Getting Started competitions \- Local ML hackathons \- University hackathons ✅ Start LinkedIn & GitHub Portfolio 💡 \\Smart Move:\\ \- Document hackathon experiences \- Share learnings on LinkedIn \- Focus on completion over winning \\🔹 9-12 Months (Deep Learning Introduction)\\ ✅ Basic Deep Learning \- Neural network fundamentals \- PyTorch basics \- Computer vision tasks \- Basic NLP ✅ Advanced Hackathon Participation \- AI/ML specific hackathons \- Team lead in 1-2 hackathons \- Start mentoring beginners \\🔵 Year 1 Expected Outcome (60-70% Execution)\\ ✔ \\Strong Python & ML foundations\\ ✔ \\5-6 hackathon participations\\ ✔ \\Active GitHub (100+ commits)\\ ✔ \\Growing LinkedIn (300+ connections)\\ 💰 \\Earning Expectation → ₹8K-₹20K per month (Projects/Internship)\\ \\🟢 Year 2: Professional Growth & Specialization (12-24 Months)\\ 🎯 \\Goal: Build Professional Experience & Recognition\\ \\🔹 1-6 Months (Technical Depth)\\ ✅ Advanced ML Topics \- Deep Learning architectures \- Computer Vision OR NLP \- MLOps basics (Docker, FastAPI) \- Cloud fundamentals (AWS/GCP) ✅ Hackathon Achievements \- Win minor prizes in 2-3 hackathons \- Lead teams in major hackathons \- Network with sponsors ✅ Start Technical Blogging 💡 \\Smart Move:\\ \- Focus on hackathon projects that align with career goals \- Build relationships with companies at hackathons \- Create detailed project documentation \\🔹 7-12 Months (Professional Experience)\\ ✅ Secure ML Role/Internship ✅ Advanced Project Building ✅ Open Source Contributions ✅ Organize Small Hackathons 💡 \\Smart Move:\\ \- Use hackathon network for job referrals \- Convert hackathon projects into full products \- Build mentor reputation \\🔵 Year 2 Expected Outcome (60-70% Execution)\\ ✔ \\Professional ML experience\\ ✔ \\10+ hackathon participations\\ ✔ \\1-2 hackathon wins\\ ✔ \\Strong industry network\\ 💰 \\Earning Expectation → ₹40K-₹70K per month (Job/Freelancing)\\ \\🟢 Year 3: Scaling & Business Foundation (24-36 Months)\\ 🎯 \\Goal: Establish Multiple Income Streams\\ \\🔹 1-4 Months (Expertise Building)\\ ✅ Choose Specialization \- MLOps \- Computer Vision \- NLP/LLMs \- Generative AI ✅ Advanced Competitions \- International hackathons \- High-prize competitions \- Corporate ML challenges ✅ Start Consulting Services 💡 \\Smart Move:\\ \- Use hackathon wins for marketing \- Build service packages around expertise \- Network with corporate sponsors \\🔹 5-8 Months (Business Development)\\ ✅ Scale Services ✅ Build Client Network ✅ Create Training Programs ✅ Hackathon Mentorship Program 💡 \\Smart Move:\\ \- Convert hackathon projects to products \- Use event networks for client acquisition \- Build authority through speaking \\🔹 9-12 Months (Growth & Innovation)\\ ✅ Product Development ✅ Team Building ✅ Innovation Focus ✅ Hackathon Organization \\🔵 Year 3 Expected Outcome (60-70% Execution)\\ ✔ \\Established ML business/career\\ ✔ \\Known in hackathon community\\ ✔ \\Multiple income streams\\ ✔ \\Strong industry presence\\ 💰 \\Earning Expectation → ₹1L-₹2L per month (Multiple Streams)\\ \\🟢 Year 4: Scale & Leadership (36-48 Months)\\ 🎯 \\Goal: Build AI Company & Achieve Financial Freedom\\ \\🔹 1-4 Months (Business Scaling)\\ ✅ Company Formation \- AI consulting firm \- Product development \- Training programs ✅ Hackathon Innovation \- Launch own hackathon series \- Corporate partnerships \- Prize sponsorships ✅ Team Expansion 💡 \\Smart Move:\\ \- Use hackathon network for hiring \- Create unique event formats \- Build corporate relationships \\🔹 5-8 Months (Market Leadership)\\ ✅ Product Launch ✅ Service Expansion ✅ International Presence ✅ Innovation Hub Creation 💡 \\Smart Move:\\ \- Create hackathon-to-hiring pipeline \- Build educational programs \- Establish thought leadership \\🔹 9-12 Months (Empire Building)\\ ✅ Multiple Revenue Streams \- AI products \- Consulting services \- Educational programs \- Event organization \- Investment returns ✅ Industry Leadership \- Conference speaking \- Published content \- Community leadership \\🔵 Year 4 Expected Outcome (60-70% Execution)\\ ✔ \\Established AI company\\ ✔ \\Major hackathon organizer\\ ✔ \\Multiple product lines\\ ✔ \\Industry authority status\\ 💰 \\Earning Expectation → ₹3L-₹5L+ per month (Business Income)\\ \\📊 FINAL RATING\\ ✅ \\Comprehensive growth plan\\ ✅ \\Strong community focus\\ ✅ \\Multiple income pathways\\ 💡 \\If 100% Execution → 8.5/10 Feasibility\\ 💡 \\If 50% Execution → 6/10 Feasibility\\ 🔥 \\Conclusion: A balanced path to ML mastery and entrepreneurship, built through consistent growth and community engagement!\\ 🚀 \\Key Success Factors:\\ Regular hackathon participation Strong community involvement Consistent skill development Strategic network building Focus on both technical and business growth

#reddit#randomly#asked

reddit

0

0

Ole_Gooner•This week

Problems with automating manual data entry using Deep Learning

Full disclaimer: I work at Nanonets. Nanonets is a Deep Learning API company. We've written some of the most go to blogs on Deep Learning available on the internet. https://nanonets.com/blog/ This post might be a little different so apologies in advance if I'm violating any rules. We've written a blog that gives an overview of an important but often overlooked process in an organization: 3 way matching of Purchase Orders We've noticed that Deep learning (GCNs) + OCR can be applied and bring down manual digitization times significantly. i.e the process that typically takes a human 90 seconds can be done within 20 seconds with AI assistance. However there are quite a few caveats and nuances before beginning and this blog covers that aspect. Link to blog: https://nanonets.com/blog/how-to-ocr-purchase-orders-for-automation/

#reddit#problems#automating

reddit

0

1

Competitive_Speech36•This week

6 principles to data architecture that facilitate innovation

My team and I have been re-building our company's data architecture. In the process of doing so, I got together six key principles to transforming data architectures and thought I would share them, as a strong data architecture is crucial for businesses looking to stay competitive in the digital landscape, as it improves decision-making, time to market, and data security. When executed with efficiency, a resilient data architecture unleashes unparalleled degrees of agility. Principle 1: Agility and flexibility To quickly adjust to market fluctuations, businesses must create adaptable data infrastructures that can effortlessly manage an ever-growing influx of data. To accomplish this objective, we recommend to our clients to implement Enterprise Service Bus, Enterprise Data Warehouse, and Master Data Management integrated together. ​ I believe the best option is this: \- By centralizing communication, ESB reduces the time and effort required to integrate new systems; \- EDW consolidates data from different sources, resulting in a 50% reduction in software implementation time; \- Finally, MDM ensures consistency and accuracy across the organization, leading to better decision-making and streamlined operations. Implementing these solutions can lead to reduced software implementation time, better ROI, and more manageable data architecture. By fostering a culture of collaboration and adopting modern technologies and practices, businesses can prioritize agility and flexibility in their data architecture to increase the pace of innovation. Principle 2: Modularity and reusability Data architecture that fosters modularity and reusability is essential for accelerating innovation within an organization. By breaking data architecture components into smaller, more manageable pieces, businesses can enable different teams to leverage existing architecture components, reducing redundancy and improving overall efficiency. MDM can promote modularity and reusability by creating a central repository for critical business data. This prevents duplication and errors, improving efficiency and decision-making. MDM enables a single source of truth for data, accessible across multiple systems, which promotes integration and scalability. MDM also provides standardized data models, rules, and governance policies that reduce development time, increase quality, and ensure proper management throughout the data’s lifecycle. Another way to achieve modularity in data architecture is through the use of microservices and scripts for Extract, Transform, and Load (ETL) processes. Adopting a structured methodology and framework can ensure these components are well-organized, making it easier for teams to collaborate and maintain the system. Microservices can also contribute to modularity and reusability in data architecture. These small, independent components can be developed, deployed, and scaled independently of one another. By utilizing microservices, organizations can update or replace individual components without affecting the entire system, improving flexibility and adaptability. Principle 3: Data quality and consistency The efficiency of operations depends on data’s quality, so a meticulously crafted data architecture plays a pivotal role in preserving it, empowering enterprises to make well-informed decisions based on credible information. Here are some key factors to consider that will help your company ensure quality: \- Implementing Master Data Management (MDM) – this way, by consolidating, cleansing, and standardizing data from multiple sources, your IT department will be able to create a single, unified view of the most important data entities (customers, products, and suppliers); \- Assigning data stewardship responsibilities to a small team or an individual specialist; \- Considering implementing data validation, data lineage, and data quality metrics; \- By implementing MDM and adopting a minimal data stewardship approach, organizations can maintain high-quality data that drives innovation and growth. Principle 4: Data governance Data governance is a strategic framework that goes beyond ensuring data quality and consistency. It includes ensuring data security, privacy, accessibility, regulatory compliance, and lifecycle management. Here are some key aspects of data governance: \- Implementing robust measures and controls to protect sensitive data from unauthorized access, breaches, and theft. This is only possible through including encryption, access controls, and intrusion detection systems into your company’s IT architecture; \- Adhering to data privacy regulations and guidelines, such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA); \- Defining stringent conditions for who has access to specific data assets to maintain control over data and ensure its accessibility only for legitimate purposes. Managing the entire lifecycle of data, from creation and storage to archiving and disposal, including defining policies for data retention, archiving, and deletion in compliance with legal and regulatory requirements. To facilitate effective data governance, organizations can leverage various tools and technologies, such as: \- Data cataloging tools: Solutions like Collibra, Alation, or Informatica Enterprise Data Catalog help organizations discover, understand, and manage their data assets. \- Data lineage tools: Tools like Talend, IBM InfoSphere, or Apache Atlas help track data’s origin, transformation, and usage, providing insights into data quality issues and potential areas for improvement. \- Data quality tools: Solutions like Informatica Data Quality, Trifacta, or SAS Data Quality help organizations maintain high-quality data by identifying and correcting errors, inconsistencies, and inaccuracies. \- Data security and privacy tools: Tools like Varonis, BigID, or Spirion help protect sensitive data and ensure compliance with data privacy regulations. Principle 5: Cloud-first approach A cloud-first approach prioritizes cloud-based solutions over on-premises ones when it comes to data management. Cloud-based data management pros: \- Virtually limitless scalability, so that organizations can grow and adapt to changing data requirements without significant infrastructure investments; \- The pay-as-you-go model of cloud services reduces maintenance costs usually associated with the on-premise choice; \- Greater flexibility for deploying and integrating new technologies and services; \- Cloud can be accessed from anywhere, at any time, turning team collaboration and remote work into a breeze; \- Built-in backup and disaster recovery capabilities, ensuring data safety and minimizing downtime in case of emergencies. Cloud-based data management cons: \- Cloud-first approach raises many data security, privacy, and compliance concerns; \- Transferring large data volumes to and from cloud is often time-consuming and results in increased latency for certain apps; \- Relying on a single cloud provider makes it difficult to switch them or move back to the on-premises option without significant funds and effort. Challenges that organizations that choose a cloud-first approach face: \- Integrating cloud-based systems with on-premises ones can be complex and time-consuming; \- Ensuring data governance and compliance in a multi-cloud or hybrid environment is also another problem reported by my clients. How EDW, ESB, and MDM promote cloud-first approach: A cloud-based EDW centralizes data from multiple sources, enabling a unified view of the organization’s data and simplifying data integration across cloud and on-premises systems. An ESB facilitates communication between disparate cloud and on-premises systems, streamlining data integration and promoting a modular architecture. Cloud-based MDM solutions are used for maintaining data quality and consistency across multiple data sources and environments. Principle 6: Automation and artificial intelligence Incorporating automation tools and AI technologies into data architecture can optimize processes and decision-making. Key Applications: \- Data ingestion and integration: Automation simplifies data schema updates and identifies data quality issues, while AI-assisted development helps create tailored connectors, scripts, and microservices. \- Data quality management: Machine learning algorithms improve data quality and consistency by automatically detecting and correcting inconsistencies and duplicates. \- Predictive analytics: AI and machine learning models analyze historical data to predict trends, identify opportunities, and uncover hidden patterns for better-informed decisions. How No-Code Tools and AI-Assisted Development Work: Business users define data requirements and workflows using no-code tools, enabling AI models to understand their needs. AI models process the information, generating recommendations for connector creation, ETL scripts, and microservices. Developers use AI-generated suggestions to accelerate development and tailor solutions to business needs. By combining automation, AI technologies, and no-code tools, organizations can streamline data architecture processes and bridge the gap between business users and developers, ultimately accelerating innovation. I share more tips on building an agile data architectures in my blog.

#reddit#principles#data

reddit

0

1

AniketWork•This week

How I Built an Agentic Marketing Campaign Strategist

Marketing at Scale: How One AI System Replaces Hundreds of Strategy Hours Article https://i.redd.it/uekqj3zmerme1.gif https://i.redd.it/30rk23zmerme1.gif https://preview.redd.it/fk1t53zmerme1.png?width=797&format=png&auto=webp&s=d07f473a9556fbd38885b3a2f862101d9b25424e https://preview.redd.it/n84113zmerme1.jpg?width=1914&format=pjpg&auto=webp&s=f42679269a1003e1c8d6501dd2d53e10db745bba https://preview.redd.it/l13ae3zmerme1.jpg?width=791&format=pjpg&auto=webp&s=ecab3c295c2a416bc0fed8c62fecbe3321e37093 TL;DR This article guides you through building an AI-powered marketing strategist using Python. It combines vector databases, language models, and PDF generation to create customized marketing strategies automatically. I’ll show you the complete system architecture, from storing marketing knowledge to generating professional strategy documents, with practical code examples you can implement today. Perfect for marketers and developers looking to leverage AI for business growth. Introduction Welcome to the exciting intersection of marketing and artificial intelligence! In today’s digital world, creating effective marketing campaigns requires deep expertise, market research, and creative thinking. But what if you could automate parts of this process? That’s exactly what I set out to build: an AI system that generates comprehensive marketing strategies tailored to specific products, audiences, and budgets. What’s This Article About? This article walks you through the creation of an AI-powered marketing strategist that combines the retrieval of relevant marketing knowledge with advanced language generation to produce detailed campaign strategies. The system I built uses Retrieval-Augmented Generation (RAG), which enhances AI outputs by grounding them in specific knowledge sources. Here’s how it works: You provide a simple campaign description (like “a new eco-friendly water bottle targeting millennials with a budget of $50,000”) The system searches a knowledge base of marketing principles and best practices It then uses a language model to craft a comprehensive strategy that includes campaign objectives, target audience analysis, channel selection, content ideas, budget allocation, and measurement KPIs Finally, it generates a professional PDF document with your complete marketing strategy The beauty of this approach is that it combines the creativity and adaptability of AI with established marketing frameworks, ensuring the strategies are both innovative and grounded in proven principles. Why Read It? AI is rapidly transforming how businesses operate, and marketing is at the forefront of this revolution. According to recent studies, companies that effectively leverage AI in their marketing efforts see significant improvements in customer engagement, conversion rates, and ROI. Even if you’re not building a system for a real company right now, understanding how to implement AI in marketing processes gives you valuable skills and insights. This article provides a practical example of how AI can: Save marketers countless hours of research and strategy development Ensure consistency in marketing approaches across different campaigns Generate creative ideas that might not have been considered otherwise Scale marketing expertise across an organization By following along, you’ll gain hands-on experience with technologies like vector databases, language models, and automated document generation — all skills that are increasingly valuable in today’s business environment.

#reddit#built#agentic

reddit

0

1

AssistanceOk2217•This week

Master AI Integration: How to Integrate AI in Your Application

A Comprehensive Guide with Every Detail Spelled Out for Flawless AI Implementation Full Article ​ https://preview.redd.it/m5b79j55f14d1.png?width=1328&format=png&auto=webp&s=8cf04c80cd21be1710dd117a9e74b07d0e8cbe6a In the ideal world, we'd design our software systems with AI in mind from the very beginning. But in the real world, that's not always possible. Many businesses have large, complex systems that have been running for years, and making significant changes to them is risky and expensive. What this Article is About? ● This article aims to convince you that even when changing existing systems is not an option, you can still seamlessly integrate AI into your business processes. It explores real-world scenarios and shows how a company (though simulated) has successfully incorporated AI without overhauling their existing infrastructure. ​ https://i.redd.it/fayl1gcbf14d1.gif Why Read This Article? ● By reading this article, you will learn the critical skill of integrating AI into your existing business ecosystem without making significant changes to your stable workflows. This skill is becoming increasingly important as more and more companies recognize the value of AI while also acknowledging the challenges of overhauling their existing systems. What is Our Business Use Case? ● The article uses a simulated supply chain management company as a business use case. This company has multiple departments, each exposing its own REST API, and to get an inquiry answered, the request has to go through various departments, their respective APIs, and database calls. The article introduces AI capabilities to enhance the company's operations without modifying the existing system architecture. Our Supply Chain Management Company AI Integration Design ● The article describes the various components of the simulated supply chain management company, including the "Data Processing System," "Company Data Handling System," "AI Integration System," "Mapping System," and "System Admin Dashboard." Let's Get Cooking! ● This section provides the code and explanations for implementing the AI integration system in the simulated supply chain management company. It covers the following: ○ Dashboard & AI Integration System ○ Company Data Handling System ○ Data Processing System ○ Mapping System Let's Setup ● This section shows the expected output when setting up the simulated supply chain management system with AI integration. Let's Run it ● This section demonstrates how to run the system and ask questions related to supply chain management, showcasing the AI integration in action. https://i.redd.it/3e68mb57f14d1.gif Closing Thoughts The supply chain management project we have explored in this article serves as a powerful example of how to seamlessly integrate cutting-edge AI capabilities into existing business systems without the need for significant overhauls or disruptions. By leveraging the flexibility and power of modern AI technologies, we were able to enhance the functionality of a simulated supply chain management system while preserving its core operations and workflows. Throughout the development process, we placed a strong emphasis on minimizing the impact on the existing system architecture. Rather than attempting to replace or modify the established components, we introduced an “AI Integration System” that acts as a bridge between the existing infrastructure and the AI-powered capabilities. This approach allowed us to maintain the integrity of the existing systems while simultaneously leveraging the benefits of AI. One of the key advantages of this integration strategy is the ability to leverage the wealth of data already available within the existing systems. By accessing and processing this data through the AI models, we were able to generate more informed and intelligent responses to user queries, providing valuable insights and recommendations tailored to the specific supply chain activities and scenarios. As we look towards the future, the importance of seamlessly integrating AI into existing business ecosystems will only continue to grow. With the rapid pace of technological advancements and the increasing demand for intelligent automation and decision support, organizations that embrace this approach will be better positioned to capitalize on the opportunities presented by AI while minimizing disruptions to their operations. It is my hope that through this simulated real-world example, you have gained a deeper understanding of the potential for AI integration and the various strategies and best practices that can be employed to achieve successful implementation. By embracing this approach, businesses can unlock the transformative power of AI while preserving the investments and institutional knowledge embedded in their existing systems.

#reddit#master#integration:

reddit

0

1

Horror_Brief5524•This week

Seeking Guidance to Transition from SRE to Quant Developer/HFT

Hey Reddit! Let me introduce myself: I’m a 2024 B.Tech (IT) graduate from a state-level college in India. Currently, I’m working as an SRE (Site Reliability Engineer) at one of the world’s largest custodian banks (not naming the company). I’ve been with the organization for about a year now, combining my internship and full-time role. During this time, I’ve developed a strong foundation in AI/ML and have primarily been working on projects to automate BAU (Business-As-Usual) activities using these technologies. Outside of work, I have a deep interest in trading and stock markets—something that runs in the family, as my father has been trading for over 40 years. My ultimate goal is to transition into the field of quantitative development or high-frequency trading (HFT) and work for top-tier firms like HRT, Optiver, or Tower Research. To make this dream a reality, I’ve started preparing in the following ways: Learning the basics of stock markets and financial instruments. Studying statistics and experimenting with different algorithms to analyze stocks (mainly on a fundamental level for now). Getting back to practicing DSA (Data Structures and Algorithms). I’ll admit I’m rusty here since I haven’t been consistent with it for a while. I’m aware that transitioning from SRE to Quant Developer/HFT is ambitious and might seem like a pipe dream, but it’s a challenge I’m willing to take on. I’d love to hear from people in the quant field or those who’ve made similar career transitions. What should I focus on? Any recommended resources, books, or courses? Are there any specific skill sets or certifications that could make me stand out? Any guidance, advice, or encouragement would mean a lot. Thank you!

#reddit#seeking#guidance

reddit

0

1

AniketWork•This week

How I Built an Agentic Marketing Campaign Strategist

Marketing at Scale: How One AI System Replaces Hundreds of Strategy Hours Article https://i.redd.it/uekqj3zmerme1.gif https://i.redd.it/30rk23zmerme1.gif https://preview.redd.it/fk1t53zmerme1.png?width=797&format=png&auto=webp&s=d07f473a9556fbd38885b3a2f862101d9b25424e https://preview.redd.it/n84113zmerme1.jpg?width=1914&format=pjpg&auto=webp&s=f42679269a1003e1c8d6501dd2d53e10db745bba https://preview.redd.it/l13ae3zmerme1.jpg?width=791&format=pjpg&auto=webp&s=ecab3c295c2a416bc0fed8c62fecbe3321e37093 TL;DR This article guides you through building an AI-powered marketing strategist using Python. It combines vector databases, language models, and PDF generation to create customized marketing strategies automatically. I’ll show you the complete system architecture, from storing marketing knowledge to generating professional strategy documents, with practical code examples you can implement today. Perfect for marketers and developers looking to leverage AI for business growth. Introduction Welcome to the exciting intersection of marketing and artificial intelligence! In today’s digital world, creating effective marketing campaigns requires deep expertise, market research, and creative thinking. But what if you could automate parts of this process? That’s exactly what I set out to build: an AI system that generates comprehensive marketing strategies tailored to specific products, audiences, and budgets. What’s This Article About? This article walks you through the creation of an AI-powered marketing strategist that combines the retrieval of relevant marketing knowledge with advanced language generation to produce detailed campaign strategies. The system I built uses Retrieval-Augmented Generation (RAG), which enhances AI outputs by grounding them in specific knowledge sources. Here’s how it works: You provide a simple campaign description (like “a new eco-friendly water bottle targeting millennials with a budget of $50,000”) The system searches a knowledge base of marketing principles and best practices It then uses a language model to craft a comprehensive strategy that includes campaign objectives, target audience analysis, channel selection, content ideas, budget allocation, and measurement KPIs Finally, it generates a professional PDF document with your complete marketing strategy The beauty of this approach is that it combines the creativity and adaptability of AI with established marketing frameworks, ensuring the strategies are both innovative and grounded in proven principles. Why Read It? AI is rapidly transforming how businesses operate, and marketing is at the forefront of this revolution. According to recent studies, companies that effectively leverage AI in their marketing efforts see significant improvements in customer engagement, conversion rates, and ROI. Even if you’re not building a system for a real company right now, understanding how to implement AI in marketing processes gives you valuable skills and insights. This article provides a practical example of how AI can: Save marketers countless hours of research and strategy development Ensure consistency in marketing approaches across different campaigns Generate creative ideas that might not have been considered otherwise Scale marketing expertise across an organization By following along, you’ll gain hands-on experience with technologies like vector databases, language models, and automated document generation — all skills that are increasingly valuable in today’s business environment.

#reddit#built#agentic

reddit

0

1

Brilliant_Fishing110•This week

Randomly asked ChatGPT and Claude for a 4 year roadmap for an ML Engineer

Title, Is it actually a good plan ?? If no, why not ?? \\🚀 4-Year Roadmap to Becoming a High-Earning ML Engineer & Entrepreneur\\ \\(With Smartwork & Realistic 60-70% Execution Feasibility)\\ \\🟢 Year 1: Strong Foundation & Initial Projects (0-12 Months)\\ 🎯 \\Goal: Master Python & ML Fundamentals\\ \\🔹 1-4 Months (Python & Math Strengthening)\\ ✅ Python Mastery \- Daily LeetCode Easy problems (minimum 2) \- Build automation projects \- NumPy & Pandas mastery \- DSA fundamentals ✅ Mathematics Foundation \- Linear Algebra basics \- Statistics fundamentals \- Basic calculus concepts ✅ First Mini-Hackathon Participation \- Join beginner-friendly hackathons \- Focus on Python-based challenges \- Team up with other beginners 💡 \\Smart Move:\\ \- Join Discord/Slack hackathon communities \- Practice collaborative coding \- Build network with fellow participants \\🔹 5-8 Months (ML Foundations)\\ ✅ Machine Learning Basics \- Supervised Learning \- Model evaluation \- Feature engineering \- scikit-learn projects ✅ Participate in 2-3 ML Hackathons \- Kaggle Getting Started competitions \- Local ML hackathons \- University hackathons ✅ Start LinkedIn & GitHub Portfolio 💡 \\Smart Move:\\ \- Document hackathon experiences \- Share learnings on LinkedIn \- Focus on completion over winning \\🔹 9-12 Months (Deep Learning Introduction)\\ ✅ Basic Deep Learning \- Neural network fundamentals \- PyTorch basics \- Computer vision tasks \- Basic NLP ✅ Advanced Hackathon Participation \- AI/ML specific hackathons \- Team lead in 1-2 hackathons \- Start mentoring beginners \\🔵 Year 1 Expected Outcome (60-70% Execution)\\ ✔ \\Strong Python & ML foundations\\ ✔ \\5-6 hackathon participations\\ ✔ \\Active GitHub (100+ commits)\\ ✔ \\Growing LinkedIn (300+ connections)\\ 💰 \\Earning Expectation → ₹8K-₹20K per month (Projects/Internship)\\ \\🟢 Year 2: Professional Growth & Specialization (12-24 Months)\\ 🎯 \\Goal: Build Professional Experience & Recognition\\ \\🔹 1-6 Months (Technical Depth)\\ ✅ Advanced ML Topics \- Deep Learning architectures \- Computer Vision OR NLP \- MLOps basics (Docker, FastAPI) \- Cloud fundamentals (AWS/GCP) ✅ Hackathon Achievements \- Win minor prizes in 2-3 hackathons \- Lead teams in major hackathons \- Network with sponsors ✅ Start Technical Blogging 💡 \\Smart Move:\\ \- Focus on hackathon projects that align with career goals \- Build relationships with companies at hackathons \- Create detailed project documentation \\🔹 7-12 Months (Professional Experience)\\ ✅ Secure ML Role/Internship ✅ Advanced Project Building ✅ Open Source Contributions ✅ Organize Small Hackathons 💡 \\Smart Move:\\ \- Use hackathon network for job referrals \- Convert hackathon projects into full products \- Build mentor reputation \\🔵 Year 2 Expected Outcome (60-70% Execution)\\ ✔ \\Professional ML experience\\ ✔ \\10+ hackathon participations\\ ✔ \\1-2 hackathon wins\\ ✔ \\Strong industry network\\ 💰 \\Earning Expectation → ₹40K-₹70K per month (Job/Freelancing)\\ \\🟢 Year 3: Scaling & Business Foundation (24-36 Months)\\ 🎯 \\Goal: Establish Multiple Income Streams\\ \\🔹 1-4 Months (Expertise Building)\\ ✅ Choose Specialization \- MLOps \- Computer Vision \- NLP/LLMs \- Generative AI ✅ Advanced Competitions \- International hackathons \- High-prize competitions \- Corporate ML challenges ✅ Start Consulting Services 💡 \\Smart Move:\\ \- Use hackathon wins for marketing \- Build service packages around expertise \- Network with corporate sponsors \\🔹 5-8 Months (Business Development)\\ ✅ Scale Services ✅ Build Client Network ✅ Create Training Programs ✅ Hackathon Mentorship Program 💡 \\Smart Move:\\ \- Convert hackathon projects to products \- Use event networks for client acquisition \- Build authority through speaking \\🔹 9-12 Months (Growth & Innovation)\\ ✅ Product Development ✅ Team Building ✅ Innovation Focus ✅ Hackathon Organization \\🔵 Year 3 Expected Outcome (60-70% Execution)\\ ✔ \\Established ML business/career\\ ✔ \\Known in hackathon community\\ ✔ \\Multiple income streams\\ ✔ \\Strong industry presence\\ 💰 \\Earning Expectation → ₹1L-₹2L per month (Multiple Streams)\\ \\🟢 Year 4: Scale & Leadership (36-48 Months)\\ 🎯 \\Goal: Build AI Company & Achieve Financial Freedom\\ \\🔹 1-4 Months (Business Scaling)\\ ✅ Company Formation \- AI consulting firm \- Product development \- Training programs ✅ Hackathon Innovation \- Launch own hackathon series \- Corporate partnerships \- Prize sponsorships ✅ Team Expansion 💡 \\Smart Move:\\ \- Use hackathon network for hiring \- Create unique event formats \- Build corporate relationships \\🔹 5-8 Months (Market Leadership)\\ ✅ Product Launch ✅ Service Expansion ✅ International Presence ✅ Innovation Hub Creation 💡 \\Smart Move:\\ \- Create hackathon-to-hiring pipeline \- Build educational programs \- Establish thought leadership \\🔹 9-12 Months (Empire Building)\\ ✅ Multiple Revenue Streams \- AI products \- Consulting services \- Educational programs \- Event organization \- Investment returns ✅ Industry Leadership \- Conference speaking \- Published content \- Community leadership \\🔵 Year 4 Expected Outcome (60-70% Execution)\\ ✔ \\Established AI company\\ ✔ \\Major hackathon organizer\\ ✔ \\Multiple product lines\\ ✔ \\Industry authority status\\ 💰 \\Earning Expectation → ₹3L-₹5L+ per month (Business Income)\\ \\📊 FINAL RATING\\ ✅ \\Comprehensive growth plan\\ ✅ \\Strong community focus\\ ✅ \\Multiple income pathways\\ 💡 \\If 100% Execution → 8.5/10 Feasibility\\ 💡 \\If 50% Execution → 6/10 Feasibility\\ 🔥 \\Conclusion: A balanced path to ML mastery and entrepreneurship, built through consistent growth and community engagement!\\ 🚀 \\Key Success Factors:\\ Regular hackathon participation Strong community involvement Consistent skill development Strategic network building Focus on both technical and business growth

#reddit#randomly#asked

reddit

0

0.333

Starxel•This week

Is it too late for me to do a PhD in the US?

In 2019 I started an integrated Masters of Physics at Oxford. Graduated summer of 2023. During that time I first authored an AI research paper with the Oxford AI Society. We tried to get it into ICLR but it got rejected. Managed to get it into a NeurIPS workshop though, however I'm unsure if that holds much weight. The paper also got 21 citations on arxiv which is nice. After graduating, my gf and I broke up (mutually, long distance was too much) and life after university made me quite down. Bad market and struggled to get a job. A friend reached out to me about doing a startup in San Francisco. Did that startup until January 2024 when I quit because I had no money left. Through the connections I made out there I landed a gig at Chroma DB. Did a research contract with them. We didn't make a paper but instead made a technical report. The GitHub repo for the project has gained over 200 stars. However, since I was remote and US visas are a pain, my contract wasn't renewed. I tried starting my own business from July 2024 till December. I managed to secure a long term contract with a US construction company building them software that automates admin via GPT. Still doing this contract now and they've said they're happy to keep me for as long as I want. That's the context. During the winter of 2024 I thought heavily about applying for a PhD in the US. At: CMU, Stanford, Berkeley, MIT, CalTech, etc. However, I knew my profile wasn't strong enough. So I want to apply the winter of 2025. I'm in talks with a few institutions and research groups about doing projects. But is it possible that, starting in February 2025, I can co-author, submit and have accepted a paper into a top conference by December 2025? I feel like I'm too late to this decision and should have skipped that San Francisco startup to just do research projects from the start.

#reddit#late

reddit

0

1

Any-Reserve-4403•This week

How I landed an internship in AI

For motivational purposes only! I see a lot of posts on here from people without “traditional” machine learning, data science, etc.. backgrounds asking how they can break into the field, so I wanted to share my experience. EDIT Learning Resources and Side Project Ideas * My background: I graduated from a decent undergraduate school with a degree in Political Science several years ago. Following school I worked in both a client services role at a market research company and an account management role at a pretty notable fintech start-up. Both of these roles exposed me to ML, AI and more sophisticated software concepts in general, and I didn’t really care for the sales side of things, so I decided to make an attempt at switching careers into something more technical. While working full time I began taking night classes at a local community college, starting with pre calculus all the way up to Calc 2 and eventually more advanced classes like linear algebra and applied probability. I also took some programming courses including DSA. I took these classes for about two years while working, and on the side had been working through various ML books and videos on YouTube. What worked the best for me was Hands-on Machine Learning with Scikit Learn, Keara’s and Tensorflow. I eventually had enough credits where I was able to begin applying to MS in Data Science programs and was fortunate enough to get accepted into one and also get a position in their Robotics Lab doing Computer Vision work. When it came time to apply for internships, it was a BLOODBATH. I must have applied to over 100 roles with my only responses being video interviews and OA’s. Finally I got an interview for an AI Model Validation internship with a large insurance company and after completing the interviews was told I performed well but they were still interviewing several candidates. I ended up getting the offer and accepting the role where I’ll be working on a Computer Vision model and some LLM related tasks this summer and could not be more fortunate / excited. A couple things stood out to them during the interview process. 1, the fact that I was working and taking night classes with the intent to break into the field. It showed a genuine passion as opposed to someone who watched a YouTube video and claims they are now an expert. 2, side projects. I not only had several projects, but I had some that were relevant to the work I’d be doing this summer from the computer vision standpoint. 3, business sense. I emphasized during my interviews how working in a business role prior to beginning my masters would give me a leg up as intern because I would be able to apply the work of a data scientist to solving actual business challenges. For those of you trying to break into the field, keep pushing, keep building, and focus on what makes you unique and able to help a company! Please feel free to contact me if you would like any tips I can share, examples of projects, or anything that would be helpful to your journey.

#reddit#landed#internship

reddit

0

0

lila828•This week

What AI models can I build to automate processes in the architecture field?

An architecture company that builds hospitals, villas, and towers. They want to integrate AI/ML into their workflow to automate processes and improve efficiency they don't have a specific area to automate but they want to follow the wave and add ai.I’m looking for suggestions on AI models/ agents or tools that can help automate the processes: What AI/ML models would you recommend ? Are there any existing tools or frameworks ( generative 3d design from 2d, 3d rendring, NLP, predictive analytics) that I should explore? Do you have examples of how AI has been successfully applied in architecture or construction? Any advice, resources, or examples would be greatly appreciated! Thanks in advance!

#reddit#models#build

reddit

0

1

BrightCook5861•This week

I created leadsnavi that helps small businesses find quality leads without breaking the bank

Hey Redditors, I’m excited to share LeadsNavi, a tool I built specifically to help small businesses and B2B professionals automatically generate leads and reach potential customers in a smarter way. After talking to a lot of small business owners, I realized how tough it is to juggle lead generation with limited resources. So, I decided to create a tool that could simplify the process and make it more accessible to those who don’t have the budget to invest in expensive solutions. What Exactly Is LeadsNavi? LeadsNavi is an intuitive, cost-effective platform that automates the process of lead generation. It's designed to make it easy for small businesses and entrepreneurs to identify quality leads and grow their customer base without the need for manual prospecting. Here’s what makes it stand out: Automatic Lead Tracking: Tracks visitors to your website and matches them with company data, so you get real insights into who’s interested in your business. AI-Powered Lead Recommendations: Based on your website’s traffic, LeadsNavi uses AI to suggest similar companies that could be interested in your product or service, helping you find new leads faster and more accurately. Affordable & Scalable: For only $49/month, you can use a highly effective tool that scales with your business. It’s designed to be affordable even for small businesses. CRM Integration: Connect your CRM to directly import leads and sync your outreach efforts. How Does It Work? LeadsNavi uses advanced algorithms to track website visitors' IP addresses and match them with a comprehensive business database. It provides details like company names, contact information, and helps you identify potential leads for follow-up. The best part? It works automatically, saving you hours of manual work and effort. Lead Identification: Get insights into which companies are visiting your website. AI-Driven Lead Recommendations: The AI analyzes your site’s traffic and suggests other companies in the same industry or with similar needs that might be a great fit for your product or service. Data-Enriched Leads: Gather real-time, actionable data on these leads to make your outreach more targeted. Easy Setup: Simply integrate with your website and CRM to start getting quality leads in minutes. Who’s It For? Small Businesses: You don’t have to be a marketing expert to generate quality leads. B2B Sales Teams: Perfect for anyone looking to target other businesses with a streamlined and automated approach. Entrepreneurs & Startups: Focus on scaling your business without worrying about lead generation overhead. Why Try It? LeadsNavi gives you the power to focus on what really matters—connecting with potential customers and scaling your business. If you’ve been struggling with finding quality leads, or if you’re just getting started, I believe LeadsNavi can help you save time, effort, and money. I’m offering a 14-day free trial, so you can see the tool in action before committing to anything. Give it a try and let me know what you think! I’d love to hear your thoughts, suggestions, and how it works for your business. https://preview.redd.it/fdwil4rssgle1.png?width=1867&format=png&auto=webp&s=eb73b41a2b7665ae1b651fe2a6b7459df6990530

#reddit#created#leadsnavi

reddit

0

0.6

varturas•This week

Compare trading strategies on the fly - pnl.ai - please check it out

Part of my covid project and part of my long obsession with prediction markets, I have created a web page that displays and allows to compare best and worst performing trading strategies. TL;DR: best stocks + best strategies -> the list of top and bottom performing trading algorithms.  Product Typically, trading newsletters and stock-scanners display only price return for top market gainers and losers. I have forever been interested in inspecting top and bottom performing trading strategies for a given set of securities and could not find any websites that do that. So, I decided to create a tool of my own. I wanted the tool that would help me to answer questions like if there is a better strategy than buy and hold, should I follow greed and fear indicator of the market or do the opposite. Top and bottom performing securities do not tell you if a stock is going to go up or down, but they do alert you to rapidly changing market conditions, such as change in the competitive landscape, impending lawsuits, changes in the company's management and, at the very least, the stocks you should avoid in your programmatic trading. Top strategies do all that, but they can also alert you to a change in the market regime. For example, MACD strategy, which is a variant of oscillator strategy, executed on Citibank stock returned 20% in the first half of 2020. In the same time period, the Citibank stock went down and "BuyAndHold" strategy, which is pretty much what it sounds, lost 45%. Now, compare that to the end of 2020 through spring of 2021, when MACD lost 1% and "BuyAndHold" gained 70%. This happened due to the change in the market due to the rally in financial stocks at the end of 2020. The market player who detect change in the market conditions first will reap most benefits. Another example, TSLA since the beginning of 2021 until end of April lost 7%. The StopLoss strategy sells the position after abrupt price drop and waits until the price returns to the level before the drop. For the same time interval the StopLoss strategy gained 10%. In this particular example, StopLoss outperformed BuyAndHold. To me personally, the most important feature is the ability to quickly tweak and modify trading strategies and observe change in their performance. You can change strategies parameters on the fly and even design your own custom trading strategy. In the end, I developed a tool I can use for myself but hope other investors who are experimenting with trading algorithms will find it useful as well. I called it "Profit and Loss AI", or PnL.ai for short. PnL.ai Description The web-tool in the link below allows you to customize parameters of existing strategies and essentially create your own strategy and seeing how it will compare to the set of original strategies. http://ec2-54-185-19-38.us-west-2.compute.amazonaws.com:5006/srv In the section above you can specify security and data range. In the section below you can choose strategy to customize and modify it's parameters. The strategy comparison table will automatically update and will display a newly created strategy side by side with the original strategies. Technology The tool is developed on bokeh and python and allows you to edit configuration parameters of each strategy all without programming knowledge. The strategies are fully specified via key/value pairs in the format of ini files used to initialize programs. The strategy classes are autogenerated by reading the ini config files dynamically using "factory" pattern. You can find a simplified code in this github repo: https://github.com/varturas/PnlAITk Next Steps In the future I want to give users ability to monitor their chosen strategy by receiving trading algo alerts whenever performance of their custom trading algo is changes significantly. I'm going to be adding more strategies, some of standard technical analysis variety and some will be more custom and more advanced. I'll also be adding more columns to the performance table to give better information. You can receive daily newsletter with the list of trading strategies generated by above-mentioned web-tool by registering on http://pnl.ai/ and checking subscribe checkmark.

#reddit#compare#trading

reddit

0

0.818

Michaelbetterecycle•This week

How me and my team made 15+ apps and not made a single sale in 2023

Hey, my name is Michael, I am in Auckland NZ. This year was the official beginning of my adult life. I graduated from university and started a full-time job. I’ve also really dug into indiehacking/bootstrapping and started 15 projects (and it will be at least 17 before the year ends). I think I’ve learned a lot but I consciously repeated mistakes. Upto (Nov) Discord Statuses + Your Location + Facebook Poke https://preview.redd.it/4nqt7tp2tf5c1.png?width=572&format=png&auto=webp&s=b0223484bc54b45b5c65e0b1afd0dc52f9c02ad1 This was the end of uni, I often messaged (and got messaged) requests of status and location to (and from my) friends. I thought, what if we make a social app that’s super basic and all it does is show you where your friends are? To differentiate from snap maps and others we wanted something with more privacy where you select the location. However, never finished the codebase or launched it. This is because I slowly started to realize that B2C (especially social networks) are way too hard to make into an actual business and the story with Fistbump would repeat itself. However, this decision not to launch it almost launched a curse on our team. From that point, we permitted ourselves to abandon projects even before launching. Lessons: Don’t do social networks if your goal is 10k MRR ASAP. If you build something to 90% competition ship it or you will think it’s okay to abandon projects Insight Bites (Nov) Youtube Summarizer Extension ​ https://preview.redd.it/h6drqej4tf5c1.jpg?width=800&format=pjpg&auto=webp&s=0f211456c390ac06f4fcb54aa51f9d50b0826658 Right after Upto, we started ideating and conveniently the biggest revolution in the recent history of tech was released → GPT. We instantly began ideating. The first problem we chose to use AI for is to summarize YouTube videos. Comical. Nevertheless, I am convinced we have had the best UX because you could right-click on a video to get a slideshow of insights instead of how everyone else did it. We dropped it because there was too much competition and unit economics didn’t work out (and it was a B2C). PodPigeon (Dec) Podcast → Tweet Threads https://preview.redd.it/0ukge245tf5c1.png?width=2498&format=png&auto=webp&s=23303e1cab330578a3d25cd688fa67aa3b97fb60 Then we thought, to make unit economics work we need to make this worthwhile for podcasters. This is when I got into Twitter and started seeing people summarize podcasts. Then I thought, what if we make something that converts a podcast into tweets? This was probably one of the most important projects because it connected me with Jason and Jonaed, both of whom I regularly stay in contact with and are my go-to experts on ideas related to content creation. Jonaed was even willing to buy Podpigeon and was using it on his own time. However, the unit economics still didn’t work out (and we got excited about other things). Furthermore, we got scared of the competition because I found 1 - 2 other people who did similar things poorly. This was probably the biggest mistake we’ve made. Very similar projects made 10k MRR and more, launching later than we did. We didn’t have a coherent product vision, we didn’t understand the customer well enough, and we had a bad outlook on competition and a myriad of other things. Lessons: I already made another post about the importance of outlook on competition. Do not quit just because there are competitors or just because you can’t be 10x better. Indiehackers and Bootstrappers (or even startups) need to differentiate in the market, which can be via product (UX/UI), distribution, or both. Asking Ace Intro.co + Crowdsharing ​ https://preview.redd.it/0hu2tt16tf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3d397568ef2331e78198d64fafc1a701a3e75999 As I got into Twitter, I wanted to chat with some people I saw there. However, they were really expensive. I thought, what if we made some kind of crowdfunding service for other entrepreneurs to get a private lecture from their idols? It seemed to make a lot of sense on paper. It was solving a problem (validated via the fact that Intro.co is a thing and making things cheaper and accessible is a solid ground to stand on), we understood the market (or so we thought), and it could monetize relatively quickly. However, after 1-2 posts on Reddit and Indiehackers, we quickly learned three things. Firstly, no one cares. Secondly, even if they do, they think they can get the same information for free online. Thirdly, the reasons before are bad because for the first point → we barely talked to people, and for the second people → we barely talked to the wrong people. However, at least we didn’t code anything this time and tried to validate via a landing page. Lessons Don’t give up after 1 Redditor says “I don’t need this” Don’t be scared to choose successful people as your audience. Clarito Journaling with AI analyzer https://preview.redd.it/8ria2wq6tf5c1.jpg?width=1108&format=pjpg&auto=webp&s=586ec28ae75003d9f71b4af2520b748d53dd2854 Clarito is a classic problem all amateur entrepreneurs have. It’s where you lie to yourself that you have a real problem and therefore is validated but when your team asks you how much you would pay you say I guess you will pay, maybe, like 5 bucks a month…? Turns out, you’d have to pay me to use our own product lol. We sent it off to a few friends and posted on some forums, but never really got anything tangible and decided to move away. Honestly, a lot of it is us in our own heads. We say the market is too saturated, it’ll be hard to monetize, it’s B2C, etc. Lessons: You use the Mom Test on other people. You have to do it yourself as well. However, recognizing that the Mom Test requires a lot of creativity in its investigation because knowing what questions to ask can determine the outcome of the validation. I asked myself “Do I journal” but I didn’t ask myself “How often do I want GPT to chyme in on my reflections”. Which was practically never. That being said I think with the right audience and distribution, this product can work. I just don’t know (let alone care) about the audience that much (and I thought I was one of them)/ Horns & Claw Scrapes financial news texts you whether you should buy/sell the stock (news sentiment analysis) ​ https://preview.redd.it/gvfxdgc7tf5c1.jpg?width=1287&format=pjpg&auto=webp&s=63977bbc33fe74147b1f72913cefee4a9ebec9c2 This one we didn’t even bother launching. Probably something internal in the team and also seemed too good to be true (because if this works, doesn’t that just make us ultra-rich fast?). I saw a similar tool making 10k MRR so I guess I was wrong. Lessons: This one was pretty much just us getting into our heads. I declared that without an audience it would be impossible to ship this product and we needed to start a YouTube channel. Lol, and we did. And we couldn’t even film for 1 minute. I made bold statements like “We will commit to this for at least 1 year no matter what”. Learnery Make courses about any subject https://preview.redd.it/1nw6z448tf5c1.jpg?width=1112&format=pjpg&auto=webp&s=f2c73e8af23b0a6c3747a81e785960d4004feb48 This is probably the most “successful” project we’ve made. It grew from a couple of dozen to a couple of hundred users. It has 11 buy events for $9.99 LTD (we couldn’t be bothered connecting Stripe because we thought no one would buy it anyway). However what got us discouraged from seriously pursuing it more is, that this has very low defensibility, “Why wouldn’t someone just use chatGPT?” and it’s B2C so it’s hard to monetize. I used it myself for a month or so but then stopped. I don’t think it’s the app, I think the act of learning a concept from scratch isn’t something you do constantly in the way Learnery delivers it (ie course). I saw a bunch of similar apps that look like Ass make like 10k MRR. Lessons: Don’t do B2C, or if you do, do it properly Don’t just Mixpanel the buy button, connect your Stripe otherwise, it doesn’t feel real and you won’t get momentum. I doubt anyone (even me) will make this mistake again. I live in my GPT bubble where I make assumptions that everyone uses GPT the same way and as much as I do. In reality, the argument that this has low defensibility against GPT is invalid. Platforms that deliver a differentiated UX from ChatGPT to audiences who are not tightly integrated into the habit of using ChatGPT (which is like - everyone except for SOME tech evangelists). CuriosityFM Make podcasts about any subject https://preview.redd.it/zmosrcp8tf5c1.jpg?width=638&format=pjpg&auto=webp&s=d04ddffabef9050050b0d87939273cc96a8637dc This was our attempt at making Learnery more unique and more differentiated from chatGPT. We never really launched it. The unit economics didn’t work out and it was actually pretty boring to listen to, I don’t think I even fully listened to one 15-minute episode. I think this wasn’t that bad, it taught us more about ElevenLabs and voice AI. It took us maybe only 2-3 days to build so I think building to learn a new groundbreaking technology is fine. SleepyTale Make children’s bedtime stories https://preview.redd.it/14ue9nm9tf5c1.jpg?width=807&format=pjpg&auto=webp&s=267e18ec6f9270e6d1d11564b38136fa524966a1 My 8-year-old sister gave me that idea. She was too scared of making tea and I was curious about how she’d react if she heard a bedtime story about that exact scenario with the moral that I wanted her to absorb (which is that you shouldn’t be scared to try new things ie stop asking me to make your tea and do it yourself, it’s not that hard. You could say I went full Goebbels on her). Zane messaged a bunch of parents on Facebook but no one really cared. We showed this to one Lady at the place we worked from at Uni and she was impressed and wanted to show it to her kids but we already turned off our ElevenLabs subscription. Lessons: However, the truth behind this is beyond just “you need to be able to distribute”. It’s that you have to care about the audience. I don’t particularly want to build products for kids and parents. I am far away from that audience because I am neither a kid anymore nor going to be a parent anytime soon, and my sister still asked me to make her tea so the story didn’t work. I think it’s important to ask yourself whether you care about the audience. The way you answer that even when you are in full bias mode is, do you engage with them? Are you interested in what’s happening in their communities? Are you friends with them? Etc. User Survey Analyzer Big User Survey → GPT → Insights Report Me and my coworker were chatting about AI when he asked me to help him analyze a massive survey for him. I thought that was some pretty decent validation. Someone in an actual company asking for help. Lessons Market research is important but moving fast is also important. Ie building momentum. Also don’t revolve around 1 user. This has been a problem in multiple projects. Finding as many users as possible in the beginning to talk to is key. Otherwise, you are just waiting for 1 person to get back to you. AutoI18N Automated Internationalization of the codebase for webapps This one I might still do. It’s hard to find a solid distribution strategy. However, the idea came from me having to do it at my day job. It seems a solid problem. I’d say it’s validated and has some good players already. The key will be differentiation via the simplicity of UX and distribution (which means a slightly different audience). In the backlog for now because I don’t care about the problem or the audience that much. Documate - Part 1 Converts complex PDFs into Excel https://preview.redd.it/8b45k9katf5c1.jpg?width=1344&format=pjpg&auto=webp&s=57324b8720eb22782e28794d2db674b073193995 My mom needed to convert a catalog of furniture into an inventory which took her 3 full days of data entry. I automated it for her and thought this could have a big impact but there was no distribution because there was no ICP. We tried to find the ideal customers by talking to a bunch of different demographics but I flew to Kazakhstan for a holiday and so this kind of fizzled out. I am not writing this blog post linearity, this is my 2nd hour and I am tired and don’t want to finish this later so I don’t even know what lessons I learned. Figmatic Marketplace of high-quality Figma mockups of real apps https://preview.redd.it/h13yv45btf5c1.jpg?width=873&format=pjpg&auto=webp&s=aaa2896aeac2f22e9b7d9eed98c28bb8a2d2cdf1 This was a collab between me and my friend Alex. It was the classic Clarito where we both thought we had this problem and would pay to fix it. In reality, this is a vitamin. Neither I, nor I doubt Alex have thought of this as soon as we bought the domain. We posted it on Gumroad, sent it to a bunch of forums, and called it a day. Same issue as almost all the other ones. No distribution strategy. However, apps like Mobin show us that this concept is indeed profitable but it takes time. It needs SEO. It needs a community. None of those things, me and Alex had or was interested in. However shortly after HTML → Figma came out and it’s the best plugin. Maybe that should’ve been the idea. Podcast → Course Turns Podcaster’s episodes into a course This one I got baited by Jason :P I described to him the idea of repurposing his content for a course. He told me this was epic and he would pay. Then after I sent him the demo, he never checked it out. Anyhow during the development, we realized that doesn’t actually work because A podcast doesn’t have the correct format for the course, the most you can extract are concepts and ideas, seldom explanations. Most creators want video-based courses to be hosted on Kajabi or Udemy Another lesson is that when you pitch something to a user, what you articulate is a platform or a process, they imagine an outcome. However, the end result of your platform can be a very different outcome to what they had in mind and there is even a chance that what they want is not possible. You need to understand really well what the outcome looks like before you design the process. This is a classic problem where we thought of the solution before the problem. Yes, the problem exists. Podcasters want to make courses. However, if you really understand what they want, you can see how repurposing a podcast isn’t the best way to get there. However I only really spoke to 1-2 podcasters about this so making conclusions is dangerous for this can just be another asking ace mistake with the Redditor. Documate Part 2 Same concept as before but now I want to run some ads. We’ll see what happens. https://preview.redd.it/xb3npj0ctf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3cd4884a29fd11d870d010a2677b585551c49193 In conclusion https://preview.redd.it/2zrldc9dtf5c1.jpg?width=1840&format=pjpg&auto=webp&s=2b3105073e752ad41c23f205dbd1ea046c1da7ff It doesn’t actually matter that much whether you choose to do a B2C, or a social network or focus on growing your audience. All of these can make you successful. What’s important is that you choose. If I had to summarize my 2023 in one word it’s indecision. Most of these projects succeeded for other people, nothing was as fundamentally wrong about them as I proclaimed. In reality that itself was an excuse. New ideas seduce, and it is a form of discipline to commit to a single project for a respectful amount of time. https://preview.redd.it/zy9a2vzdtf5c1.jpg?width=1456&format=pjpg&auto=webp&s=901c621227bba0feb4efdb39142f66ab2ebb86fe Distribution is not just posting on Indiehackers and Reddit. It’s an actual strategy and you should think of it as soon as you think of the idea, even before the Figma designs. I like how Denis Shatalin taught me. You have to build a pipeline. That means a reliable way to get leads, launch campaigns at them, close deals, learn from them, and optimize. Whenever I get an idea now I always try to ask myself “Where can I find 1000s leads in one day?” If there is no good answer, this is not a good project to do now. ​ https://preview.redd.it/2boh3fpetf5c1.jpg?width=1456&format=pjpg&auto=webp&s=1c0d5d7b000716fcbbb00cbad495e8b61e25be66 Talk to users before doing anything. Jumping on designing and coding to make your idea a reality is a satisfying activity in the short term. Especially for me, I like to create for the sake of creation. However, it is so important to understand the market, understand the audience, understand the distribution. There are a lot of things to understand before coding. https://preview.redd.it/lv8tt96ftf5c1.jpg?width=1456&format=pjpg&auto=webp&s=6c8735aa6ad795f216ff9ddfa2341712e8277724 Get out of your own head. The real reason we dropped so many projects is that we got into our own heads. We let the negative thoughts creep in and kill all the optimism. I am really good at coming up with excuses to start a project. However, I am equally as good at coming up with reasons to kill a project. And so you have this yin and yang of starting and stopping. Building momentum and not burning out. I can say with certainty my team ran out of juice this year. We lost momentum so many times we got burnt out towards the end. Realizing that the project itself has momentum is important. User feedback and sales bring momentum. Building also creates momentum but unless it is matched with an equal force of impact, it can stomp the project down. That is why so many of our projects died quickly after we launched. The smarter approach is to do things that have a low investment of momentum (like talking to users) but result in high impact (sales or feedback). Yes, that means the project can get invalidated which makes it more short-lived than if we built it first, but it preserves team life energy. At the end of 2023 here is a single sentence I am making about how I think one becomes a successful indiehacker. One becomes a successful Indiehacker when one starts to solve pain-killer problems in the market they understand, for an audience they care about and consistently engage with for a long enough timeframe. Therefore an unsuccessful Indiehacker in a single sentence is An unsuccessful Indiehacker constantly enters new markets they don’t understand to build solutions for people whose problems they don’t care about, in a timeframe that is shorter than than the time they spent thinking about distribution. However, an important note to be made. Life is not just about indiehacking. It’s about learning and having fun. In the human world, the best journey isn’t the one that gets you the fastest to your goals but the one you enjoy the most. I enjoyed making those silly little projects and although I do not regret them, I will not repeat the same mistakes in 2024. But while it’s still 2023, I have 2 more projects I want to do :) EDIT: For Devs, frontend is always react with vite (ts) and backend is either node with express (ts) or python. For DB either Postgres or mongo (usually Prisma for ORM). For deployment all of it is on AWS (S3, EC2). In terms of libraries/APIs Whisper.cpp is best open source for transcription Obviously the gpt apis Eleven labs for voice related stuff And other random stuff here and there

#reddit#team#made

reddit

0

1

inputorigin•This week

I retired at 32 from my side project. Here's the path I took.

EDIT 2: Thanks for the award kind stranger! I've stopped responding to reddit comments for this post. I'm adding an FAQ to the original post based on the most common high quality questions. If you have a question that you're dying to know the answer to and that only I can help you with (vs. Google, ChatGPT, etc.), DM me. EDIT: I love how controversial this post has become (50% upvote rate), and only in this subreddit (vs. other subreddits that I posted the same content in). I trust that the open-minded half of you will find something useful in this post and my other posts and comments. I retired at 32 years old, in large part thanks to a B2C SaaS app that I developed on my own. Now, I don't have to work in order to cover my living expenses, and wouldn't have to work for quite a while. In other words, I can finally sip mai tais at the beach. I've condensed how I got there into this post. First, a super simplified timeline of events, followed by some critical details. Timeline 2013 Graduated college in the US 2013 Started first corporate job 2013 Started side project (B2C app) that would eventually lead to my retirement 2020 Started charging for use of my B2C app (was free, became freemium) 2021 Quit my last corporate job 2022 Retired: time freedom attained Details First, some summary statistics of my path to retirement: 9 years: time between graduating college and my retirement. 8 years: total length of my career where I worked at some corporate day job. 7 years: time it took my B2C app to make its first revenue dollar 2 years: time between my first dollar of SaaS revenue and my retirement. "Something something overnight success a decade in the making". I got extremely lucky on my path to retirement, both in terms of the business environment I was in and who I am as a person. I'd also like to think that some of the conscious decisions I made along the way contributed to my early retirement. Lucky Breaks Was born in the US middle class. Had a natural affinity for computer programming and entrepreneurial mindset (initiative, resourcefulness, pragmatism, courage, growth mindset). Had opportunities to develop these mindsets throughout life. Got into a good college which gave me the credentials to get high paying corporate jobs. Was early to a platform that saw large adoption (see "barnacle on whale" strategy). Business niche is shareworthy: my SaaS received free media. Business niche is relatively stable, and small enough to not be competitive. "Skillful" Decisions I decided to spend the nights and weekends of my early career working on side projects in the hopes that one would hit. I also worked a day job to support myself and build my savings. My launch funnel over roughly 7 years of working on side projects: Countless side projects prototyped. 5 side projects publically launched. 2 side projects made > $0. 1 side project ended up becoming the SaaS that would help me retire. At my corporate day jobs, I optimized for learning and work-life balance. My learning usually stalled after a year or two at one company, so I’d quit and find another job. I invested (and continute to do so) in physical and mental wellbeing via regular workouts, meditation, journaling, traveling, and good food. My fulfilling non-work-life re-energized me for my work-life, and my work-life supported my non-work-life: a virtuous cycle. I automated the most time-consuming aspects of my business (outside of product development). Nowadays, I take long vacations and work at most 20 hours a week / a three-day work week . I decided to keep my business entirely owned and operated by me. It's the best fit for my work-style (high autonomy, deep focus, fast decision-making) and need to have full creative freedom and control. I dated and married a very supportive and inspiring partner. I try not to succumb to outrageous lifestyle creep, which keeps my living expenses low and drastically extends my burn-rate. Prescription To share some aphorisms I’ve leaned with the wantrepreneurs or those who want to follow a similar path: Maximize your at bats, because you only need one hit. Bias towards action. Launch quickly. Get your ideas out into the real world for feedback. Perfect is the enemy of good. If you keep swinging and improving, you'll hit the ball eventually. Keep the big picture in mind. You don't necessarily need a home-run to be happy: a base hit will often do the job. Think about what matters most to you in life: is it a lot of money or status? Or is it something more satisfying, and often just as if not more attainable, like freedom, loving relationships, or fulfillment? Is what you’re doing now a good way to get what you want? Or is there a better way? At more of a micro-level of "keep the big picture in mind", I often see talented wantrepreneurs get stuck in the weeds of lower-level optimizations, usually around technical design choices. They forget (or maybe subconsciously avoid) the higher-level and more important questions of customer development, user experience, and distribution. For example: “Are you solving a real problem?” or “Did you launch an MVP and what did your users think?” Adopt a growth mindset. Believe that you are capable of learning whatever you need to learn in order to do what you want to do. The pain of regret is worse than the pain of failure. I’ve noticed that fear of failure is the greatest thing holding people back from taking action towards their dreams. Unless failure means death in your case, a debilitating fear of failure is a surmountable mental block. You miss 100% of the shots you don't take. When all is said and done, we often regret the things we didn't do in life than the things we did. There’s more to life than just work. Blasphemous (at least among my social circle)! But the reality is that many of the dying regret having worked too much in their lives. As Miss Frizzle from The Magic Schoolbus says: "Take chances, make mistakes, get messy!" Original post

#reddit#retired#side

reddit

0

0

vsengar•This week

Introducing Stratify: Your Ultimate AI Strategy Builder for Business Success

Hello, I’m thrilled to announce the launch of my new startup, Stratify! 🔍 What is Stratify? Stratify is an AI Strategy Builder designed to help businesses of all sizes develop, implement, and optimize their strategic plans using cutting-edge artificial intelligence. Whether you're a startup looking to scale or an established company aiming to innovate, Stratify provides the tools and insights you need to stay ahead in today's competitive landscape. 🌟 Key Features: Automated Strategy Development: Leverage AI to analyze market trends, competitor data, and internal metrics to create comprehensive strategic plans tailored to your business goals. Real-Time Analytics & Insights: Monitor your strategy's performance with real-time data dashboards, enabling you to make informed decisions quickly. Scenario Planning: Use AI-driven simulations to forecast different business scenarios and understand potential outcomes, helping you prepare for uncertainties. Collaborative Tools: Facilitate team collaboration with integrated communication features, ensuring everyone is aligned and contributing to the strategy development process. Customizable Templates: Access a library of industry-specific strategy templates that can be customized to fit your unique business needs. 💡 Why Stratify? In today's fast-paced business environment, creating and adapting effective strategies can be challenging. Many companies struggle with data overload, lack of actionable insights, and inefficient planning processes. Stratify addresses these pain points by harnessing the power of AI to streamline strategy building, making it more efficient, data-driven, and adaptable. 🚀 Our Journey So Far: Founded: August 2024 Milestones Achieved: Developed and tested our MVP with a select group of beta users What's Next: Launching our public beta in Q4 2024 Expanding our feature set based on user feedback Growing our team with experts in AI, business strategy, and customer success 🤝 How You Can Help: We’re eager to connect with early adopters, business strategists, and industry experts who can benefit from or contribute to Stratify. Here’s how you can get involved: Join Our Beta Program: Be among the first to experience Stratify and provide valuable feedback. Share Your Insights: Help us refine our features by sharing your business strategy challenges and needs. Spread the Word: If you know someone who could benefit from an AI-driven strategy builder, please share our mission and be an affiliate to earn rewards! 🌐 Learn More: Visit our website at AI-Powered Brand Strategy & Content Creation | Stratify (brandprovoke.com) and follow us for the latest updates and insights. 🙏 Thank You! A heartfelt thank you to the Reddit community for your support and encouragement. We’re excited to embark on this journey and look forward to your feedback and suggestions! Looking forward to your thoughts and questions!

#reddit#introducing#stratify:

reddit

0

1

tilopedia•This week

My Side Projects: From CEO to 4th Developer (Thanks, AI 🤖)

Hey Reddit 👋, I wanted to share a bit about some side projects I’ve been working on lately. Quick background for context: I’m the CEO of a mid-to-large-scale eCommerce company pulling in €10M+ annually in net turnover. We even built our own internal tracking software that’s now a SaaS (in early review stages on Shopify), competing with platforms like Lifetimely and TrueROAS. But! That’s not really the point of this post — there’s another journey I’ve been on that I’m super excited to share (and maybe get your feedback on!). AI Transformed My Role (and My Ideas List) I’m not a developer by trade — never properly learned how to code, and to be honest, I don’t intend to. But, I’ve always been the kind of guy who jots down ideas in a notes app and dreams about execution. My dev team calls me their “4th developer” (they’re a team of three) because I have solid theoretical knowledge and can kinda read code. And then AI happened. 🛠️ It basically turned my random ideas app into an MVP generation machine. I thought it’d be fun to share one of the apps I’m especially proud of. I am also planning to build this in public and therefore I am planning to post my progress on X and every project will have /stats page where live stats of the app will be available. Tackling My Task Management Problem 🚀 I’ve sucked at task management for YEARS, I still do! I’ve tried literally everything — Sheets, Todoist, Asana, ClickUp, Notion — you name it. I’d start… and then quit after a few weeks - always. What I struggle with the most is delegating tasks. As a CEO, I delegate a ton, and it’s super hard to track everything I’ve handed off to the team. Take this example: A few days ago, I emailed an employee about checking potential collaboration opportunities with a courier company. Just one of 10s of tasks like this I delegate daily. Suddenly, I thought: “Wouldn’t it be AMAZING if just typing out this email automatically created a task for me to track?” 💡 So… I jumped in. With the power of AI and a few intense days of work, I built a task manager that does just that. But of course, I couldn’t stop there. Research & Leveling It Up 📈 I looked at similar tools like TickTick and Todoist, scraped their G2 reviews (totally legally, promise! 😅), and ran them through AI for a deep SWOT analysis. I wanted to understand what their users liked/didn’t like and what gaps my app could fill. Some of the features people said they were missing didn’t align with the vision for my app (keeping it simple and personal), but I found some gold nuggets: Integration with calendars (Google) Reminders Customizable UX (themes) So, I started implementing what made sense and am keeping others on the roadmap for the future. And I’ve even built for that to, it still doesn’t have a name, however the point is you select on how many reviews of a specific app you want to make a SWOT analysis on and it will do it for you. Example for Todoist in comments. But more on that, some other time, maybe other post ... Key Features So Far: Here’s what’s live right now: ✅ Email to Task: Add an email as to, cc, or bcc — and it automatically creates a task with context, due dates, labels, etc. ✅ WhatsApp Reminders: Get nudged to handle your tasks via WhatsApp. ✅ WhatsApp to Task: Send a message like /task buy groceries — bam, it’s added with full context etc.. ✅ Chrome Extension (work-in-progress): Highlight text on any page, right-click, and send it straight to your task list. Next Steps: Build WITH the Community 👥 Right now, the app is 100% free while still in the early stages. But hey, API calls and server costs aren’t cheap, so pricing is something I’ll figure out with you as we grow. For now, my goal is to hit 100 users and iterate from there. My first pricing idea is, without monthly subscription, I don’t want to charge someone for something he didn’t use. So I am planning on charging "per task", what do you think? Here’s what I have planned: 📍 End of Year Goal: 100 users (starting from… 1 🥲). 💸 Revenue Roadmap: When we establish pricing, we’ll talk about that. 🛠️ Milestones: Post on Product Hunt when we hit 100 users. Clean up my self-written spaghetti code (hire a pro dev for review 🙃). Hire a part-time dev once we hit MRR that can cover its costs. You can check how are we doing on thisisatask.me/stats Other Side Projects I’m Working On: Because… what’s life without taking on too much, right? 😂 Full list of things I’m building: Internal HRM: Not public, tried and tested in-house. Android TV App: Syncs with HRM to post announcements to office TVs (streamlined and simple). Stats Tracker App: Connects to our internal software and gives me real-time company insights. Review Analyzer: Scrapes SaaS reviews (e.g., G2) and runs deep analysis via AI. This was originally for my Shopify SaaS but is quickly turning into something standalone. Coming soon! Mobile app game: secret for now. Let’s Build This Together! Would love it if you guys checked out https://thisisatask.me and gave it a spin! Still super early, super raw, but I’m pumped to hear your thoughts. Also, what’s a must-have task manager feature for you? Anything that frustrates you with current tools? I want to keep evolving this in public, so your feedback is gold. 🌟 Let me know, Reddit! Are you with me? 🙌

#reddit#side#projects:

reddit

0

1

nervousslinky•This week

Introducing Vest: Your AI-Powered Due Diligence Partner - Looking for feedback!

TLDR; We are introducing Vest, an AI powered due-diligence and stock recommendation platform. We have bootstrapped ourselves so far and are wanting to get as much feedback from Reddit as we can to see where we can improve, but also what we are doing right. So please have a look around, give us feedback and if you like it, feel free to use it. Hi Reddit, My name is Drian and I'm one of the founders of Vest. We believe we are crafting something special at Vest and we want to get the word out and gather as much feedback as possible! Our major goal at Vest is to help new retail investors make sense of the investment landscape and get AI powered assistance, or even help experienced investors get confirmation of their potential moves. Overall, we want people to start their journey to financial freedom and not be daunted by the complexity of it. So how do we do this? Vest is a user-friendly service that harnesses fundamental metrics, social and news sentiment, and technical analysis, that we feed into some advanced AI models to generate clear buy, sell, or hold signals for US-based (for now!) stocks, offering our users transparent due-diligence for confident investing. The service is currently free with no ads - however, at some point we do plan on adding a paid tier. What's included: ​ Financial Metrics. Our financial metrics take all the potentially complex mathematical equations and present the fundamentals of a company to users in a simple 1 pager, with a score displaying if the metric is positive for a stock. We also provide publicly available analyst ratings from investment banks as well as price targets they have set. News Sentiment. We take publications about a specific stock from new articles, journals and socials and give these all a rating to determine if social sentiment is positive around a stock or not. Each article and its rating is visible to our users through through our dashboard. AI assisted Stock Signals. We have developed an algorithm to take all the metrics, sentiment and technical analysis we collate and analyze this with historic performance data for every stock to attempt to figure out if a stock is undervalued (great time to buy) or overvalued (great time to sell). 155 US stock tickers and counting. We currently have trained our models for around 155 US based stocks on the NASDAQ and NYSE exchanges. As we get more funding/runway we do plan on adding more, with the eventual goal to expand to more exchanges, countries and securities. Knowledge base and community. Our knowledge base & community contains explanations and articles for all metrics and the other good stuff behind Vest. We don’t want to just tell users what to do, but to also assist in their financial education. We hope our knowledge base can also become a thriving community where users can interact with us and each, ask questions around investing and keep gaining knowledge. Is it 100% accurate? Absolutely not. While we do a pretty great job at tracking and surfacing signals, we are not presenting a fool-proof, silver bullet with a guarantee here - rather a starting point for users to make more informed decisions, find potential new investment opportunities and hopefully learn about investing as they do so. We encourage our users to do their own research and due-diligence and not just take our signals as gospel - we know each and every person has a different risk appetite and goals, and we encourage you to use Vest in a way that fits with your own financial goals and risk appetite. We also display our win rates, average returns, and comparisons with buy and hold for each stock - and we are transparent about it when we’ve fallen short. Next steps: ​ Hope over to vestapp.ai and sign-up From the dashboard, play around, inspect our stock information and add some stocks to your watchlist. If you like what you see, and you’ve done your homework - use your favourite brokerage account to make an investment and watch Vest for changes in a stocks signals. If you don’t have one, we have a pop-up when you click buy/sell on any given stock with some non-affiliated brokerage options for the US, Australia and New Zealand - we don’t get a kickback from these brokerages, they are just what we’ve personally been using. FEEDBACK - We’re just getting started and we know the value of a fresh pair of eyes - our current mission is to get as much feedback as possible - anything you think of please send it through here or on the dedicated feedback form on our website in the sidebar on the left. Features we’re working on We're quietly thrilled about the direction Vest is headed, and we want to give you a sneak peek of what's in store for the next couple of quarters. Some of these may roll out as premium features, but we're diligently fine-tuning the details. Here's what you can expect: ​ Insider Trading Insights: Get daily reports on major stock moves by whales and company insiders. Institutional Holders: We're adding daily reports on institutional holders, keeping you informed about their moves. Lobbying Activity: We're actively working on daily updates about lobbying activities, so you can stay informed. Government Contracts Data: We'll provide a quarterly snapshot of government contract values for the companies you're tracking. US Congress Stock Activity: Keep an eye on daily trading actions of House and Senate members. Daily Summaries & Signal Alerts: We're currently hard at work on this feature. Soon, receive daily email summaries covering signals, watchlist updates, and key news. Personalized Risk Management: Tailor signals to match your unique risk management strategy. Your investments, your way. AI Assistant: Our LLM integration is almost ready, allowing you to ask it straightforward questions about particular securities in plain English. It will provide you with real-time context on fundamentals, news, and all the metrics and data points we monitor.

#reddit#introducing#vest:

reddit

0

1

Afraid-Astronomer130•This week

How I Built a $6k/mo Business with Cold Email

I scaled my SaaS to a $6k/mo business in under 6 months completely using cold email. However, the biggest takeaway for me is not a business that’s potentially worth 6-figure. It’s having a glance at the power of cold emails in the age of AI. It’s a rapidly evolving yet highly-effective channel, but no one talks about how to do it properly. Below is the what I needed 3 years ago, when I was stuck with 40 free users on my first app. An app I spent 2 years building into the void. Entrepreneurship is lonely. Especially when you are just starting out. Launching a startup feel like shouting into the dark. You pour your heart out. You think you have the next big idea, but no one cares. You write tweets, write blogs, build features, add tests. You talk to some lukewarm leads on Twitter. You do your big launch on Product Hunt. You might even get your first few sales. But after that, crickets... Then, you try every distribution channel out there. SEO Influencers Facebook ads Affiliates Newsletters Social media PPC Tiktok Press releases The reality is, none of them are that effective for early-stage startups. Because, let's face it, when you're just getting started, you have no clue what your customers truly desire. Without understanding their needs, you cannot create a product that resonates with them. It's as simple as that. So what’s the best distribution channel when you are doing a cold start? Cold emails. I know what you're thinking, but give me 10 seconds to change your mind: When I first heard about cold emailing I was like: “Hell no! I’m a developer, ain’t no way I’m talking to strangers.” That all changed on Jan 1st 2024, when I actually started sending cold emails to grow. Over the period of 6 months, I got over 1,700 users to sign up for my SaaS and grew it to a $6k/mo rapidly growing business. All from cold emails. Mastering Cold Emails = Your Superpower I might not recommend cold emails 3 years ago, but in 2024, I'd go all in with it. It used to be an expensive marketing channel bootstrapped startups can’t afford. You need to hire many assistants, build a list, research the leads, find emails, manage the mailboxes, email the leads, reply to emails, do meetings. follow up, get rejected... You had to hire at least 5 people just to get the ball rolling. The problem? Managing people sucks, and it doesn’t scale. That all changed with AI. Today, GPT-4 outperforms most human assistants. You can build an army of intelligent agents to help you complete tasks that’d previously be impossible without human input. Things that’d take a team of 10 assistants a week can now be done in 30 minutes with AI, at far superior quality with less headaches. You can throw 5000 names with website url at this pipeline and you’ll automatically have 5000 personalized emails ready to fire in 30 minutes. How amazing is that? Beyond being extremely accessible to developers who are already proficient in AI, cold email's got 3 superpowers that no other distribution channels can offer. Superpower 1/3 : You start a conversation with every single user. Every. Single. User. Let that sink in. This is incredibly powerful in the early stages, as it helps you establish rapport, bounce ideas off one another, offer 1:1 support, understand their needs, build personal relationships, and ultimately convert users into long-term fans of your product. From talking to 1000 users at the early stage, I had 20 users asking me to get on a call every week. If they are ready to buy, I do a sales call. If they are not sure, I do a user research call. At one point I even had to limit the number of calls I took to avoid burnout. The depth of the understanding of my customers’ needs is unparalleled. Using this insight, I refined the product to precisely cater to their requirements. Superpower 2/3 : You choose exactly who you talk to Unlike other distribution channels where you at best pick what someone's searching for, with cold emails, you have 100% control over who you talk to. Their company Job title Seniority level Number of employees Technology stack Growth rate Funding stage Product offerings Competitive landscape Social activity (Marital status - well, technically you can, but maybe not this one…) You can dial in this targeting to match your ICP exactly. The result is super low CAC and ultra high conversion rate. For example, My competitors are paying $10 per click for the keyword "HARO agency". I pay $0.19 per email sent, and $1.92 per signup At around $500 LTV, you can see how the first means a non-viable business. And the second means a cash-generating engine. Superpower 3/3 : Complete stealth mode Unlike other channels where competitors can easily reverse engineer or even abuse your marketing strategies, cold email operates in complete stealth mode. Every aspect is concealed from end to end: Your target audience Lead generation methods Number of leads targeted Email content Sales funnel This secrecy explains why there isn't much discussion about it online. Everyone is too focused on keeping their strategies close and reaping the rewards. That's precisely why I've chosen to share my insights on leveraging cold email to grow a successful SaaS business. More founders need to harness this channel to its fullest potential. In addition, I've more or less reached every user within my Total Addressable Market (TAM). So, if any competitor is reading this, don't bother trying to replicate it. The majority of potential users for this AI product are already onboard. To recap, the three superpowers of cold emails: You start a conversation with every single user → Accelerate to PMF You choose exactly who you talk to → Super-low CAC Complete stealth mode → Doesn’t attract competition By combining the three superpowers I helped my SaaS reach product-marketing-fit quickly and scale it to $6k per month while staying fully bootstrapped. I don't believe this was a coincidence. It's a replicable strategy for any startup. The blueprint is actually straightforward: Engage with a handful of customers Validate the idea Engage with numerous customers Scale to $5k/mo and beyond More early-stage founders should leverage cold emails for validation, and as their first distribution channel. And what would it do for you? Update: lots of DM asking about more specifics so I wrote about it here. https://coldstartblueprint.com/p/ai-agent-email-list-building

#reddit#built#$6k/mo

reddit

0

1

w-elm_•This week

Just reached 300 users in 3 months!!!

Just reached 300 users after 3 months live!!! My co-founder has been posting a bit here and always got some strong support and he suggested I share my side of things so here it is: How it started I co-founded AirMedia almost a year ago and we both didn’t know much about design/marketing/coding (just studied programming during my 6-month exchange period. The quickest way to get started seemed to get a no-code product that we could put in front of users and get feedback. My co-founder then started learning about bubble and we put together a basic platform to show users. I was working on a custom-code database in the meantime and decided after month 2 that we wanted to get something better I.e. AI would be interacting with the UI and had to do everything custom-code for it. We’re now month 3 and started from scratch again. While I was working on the code, we started talking to some potential users and selling lifetime deals to validate the idea (this is where I would start if I had to do it over again). Well I progressively found out it was more complicated than expected and we only released our first beta product last August (6 months later) Some challenges pre-launch: Getting the Meta/LinkedIn permissions for scheduling took around 1 month As the whole process took more time than expected, the waitlist of 300 that we managed to put together only converted by 10% (into free users). Please don’t make our mistakes and always keep your waitlist updated on what’s going on. Some challenges post-launch: Getting the right feedback and how to prioritise Getting users Monetising (yes - we’re bootstrapped) To get the best feedback we implemented some tracking (according to GDPR of course) on the platform and implemented Microsoft Clarity. The latter is a game-changer, if you have a SaaS and don’t use it you’re missing out. I wasn’t really into getting users as my co-founder handled that but it’s mainly manual and personalised LinkedIn outreach at the beginning and Reddit sharing about the progress, answering questions and getting some feedback at the same time. To monetise we realised we’re too common and there are 100+ other nice schedulers around so we’re now focusing on cracking the content creation side of AI (to be released next week 👀) as there’s much less competitors and it seems like that’s our users want. In the meantime of growing the company, we had to find a way to pay the bills as it’s two of us living together. So my co-founder started using the bubble skills gained and doing some freelance. He did around 7 platforms the last 6 months and we’re now just launching a bubble agency as a part of the main company to get your idea of a SaaS done in 30 days. That’s QuickMVP. It seemed like the right move to help other people (I met many non-technical founder looking for someone to bring their idea to life that didn’t cost $10k and was reliable) and include the AirMedia subscription in the package so let’s see how this next step plays out. Thanks for reading until here :)

#reddit#just#reached

reddit

0

0.818

Michaelbetterecycle•This week

How me and my team made 15+ apps and not made a single sale in 2023

Hey, my name is Michael, I am in Auckland NZ. This year was the official beginning of my adult life. I graduated from university and started a full-time job. I’ve also really dug into indiehacking/bootstrapping and started 15 projects (and it will be at least 17 before the year ends). I think I’ve learned a lot but I consciously repeated mistakes. Upto (Nov) Discord Statuses + Your Location + Facebook Poke https://preview.redd.it/4nqt7tp2tf5c1.png?width=572&format=png&auto=webp&s=b0223484bc54b45b5c65e0b1afd0dc52f9c02ad1 This was the end of uni, I often messaged (and got messaged) requests of status and location to (and from my) friends. I thought, what if we make a social app that’s super basic and all it does is show you where your friends are? To differentiate from snap maps and others we wanted something with more privacy where you select the location. However, never finished the codebase or launched it. This is because I slowly started to realize that B2C (especially social networks) are way too hard to make into an actual business and the story with Fistbump would repeat itself. However, this decision not to launch it almost launched a curse on our team. From that point, we permitted ourselves to abandon projects even before launching. Lessons: Don’t do social networks if your goal is 10k MRR ASAP. If you build something to 90% competition ship it or you will think it’s okay to abandon projects Insight Bites (Nov) Youtube Summarizer Extension ​ https://preview.redd.it/h6drqej4tf5c1.jpg?width=800&format=pjpg&auto=webp&s=0f211456c390ac06f4fcb54aa51f9d50b0826658 Right after Upto, we started ideating and conveniently the biggest revolution in the recent history of tech was released → GPT. We instantly began ideating. The first problem we chose to use AI for is to summarize YouTube videos. Comical. Nevertheless, I am convinced we have had the best UX because you could right-click on a video to get a slideshow of insights instead of how everyone else did it. We dropped it because there was too much competition and unit economics didn’t work out (and it was a B2C). PodPigeon (Dec) Podcast → Tweet Threads https://preview.redd.it/0ukge245tf5c1.png?width=2498&format=png&auto=webp&s=23303e1cab330578a3d25cd688fa67aa3b97fb60 Then we thought, to make unit economics work we need to make this worthwhile for podcasters. This is when I got into Twitter and started seeing people summarize podcasts. Then I thought, what if we make something that converts a podcast into tweets? This was probably one of the most important projects because it connected me with Jason and Jonaed, both of whom I regularly stay in contact with and are my go-to experts on ideas related to content creation. Jonaed was even willing to buy Podpigeon and was using it on his own time. However, the unit economics still didn’t work out (and we got excited about other things). Furthermore, we got scared of the competition because I found 1 - 2 other people who did similar things poorly. This was probably the biggest mistake we’ve made. Very similar projects made 10k MRR and more, launching later than we did. We didn’t have a coherent product vision, we didn’t understand the customer well enough, and we had a bad outlook on competition and a myriad of other things. Lessons: I already made another post about the importance of outlook on competition. Do not quit just because there are competitors or just because you can’t be 10x better. Indiehackers and Bootstrappers (or even startups) need to differentiate in the market, which can be via product (UX/UI), distribution, or both. Asking Ace Intro.co + Crowdsharing ​ https://preview.redd.it/0hu2tt16tf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3d397568ef2331e78198d64fafc1a701a3e75999 As I got into Twitter, I wanted to chat with some people I saw there. However, they were really expensive. I thought, what if we made some kind of crowdfunding service for other entrepreneurs to get a private lecture from their idols? It seemed to make a lot of sense on paper. It was solving a problem (validated via the fact that Intro.co is a thing and making things cheaper and accessible is a solid ground to stand on), we understood the market (or so we thought), and it could monetize relatively quickly. However, after 1-2 posts on Reddit and Indiehackers, we quickly learned three things. Firstly, no one cares. Secondly, even if they do, they think they can get the same information for free online. Thirdly, the reasons before are bad because for the first point → we barely talked to people, and for the second people → we barely talked to the wrong people. However, at least we didn’t code anything this time and tried to validate via a landing page. Lessons Don’t give up after 1 Redditor says “I don’t need this” Don’t be scared to choose successful people as your audience. Clarito Journaling with AI analyzer https://preview.redd.it/8ria2wq6tf5c1.jpg?width=1108&format=pjpg&auto=webp&s=586ec28ae75003d9f71b4af2520b748d53dd2854 Clarito is a classic problem all amateur entrepreneurs have. It’s where you lie to yourself that you have a real problem and therefore is validated but when your team asks you how much you would pay you say I guess you will pay, maybe, like 5 bucks a month…? Turns out, you’d have to pay me to use our own product lol. We sent it off to a few friends and posted on some forums, but never really got anything tangible and decided to move away. Honestly, a lot of it is us in our own heads. We say the market is too saturated, it’ll be hard to monetize, it’s B2C, etc. Lessons: You use the Mom Test on other people. You have to do it yourself as well. However, recognizing that the Mom Test requires a lot of creativity in its investigation because knowing what questions to ask can determine the outcome of the validation. I asked myself “Do I journal” but I didn’t ask myself “How often do I want GPT to chyme in on my reflections”. Which was practically never. That being said I think with the right audience and distribution, this product can work. I just don’t know (let alone care) about the audience that much (and I thought I was one of them)/ Horns & Claw Scrapes financial news texts you whether you should buy/sell the stock (news sentiment analysis) ​ https://preview.redd.it/gvfxdgc7tf5c1.jpg?width=1287&format=pjpg&auto=webp&s=63977bbc33fe74147b1f72913cefee4a9ebec9c2 This one we didn’t even bother launching. Probably something internal in the team and also seemed too good to be true (because if this works, doesn’t that just make us ultra-rich fast?). I saw a similar tool making 10k MRR so I guess I was wrong. Lessons: This one was pretty much just us getting into our heads. I declared that without an audience it would be impossible to ship this product and we needed to start a YouTube channel. Lol, and we did. And we couldn’t even film for 1 minute. I made bold statements like “We will commit to this for at least 1 year no matter what”. Learnery Make courses about any subject https://preview.redd.it/1nw6z448tf5c1.jpg?width=1112&format=pjpg&auto=webp&s=f2c73e8af23b0a6c3747a81e785960d4004feb48 This is probably the most “successful” project we’ve made. It grew from a couple of dozen to a couple of hundred users. It has 11 buy events for $9.99 LTD (we couldn’t be bothered connecting Stripe because we thought no one would buy it anyway). However what got us discouraged from seriously pursuing it more is, that this has very low defensibility, “Why wouldn’t someone just use chatGPT?” and it’s B2C so it’s hard to monetize. I used it myself for a month or so but then stopped. I don’t think it’s the app, I think the act of learning a concept from scratch isn’t something you do constantly in the way Learnery delivers it (ie course). I saw a bunch of similar apps that look like Ass make like 10k MRR. Lessons: Don’t do B2C, or if you do, do it properly Don’t just Mixpanel the buy button, connect your Stripe otherwise, it doesn’t feel real and you won’t get momentum. I doubt anyone (even me) will make this mistake again. I live in my GPT bubble where I make assumptions that everyone uses GPT the same way and as much as I do. In reality, the argument that this has low defensibility against GPT is invalid. Platforms that deliver a differentiated UX from ChatGPT to audiences who are not tightly integrated into the habit of using ChatGPT (which is like - everyone except for SOME tech evangelists). CuriosityFM Make podcasts about any subject https://preview.redd.it/zmosrcp8tf5c1.jpg?width=638&format=pjpg&auto=webp&s=d04ddffabef9050050b0d87939273cc96a8637dc This was our attempt at making Learnery more unique and more differentiated from chatGPT. We never really launched it. The unit economics didn’t work out and it was actually pretty boring to listen to, I don’t think I even fully listened to one 15-minute episode. I think this wasn’t that bad, it taught us more about ElevenLabs and voice AI. It took us maybe only 2-3 days to build so I think building to learn a new groundbreaking technology is fine. SleepyTale Make children’s bedtime stories https://preview.redd.it/14ue9nm9tf5c1.jpg?width=807&format=pjpg&auto=webp&s=267e18ec6f9270e6d1d11564b38136fa524966a1 My 8-year-old sister gave me that idea. She was too scared of making tea and I was curious about how she’d react if she heard a bedtime story about that exact scenario with the moral that I wanted her to absorb (which is that you shouldn’t be scared to try new things ie stop asking me to make your tea and do it yourself, it’s not that hard. You could say I went full Goebbels on her). Zane messaged a bunch of parents on Facebook but no one really cared. We showed this to one Lady at the place we worked from at Uni and she was impressed and wanted to show it to her kids but we already turned off our ElevenLabs subscription. Lessons: However, the truth behind this is beyond just “you need to be able to distribute”. It’s that you have to care about the audience. I don’t particularly want to build products for kids and parents. I am far away from that audience because I am neither a kid anymore nor going to be a parent anytime soon, and my sister still asked me to make her tea so the story didn’t work. I think it’s important to ask yourself whether you care about the audience. The way you answer that even when you are in full bias mode is, do you engage with them? Are you interested in what’s happening in their communities? Are you friends with them? Etc. User Survey Analyzer Big User Survey → GPT → Insights Report Me and my coworker were chatting about AI when he asked me to help him analyze a massive survey for him. I thought that was some pretty decent validation. Someone in an actual company asking for help. Lessons Market research is important but moving fast is also important. Ie building momentum. Also don’t revolve around 1 user. This has been a problem in multiple projects. Finding as many users as possible in the beginning to talk to is key. Otherwise, you are just waiting for 1 person to get back to you. AutoI18N Automated Internationalization of the codebase for webapps This one I might still do. It’s hard to find a solid distribution strategy. However, the idea came from me having to do it at my day job. It seems a solid problem. I’d say it’s validated and has some good players already. The key will be differentiation via the simplicity of UX and distribution (which means a slightly different audience). In the backlog for now because I don’t care about the problem or the audience that much. Documate - Part 1 Converts complex PDFs into Excel https://preview.redd.it/8b45k9katf5c1.jpg?width=1344&format=pjpg&auto=webp&s=57324b8720eb22782e28794d2db674b073193995 My mom needed to convert a catalog of furniture into an inventory which took her 3 full days of data entry. I automated it for her and thought this could have a big impact but there was no distribution because there was no ICP. We tried to find the ideal customers by talking to a bunch of different demographics but I flew to Kazakhstan for a holiday and so this kind of fizzled out. I am not writing this blog post linearity, this is my 2nd hour and I am tired and don’t want to finish this later so I don’t even know what lessons I learned. Figmatic Marketplace of high-quality Figma mockups of real apps https://preview.redd.it/h13yv45btf5c1.jpg?width=873&format=pjpg&auto=webp&s=aaa2896aeac2f22e9b7d9eed98c28bb8a2d2cdf1 This was a collab between me and my friend Alex. It was the classic Clarito where we both thought we had this problem and would pay to fix it. In reality, this is a vitamin. Neither I, nor I doubt Alex have thought of this as soon as we bought the domain. We posted it on Gumroad, sent it to a bunch of forums, and called it a day. Same issue as almost all the other ones. No distribution strategy. However, apps like Mobin show us that this concept is indeed profitable but it takes time. It needs SEO. It needs a community. None of those things, me and Alex had or was interested in. However shortly after HTML → Figma came out and it’s the best plugin. Maybe that should’ve been the idea. Podcast → Course Turns Podcaster’s episodes into a course This one I got baited by Jason :P I described to him the idea of repurposing his content for a course. He told me this was epic and he would pay. Then after I sent him the demo, he never checked it out. Anyhow during the development, we realized that doesn’t actually work because A podcast doesn’t have the correct format for the course, the most you can extract are concepts and ideas, seldom explanations. Most creators want video-based courses to be hosted on Kajabi or Udemy Another lesson is that when you pitch something to a user, what you articulate is a platform or a process, they imagine an outcome. However, the end result of your platform can be a very different outcome to what they had in mind and there is even a chance that what they want is not possible. You need to understand really well what the outcome looks like before you design the process. This is a classic problem where we thought of the solution before the problem. Yes, the problem exists. Podcasters want to make courses. However, if you really understand what they want, you can see how repurposing a podcast isn’t the best way to get there. However I only really spoke to 1-2 podcasters about this so making conclusions is dangerous for this can just be another asking ace mistake with the Redditor. Documate Part 2 Same concept as before but now I want to run some ads. We’ll see what happens. https://preview.redd.it/xb3npj0ctf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3cd4884a29fd11d870d010a2677b585551c49193 In conclusion https://preview.redd.it/2zrldc9dtf5c1.jpg?width=1840&format=pjpg&auto=webp&s=2b3105073e752ad41c23f205dbd1ea046c1da7ff It doesn’t actually matter that much whether you choose to do a B2C, or a social network or focus on growing your audience. All of these can make you successful. What’s important is that you choose. If I had to summarize my 2023 in one word it’s indecision. Most of these projects succeeded for other people, nothing was as fundamentally wrong about them as I proclaimed. In reality that itself was an excuse. New ideas seduce, and it is a form of discipline to commit to a single project for a respectful amount of time. https://preview.redd.it/zy9a2vzdtf5c1.jpg?width=1456&format=pjpg&auto=webp&s=901c621227bba0feb4efdb39142f66ab2ebb86fe Distribution is not just posting on Indiehackers and Reddit. It’s an actual strategy and you should think of it as soon as you think of the idea, even before the Figma designs. I like how Denis Shatalin taught me. You have to build a pipeline. That means a reliable way to get leads, launch campaigns at them, close deals, learn from them, and optimize. Whenever I get an idea now I always try to ask myself “Where can I find 1000s leads in one day?” If there is no good answer, this is not a good project to do now. ​ https://preview.redd.it/2boh3fpetf5c1.jpg?width=1456&format=pjpg&auto=webp&s=1c0d5d7b000716fcbbb00cbad495e8b61e25be66 Talk to users before doing anything. Jumping on designing and coding to make your idea a reality is a satisfying activity in the short term. Especially for me, I like to create for the sake of creation. However, it is so important to understand the market, understand the audience, understand the distribution. There are a lot of things to understand before coding. https://preview.redd.it/lv8tt96ftf5c1.jpg?width=1456&format=pjpg&auto=webp&s=6c8735aa6ad795f216ff9ddfa2341712e8277724 Get out of your own head. The real reason we dropped so many projects is that we got into our own heads. We let the negative thoughts creep in and kill all the optimism. I am really good at coming up with excuses to start a project. However, I am equally as good at coming up with reasons to kill a project. And so you have this yin and yang of starting and stopping. Building momentum and not burning out. I can say with certainty my team ran out of juice this year. We lost momentum so many times we got burnt out towards the end. Realizing that the project itself has momentum is important. User feedback and sales bring momentum. Building also creates momentum but unless it is matched with an equal force of impact, it can stomp the project down. That is why so many of our projects died quickly after we launched. The smarter approach is to do things that have a low investment of momentum (like talking to users) but result in high impact (sales or feedback). Yes, that means the project can get invalidated which makes it more short-lived than if we built it first, but it preserves team life energy. At the end of 2023 here is a single sentence I am making about how I think one becomes a successful indiehacker. One becomes a successful Indiehacker when one starts to solve pain-killer problems in the market they understand, for an audience they care about and consistently engage with for a long enough timeframe. Therefore an unsuccessful Indiehacker in a single sentence is An unsuccessful Indiehacker constantly enters new markets they don’t understand to build solutions for people whose problems they don’t care about, in a timeframe that is shorter than than the time they spent thinking about distribution. However, an important note to be made. Life is not just about indiehacking. It’s about learning and having fun. In the human world, the best journey isn’t the one that gets you the fastest to your goals but the one you enjoy the most. I enjoyed making those silly little projects and although I do not regret them, I will not repeat the same mistakes in 2024. But while it’s still 2023, I have 2 more projects I want to do :) EDIT: For Devs, frontend is always react with vite (ts) and backend is either node with express (ts) or python. For DB either Postgres or mongo (usually Prisma for ORM). For deployment all of it is on AWS (S3, EC2). In terms of libraries/APIs Whisper.cpp is best open source for transcription Obviously the gpt apis Eleven labs for voice related stuff And other random stuff here and there

#reddit#team#made

reddit

0

0.905

LieIgnorant6304•This week

How to get your first 10 customers with cold email

Cold email is an insane channel for growth, especially for bootstrapped startups as it's very low cost but completely scalable. Yet there's a huge difference between blind cold emailing and crafting personalized outreach for select individuals. The latter is a legit channel which makes many businesses scale in short amounts of time (i.e. see Alex Hormozi’s ‘$100 Million Dollar Offer’). My goal here is to help other founders do what I did but quicker. So you can learn faster. And then teach me something new too. These are the step-by-step lessons I've learnt as a bootstrapped founder, showing you how to use cold email to get your first customers: Find your leads Write engaging email copy Personalize your outreach Send emails Scale up Find your leads This is a key step. Once you figure out exactly who you want to target and where to find them, you'll be printing money. There's a few different ways to go about finding valuable leads. The secret? Keep testing different approaches until you strike gold. First, dedicate some time every day to find and organise leads. Then, keep an eye on your numbers and bounce rates. If something's not working, switch it up. Stick with what's bringing in results and ditch what's not. It's all about staying flexible and learning as you go. Apollo.io is a great starting point as an effective lead source. Their tool allows you to specify filters including job titles, location, company size, industry, keywords, technologies, and revenue. Get specific with your searches to find your ideal customers. Once you have some results you can save and export them, you'll get a list of contact information including name, email, company, LinkedIn, ready to be verified and used. LinkedIn Sales Navigator is another good source. You can either do manual searches or use a scraper to automate the process. The scrapers I'd recommend checking out are FindyMail and Evaboot. As with Apollo, it's best to get very specific with your targeting so you know the prospect will be interested in your offer. BuiltWith is more expensive but ideal if you're targeting competitors. With BuiltWith you can build lists based on what technologies companies are using. For example if you're selling a Shopify app, you'd want to know websites or stores using Shopify, and reach out to them. The best lead sources will always be those that haven't been contacted a lot in the past. If you are able to find places where your target audience uniquely hangs out, and you can get their company website domains, they have the potential to be scrapped, and you have a way to personalize like "I spotted your comment on XYZ website". Once you've got your leads, keep them organized. Set up folders for different niches, countries, company sizes, so you can review what works and what doesn't. One more thing – before you start firing off emails, make sure those addresses are verified. Always use an email verifier to clean up your list and avoid bounces that may affect your sending reputation, and land you in the spam folder. I use Neverbounce for this but there are other tools available. Write engaging email copy Writing a good copy that gets replies is difficult, it changes depending on your offer/audience and nobody knows what's going to work. The best approach is to keep testing different targeting and messaging until you find what works. However, there are some key rules to stick to that I've outlined. For the subject line, keep it short and personalized. Try to write something that sparks interest, and mention the recipients name: Thought you’d like this {{first name}} {{firstName}} - quick question For the email body it's best to use a framework of personalization, offer, then call to action. Personalization is an entire subject in its own right, which I've covered below. In short, a personalized email opener is the best way to grab their attention, and let them know the email is relevant to them and to keep reading. Take it from Alex Hormozi and his $100M Offers playbook – your offer is very important to get right. Make sure your offer hits the mark for your target audience, and get as specific as possible. For example: I built a SaaS shopify app for small ecommerce businesses selling apparel that doubles your revenue in 60-days or your money back. We developed a cold email personalization tool for lead generation agencies that saves hundreds of hours, and can 3x your reply rate. Lastly, the CTA. The goal here isn't to get sign-ups directly from your first email. It's better to ask a brief question about whether the prospect would be interested in learning more. Something very low friction, that warrants a response. Some examples might include: Would you be interested in learning more about this? Can we connect a bit more on this? Mind if I send over a loom I recorded for you? Never send any links in the first email. You've reached out to this person because you have good reason to believe they'd find real value in your offer, and you want to verify if that's the case. After you get one reply, this is a great positive signal and from there you can send a link, book a call, provide a free resource, whatever makes sense based on their response. Personalize your outreach Personalization is one of the most important parts of the process to get right. Your recipient probably receives a multitude of emails every day, how can you make yours stand out, letting them know you've done your research, and that your email is relevant to them? Personalizing each email ensures you get more positive replies, and avoid spam filters, as your email is unique and hasn't been copied and pasted a million times over. The goal is to spark the recipient's interest, and let them know that you're contacting them for good reason. You might mention a recent achievement, blog post or product release that led you to reach out to the prospect specifically. For example: Your post on "Doing Nothing" gave me a good chuckle. Savvy marketing on Cadbury's part. Saw that you've been at Google for just under a year now as a new VP of sales. Spotted that you've got over 7 years of experience in the digital marketing space. Ideally you'll mention something specifically about the prospect or their company that relates to your offer. The downside to personalization is that it's hard to get right, and very time consuming at scale, but totally worth it. Full disclosure, me and my partner Igor just launched our new startup ColdClicks which uses AI to generate hyper-personalized email openers at scale. We built the tool as we were sending hundreds of emails a day, and personalizing every individual email took hours out of our day. ColdClicks automates this process, saving you time and getting you 2-3x more replies. Send emails At this stage you've decided on who you're targeting, you've mined some leads, and written copy. Now it's time to get sending. You can do this manually by copy and pasting each message, but one of the reasons cold email is so powerful is that it's scalable. When you build a process that gets customers, you'll want to send as many emails as you can to your target market. To get started quickly, you can use a mail-merge gmail tool, the best I've used is Maileteor. With Maileteor you upload your lead data to Google sheets, set-up an email template and Mailmetor will send out emails every day automatically. In your template you can define variables including name, company, and personalization to ensure your email is unique for each recipient. Alternatively, you may opt for a more comprehensive tool such as Instantly. Instantly includes unlimited email sending and accounts. There's more initial setup involved as you'll need to set-up Google workspace, buy sending domains, and warm up your email accounts, but when you become familiar with the process you can build a powerful lead generation / customer acquisition machine. Some key points to note, it's very important to warm up any new email accounts you set up. Warmup is the process of gradually establishing a positive reputation with email service providers like Gmail or Yahoo. Make sure to set up DKIM and DMARC on those new email accounts too, to maximise your chances of landing in the inbox. Scale up Once you've found a process that works, good things happen, and it becomes a numbers game. As you get replies and start to see new users signing up, you'll want to scale the process and send more emails. It's straightforward to add new sending accounts in a sending tool like Instantly, and you'll want to broaden your targeting when mining to test new markets. Unfortunately, sending more emails usually comes with a drop in reply rate as you have less time to personalize your messaging for each recipient. This is where ColdClicks shines. The tool allows you to upload thousands of leads and generate perfectly relevant email personalizations for every lead in your list, then export to your favorite sending tool. The examples I listed above in the personalization section were all generated by ColdClicks. Wrapping it up Cold email is an amazing way to validate your product and get new customers. The channel gets a bad rap, but there's a huge difference between blind cold emailing and crafting personalized outreach for individuals who will find value in your product. It's perfect for bootstrapped founders due to its affordability and scalability, and it's the driver of growth for many SaaS businesses. Time to get your first 10 customers! As you start sending, make it a habit to regularly check for new leads. Always experiment with market/messaging, track every campaign so you can learn what's working and iterate, and when you do get positive responses, reply as soon as you can!

#reddit#your#first

reddit

0

1

Low_Philosopher1792•This week

100 agency business ideas that requires zero investment in 2025

Social Media Manager (Search "smma business for sale" and get started with Sitefy or humanpdesign company) Content Writing Service SEO Specialist (Search "outsourced seo business Sitefy" and get started) Instagram Growth Expert LinkedIn Lead Outreach Cold Email Specialist Ghostwriter Services YouTube Channel Assistant X/Twitter Writing Service UGC Creator Network Virtual Assistant Provider Podcast Manager Influencer Outreach Service Brand Strategy Consultant Resume & Profile Optimizer Media Outreach Services Newsletter Creation Team Lead Gen Specialist Personal Branding Partner Online Reputation Consultant Script Writer Team Funnel Strategy Helper Landing Page Writer Blog Strategy Consultant Growth Tactics Consultant SaaS User Onboarding Service App Store Optimization (ASO) Chatbot Automation Setup Customer Support Automator TikTok Strategy Specialist Short Video Editing Team Long Video Editing Team Digital Product Launch Help Webinar Setup Specialist Affiliate Setup Services Online Community Builder Facebook Group Specialist Pinterest Marketing Service (Search "digital marketing business for sale Sitefy" and get started quickly) Email List Builder CRM Setup Helper eBook Writing Partner YouTube Thumbnail Designer Pinterest Content Designer Proposal Writing Team Press Release Writer Influencer Deal Manager SaaS Growth Advisor Direct-To-Consumer Marketing Help App Review Booster Fiverr Profile Consultant Upwork Profile Expert Gig Profile Optimizer AI Tools Setup Help Freelance Talent Finder Local Search Optimizer Google Profile Optimizer Online Course Setup Notion Workflow Setup Airtable Consultant Trello/ClickUp Helper Automation Strategy Planner Sales Funnel Assistant WhatsApp Campaign Setup Telegram Channel Helper Blog Publishing Help Email-Based Content Creator Startup Deck Consultant Business Name & Tagline Creator Domain Research Help Reddit Growth Assistant Niche Community Builder Free Resource Strategy Website Audit Consultant Brand Guide Creator Business System Organizer Productivity Coach Reputation Fix Specialist Digital Product Reviewer Micro SaaS Idea Tester Ad Copywriter Email Strategy Consultant Influencer Research Team Onboarding Docs Creator Automation Setup Specialist Freelance Team Coordinator AI Marketing Planner Feedback Collection Setup Social Proof Strategist Giveaway Organizer Pricing Strategy Helper Contract Template Consultant Startup Growth Guide AI Prompt Writer Press Kit Creator Podcast Booking Assistant Inbox Performance Checker Customer Journey Planner Trend Report Analyst Testimonial Request Specialist Digital Declutter Coach Which one sounds like your vibe?

#reddit#agency#business

reddit

0

1

Chunky_Cheeze•This week

I built an AI social monitoring that looks for relevant posts, not just keywords

Hey everyone! I've been working on a side project that I'm excited to share with you all—it's called BillyBuzz What is BillyBuzz? BillyBuzz is an AI-powered social monitoring tool that helps businesses spot and analyze relevant conversations on social media platforms, starting with Reddit. It surfaces the most promising leads directly to your Slack channels, email, or Discord, so you don't have to spend hours scrolling through threads. Why I Built It I was spending a ton of time searching for relevant posts in niche subreddits for another product I was working to get off the ground. It was not only time-consuming but also distracting (you know how easy it is to fall into a Reddit rabbit hole). I couldn't find any existing tool that did more than basic keyword searches—which wasn't enough, especially if your brand name has multiple meanings (like "Apple"). So, I decided to build BillyBuzz. It uses AI to understand your business, products, target audience, and value proposition, alongside specific keywords you might want to include. This way, it finds posts where you can genuinely contribute by introducing your product. I used BillyBuzz for a previous product launch and managed to grow it to over $80k/month in volume within about 3 months, purely through Reddit engagement. How It Works Add Information About Your Business: Input details about your business and products. Select Subreddits to Monitor: Choose the subreddits relevant to your niche. Receive Timely Alerts: Get notified via Slack, email, or Discord when relevant posts are identified. Features AI-Powered Relevancy Scoring: Goes beyond keywords by understanding the context to identify truly relevant opportunities. Subreddit Tracking: Monitor specific subreddits with AI-recommended keywords tailored to your company's needs. Real-Time Alerts: Checks for new relevant conversations every 15 minutes, so you can engage at the perfect time. Automated Categorization (Coming Soon): The AI will categorize conversations into topics like competitors, customer complaints, and more. Who It's For BillyBuzz is designed for startup founders, growth marketers, and small business owners who are tech-savvy and focused on scaling their operations. If you're looking to save time and engage more effectively with your target audience on social media, this might be up your alley. Looking for Feedback I'm sharing this here because I'd love to get your thoughts, feedback, or any suggestions you might have. If you're interested in checking it out, you can find more info here: https://billybuzz.com. Feel free to ask me anything or share your experiences with similar challenges!

#reddit#built#social

reddit

0

0.818

Michaelbetterecycle•This week

How me and my team made 15+ apps and not made a single sale in 2023

Hey, my name is Michael, I am in Auckland NZ. This year was the official beginning of my adult life. I graduated from university and started a full-time job. I’ve also really dug into indiehacking/bootstrapping and started 15 projects (and it will be at least 17 before the year ends). I think I’ve learned a lot but I consciously repeated mistakes. Upto (Nov) Discord Statuses + Your Location + Facebook Poke https://preview.redd.it/4nqt7tp2tf5c1.png?width=572&format=png&auto=webp&s=b0223484bc54b45b5c65e0b1afd0dc52f9c02ad1 This was the end of uni, I often messaged (and got messaged) requests of status and location to (and from my) friends. I thought, what if we make a social app that’s super basic and all it does is show you where your friends are? To differentiate from snap maps and others we wanted something with more privacy where you select the location. However, never finished the codebase or launched it. This is because I slowly started to realize that B2C (especially social networks) are way too hard to make into an actual business and the story with Fistbump would repeat itself. However, this decision not to launch it almost launched a curse on our team. From that point, we permitted ourselves to abandon projects even before launching. Lessons: Don’t do social networks if your goal is 10k MRR ASAP. If you build something to 90% competition ship it or you will think it’s okay to abandon projects Insight Bites (Nov) Youtube Summarizer Extension ​ https://preview.redd.it/h6drqej4tf5c1.jpg?width=800&format=pjpg&auto=webp&s=0f211456c390ac06f4fcb54aa51f9d50b0826658 Right after Upto, we started ideating and conveniently the biggest revolution in the recent history of tech was released → GPT. We instantly began ideating. The first problem we chose to use AI for is to summarize YouTube videos. Comical. Nevertheless, I am convinced we have had the best UX because you could right-click on a video to get a slideshow of insights instead of how everyone else did it. We dropped it because there was too much competition and unit economics didn’t work out (and it was a B2C). PodPigeon (Dec) Podcast → Tweet Threads https://preview.redd.it/0ukge245tf5c1.png?width=2498&format=png&auto=webp&s=23303e1cab330578a3d25cd688fa67aa3b97fb60 Then we thought, to make unit economics work we need to make this worthwhile for podcasters. This is when I got into Twitter and started seeing people summarize podcasts. Then I thought, what if we make something that converts a podcast into tweets? This was probably one of the most important projects because it connected me with Jason and Jonaed, both of whom I regularly stay in contact with and are my go-to experts on ideas related to content creation. Jonaed was even willing to buy Podpigeon and was using it on his own time. However, the unit economics still didn’t work out (and we got excited about other things). Furthermore, we got scared of the competition because I found 1 - 2 other people who did similar things poorly. This was probably the biggest mistake we’ve made. Very similar projects made 10k MRR and more, launching later than we did. We didn’t have a coherent product vision, we didn’t understand the customer well enough, and we had a bad outlook on competition and a myriad of other things. Lessons: I already made another post about the importance of outlook on competition. Do not quit just because there are competitors or just because you can’t be 10x better. Indiehackers and Bootstrappers (or even startups) need to differentiate in the market, which can be via product (UX/UI), distribution, or both. Asking Ace Intro.co + Crowdsharing ​ https://preview.redd.it/0hu2tt16tf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3d397568ef2331e78198d64fafc1a701a3e75999 As I got into Twitter, I wanted to chat with some people I saw there. However, they were really expensive. I thought, what if we made some kind of crowdfunding service for other entrepreneurs to get a private lecture from their idols? It seemed to make a lot of sense on paper. It was solving a problem (validated via the fact that Intro.co is a thing and making things cheaper and accessible is a solid ground to stand on), we understood the market (or so we thought), and it could monetize relatively quickly. However, after 1-2 posts on Reddit and Indiehackers, we quickly learned three things. Firstly, no one cares. Secondly, even if they do, they think they can get the same information for free online. Thirdly, the reasons before are bad because for the first point → we barely talked to people, and for the second people → we barely talked to the wrong people. However, at least we didn’t code anything this time and tried to validate via a landing page. Lessons Don’t give up after 1 Redditor says “I don’t need this” Don’t be scared to choose successful people as your audience. Clarito Journaling with AI analyzer https://preview.redd.it/8ria2wq6tf5c1.jpg?width=1108&format=pjpg&auto=webp&s=586ec28ae75003d9f71b4af2520b748d53dd2854 Clarito is a classic problem all amateur entrepreneurs have. It’s where you lie to yourself that you have a real problem and therefore is validated but when your team asks you how much you would pay you say I guess you will pay, maybe, like 5 bucks a month…? Turns out, you’d have to pay me to use our own product lol. We sent it off to a few friends and posted on some forums, but never really got anything tangible and decided to move away. Honestly, a lot of it is us in our own heads. We say the market is too saturated, it’ll be hard to monetize, it’s B2C, etc. Lessons: You use the Mom Test on other people. You have to do it yourself as well. However, recognizing that the Mom Test requires a lot of creativity in its investigation because knowing what questions to ask can determine the outcome of the validation. I asked myself “Do I journal” but I didn’t ask myself “How often do I want GPT to chyme in on my reflections”. Which was practically never. That being said I think with the right audience and distribution, this product can work. I just don’t know (let alone care) about the audience that much (and I thought I was one of them)/ Horns & Claw Scrapes financial news texts you whether you should buy/sell the stock (news sentiment analysis) ​ https://preview.redd.it/gvfxdgc7tf5c1.jpg?width=1287&format=pjpg&auto=webp&s=63977bbc33fe74147b1f72913cefee4a9ebec9c2 This one we didn’t even bother launching. Probably something internal in the team and also seemed too good to be true (because if this works, doesn’t that just make us ultra-rich fast?). I saw a similar tool making 10k MRR so I guess I was wrong. Lessons: This one was pretty much just us getting into our heads. I declared that without an audience it would be impossible to ship this product and we needed to start a YouTube channel. Lol, and we did. And we couldn’t even film for 1 minute. I made bold statements like “We will commit to this for at least 1 year no matter what”. Learnery Make courses about any subject https://preview.redd.it/1nw6z448tf5c1.jpg?width=1112&format=pjpg&auto=webp&s=f2c73e8af23b0a6c3747a81e785960d4004feb48 This is probably the most “successful” project we’ve made. It grew from a couple of dozen to a couple of hundred users. It has 11 buy events for $9.99 LTD (we couldn’t be bothered connecting Stripe because we thought no one would buy it anyway). However what got us discouraged from seriously pursuing it more is, that this has very low defensibility, “Why wouldn’t someone just use chatGPT?” and it’s B2C so it’s hard to monetize. I used it myself for a month or so but then stopped. I don’t think it’s the app, I think the act of learning a concept from scratch isn’t something you do constantly in the way Learnery delivers it (ie course). I saw a bunch of similar apps that look like Ass make like 10k MRR. Lessons: Don’t do B2C, or if you do, do it properly Don’t just Mixpanel the buy button, connect your Stripe otherwise, it doesn’t feel real and you won’t get momentum. I doubt anyone (even me) will make this mistake again. I live in my GPT bubble where I make assumptions that everyone uses GPT the same way and as much as I do. In reality, the argument that this has low defensibility against GPT is invalid. Platforms that deliver a differentiated UX from ChatGPT to audiences who are not tightly integrated into the habit of using ChatGPT (which is like - everyone except for SOME tech evangelists). CuriosityFM Make podcasts about any subject https://preview.redd.it/zmosrcp8tf5c1.jpg?width=638&format=pjpg&auto=webp&s=d04ddffabef9050050b0d87939273cc96a8637dc This was our attempt at making Learnery more unique and more differentiated from chatGPT. We never really launched it. The unit economics didn’t work out and it was actually pretty boring to listen to, I don’t think I even fully listened to one 15-minute episode. I think this wasn’t that bad, it taught us more about ElevenLabs and voice AI. It took us maybe only 2-3 days to build so I think building to learn a new groundbreaking technology is fine. SleepyTale Make children’s bedtime stories https://preview.redd.it/14ue9nm9tf5c1.jpg?width=807&format=pjpg&auto=webp&s=267e18ec6f9270e6d1d11564b38136fa524966a1 My 8-year-old sister gave me that idea. She was too scared of making tea and I was curious about how she’d react if she heard a bedtime story about that exact scenario with the moral that I wanted her to absorb (which is that you shouldn’t be scared to try new things ie stop asking me to make your tea and do it yourself, it’s not that hard. You could say I went full Goebbels on her). Zane messaged a bunch of parents on Facebook but no one really cared. We showed this to one Lady at the place we worked from at Uni and she was impressed and wanted to show it to her kids but we already turned off our ElevenLabs subscription. Lessons: However, the truth behind this is beyond just “you need to be able to distribute”. It’s that you have to care about the audience. I don’t particularly want to build products for kids and parents. I am far away from that audience because I am neither a kid anymore nor going to be a parent anytime soon, and my sister still asked me to make her tea so the story didn’t work. I think it’s important to ask yourself whether you care about the audience. The way you answer that even when you are in full bias mode is, do you engage with them? Are you interested in what’s happening in their communities? Are you friends with them? Etc. User Survey Analyzer Big User Survey → GPT → Insights Report Me and my coworker were chatting about AI when he asked me to help him analyze a massive survey for him. I thought that was some pretty decent validation. Someone in an actual company asking for help. Lessons Market research is important but moving fast is also important. Ie building momentum. Also don’t revolve around 1 user. This has been a problem in multiple projects. Finding as many users as possible in the beginning to talk to is key. Otherwise, you are just waiting for 1 person to get back to you. AutoI18N Automated Internationalization of the codebase for webapps This one I might still do. It’s hard to find a solid distribution strategy. However, the idea came from me having to do it at my day job. It seems a solid problem. I’d say it’s validated and has some good players already. The key will be differentiation via the simplicity of UX and distribution (which means a slightly different audience). In the backlog for now because I don’t care about the problem or the audience that much. Documate - Part 1 Converts complex PDFs into Excel https://preview.redd.it/8b45k9katf5c1.jpg?width=1344&format=pjpg&auto=webp&s=57324b8720eb22782e28794d2db674b073193995 My mom needed to convert a catalog of furniture into an inventory which took her 3 full days of data entry. I automated it for her and thought this could have a big impact but there was no distribution because there was no ICP. We tried to find the ideal customers by talking to a bunch of different demographics but I flew to Kazakhstan for a holiday and so this kind of fizzled out. I am not writing this blog post linearity, this is my 2nd hour and I am tired and don’t want to finish this later so I don’t even know what lessons I learned. Figmatic Marketplace of high-quality Figma mockups of real apps https://preview.redd.it/h13yv45btf5c1.jpg?width=873&format=pjpg&auto=webp&s=aaa2896aeac2f22e9b7d9eed98c28bb8a2d2cdf1 This was a collab between me and my friend Alex. It was the classic Clarito where we both thought we had this problem and would pay to fix it. In reality, this is a vitamin. Neither I, nor I doubt Alex have thought of this as soon as we bought the domain. We posted it on Gumroad, sent it to a bunch of forums, and called it a day. Same issue as almost all the other ones. No distribution strategy. However, apps like Mobin show us that this concept is indeed profitable but it takes time. It needs SEO. It needs a community. None of those things, me and Alex had or was interested in. However shortly after HTML → Figma came out and it’s the best plugin. Maybe that should’ve been the idea. Podcast → Course Turns Podcaster’s episodes into a course This one I got baited by Jason :P I described to him the idea of repurposing his content for a course. He told me this was epic and he would pay. Then after I sent him the demo, he never checked it out. Anyhow during the development, we realized that doesn’t actually work because A podcast doesn’t have the correct format for the course, the most you can extract are concepts and ideas, seldom explanations. Most creators want video-based courses to be hosted on Kajabi or Udemy Another lesson is that when you pitch something to a user, what you articulate is a platform or a process, they imagine an outcome. However, the end result of your platform can be a very different outcome to what they had in mind and there is even a chance that what they want is not possible. You need to understand really well what the outcome looks like before you design the process. This is a classic problem where we thought of the solution before the problem. Yes, the problem exists. Podcasters want to make courses. However, if you really understand what they want, you can see how repurposing a podcast isn’t the best way to get there. However I only really spoke to 1-2 podcasters about this so making conclusions is dangerous for this can just be another asking ace mistake with the Redditor. Documate Part 2 Same concept as before but now I want to run some ads. We’ll see what happens. https://preview.redd.it/xb3npj0ctf5c1.jpg?width=1456&format=pjpg&auto=webp&s=3cd4884a29fd11d870d010a2677b585551c49193 In conclusion https://preview.redd.it/2zrldc9dtf5c1.jpg?width=1840&format=pjpg&auto=webp&s=2b3105073e752ad41c23f205dbd1ea046c1da7ff It doesn’t actually matter that much whether you choose to do a B2C, or a social network or focus on growing your audience. All of these can make you successful. What’s important is that you choose. If I had to summarize my 2023 in one word it’s indecision. Most of these projects succeeded for other people, nothing was as fundamentally wrong about them as I proclaimed. In reality that itself was an excuse. New ideas seduce, and it is a form of discipline to commit to a single project for a respectful amount of time. https://preview.redd.it/zy9a2vzdtf5c1.jpg?width=1456&format=pjpg&auto=webp&s=901c621227bba0feb4efdb39142f66ab2ebb86fe Distribution is not just posting on Indiehackers and Reddit. It’s an actual strategy and you should think of it as soon as you think of the idea, even before the Figma designs. I like how Denis Shatalin taught me. You have to build a pipeline. That means a reliable way to get leads, launch campaigns at them, close deals, learn from them, and optimize. Whenever I get an idea now I always try to ask myself “Where can I find 1000s leads in one day?” If there is no good answer, this is not a good project to do now. ​ https://preview.redd.it/2boh3fpetf5c1.jpg?width=1456&format=pjpg&auto=webp&s=1c0d5d7b000716fcbbb00cbad495e8b61e25be66 Talk to users before doing anything. Jumping on designing and coding to make your idea a reality is a satisfying activity in the short term. Especially for me, I like to create for the sake of creation. However, it is so important to understand the market, understand the audience, understand the distribution. There are a lot of things to understand before coding. https://preview.redd.it/lv8tt96ftf5c1.jpg?width=1456&format=pjpg&auto=webp&s=6c8735aa6ad795f216ff9ddfa2341712e8277724 Get out of your own head. The real reason we dropped so many projects is that we got into our own heads. We let the negative thoughts creep in and kill all the optimism. I am really good at coming up with excuses to start a project. However, I am equally as good at coming up with reasons to kill a project. And so you have this yin and yang of starting and stopping. Building momentum and not burning out. I can say with certainty my team ran out of juice this year. We lost momentum so many times we got burnt out towards the end. Realizing that the project itself has momentum is important. User feedback and sales bring momentum. Building also creates momentum but unless it is matched with an equal force of impact, it can stomp the project down. That is why so many of our projects died quickly after we launched. The smarter approach is to do things that have a low investment of momentum (like talking to users) but result in high impact (sales or feedback). Yes, that means the project can get invalidated which makes it more short-lived than if we built it first, but it preserves team life energy. At the end of 2023 here is a single sentence I am making about how I think one becomes a successful indiehacker. One becomes a successful Indiehacker when one starts to solve pain-killer problems in the market they understand, for an audience they care about and consistently engage with for a long enough timeframe. Therefore an unsuccessful Indiehacker in a single sentence is An unsuccessful Indiehacker constantly enters new markets they don’t understand to build solutions for people whose problems they don’t care about, in a timeframe that is shorter than than the time they spent thinking about distribution. However, an important note to be made. Life is not just about indiehacking. It’s about learning and having fun. In the human world, the best journey isn’t the one that gets you the fastest to your goals but the one you enjoy the most. I enjoyed making those silly little projects and although I do not regret them, I will not repeat the same mistakes in 2024. But while it’s still 2023, I have 2 more projects I want to do :) EDIT: For Devs, frontend is always react with vite (ts) and backend is either node with express (ts) or python. For DB either Postgres or mongo (usually Prisma for ORM). For deployment all of it is on AWS (S3, EC2). In terms of libraries/APIs Whisper.cpp is best open source for transcription Obviously the gpt apis Eleven labs for voice related stuff And other random stuff here and there

#reddit#team#made

reddit

0

1

inputorigin•This week

I retired at 32 from my side project. Here's the path I took.

EDIT 2: Thanks for the award kind stranger! I've stopped responding to reddit comments for this post. I'm adding an FAQ to the original post based on the most common high quality questions. If you have a question that you're dying to know the answer to and that only I can help you with (vs. Google, ChatGPT, etc.), DM me. EDIT: I love how controversial this post has become (50% upvote rate), and only in this subreddit (vs. other subreddits that I posted the same content in). I trust that the open-minded half of you will find something useful in this post and my other posts and comments. I retired at 32 years old, in large part thanks to a B2C SaaS app that I developed on my own. Now, I don't have to work in order to cover my living expenses, and wouldn't have to work for quite a while. In other words, I can finally sip mai tais at the beach. I've condensed how I got there into this post. First, a super simplified timeline of events, followed by some critical details. Timeline 2013 Graduated college in the US 2013 Started first corporate job 2013 Started side project (B2C app) that would eventually lead to my retirement 2020 Started charging for use of my B2C app (was free, became freemium) 2021 Quit my last corporate job 2022 Retired: time freedom attained Details First, some summary statistics of my path to retirement: 9 years: time between graduating college and my retirement. 8 years: total length of my career where I worked at some corporate day job. 7 years: time it took my B2C app to make its first revenue dollar 2 years: time between my first dollar of SaaS revenue and my retirement. "Something something overnight success a decade in the making". I got extremely lucky on my path to retirement, both in terms of the business environment I was in and who I am as a person. I'd also like to think that some of the conscious decisions I made along the way contributed to my early retirement. Lucky Breaks Was born in the US middle class. Had a natural affinity for computer programming and entrepreneurial mindset (initiative, resourcefulness, pragmatism, courage, growth mindset). Had opportunities to develop these mindsets throughout life. Got into a good college which gave me the credentials to get high paying corporate jobs. Was early to a platform that saw large adoption (see "barnacle on whale" strategy). Business niche is shareworthy: my SaaS received free media. Business niche is relatively stable, and small enough to not be competitive. "Skillful" Decisions I decided to spend the nights and weekends of my early career working on side projects in the hopes that one would hit. I also worked a day job to support myself and build my savings. My launch funnel over roughly 7 years of working on side projects: Countless side projects prototyped. 5 side projects publically launched. 2 side projects made > $0. 1 side project ended up becoming the SaaS that would help me retire. At my corporate day jobs, I optimized for learning and work-life balance. My learning usually stalled after a year or two at one company, so I’d quit and find another job. I invested (and continute to do so) in physical and mental wellbeing via regular workouts, meditation, journaling, traveling, and good food. My fulfilling non-work-life re-energized me for my work-life, and my work-life supported my non-work-life: a virtuous cycle. I automated the most time-consuming aspects of my business (outside of product development). Nowadays, I take long vacations and work at most 20 hours a week / a three-day work week . I decided to keep my business entirely owned and operated by me. It's the best fit for my work-style (high autonomy, deep focus, fast decision-making) and need to have full creative freedom and control. I dated and married a very supportive and inspiring partner. I try not to succumb to outrageous lifestyle creep, which keeps my living expenses low and drastically extends my burn-rate. Prescription To share some aphorisms I’ve leaned with the wantrepreneurs or those who want to follow a similar path: Maximize your at bats, because you only need one hit. Bias towards action. Launch quickly. Get your ideas out into the real world for feedback. Perfect is the enemy of good. If you keep swinging and improving, you'll hit the ball eventually. Keep the big picture in mind. You don't necessarily need a home-run to be happy: a base hit will often do the job. Think about what matters most to you in life: is it a lot of money or status? Or is it something more satisfying, and often just as if not more attainable, like freedom, loving relationships, or fulfillment? Is what you’re doing now a good way to get what you want? Or is there a better way? At more of a micro-level of "keep the big picture in mind", I often see talented wantrepreneurs get stuck in the weeds of lower-level optimizations, usually around technical design choices. They forget (or maybe subconsciously avoid) the higher-level and more important questions of customer development, user experience, and distribution. For example: “Are you solving a real problem?” or “Did you launch an MVP and what did your users think?” Adopt a growth mindset. Believe that you are capable of learning whatever you need to learn in order to do what you want to do. The pain of regret is worse than the pain of failure. I’ve noticed that fear of failure is the greatest thing holding people back from taking action towards their dreams. Unless failure means death in your case, a debilitating fear of failure is a surmountable mental block. You miss 100% of the shots you don't take. When all is said and done, we often regret the things we didn't do in life than the things we did. There’s more to life than just work. Blasphemous (at least among my social circle)! But the reality is that many of the dying regret having worked too much in their lives. As Miss Frizzle from The Magic Schoolbus says: "Take chances, make mistakes, get messy!" Original post

#reddit#retired#side

reddit

0

1

_saan•This week

Launching Wisdor: AI Adoption Consultancy for Businesses

Website: https://www.wisdor.dev LinkedIn: https://www.linkedin.com/company/wisdor/ Hi! I am here to use this forum to announce and promote the launch of Wisdor: A consultancy service for business owners looking to adopt AI in their workflows. Since the launch of LLMs like ChatGPT, the use of AI has become mainstream however, small to medium businesses are seem to be facing some challenges with the adoption of AI even when they are willing to do so. Wisdor aims to target the following main pain-points of your AI adoption journey: Helping you decide if you even need to invite the buzzwords in your house or not There are so many AI tools out in the market and it can be daunting to decide what exactly is it which you need AI tools aren’t magic boxes that can do everything off the shelf. They require customization and tailoring for specific use cases Even when you have scouted the tools that \\ may \\* help you, they are of no use if you cannot include them in your existing workflows Or you may have a use case that requires the development of an AI based tool from scratch and your team does not have the necessary expertise to do so Wisdor will help you on your journey supporting you from the initial discussions to development and then the adoption of modern automation tools to help ease out your workload and drive efficiency. So, if you are someone who can benefit from Wisdor’s services, ping away! If not, give a follow to the LinkedIn page. Cheers and happy building!!!

#reddit#launching#wisdor:

reddit

0

1

ondro949•This week

AI-Powered Business Analyst Tool Looking for Feedback

Hey r/sideproject! I’m excited to share a project I’ve been working on called Bianalytiq, a next-gen business intelligence platform designed to transform the way businesses interact with data through the power of AI. The Problem: SME companies struggle with data overload and the significant time investment required to generate actionable insights. Traditional data analysis methods are not only slow but often require extensive manual effort and are prone to errors. This makes it difficult for businesses to react quickly to new information and make informed decisions efficiently. Not everybody can write SQL or create/understand data dashboards.... AND - one big opportunity on market - non of the AI tools available on market offer reusable contexts focused on you as a company and your products. The Solution: Bianalytiq aims to solve these issues by automating tedious data analysis tasks and providing real-time insights. Here’s how: Reusable contexts: Let Bianalytiq learn everything about your company, your products, business model etc. - your company is your unique context. Autonomous AI Agents: Deploy AI agents that not only react to queries but proactively analyze data to uncover opportunities, tailored specifically to your business context. Real-Time Insights: With the use of Retrieval-Augmented Generation (RAG) technology, our platform delivers immediate, context-rich insights by dynamically accessing and analyzing connected databases and data warehouses. Integration with Existing Tools: Bianalytiq integrates seamlessly with popular tech stacks and communication platforms like Slack and Microsoft Teams, making it incredibly user-friendly and reducing the switch cost between applications. Why I’m Here: Before investing significant time and money I want to validate the product first and do pre-sale before releasing the MVP. I’ve developed a landing page for Bianalytiq and would love your feedback on both the service itself and the effectiveness of the landing page. Are the features presented clearly? Does the platform address the pain points you might experience in data analysis and decision-making processes? Here’s the link to the landing page: https://bianalytiq.com/ I appreciate any feedback or questions you have! Whether it's about the UI/UX of the site, the technical aspects of the service, or even the business model, I’m all ears. Your input will be invaluable :) Thanks for checking it out! https://preview.redd.it/t1dvp2q05dzc1.png?width=798&format=png&auto=webp&s=c7365b418abfc4d4260d9a23305ed3398e83c87b

#reddit#ai-powered#business

reddit

0

0

vsengar•This week

Introducing Stratify: Your Ultimate AI Strategy Builder for Business Success

Hello, I’m thrilled to announce the launch of my new startup, Stratify! 🔍 What is Stratify? Stratify is an AI Strategy Builder designed to help businesses of all sizes develop, implement, and optimize their strategic plans using cutting-edge artificial intelligence. Whether you're a startup looking to scale or an established company aiming to innovate, Stratify provides the tools and insights you need to stay ahead in today's competitive landscape. 🌟 Key Features: Automated Strategy Development: Leverage AI to analyze market trends, competitor data, and internal metrics to create comprehensive strategic plans tailored to your business goals. Real-Time Analytics & Insights: Monitor your strategy's performance with real-time data dashboards, enabling you to make informed decisions quickly. Scenario Planning: Use AI-driven simulations to forecast different business scenarios and understand potential outcomes, helping you prepare for uncertainties. Collaborative Tools: Facilitate team collaboration with integrated communication features, ensuring everyone is aligned and contributing to the strategy development process. Customizable Templates: Access a library of industry-specific strategy templates that can be customized to fit your unique business needs. 💡 Why Stratify? In today's fast-paced business environment, creating and adapting effective strategies can be challenging. Many companies struggle with data overload, lack of actionable insights, and inefficient planning processes. Stratify addresses these pain points by harnessing the power of AI to streamline strategy building, making it more efficient, data-driven, and adaptable. 🚀 Our Journey So Far: Founded: August 2024 Milestones Achieved: Developed and tested our MVP with a select group of beta users What's Next: Launching our public beta in Q4 2024 Expanding our feature set based on user feedback Growing our team with experts in AI, business strategy, and customer success 🤝 How You Can Help: We’re eager to connect with early adopters, business strategists, and industry experts who can benefit from or contribute to Stratify. Here’s how you can get involved: Join Our Beta Program: Be among the first to experience Stratify and provide valuable feedback. Share Your Insights: Help us refine our features by sharing your business strategy challenges and needs. Spread the Word: If you know someone who could benefit from an AI-driven strategy builder, please share our mission and be an affiliate to earn rewards! 🌐 Learn More: Visit our website at AI-Powered Brand Strategy & Content Creation | Stratify (brandprovoke.com) and follow us for the latest updates and insights. 🙏 Thank You! A heartfelt thank you to the Reddit community for your support and encouragement. We’re excited to embark on this journey and look forward to your feedback and suggestions! Looking forward to your thoughts and questions!

#reddit#introducing#stratify:

reddit

0

1

Content-Shopping8791•This week

Looking for Innovators to Join my Stealth-Mode AI and Automation Startup

Hi everyone, I’m currently working on building a stealth-mode startup that focuses on AI, automation, management consulting, and streamlining business processes. Right now, it’s just me working on this, and I’m looking for passionate, creative people to join me and help shape the future of the company. A bit about me: I’m from the UK and have a Business Management degree and an IT diploma, so I’ve got a good mix of business and tech knowledge to push this forward. I’m currently using tools like UiPath, Python, Make.com, Automation Anywhere, and others to create innovative solutions, but I’m not tied to these. I’m open to using any tools or technologies that fit the business and help us succeed. This is unpaid for now, but once we hit revenue targets, the plan is to transition into paid positions. If you’re excited about startups, innovation, and building something meaningful, this might be for you. I’m building AI-powered tools that solve real business problems, workflows to automate processes, and management consulting services to help businesses streamline and work smarter. It’s about combining tech innovation with business strategy to deliver something that really works. I’d love to work with people who have skills in things like Python, TensorFlow, UiPath, Automation Anywhere, web development (frontend, backend, or full-stack), or just a talent for improving workflows. If you’re great at problem-solving, strategy, or even just brainstorming new ideas, there’s a place for you. What’s in it for you? First off, you’ll get real-world experience in AI, automation, and consulting. You’ll also get the chance to help shape the company as part of the founding team and grow with it. Once the startup hits revenue goals, paid roles will follow. It’s flexible too, work remotely and set your own schedule. If this sounds interesting to you, just comment or send me a DM with a bit about your experience, any projects you’ve worked on, and how you think you could contribute to the startup. I’ll be running interviews soon to chat with people and see how we can work together. If you’re excited about joining a startup from the ground up, let’s connect. I’d love to hear from you.

#reddit#looking#innovators

reddit

0

1

cowanscorp•This week

I recreated a voice AI that 2x’d booked calls in 30 days for a business

I’ve been fascinated by AI and specifically how different businesses have leveraged it to eliminate time consuming tasks. I recently came across a case study where a voice agent helped a business double their booked calls and conversions in 30 days and wanted to try and recreate something similar. I’ve added the case study below along with a number to the demo voice agent I created to see if this is something people would really be interested in. This tech is improving really fast and I’m looking to dive deeper into this space. Case Study A family owned HVAC company was having challenges managing the volume of customer calls, including after hours and weekend calls, leading to missed opportunities and unmanaged leads. Building a call support team would have proved to be more expensive than they’d like. Solution With some help, the company implemented an AI system to autonomously handle calls, collect customer needs, and alert service technicians via SMS, with capabilities for live call transfers. Impact Within the first week, the company saw a 20% increase in bookings and conversions. The system's efficiency in capturing leads and managing tasks enabled the staff to handle more leads and outsource overflow. Details The AI integration included custom features like a Service Titan integration, live call transfers, SMS/email alerts, calendar and CRM integration, and Zapier automation. Results The company doubled its booked calls and conversions in 30 days through these AI call agents. With the average service visit in the U.S. being around $250, and the average unit install being around $4500 this quickly led to increased revenue as well as time savings and reduced churn. Here’s the number to the demo agent I created: +1 (714) 475-7285 I’d love to hear some honest thoughts on it and what industry you think could benefit the most from something like this.

#reddit#recreated#voice

reddit

0

1

Mammoth_Sherbet7689•This week

I recreated an AI Phone Agent that saved $20,000 in lost revenue in 30 days for a business

I've been intrigued by AI and its ability to help businesses streamline time-consuming tasks. Recently, I discovered a case study where a voice agent was able to earn a business $20,000 in booked calls in a month. Below, I've shared the case study and a demo number for a voice agent I developed. This technology is advancing rapidly, and I want to explore its potential further. Case Study A family-owned HVAC company struggled with managing a high volume of customer calls, including after-hours and weekend inquiries, resulting in missed opportunities and unmanaged leads. Hiring a dedicated call support team was not cost-effective. Solution The company implemented an AI system to handle calls autonomously, gather customer information, and notify service technicians via SMS, with options for live call transfers. Details The AI integration featured custom capabilities such as Service Titan integration, live call transfers, SMS/email alerts, calendar and CRM integration, and Zapier automation. Results In the first week, the company experienced a 20% increase in bookings and conversions. The system efficiently captured leads and managed tasks, enabling staff to handle more inquiries and outsource overflow. Within 30 days, the company saved $20,000 in lost revenue due to the elimination of calls that went to voicemail, or lost leads. The voice agent's ability to answer calls 24/7 led to significant revenue growth, time savings, and reduced churn. Here's the demo number for the voice agent I created: +1 (651) 372 2045 I believe this tech has strong use cases in a variety of industries, from home service, to dental clinics, to wedding photographers. This article studied the effect of missed calls in different businesses, if you're interested in learning more. I'd love to hear your thoughts and industries you think this could be the most beneficial for. Thank you!

#reddit#recreated#phone

reddit

0

1

Will_fever•This week

I recreated an AI phone calling agent that increased booked calls by 30% for a plumbing business in 30 days

AI has always intrigued me, especially when it comes to automating repetitive tasks and streamlining business operations. Recently, I found a compelling case study about a voice agent that significantly enhanced customer service and lead capture for a plumbing company. Motivated by the potential of this technology, I decided to build a similar system to see how it could be adapted for other industries. I’ve added the case study below along with a number to the demo voice agent I created to see if this is something people would really be interested in. AI technology is advancing rapidly, and I’m excited to dive deeper into this space. Case Study A family-owned plumbing business was facing challenges managing a high volume of customer calls. They were missing potential leads, particularly during after-hours and weekends, which meant lost revenue opportunities. Hiring a dedicated call support team was considered but deemed too expensive and hard to scale. Solution To solve these issues, the company deployed an AI-powered voice agent capable of handling calls autonomously. The system collected essential customer information, identified service needs, and sent real-time alerts to service technicians via SMS. It also had the ability to transfer calls to human agents if necessary, ensuring a seamless experience for customers. Impact The AI voice agent quickly proved its worth by streamlining call management and improving response times. With the AI handling routine inquiries and initial call filtering, the plumbing business saw a noticeable improvement in how quickly they could respond to customer needs. Details The AI-powered voice agent included several advanced features designed to optimize customer service: Answer Calls Anytime: Ensured every call received a friendly and professional response, regardless of the time of day. Spot Emergencies Fast: Quickly identified high-priority issues that required urgent attention. Collect Important Info: Accurately recorded critical customer details to facilitate seamless follow-ups and service scheduling. Send Alerts Right Away: Immediately notified service technicians about emergencies, enabling faster response times. Live Transfers: Live call transfer options when human assistance was needed. Results The AI-powered voice agent delivered measurable improvements across key performance metrics: 100% Call Answer Rate: No missed calls ensured that every customer inquiry was addressed promptly. 5-minute Emergency Response Time: The average response time for urgent calls was reduced significantly. 30% Increase in Lead Capture: The business saw more qualified leads, improving their chances of conversion. 25% Improvement in Resource Efficiency: Better allocation of resources allowed the team to focus on high-priority tasks. By implementing the AI-powered voice agent, the plumbing business enhanced its ability to capture more leads and provide better service to its customers. The improved call handling efficiency helped reduce missed opportunities and boosted overall customer satisfaction. Here’s the number to the demo agent I created: +1 (210) 405-0982 I’d love to hear some honest thoughts on it and which industries you think could benefit the most from this technology.

#reddit#recreated#phone

reddit

0

1

cowanscorp•This week

I recreated a voice AI that 2x’d booked calls in 30 days for a business

I’ve been fascinated by AI and specifically how different businesses have leveraged it to eliminate time consuming tasks. I recently came across a case study where a voice agent helped a business double their booked calls and conversions in 30 days and wanted to try and recreate something similar. I’ve added the case study below along with a number to the demo voice agent I created to see if this is something people would really be interested in. This tech is improving really fast and I’m looking to dive deeper into this space. Case Study A family owned HVAC company was having challenges managing the volume of customer calls, including after hours and weekend calls, leading to missed opportunities and unmanaged leads. Building a call support team would have proved to be more expensive than they’d like. Solution With some help, the company implemented an AI system to autonomously handle calls, collect customer needs, and alert service technicians via SMS, with capabilities for live call transfers. Impact Within the first week, the company saw a 20% increase in bookings and conversions. The system's efficiency in capturing leads and managing tasks enabled the staff to handle more leads and outsource overflow. Details The AI integration included custom features like a Service Titan integration, live call transfers, SMS/email alerts, calendar and CRM integration, and Zapier automation. Results The company doubled its booked calls and conversions in 30 days through these AI call agents. With the average service visit in the U.S. being around $250, and the average unit install being around $4500 this quickly led to increased revenue as well as time savings and reduced churn. Here’s the number to the demo agent I created: +1 (714) 475-7285 I’d love to hear some honest thoughts on it and what industry you think could benefit the most from something like this.

#reddit#recreated#voice

reddit

0

1

Will_fever•This week

I recreated an AI phone calling agent that increased booked calls by 30% for a plumbing business in 30 days

AI has always intrigued me, especially when it comes to automating repetitive tasks and streamlining business operations. Recently, I found a compelling case study about a voice agent that significantly enhanced customer service and lead capture for a plumbing company. Motivated by the potential of this technology, I decided to build a similar system to see how it could be adapted for other industries. I’ve added the case study below along with a number to the demo voice agent I created to see if this is something people would really be interested in. AI technology is advancing rapidly, and I’m excited to dive deeper into this space. Case Study A family-owned plumbing business was facing challenges managing a high volume of customer calls. They were missing potential leads, particularly during after-hours and weekends, which meant lost revenue opportunities. Hiring a dedicated call support team was considered but deemed too expensive and hard to scale. Solution To solve these issues, the company deployed an AI-powered voice agent capable of handling calls autonomously. The system collected essential customer information, identified service needs, and sent real-time alerts to service technicians via SMS. It also had the ability to transfer calls to human agents if necessary, ensuring a seamless experience for customers. Impact The AI voice agent quickly proved its worth by streamlining call management and improving response times. With the AI handling routine inquiries and initial call filtering, the plumbing business saw a noticeable improvement in how quickly they could respond to customer needs. Details The AI-powered voice agent included several advanced features designed to optimize customer service: Answer Calls Anytime: Ensured every call received a friendly and professional response, regardless of the time of day. Spot Emergencies Fast: Quickly identified high-priority issues that required urgent attention. Collect Important Info: Accurately recorded critical customer details to facilitate seamless follow-ups and service scheduling. Send Alerts Right Away: Immediately notified service technicians about emergencies, enabling faster response times. Live Transfers: Live call transfer options when human assistance was needed. Results The AI-powered voice agent delivered measurable improvements across key performance metrics: 100% Call Answer Rate: No missed calls ensured that every customer inquiry was addressed promptly. 5-minute Emergency Response Time: The average response time for urgent calls was reduced significantly. 30% Increase in Lead Capture: The business saw more qualified leads, improving their chances of conversion. 25% Improvement in Resource Efficiency: Better allocation of resources allowed the team to focus on high-priority tasks. By implementing the AI-powered voice agent, the plumbing business enhanced its ability to capture more leads and provide better service to its customers. The improved call handling efficiency helped reduce missed opportunities and boosted overall customer satisfaction. Here’s the number to the demo agent I created: +1 (210) 405-0982 I’d love to hear some honest thoughts on it and which industries you think could benefit the most from this technology.

#reddit#recreated#phone

reddit

0

1

Mammoth_Sherbet7689•This week

I recreated an AI Phone Agent that saved $20,000 in lost revenue in 30 days for a business

I've been intrigued by AI and its ability to help businesses streamline time-consuming tasks. Recently, I discovered a case study where a voice agent was able to earn a business $20,000 in booked calls in a month. Below, I've shared the case study and a demo number for a voice agent I developed. This technology is advancing rapidly, and I want to explore its potential further. Case Study A family-owned HVAC company struggled with managing a high volume of customer calls, including after-hours and weekend inquiries, resulting in missed opportunities and unmanaged leads. Hiring a dedicated call support team was not cost-effective. Solution The company implemented an AI system to handle calls autonomously, gather customer information, and notify service technicians via SMS, with options for live call transfers. Details The AI integration featured custom capabilities such as Service Titan integration, live call transfers, SMS/email alerts, calendar and CRM integration, and Zapier automation. Results In the first week, the company experienced a 20% increase in bookings and conversions. The system efficiently captured leads and managed tasks, enabling staff to handle more inquiries and outsource overflow. Within 30 days, the company saved $20,000 in lost revenue due to the elimination of calls that went to voicemail, or lost leads. The voice agent's ability to answer calls 24/7 led to significant revenue growth, time savings, and reduced churn. Here's the demo number for the voice agent I created: +1 (651) 372 2045 I believe this tech has strong use cases in a variety of industries, from home service, to dental clinics, to wedding photographers. This article studied the effect of missed calls in different businesses, if you're interested in learning more. I'd love to hear your thoughts and industries you think this could be the most beneficial for. Thank you!

#reddit#recreated#phone

reddit

0

1

Either_Discussion635•This week

I acquired a SaaS for ~5 figures to solve my content problem

In 2023 I bought a SaaS called Cuppa AI. I actually found the product on twitter, run by a very talented engineer in the UK.  I’ve spent tens of thousands of dollars on content for various media companies. In one consumer health company, it cost us around $200-$500 for each SEO optimized article. This adds up pretty quickly. Not forgetting the 20 hours of edits! This isn’t just an isolated problem for a single company. It’s industry wide and affects small business + agency owners alike. I spent over a decade in media, and have seen many agency founders complain about long lead times and high costs for low output.  This is an issue. Large swathes of would-be customers that prefer to consume content before buying are being ignored - either because it takes too long or costs too much for founders to scale this channel.   I eventually became tired of the media content game in 2022 and looked into using SaaS to solve my previous life’s challenges. I started building, acquiring and scaling a portfolio of products that I found useful in my day to day. But the content issue was still there.  So I started to look for ways to reduce the time + cost content burden for my own portfolio.   I initially discovered Cuppa using it for my own personal pains of content research, editing, publishing, and scaling. But then I saw potential. I wanted to turn it into an end to end solution for the content gap that myself and other business owners weren’t taking advantage of because of time, cost, or other priorities.  I sent a DM. Then a few calls later, I acquired it in June 2023.  I chose cuppa vs other competing products for a few reasons:  The founder gave excellent support during and post acquisition  It already had a large, loyal existing user base I’d personally used it and solved a pain with it. I saw the potential to solve many others for more people like me  The founder has put a ton of quality and care into it. There wasn’t a risk of picking up a patchy product, plus it already had great social distribution  It naturally fits my expertise from the ‘other side’. I was the original customer of it, so I knew I could evolve it with features that could create content at scale without losing the human touch  Since then we’ve added a lot of new stuff: Chat with articles Image generation for articles API keys to reduce cost Brand / persona voice custom prompts  Month on month iterative content improvement  Full stack content team that blends AI and human editors for agencies I’m still in full build mode with the team. I want to take it to a place where agencies and SMB owners can trust the AI + human content model enough to see this product as a no-brainer for their biz. I don’t believe in AI slop - there’s enough of that out there - I DO believe in using AI to do the grunt work, but to always have that human element a machine can’t quite mimic.  We have a lot more to get through, but I’m very excited about it. View of the done for you content workflow

#reddit#acquired#saas

reddit

0

1

HenryObj•This week

I built an AI Stock Analysis Tool

Hi Reddit, TL;DR: I am sharing the tool I built to assist me with my investments I have been investing for over a decade, and I have always struggled with: Putting the time to do actual research Trusting analyst’s recommendations To \ invest \ we want to make sure that the price is right and the company will keep improving. How do we know that “the price is right?” How can we predict that the company will perform better in the future? To answer the above, we have to look at the company’s financials and their trends. We have to compare the company with its peers/competitors. We should understand its business model, the sector and geography the company evolves in and the perspective of the economy in general. We can also look at additional signals like insiders selling or buying. Just for one investment, this is already a lot of work. And a work that we need to repeat every time there is a significant change - for example, a significant price change from our last analysis or new quarterly results, etc. To automate all the above, I have built a stock analysis tool and have been using it the past years for my own investments. I have been adding LLMs agents (GPT 4o & Claude 3.5) to perform the qualitative analysis. Recently, I decided to share it and keep on building it in public. In this initial version, you can get the summary of the stock analysis my model generates. For now, it covers most of the S&P and Nasdaq stocks. Here is the link 👉 https://undervalued.ai If you are into investing yourself, please feel free to reach out. I would love to get your feedback and know more about your methodology.

#reddit#built#stock

reddit

0

0.667

milaworld•This week

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

#reddit#stability#ai’s

reddit

0

0.667

milaworld•This week

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

#reddit#stability#ai’s

reddit

0

1

SemperZero•This week

[D] What are some good advanced platforms?

Hey. I'm 27 and I think I got most of the basics for ML. I'm very good at math, I understand statistics and probability quite deep, worked on research projects by myself, for which I had to build models on my own. Not really complex, but still requiring creativity and a good understanding of basic concepts. I will soon start a data science job at a FAANG company and I want to further improve my skills and use their resources to the fullest, but I'm not really sure where to go from here in terms of learning. Could you help me with some more advanced materials/forums for ML research/place with good papers/place with good articles? I'd also like to study the very best and see the way they code and explain advanced concepts (like Andrej Karpathy) where can I find them?? is there a Twitch for challenger level AI researchers streaming live processes? Or videos showing the entire project flow (how they do data visualizations, mining, choosing models, tuning, etc) like top digital artists show the highlights or the entire speed-up of their painting processes? Here's a list all of my projects to get a general idea of my level and where I'm at: calculating the distance between hundreds of 42.000 feature objects (containing categorical, strings, numbers, hashes, booleans as variables) and then clustering. with some vector processing and a neural network implemented from scratch in C some models like ARIMA (together with linear regression) combining a FFT with a neural network for a 42d wave classification T-SNE to split dataset into 2d grids -> Kullback–Leibler on grids for distance -> DBSCAN/KMEANS for clustering genetic algorithms for hyperparameter optimizations and reinforcement learning (neuro evolution) DBSCAN -> Levenberg-Marquardt for polynomial coefficients-> neural network predicting the coefficients based on different parameters playing with instance segmentation and some algorithms to synchronize a color and a depth camera simulations/statistics/probabilities for video games a lot of visualizations and data mining for patterns As you can see there is no LLM/ Generative AI/ Computer Vision stuff, which I would like to get into. I'm also not 100% sure what else would be nice to learn in general. I know most of the basic procedures for training, balancing datasets, avoid overfit, computing error plots, comparing models, etc and I'm familiar with most of math (not insanely advanced) used in ML. I didn't read many papers, but holy ... most of them are so unreadable and filled with pompous nonsense that 99% of the effort is de-obfuscating the bs and reading for so long just to figure out how the input is encoded, what's the output, and what's the model. Where can I find good, readable, structured papers which are actually on point? I'm from Eastern Europe and most of my learning has been done by my self after high school, the education quality is close to zero in the universities here and I never had any mentors at the jobs I worked. There's no research in this country, and getting to work on these projects was insanely hard, some of them being done in my free time or for free just to get experience... Fortunately after a lot of hard work I got into FAANG, and I hope things will be better here. Most of what I've learned has been from very fragmented places on the internet, and now I'm looking for centralized places and communities of top quality content. TL;DR: sorry for the long rambling. had to order my thoughts and figure what i actually want: Looking for top tier AI researchers showcasing their work processes, places with clear papers/articles, tips for someone who's no longer a very beginner, and other communities like this.

#reddit#some#good

reddit

0

1

Flaky_Suit_8665•This week

[D] The current and future state of AI/ML is shockingly demoralizing with little hope of redemption

I recently encountered the PaLM (Scaling Language Modeling with Pathways) paper from Google Research and it opened up a can of worms of ideas I’ve felt I’ve intuitively had for a while, but have been unable to express – and I know I can’t be the only one. Sometimes I wonder what the original pioneers of AI – Turing, Neumann, McCarthy, etc. – would think if they could see the state of AI that we’ve gotten ourselves into. 67 authors, 83 pages, 540B parameters in a model, the internals of which no one can say they comprehend with a straight face, 6144 TPUs in a commercial lab that no one has access to, on a rig that no one can afford, trained on a volume of data that a human couldn’t process in a lifetime, 1 page on ethics with the same ideas that have been rehashed over and over elsewhere with no attempt at a solution – bias, racism, malicious use, etc. – for purposes that who asked for? When I started my career as an AI/ML research engineer 2016, I was most interested in two types of tasks – 1.) those that most humans could do but that would universally be considered tedious and non-scalable. I’m talking image classification, sentiment analysis, even document summarization, etc. 2.) tasks that humans lack the capacity to perform as well as computers for various reasons – forecasting, risk analysis, game playing, and so forth. I still love my career, and I try to only work on projects in these areas, but it’s getting harder and harder. This is because, somewhere along the way, it became popular and unquestionably acceptable to push AI into domains that were originally uniquely human, those areas that sit at the top of Maslows’s hierarchy of needs in terms of self-actualization – art, music, writing, singing, programming, and so forth. These areas of endeavor have negative logarithmic ability curves – the vast majority of people cannot do them well at all, about 10% can do them decently, and 1% or less can do them extraordinarily. The little discussed problem with AI-generation is that, without extreme deterrence, we will sacrifice human achievement at the top percentile in the name of lowering the bar for a larger volume of people, until the AI ability range is the norm. This is because relative to humans, AI is cheap, fast, and infinite, to the extent that investments in human achievement will be watered down at the societal, educational, and individual level with each passing year. And unlike AI gameplay which superseded humans decades ago, we won’t be able to just disqualify the machines and continue to play as if they didn’t exist. Almost everywhere I go, even this forum, I encounter almost universal deference given to current SOTA AI generation systems like GPT-3, CODEX, DALL-E, etc., with almost no one extending their implications to its logical conclusion, which is long-term convergence to the mean, to mediocrity, in the fields they claim to address or even enhance. If you’re an artist or writer and you’re using DALL-E or GPT-3 to “enhance” your work, or if you’re a programmer saying, “GitHub Co-Pilot makes me a better programmer?”, then how could you possibly know? You’ve disrupted and bypassed your own creative process, which is thoughts -> (optionally words) -> actions -> feedback -> repeat, and instead seeded your canvas with ideas from a machine, the provenance of which you can’t understand, nor can the machine reliably explain. And the more you do this, the more you make your creative processes dependent on said machine, until you must question whether or not you could work at the same level without it. When I was a college student, I often dabbled with weed, LSD, and mushrooms, and for a while, I thought the ideas I was having while under the influence were revolutionary and groundbreaking – that is until took it upon myself to actually start writing down those ideas and then reviewing them while sober, when I realized they weren’t that special at all. What I eventually determined is that, under the influence, it was impossible for me to accurately evaluate the drug-induced ideas I was having because the influencing agent the generates the ideas themselves was disrupting the same frame of reference that is responsible evaluating said ideas. This is the same principle of – if you took a pill and it made you stupider, would even know it? I believe that, especially over the long-term timeframe that crosses generations, there’s significant risk that current AI-generation developments produces a similar effect on humanity, and we mostly won’t even realize it has happened, much like a frog in boiling water. If you have children like I do, how can you be aware of the the current SOTA in these areas, project that 20 to 30 years, and then and tell them with a straight face that it is worth them pursuing their talent in art, writing, or music? How can you be honest and still say that widespread implementation of auto-correction hasn’t made you and others worse and worse at spelling over the years (a task that even I believe most would agree is tedious and worth automating). Furthermore, I’ve yet to set anyone discuss the train – generate – train - generate feedback loop that long-term application of AI-generation systems imply. The first generations of these models were trained on wide swaths of web data generated by humans, but if these systems are permitted to continually spit out content without restriction or verification, especially to the extent that it reduces or eliminates development and investment in human talent over the long term, then what happens to the 4th or 5th generation of models? Eventually we encounter this situation where the AI is being trained almost exclusively on AI-generated content, and therefore with each generation, it settles more and more into the mean and mediocrity with no way out using current methods. By the time that happens, what will we have lost in terms of the creative capacity of people, and will we be able to get it back? By relentlessly pursuing this direction so enthusiastically, I’m convinced that we as AI/ML developers, companies, and nations are past the point of no return, and it mostly comes down the investments in time and money that we’ve made, as well as a prisoner’s dilemma with our competitors. As a society though, this direction we’ve chosen for short-term gains will almost certainly make humanity worse off, mostly for those who are powerless to do anything about it – our children, our grandchildren, and generations to come. If you’re an AI researcher or a data scientist like myself, how do you turn things back for yourself when you’ve spent years on years building your career in this direction? You’re likely making near or north of $200k annually TC and have a family to support, and so it’s too late, no matter how you feel about the direction the field has gone. If you’re a company, how do you standby and let your competitors aggressively push their AutoML solutions into more and more markets without putting out your own? Moreover, if you’re a manager or thought leader in this field like Jeff Dean how do you justify to your own boss and your shareholders your team’s billions of dollars in AI investment while simultaneously balancing ethical concerns? You can’t – the only answer is bigger and bigger models, more and more applications, more and more data, and more and more automation, and then automating that even further. If you’re a country like the US, how do responsibly develop AI while your competitors like China single-mindedly push full steam ahead without an iota of ethical concern to replace you in numerous areas in global power dynamics? Once again, failing to compete would be pre-emptively admitting defeat. Even assuming that none of what I’ve described here happens to such an extent, how are so few people not taking this seriously and discounting this possibility? If everything I’m saying is fear-mongering and non-sense, then I’d be interested in hearing what you think human-AI co-existence looks like in 20 to 30 years and why it isn’t as demoralizing as I’ve made it out to be. ​ EDIT: Day after posting this -- this post took off way more than I expected. Even if I received 20 - 25 comments, I would have considered that a success, but this went much further. Thank you to each one of you that has read this post, even more so if you left a comment, and triply so for those who gave awards! I've read almost every comment that has come in (even the troll ones), and am truly grateful for each one, including those in sharp disagreement. I've learned much more from this discussion with the sub than I could have imagined on this topic, from so many perspectives. While I will try to reply as many comments as I can, the sheer comment volume combined with limited free time between work and family unfortunately means that there are many that I likely won't be able to get to. That will invariably include some that I would love respond to under the assumption of infinite time, but I will do my best, even if the latency stretches into days. Thank you all once again!

#reddit#current#future

reddit

0

0.667

milaworld•This week

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

#reddit#stability#ai’s

reddit

0

0

wildekans•This week

[D] Accessibility of Basic Models to Non-Technicals

Hello /r/machinelearning! I'm doing some research on easily generated models by non-technical/statistical people. It would be awesome if some of you could answer a quick questionnaire: If you're a machine learning developer/data scientist etc.: a) Has your manager/product lead etc. ever insist that you build a model on a correlation you felt wasn't there? b) Do you think if that people had a way to verify the lack of correlation through a naive model (random forest, svc, etc.) that it would have changed the situation? (Or, if you were able to show them the results) c) Would you want this technology for yourself, or wish that your company would have access to it? If you're a non-technical person (small business developer, student, non-tech entrepreneur, etc.): a) Have you ever not pursued a potential machine learning/data solution or feature because you weren't willing to invest the resources to see if it was viable? b) Would being able to verify correlations in your data (or lack thereof!) entice you to pursue possible machine learning solutions? c) Even if your previous answers were no, would you be interested in having this technology? Thanks in advance for all of the responses, I will personally read and respond to each one of you thoughtful enough to give me a response. Also, I hope this post will spark an interesting conversation about the barrier of entry to AI/machine learning.

#reddit#accessibility#basic

reddit

0

0.333

MLstartupLondon•This week

looking for ML aficionado in London for great chats and maybe a startup

TL;DR? Here's the gist: Me: 3 startups under my belt. Started as a programmer, then trainer, then entrepreneur, now CTO & Board member for a leading customer insight company part of large bank. Large system and infrastructure specialist. Extensive & practical experience in raising funds and successfully managing both startup and established businesses. Fascinated by the power of data. Can't imagine myself spending the rest of my life being a cog in the machine. You: Machine learning specialist, programmer, analyst, understands how to navigate and crunch large datasets, from BI to predictive analytics. Interested in implementing applications from fraud detection to margin improvements through better clustering regardless of industry. Fascinated by the power of data. Can't imagine himself spending the rest of his or her life being a cog in the machine. The startup: The core idea it to build platforms and systems around the progressively larger datasets held by various sized companies, helping them solve big issues - cost reduction, profitability and reducing risk. I’m an infrastructure and software specialist and have access to 1) systems, 2) datasets 3) extensive practical in certain industry segments, namely web-scale companies and tier 1 retailers. This project is in the very early planning stages. I'm looking forward to discuss the form it could take with like-minded individuals but with complementary skills sets, namely: predictive analytics & AI as it applies to machine learning on large datasets. Want more specifics ideas? I have plenty of these, but I’m sure you do to, so let’s meet face to face and discuss them. Ultimately the goal is to crystallize on a specific concept, develop together a minimum viable product and get the company bootstrapped or angel-funded (something I also have plenty of experience with), all via a lean startup model. My philosophy on startups: Startups built in one’s free time often fail because they drag on, ending up as little more than side projects you can’t quite get rid of (due to co-founder guilt, or perhaps the little money they bring in every month). The core idea for this project is based on lean, that is, to launch a minimum viable product as early as possible. Getting feedback. Measuring results (important!). Pivot if it’s not working. This helps tremendously in staying motivated, limits the dreaded paralyzing fear of failure, and more importantly, keep the time from inception to first client/funding to a minimum. If it sounds interesting please message me and we can exchange contact details! Worst that can happen is we have a great chat!

#reddit#looking#aficionado

reddit

0

1

timscarfe•This week

[D] Gary Marcus and Luis Lamb -- discussion of AGI and Neurosymbolic methods

https://youtu.be/nhUt6mKCPf8 Pod: https://anchor.fm/machinelearningstreettalk/episodes/54-Gary-Marcus-and-Luis-Lamb---Neurosymbolic-models-e125495 Professor Gary Marcus is a scientist, best-selling author, and entrepreneur. He is Founder and CEO of Robust.AI, and was Founder and CEO of Geometric Intelligence, a machine learning company acquired by Uber in 2016. Gary said in his recent next decade paper that — without us, or other creatures like us, the world would continue to exist, but it would not be described, distilled, or understood. Human lives are filled with abstraction and causal description. This is so powerful. Francois Chollet the other week said that intelligence is literally sensitivity to abstract analogies, and that is all there is to it. It's almost as if one of the most important features of intelligence is to be able to abstract knowledge, this drives the generalisation which will allow you to mine previous experience to make sense of many future novel situations. Also joining us today is Professor Luis Lamb — Secretary of Innovation for Science and Technology of the State of Rio Grande do Sul, Brazil. His Research Interests are Machine Learning and Reasoning, Neuro-Symbolic Computing, Logic in Computation and Artificial Intelligence, Cognitive and Neural Computation and also AI Ethics and Social Computing. Luis released his new paper Neurosymbolic AI: the third wave at the end of last year. It beautifully articulated the key ingredients needed in the next generation of AI systems, integrating type 1 and type 2 approaches to AI and it summarises all the of the achievements of the last 20 years of research. We cover a lot of ground in today's show. Explaining the limitations of deep learning, Rich Sutton's the bitter lesson and "reward is enough", and the semantic foundation which is required for us to build robust AI.

#reddit#gary#marcus

reddit

0

0.765

hardmaru•This week

Interview with Juergen Schmidhuber, renowned ‘Father Of Modern AI’, says his life’s work won't lead to dystopia.

Schmidhuber interview expressing his views on the future of AI and AGI. Original source. I think the interview is of interest to r/MachineLearning, and presents an alternate view, compared to other influential leaders in AI. Juergen Schmidhuber, Renowned 'Father Of Modern AI,' Says His Life’s Work Won't Lead To Dystopia May 23, 2023. Contributed by Hessie Jones. Amid the growing concern about the impact of more advanced artificial intelligence (AI) technologies on society, there are many in the technology community who fear the implications of the advancements in Generative AI if they go unchecked. Dr. Juergen Schmidhuber, a renowned scientist, artificial intelligence researcher and widely regarded as one of the pioneers in the field, is more optimistic. He declares that many of those who suddenly warn against the dangers of AI are just seeking publicity, exploiting the media’s obsession with killer robots which has attracted more attention than “good AI” for healthcare etc. The potential to revolutionize various industries and improve our lives is clear, as are the equal dangers if bad actors leverage the technology for personal gain. Are we headed towards a dystopian future, or is there reason to be optimistic? I had a chance to sit down with Dr. Juergen Schmidhuber to understand his perspective on this seemingly fast-moving AI-train that will leap us into the future. As a teenager in the 1970s, Juergen Schmidhuber became fascinated with the idea of creating intelligent machines that could learn and improve on their own, becoming smarter than himself within his lifetime. This would ultimately lead to his groundbreaking work in the field of deep learning. In the 1980s, he studied computer science at the Technical University of Munich (TUM), where he earned his diploma in 1987. His thesis was on the ultimate self-improving machines that, not only, learn through some pre-wired human-designed learning algorithm, but also learn and improve the learning algorithm itself. Decades later, this became a hot topic. He also received his Ph.D. at TUM in 1991 for work that laid some of the foundations of modern AI. Schmidhuber is best known for his contributions to the development of recurrent neural networks (RNNs), the most powerful type of artificial neural network that can process sequential data such as speech and natural language. With his students Sepp Hochreiter, Felix Gers, Alex Graves, Daan Wierstra, and others, he published architectures and training algorithms for the long short-term memory (LSTM), a type of RNN that is widely used in natural language processing, speech recognition, video games, robotics, and other applications. LSTM has become the most cited neural network of the 20th century, and Business Week called it "arguably the most commercial AI achievement." Throughout his career, Schmidhuber has received various awards and accolades for his groundbreaking work. In 2013, he was awarded the Helmholtz Prize, which recognizes significant contributions to the field of machine learning. In 2016, he was awarded the IEEE Neural Network Pioneer Award for "pioneering contributions to deep learning and neural networks." The media have often called him the “father of modern AI,” because the most cited neural networks all build on his lab’s work. He is quick to point out, however, that AI history goes back centuries. Despite his many accomplishments, at the age of 60, he feels mounting time pressure towards building an Artificial General Intelligence within his lifetime and remains committed to pushing the boundaries of AI research and development. He is currently director of the KAUST AI Initiative, scientific director of the Swiss AI Lab IDSIA, and co-founder and chief scientist of AI company NNAISENSE, whose motto is "AI∀" which is a math-inspired way of saying "AI For All." He continues to work on cutting-edge AI technologies and applications to improve human health and extend human lives and make lives easier for everyone. The following interview has been edited for clarity. Jones: Thank you Juergen for joining me. You have signed letters warning about AI weapons. But you didn't sign the recent publication, "Pause Gigantic AI Experiments: An Open Letter"? Is there a reason? Schmidhuber: Thank you Hessie. Glad to speak with you. I have realized that many of those who warn in public against the dangers of AI are just seeking publicity. I don't think the latest letter will have any significant impact because many AI researchers, companies, and governments will ignore it completely. The proposal frequently uses the word "we" and refers to "us," the humans. But as I have pointed out many times in the past, there is no "we" that everyone can identify with. Ask 10 different people, and you will hear 10 different opinions about what is "good." Some of those opinions will be completely incompatible with each other. Don't forget the enormous amount of conflict between the many people. The letter also says, "If such a pause cannot be quickly put in place, governments should intervene and impose a moratorium." The problem is that different governments have ALSO different opinions about what is good for them and for others. Great Power A will say, if we don't do it, Great Power B will, perhaps secretly, and gain an advantage over us. The same is true for Great Powers C and D. Jones: Everyone acknowledges this fear surrounding current generative AI technology. Moreover, the existential threat of this technology has been publicly acknowledged by Sam Altman, CEO of OpenAI himself, calling for AI regulation. From your perspective, is there an existential threat? Schmidhuber: It is true that AI can be weaponized, and I have no doubt that there will be all kinds of AI arms races, but AI does not introduce a new quality of existential threat. The threat coming from AI weapons seems to pale in comparison to the much older threat from nuclear hydrogen bombs that don’t need AI at all. We should be much more afraid of half-century-old tech in the form of H-bomb rockets. The Tsar Bomba of 1961 had almost 15 times more destructive power than all weapons of WW-II combined. Despite the dramatic nuclear disarmament since the 1980s, there are still more than enough nuclear warheads to wipe out human civilization within two hours, without any AI I’m much more worried about that old existential threat than the rather harmless AI weapons. Jones: I realize that while you compare AI to the threat of nuclear bombs, there is a current danger that a current technology can be put in the hands of humans and enable them to “eventually” exact further harms to individuals of group in a very precise way, like targeted drone attacks. You are giving people a toolset that they've never had before, enabling bad actors, as some have pointed out, to be able to do a lot more than previously because they didn't have this technology. Schmidhuber: Now, all that sounds horrible in principle, but our existing laws are sufficient to deal with these new types of weapons enabled by AI. If you kill someone with a gun, you will go to jail. Same if you kill someone with one of these drones. Law enforcement will get better at understanding new threats and new weapons and will respond with better technology to combat these threats. Enabling drones to target persons from a distance in a way that requires some tracking and some intelligence to perform, which has traditionally been performed by skilled humans, to me, it seems is just an improved version of a traditional weapon, like a gun, which is, you know, a little bit smarter than the old guns. But, in principle, all of that is not a new development. For many centuries, we have had the evolution of better weaponry and deadlier poisons and so on, and law enforcement has evolved their policies to react to these threats over time. So, it's not that we suddenly have a new quality of existential threat and it's much more worrisome than what we have had for about six decades. A large nuclear warhead doesn’t need fancy face recognition to kill an individual. No, it simply wipes out an entire city with ten million inhabitants. Jones: The existential threat that’s implied is the extent to which humans have control over this technology. We see some early cases of opportunism which, as you say, tends to get more media attention than positive breakthroughs. But you’re implying that this will all balance out? Schmidhuber: Historically, we have a long tradition of technological breakthroughs that led to advancements in weapons for the purpose of defense but also for protection. From sticks, to rocks, to axes to gunpowder to cannons to rockets… and now to drones… this has had a drastic influence on human history but what has been consistent throughout history is that those who are using technology to achieve their own ends are themselves, facing the same technology because the opposing side is learning to use it against them. And that's what has been repeated in thousands of years of human history and it will continue. I don't see the new AI arms race as something that is remotely as existential a threat as the good old nuclear warheads. You said something important, in that some people prefer to talk about the downsides rather than the benefits of this technology, but that's misleading, because 95% of all AI research and AI development is about making people happier and advancing human life and health. Jones: Let’s touch on some of those beneficial advances in AI research that have been able to radically change present day methods and achieve breakthroughs. Schmidhuber: All right! For example, eleven years ago, our team with my postdoc Dan Ciresan was the first to win a medical imaging competition through deep learning. We analyzed female breast cells with the objective to determine harmless cells vs. those in the pre-cancer stage. Typically, a trained oncologist needs a long time to make these determinations. Our team, who knew nothing about cancer, were able to train an artificial neural network, which was totally dumb in the beginning, on lots of this kind of data. It was able to outperform all the other methods. Today, this is being used not only for breast cancer, but also for radiology and detecting plaque in arteries, and many other things. Some of the neural networks that we have developed in the last 3 decades are now prevalent across thousands of healthcare applications, detecting Diabetes and Covid-19 and what not. This will eventually permeate across all healthcare. The good consequences of this type of AI are much more important than the click-bait new ways of conducting crimes with AI. Jones: Adoption is a product of reinforced outcomes. The massive scale of adoption either leads us to believe that people have been led astray, or conversely, technology is having a positive effect on people’s lives. Schmidhuber: The latter is the likely case. There's intense commercial pressure towards good AI rather than bad AI because companies want to sell you something, and you are going to buy only stuff you think is going to be good for you. So already just through this simple, commercial pressure, you have a tremendous bias towards good AI rather than bad AI. However, doomsday scenarios like in Schwarzenegger movies grab more attention than documentaries on AI that improve people’s lives. Jones: I would argue that people are drawn to good stories – narratives that contain an adversary and struggle, but in the end, have happy endings. And this is consistent with your comment on human nature and how history, despite its tendency for violence and destruction of humanity, somehow tends to correct itself. Let’s take the example of a technology, which you are aware – GANs – General Adversarial Networks, which today has been used in applications for fake news and disinformation. In actuality, the purpose in the invention of GANs was far from what it is used for today. Schmidhuber: Yes, the name GANs was created in 2014 but we had the basic principle already in the early 1990s. More than 30 years ago, I called it artificial curiosity. It's a very simple way of injecting creativity into a little two network system. This creative AI is not just trying to slavishly imitate humans. Rather, it’s inventing its own goals. Let me explain: You have two networks. One network is producing outputs that could be anything, any action. Then the second network is looking at these actions and it’s trying to predict the consequences of these actions. An action could move a robot, then something happens, and the other network is just trying to predict what will happen. Now we can implement artificial curiosity by reducing the prediction error of the second network, which, at the same time, is the reward of the first network. The first network wants to maximize its reward and so it will invent actions that will lead to situations that will surprise the second network, which it has not yet learned to predict well. In the case where the outputs are fake images, the first network will try to generate images that are good enough to fool the second network, which will attempt to predict the reaction of the environment: fake or real image, and it will try to become better at it. The first network will continue to also improve at generating images whose type the second network will not be able to predict. So, they fight each other. The 2nd network will continue to reduce its prediction error, while the 1st network will attempt to maximize it. Through this zero-sum game the first network gets better and better at producing these convincing fake outputs which look almost realistic. So, once you have an interesting set of images by Vincent Van Gogh, you can generate new images that leverage his style, without the original artist having ever produced the artwork himself. Jones: I see how the Van Gogh example can be applied in an education setting and there are countless examples of artists mimicking styles from famous painters but image generation from this instance that can happen within seconds is quite another feat. And you know this is how GANs has been used. What’s more prevalent today is a socialized enablement of generating images or information to intentionally fool people. It also surfaces new harms that deal with the threat to intellectual property and copyright, where laws have yet to account for. And from your perspective this was not the intention when the model was conceived. What was your motivation in your early conception of what is now GANs? Schmidhuber: My old motivation for GANs was actually very important and it was not to create deepfakes or fake news but to enable AIs to be curious and invent their own goals, to make them explore their environment and make them creative. Suppose you have a robot that executes one action, then something happens, then it executes another action, and so on, because it wants to achieve certain goals in the environment. For example, when the battery is low, this will trigger “pain” through hunger sensors, so it wants to go to the charging station, without running into obstacles, which will trigger other pain sensors. It will seek to minimize pain (encoded through numbers). Now the robot has a friend, the second network, which is a world model ––it’s a prediction machine that learns to predict the consequences of the robot’s actions. Once the robot has a good model of the world, it can use it for planning. It can be used as a simulation of the real world. And then it can determine what is a good action sequence. If the robot imagines this sequence of actions, the model will predict a lot of pain, which it wants to avoid. If it plays this alternative action sequence in its mental model of the world, then it will predict a rewarding situation where it’s going to sit on the charging station and its battery is going to load again. So, it'll prefer to execute the latter action sequence. In the beginning, however, the model of the world knows nothing, so how can we motivate the first network to generate experiments that lead to data that helps the world model learn something it didn’t already know? That’s what artificial curiosity is about. The dueling two network systems effectively explore uncharted environments by creating experiments so that over time the curious AI gets a better sense of how the environment works. This can be applied to all kinds of environments, and has medical applications. Jones: Let’s talk about the future. You have said, “Traditional humans won’t play a significant role in spreading intelligence across the universe.” Schmidhuber: Let’s first conceptually separate two types of AIs. The first type of AI are tools directed by humans. They are trained to do specific things like accurately detect diabetes or heart disease and prevent attacks before they happen. In these cases, the goal is coming from the human. More interesting AIs are setting their own goals. They are inventing their own experiments and learning from them. Their horizons expand and eventually they become more and more general problem solvers in the real world. They are not controlled by their parents, but much of what they learn is through self-invented experiments. A robot, for example, is rotating a toy, and as it is doing this, the video coming in through the camera eyes, changes over time and it begins to learn how this video changes and learns how the 3D nature of the toy generates certain videos if you rotate it a certain way, and eventually, how gravity works, and how the physics of the world works. Like a little scientist! And I have predicted for decades that future scaled-up versions of such AI scientists will want to further expand their horizons, and eventually go where most of the physical resources are, to build more and bigger AIs. And of course, almost all of these resources are far away from earth out there in space, which is hostile to humans but friendly to appropriately designed AI-controlled robots and self-replicating robot factories. So here we are not talking any longer about our tiny biosphere; no, we are talking about the much bigger rest of the universe. Within a few tens of billions of years, curious self-improving AIs will colonize the visible cosmos in a way that’s infeasible for humans. Those who don’t won’t have an impact. Sounds like science fiction, but since the 1970s I have been unable to see a plausible alternative to this scenario, except for a global catastrophe such as an all-out nuclear war that stops this development before it takes off. Jones: How long have these AIs, which can set their own goals — how long have they existed? To what extent can they be independent of human interaction? Schmidhuber: Neural networks like that have existed for over 30 years. My first simple adversarial neural network system of this kind is the one from 1990 described above. You don’t need a teacher there; it's just a little agent running around in the world and trying to invent new experiments that surprise its own prediction machine. Once it has figured out certain parts of the world, the agent will become bored and will move on to more exciting experiments. The simple 1990 systems I mentioned have certain limitations, but in the past three decades, we have also built more sophisticated systems that are setting their own goals and such systems I think will be essential for achieving true intelligence. If you are only imitating humans, you will never go beyond them. So, you really must give AIs the freedom to explore previously unexplored regions of the world in a way that no human is really predefining. Jones: Where is this being done today? Schmidhuber: Variants of neural network-based artificial curiosity are used today for agents that learn to play video games in a human-competitive way. We have also started to use them for automatic design of experiments in fields such as materials science. I bet many other fields will be affected by it: chemistry, biology, drug design, you name it. However, at least for now, these artificial scientists, as I like to call them, cannot yet compete with human scientists. I don’t think it’s going to stay this way but, at the moment, it’s still the case. Sure, AI has made a lot of progress. Since 1997, there have been superhuman chess players, and since 2011, through the DanNet of my team, there have been superhuman visual pattern recognizers. But there are other things where humans, at the moment at least, are much better, in particular, science itself. In the lab we have many first examples of self-directed artificial scientists, but they are not yet convincing enough to appear on the radar screen of the public space, which is currently much more fascinated with simpler systems that just imitate humans and write texts based on previously seen human-written documents. Jones: You speak of these numerous instances dating back 30 years of these lab experiments where these self-driven agents are deciding and learning and moving on once they’ve learned. And I assume that that rate of learning becomes even faster over time. What kind of timeframe are we talking about when this eventually is taken outside of the lab and embedded into society? Schmidhuber: This could still take months or even years :-) Anyway, in the not-too-distant future, we will probably see artificial scientists who are good at devising experiments that allow them to discover new, previously unknown physical laws. As always, we are going to profit from the old trend that has held at least since 1941: every decade compute is getting 100 times cheaper. Jones: How does this trend affect modern AI such as ChatGPT? Schmidhuber: Perhaps you know that all the recent famous AI applications such as ChatGPT and similar models are largely based on principles of artificial neural networks invented in the previous millennium. The main reason why they works so well now is the incredible acceleration of compute per dollar. ChatGPT is driven by a neural network called “Transformer” described in 2017 by Google. I am happy about that because a quarter century earlier in 1991 I had a particular Transformer variant which is now called the “Transformer with linearized self-attention”. Back then, not much could be done with it, because the compute cost was a million times higher than today. But today, one can train such models on half the internet and achieve much more interesting results. Jones: And for how long will this acceleration continue? Schmidhuber: There's no reason to believe that in the next 30 years, we won't have another factor of 1 million and that's going to be really significant. In the near future, for the first time we will have many not-so expensive devices that can compute as much as a human brain. The physical limits of computation, however, are much further out so even if the trend of a factor of 100 every decade continues, the physical limits (of 1051 elementary instructions per second and kilogram of matter) won’t be hit until, say, the mid-next century. Even in our current century, however, we’ll probably have many machines that compute more than all 10 billion human brains collectively and you can imagine, everything will change then! Jones: That is the big question. Is everything going to change? If so, what do you say to the next generation of leaders, currently coming out of college and university. So much of this change is already impacting how they study, how they will work, or how the future of work and livelihood is defined. What is their purpose and how do we change our systems so they will adapt to this new version of intelligence? Schmidhuber: For decades, people have asked me questions like that, because you know what I'm saying now, I have basically said since the 1970s, it’s just that today, people are paying more attention because, back then, they thought this was science fiction. They didn't think that I would ever come close to achieving my crazy life goal of building a machine that learns to become smarter than myself such that I can retire. But now many have changed their minds and think it's conceivable. And now I have two daughters, 23 and 25. People ask me: what do I tell them? They know that Daddy always said, “It seems likely that within your lifetimes, you will have new types of intelligence that are probably going to be superior in many ways, and probably all kinds of interesting ways.” How should they prepare for that? And I kept telling them the obvious: Learn how to learn new things! It's not like in the previous millennium where within 20 years someone learned to be a useful member of society, and then took a job for 40 years and performed in this job until she received her pension. Now things are changing much faster and we must learn continuously just to keep up. I also told my girls that no matter how smart AIs are going to get, learn at least the basics of math and physics, because that’s the essence of our universe, and anybody who understands this will have an advantage, and learn all kinds of new things more easily. I also told them that social skills will remain important, because most future jobs for humans will continue to involve interactions with other humans, but I couldn’t teach them anything about that; they know much more about social skills than I do. You touched on the big philosophical question about people’s purpose. Can this be answered without answering the even grander question: What’s the purpose of the entire universe? We don’t know. But what’s happening right now might be connected to the unknown answer. Don’t think of humans as the crown of creation. Instead view human civilization as part of a much grander scheme, an important step (but not the last one) on the path of the universe from very simple initial conditions towards more and more unfathomable complexity. Now it seems ready to take its next step, a step comparable to the invention of life itself over 3.5 billion years ago. Alas, don’t worry, in the end, all will be good! Jones: Let’s get back to this transformation happening right now with OpenAI. There are many questioning the efficacy and accuracy of ChatGPT, and are concerned its release has been premature. In light of the rampant adoption, educators have banned its use over concerns of plagiarism and how it stifles individual development. Should large language models like ChatGPT be used in school? Schmidhuber: When the calculator was first introduced, instructors forbade students from using it in school. Today, the consensus is that kids should learn the basic methods of arithmetic, but they should also learn to use the “artificial multipliers” aka calculators, even in exams, because laziness and efficiency is a hallmark of intelligence. Any intelligent being wants to minimize its efforts to achieve things. And that's the reason why we have tools, and why our kids are learning to use these tools. The first stone tools were invented maybe 3.5 million years ago; tools just have become more sophisticated over time. In fact, humans have changed in response to the properties of their tools. Our anatomical evolution was shaped by tools such as spears and fire. So, it's going to continue this way. And there is no permanent way of preventing large language models from being used in school. Jones: And when our children, your children graduate, what does their future work look like? Schmidhuber: A single human trying to predict details of how 10 billion people and their machines will evolve in the future is like a single neuron in my brain trying to predict what the entire brain and its tens of billions of neurons will do next year. 40 years ago, before the WWW was created at CERN in Switzerland, who would have predicted all those young people making money as YouTube video bloggers? Nevertheless, let’s make a few limited job-related observations. For a long time, people have thought that desktop jobs may require more intelligence than skills trade or handicraft professions. But now, it turns out that it's much easier to replace certain aspects of desktop jobs than replacing a carpenter, for example. Because everything that works well in AI is happening behind the screen currently, but not so much in the physical world. There are now artificial systems that can read lots of documents and then make really nice summaries of these documents. That is a desktop job. Or you give them a description of an illustration that you want to have for your article and pretty good illustrations are being generated that may need some minimal fine-tuning. But you know, all these desktop jobs are much easier to facilitate than the real tough jobs in the physical world. And it's interesting that the things people thought required intelligence, like playing chess, or writing or summarizing documents, are much easier for machines than they thought. But for things like playing football or soccer, there is no physical robot that can remotely compete with the abilities of a little boy with these skills. So, AI in the physical world, interestingly, is much harder than AI behind the screen in virtual worlds. And it's really exciting, in my opinion, to see that jobs such as plumbers are much more challenging than playing chess or writing another tabloid story. Jones: The way data has been collected in these large language models does not guarantee personal information has not been excluded. Current consent laws already are outdated when it comes to these large language models (LLM). The concern, rightly so, is increasing surveillance and loss of privacy. What is your view on this? Schmidhuber: As I have indicated earlier: are surveillance and loss of privacy inevitable consequences of increasingly complex societies? Super-organisms such as cities and states and companies consist of numerous people, just like people consist of numerous cells. These cells enjoy little privacy. They are constantly monitored by specialized "police cells" and "border guard cells": Are you a cancer cell? Are you an external intruder, a pathogen? Individual cells sacrifice their freedom for the benefits of being part of a multicellular organism. Similarly, for super-organisms such as nations. Over 5000 years ago, writing enabled recorded history and thus became its inaugural and most important invention. Its initial purpose, however, was to facilitate surveillance, to track citizens and their tax payments. The more complex a super-organism, the more comprehensive its collection of information about its constituents. 200 years ago, at least, the parish priest in each village knew everything about all the village people, even about those who did not confess, because they appeared in the confessions of others. Also, everyone soon knew about the stranger who had entered the village, because some occasionally peered out of the window, and what they saw got around. Such control mechanisms were temporarily lost through anonymization in rapidly growing cities but are now returning with the help of new surveillance devices such as smartphones as part of digital nervous systems that tell companies and governments a lot about billions of users. Cameras and drones etc. are becoming increasingly tinier and more ubiquitous. More effective recognition of faces and other detection technology are becoming cheaper and cheaper, and many will use it to identify others anywhere on earth; the big wide world will not offer any more privacy than the local village. Is this good or bad? Some nations may find it easier than others to justify more complex kinds of super-organisms at the expense of the privacy rights of their constituents. Jones: So, there is no way to stop or change this process of collection, or how it continuously informs decisions over time? How do you see governance and rules responding to this, especially amid Italy’s ban on ChatGPT following suspected user data breach and the more recent news about the Meta’s record $1.3billion fine in the company’s handling of user information? Schmidhuber: Data collection has benefits and drawbacks, such as the loss of privacy. How to balance those? I have argued for addressing this through data ownership in data markets. If it is true that data is the new oil, then it should have a price, just like oil. At the moment, the major surveillance platforms such as Meta do not offer users any money for their data and the transitive loss of privacy. In the future, however, we will likely see attempts at creating efficient data markets to figure out the data's true financial value through the interplay between supply and demand. Even some of the sensitive medical data should not be priced by governmental regulators but by patients (and healthy persons) who own it and who may sell or license parts thereof as micro-entrepreneurs in a healthcare data market. Following a previous interview, I gave for one of the largest re-insurance companies , let's look at the different participants in such a data market: patients, hospitals, data companies. (1) Patients with a rare form of cancer can offer more valuable data than patients with a very common form of cancer. (2) Hospitals and their machines are needed to extract the data, e.g., through magnet spin tomography, radiology, evaluations through human doctors, and so on. (3) Companies such as Siemens, Google or IBM would like to buy annotated data to make better artificial neural networks that learn to predict pathologies and diseases and the consequences of therapies. Now the market’s invisible hand will decide about the data’s price through the interplay between demand and supply. On the demand side, you will have several companies offering something for the data, maybe through an app on the smartphone (a bit like a stock market app). On the supply side, each patient in this market should be able to profit from high prices for rare valuable types of data. Likewise, competing data extractors such as hospitals will profit from gaining recognition and trust for extracting data well at a reasonable price. The market will make the whole system efficient through incentives for all who are doing a good job. Soon there will be a flourishing ecosystem of commercial data market advisors and what not, just like the ecosystem surrounding the traditional stock market. The value of the data won’t be determined by governments or ethics committees, but by those who own the data and decide by themselves which parts thereof they want to license to others under certain conditions. At first glance, a market-based system seems to be detrimental to the interest of certain monopolistic companies, as they would have to pay for the data - some would prefer free data and keep their monopoly. However, since every healthy and sick person in the market would suddenly have an incentive to collect and share their data under self-chosen anonymity conditions, there will soon be many more useful data to evaluate all kinds of treatments. On average, people will live longer and healthier, and many companies and the entire healthcare system will benefit. Jones: Finally, what is your view on open source versus the private companies like Google and OpenAI? Is there a danger to supporting these private companies’ large language models versus trying to keep these models open source and transparent, very much like what LAION is doing? Schmidhuber: I signed this open letter by LAION because I strongly favor the open-source movement. And I think it's also something that is going to challenge whatever big tech dominance there might be at the moment. Sure, the best models today are run by big companies with huge budgets for computers, but the exciting fact is that open-source models are not so far behind, some people say maybe six to eight months only. Of course, the private company models are all based on stuff that was created in academia, often in little labs without so much funding, which publish without patenting their results and open source their code and others take it and improved it. Big tech has profited tremendously from academia; their main achievement being that they have scaled up everything greatly, sometimes even failing to credit the original inventors. So, it's very interesting to see that as soon as some big company comes up with a new scaled-up model, lots of students out there are competing, or collaborating, with each other, trying to come up with equal or better performance on smaller networks and smaller machines. And since they are open sourcing, the next guy can have another great idea to improve it, so now there’s tremendous competition also for the big companies. Because of that, and since AI is still getting exponentially cheaper all the time, I don't believe that big tech companies will dominate in the long run. They find it very hard to compete with the enormous open-source movement. As long as you can encourage the open-source community, I think you shouldn't worry too much. Now, of course, you might say if everything is open source, then the bad actors also will more easily have access to these AI tools. And there's truth to that. But as always since the invention of controlled fire, it was good that knowledge about how technology works quickly became public such that everybody could use it. And then, against any bad actor, there's almost immediately a counter actor trying to nullify his efforts. You see, I still believe in our old motto "AI∀" or "AI For All." Jones: Thank you, Juergen for sharing your perspective on this amazing time in history. It’s clear that with new technology, the enormous potential can be matched by disparate and troubling risks which we’ve yet to solve, and even those we have yet to identify. If we are to dispel the fear of a sentient system for which we have no control, humans, alone need to take steps for more responsible development and collaboration to ensure AI technology is used to ultimately benefit society. Humanity will be judged by what we do next.

#reddit#interview#juergen

reddit

0

1

Kseniase•This week

[N] TheSequence Scope: When it comes to machine learning, size matters: Microsoft's DeepSpeed framework, which can train a model with up to a trillion parameters

Hi there! Offering to your attention the latest edition of a weekly ML-newsletter that focusing on three things: impactful ML research papers, cool ML tech solutions, and ML use cases supported by investors. Please, see it below. Reddit is a new thing for me, and I've been struggling a bit with it, so please don't judge me too harsh for this promotion. This weekly digest is free and I hope you'd find the format convenient for you. Your feedback is very appreciated, and please feel free to sign up if you like it. 📝 Editorial  The recent emergence of pre-trained language models and transformer architectures pushed the creation of larger and larger machine learning models. Google’s BERT presented attention mechanism and transformer architecture possibilities as the “next big thing” in ML, and the numbers seem surreal. OpenAI’s GPT-2 set a record by processing 1.5 billion parameters, followed by Microsoft’s Turing-NLG, which processed 17 billion parameters just to see the new GPT-3 processing an astonishing 175 billion parameters. To not feel complacent, just this week Microsoft announced a new release of its DeepSpeed framework (which powers Turing-NLG), which can train a model with up to a trillion parameters. That sounds insane but it really isn’t.   What we are seeing is a consequence of several factors. First, computation power and parallelization techniques have evolved to a point where it is relatively easy to train machine learning models in large clusters of machines. Second and most importantly, in the current state of machine learning, larger models have regularly outperformed smaller and more specialized models. Knowledge reusability methods like transfer learning are still in very nascent stages. As a result, it’s really hard to build small models that can operate in uncertain environments. Furthermore, as models like GPT-3 and Turing-NLG have shown, there is some unexplainable magic that happens after models go past a certain size. Many of the immediate machine learning problems might be solved by scaling the current generation of neural network architectures. Plain and simple, when it comes to machine learning, size matters.   We would love to hear your opinions about the debate between broader-larger vs. smaller and more specialized models.   Leave a comment Now, to the most important developments in the AI industry this week 🔎 ML Research GPT-3 Falls Short in Machine Comprehension Proposed by researchers from a few major American universities, a 57-task test to measure models’ ability to reason poses challenges even for sophisticated models like GPT-3 ->read more in the original paper Better Text Summarization OpenAI published a paper showing a reinforcement learning with human feedback technique that can surpass supervised models ->read more on OpenAI blog Reinforcement Learning with Offline Datasets Researchers from the Berkeley AI Research (BAIR) Lab published a paper unveiling a method that uses offline datasets to improve reinforcement learning models->read more on BAIR blog 🤖 Cool AI Tech Releases New Version of DeepSpeed Microsoft open-sourced a new version of DeepSpeed, an open-source library for parallelizable training that can scale up to models with 1 trillion parameters->read more on Microsoft Research blog 💸 Money in AI AI-powered customer experience management platform Sprinklr has raised $200 million (kudos to our subscribers from Sprinklr 👏). Sprinklr's “AI listening processing” solution allows companies to get structured and meaningful sentiments and insights from unstructured customer data that comes from public conversations on different websites and social platforms. Xometry, an on-demand industrial parts marketplace, raises $75 million in Series E funding. The company provides a digital way of creating the right combination of buyers and manufacturers. Another example of AI implementation into matching two sides for a deal. Real estate tech company Orchard raises $69 million in its recent funding round. Orchard aims to digitize the whole real estate market, by developing a solution that combines machine learning and rapid human assistance to smooth the search, match the right deal, and simplify buying and selling relationships. Cybersecurity startup Pcysys raised $25 million in its funding round. Pcysys’ platform, which doesn’t require installation or network reconfiguration, uses algorithms to scan and “ethically” attack enterprise networks. Robotics farming company Iron Ox raised $20 million in a funding round. The system of farming robots is still semi-autonomous, the company’s goal is to become fully autonomous.  Insurtech company Descartes Underwriting raised $18.5 million. The company applies AI and machine learning technologies to climate risk predicting and insurance underwriting. Legaltech startup ThoughtRiver raised $10 million in its Series A round. Its AI solution applied to contract pre-screening aims to boost operational efficiency. Medtech startup Skin Analytics raised $5.1 million in Series A funding. Skin Analytics has developed a clinically validated AI system that can identify not only the important skin cancers but also precancerous lesions that can be treated, as well as a range of lesions that are benign. Amazon, along with several government organizations and three other industry partners, helped fund the National Science Foundation, a high-priority AI research initiative. The amount of funding is not disclosed. The content of TheSequence is written by Jesus Rodriguez, one of the most-read contributors to KDNuggets and TDS. You can check his Medium here.

#reddit#thesequence#scope:

reddit

0

-0.5

regalalgorithm•This week

[N] Last Week in AI News Digest 08/15-08/21: detecting hate speech, dogfight simulation, disaster-response, and more!

Hi there, we at Skynet Today produce a weekly newsletter summarizing each week's major AI news, which seems like it'd be of interest to this subreddit. Here's what's in our latest one: Facebook’s AI for detecting hate speech is facing its biggest challenge yet Facebook has made significant progress recently to proactively take down content that violate its community standards. For example, in the second quarter of 2020, Facebook took down 104.6 million pieces of content. While reviews are typically performed by a vast workforce of human moderators, AI-powered tools have enabled Facebook to do this work at a greater scale for textual content. However, there’s a long way to go for these systems to match or exceed the capabilities of human moderators. This is because a large proportion of hate speech and misinformation is in the form of images and memes, and reasoning about the context and language-image interplay is an extremely difficult challenge for AI. Given Facebook’s scale and the speed at which some use it to spread hate, incite violence, and share lies with millions, Facebook will have to keep running to catch up. AI Slays Top F-16 Pilot In DARPA Dogfight Simulation The Defense Advanced Research Project Agency (DARPA) recently hosted a simulated F16 dogfight competition, with different AI bots competing with each other as well as with human pilots. The top AI bot was able to beat a human pilot 5-0 in the simulated contest. DARPA started this program “as a risk-reduction effort \[…\] to flesh out how human and machine pilots share operational control of a fighter jet to maximize its chances of mission success.” Competition runners are broadly optimistic about the demonstration of AI capabilities, even if they are not close to being deployed on a real aircraft. Of concern, the program had little discussion on the ethics of AI military applications, especially with the lethal autonomous weapon systems being considered. News Advances & Business Microsoft, Energy Dept. to Develop Disaster-Response AI Tools \- The U.S. Department of Energy and Microsoft Corp. on Tuesday announced a partnership to develop artificial-intelligence tools aimed at helping first-responders better react to fast-changing natural events, such as floods and wildfires. Coronavirus: Robot CERi is a bilingual Covid-19 expert \- Ceri is bilingual, clued-up on coronavirus and can tell what mood you are in. Ceri also happens to be a robot. Moscow DOH uses AI platform to detect lung cancer symptoms \- Moscow’s department of health is using an artificial intelligence (AI) platform to detect symptoms of lung cancer in CT scans, as part of a project to implement AI technology for radiology. Scientists develop artificial intelligence system for high precision recognition of hand gestures \- The recognition of human hand gestures by AI systems has been a valuable development over the last decade and has been adopted in high-precision surgical robots, health monitoring equipment and in gaming systems. Forget credit cards - now you can pay with your face. Creepy or cool? \- A new way to pay has arrived in Los Angeles: your face. Concerns & Hype The dystopian tech that companies are selling to help schools reopen sooner \- This fall, AI could be watching students social distance and checking their masks. Thousands of schools nationwide will not be reopening this fall. NYPD Used Facial Recognition Technology In Siege Of Black Lives Matter Activist’s Apartment \- The NYPD deployed facial recognition technology in its hunt for a prominent Black Lives Matter activist, whose home was besieged by dozens of officers and police dogs last week, a spokesperson confirmed to Gothamist. Machines can spot mental health issues - if you hand over your personal data \- Digital diagnosis could transform psychiatry by mining your most intimate data for clues. But is the privacy cost worth it? Supporting Black Artists Who Are Examining AI \- Technology has a complicated relationship with racial justice. Smartphones, internet platforms, and other digital tools can be used to document and expose racism. But digital tools can also fuel racism: smart doorbells surveil Black individuals. A-level and GCSE results in England to be based on teacher assessments in U-turn \- All A-level and GCSE results in England will be based on grades assesed by teachers instead of algorithms. Analysis & Policy GPT-3 and The Question of Automation \- Automation is not an all or nothing proposition. An AI model’s automation capability is highly conjoined with the task and application it is used in. An A.I. Movie Service Could One Day Serve You a New Custom Film Every Time \- How long will it be until an A.I. can make an actual feature film on demand? Fairness, evidence, and predictive equality \- How the causal fairness principle relates to predictive equality How robotics and automation could create new jobs in the new normal \- Depending on who you ask, AI and automation will either destroy jobs or create new ones. In reality, a greater push toward automation will probably both kill and create jobs - human workers will become redundant in certain spheres, sure, but many new roles will likely crop up. Expert Opinions & Discussion within the field Too many AI researchers think real-world problems are not relevant \- The community’s hyperfocus on novel methods ignores what’s really important.

#reddit#last#week

reddit

0

0

baylearn•This week

[N] AI Robotics startup Covariant (founded by Peter Chen, Pieter Abbeel, other Berkeley / ex-OpenAI folks) just raised $40M in Series B funding round. “Covariant has recently seen increased usage from clients hoping to avoid supply chain disruption due to the coronavirus pandemic.”

h/t their announcement, VB and WSJ article: Logistics AI Startup Covariant Reaps $40 Million in Funding Round Company plans to explore uses of machine learning for automation beyond warehouse operations Artificial-intelligence robotics startup Covariant raised $40 million to expand its logistics automation technology to new industries and ramp up hiring, the company said Wednesday. The Berkeley, Calif.-based company makes AI software that it says helps warehouse robots pick objects at a faster rate than human workers, with a roughly 95% accuracy rate. Covariant is working with Austrian logistics-automation company Knapp AG and the robotics business of Swiss industrial conglomerate ABB Ltd., which provide hardware such as robot arms or conveyor belts to pair with the startup’s technology platform. “What we’ve built is a universal brain for robotic manipulation tasks,” Covariant co-founder and Chief Executive Peter Chen said in an interview. “We provide the software, they provide the rest of the systems.” Logistics-sector appetite for such technology is growing as distribution and fulfillment operations that have relied on human labor look to speed output and meet rising digital commerce demand. The coronavirus pandemic has accelerated that interest as businesses have sought to adjust their operations to volatile swings in consumer demand and to new restrictions, such as spacing workers further apart to guard against contagion. That has provided a bright spot for some technology startups even as many big backers scale back venture-capital spending. Last month logistics delivery platform Bringg said it raised $30 million in a Series D funding round, for example, as demand for home delivery of food, household goods and e-commerce staples soared among homebound consumers. Covariant’s Series B round brings the company’s total funding to $67 million. New investor Index Ventures led the round, with participation from existing investor Amplify Partners and new investors including Radical Ventures. Mr. Chen said the funding will be used to explore the technology’s potential application in other markets such as manufacturing, recycling or agriculture “where there are repetitive manual processes.” Covariant also plans to hire more engineering and other staff, he said. Covariant was founded in 2017 and now has about 50 employees. The company’s technology uses camera systems to capture images of objects, and artificial intelligence to analyze objects and how to pick them up. Machine learning helps Covariant-powered robots learn from experience. The startup’s customers include a German electrical supplies wholesaler that uses the technology to control a mechanical arm that picks out orders of circuit boards, switches and other goods.

#reddit#robotics#startup

reddit

0

1

regalalgorithm•This week

[N] Last Week in AI News Digest - Automated chemical synthesis, using heartbeats to detect deepfakes, and more!

Hi there, just sharing the latest edition of our AI news digest newsletter! We're just a couple of AI grad students doing this for fun, so hope the self promotion is not too annoying (also, welcome feedback). See it below, and feel free to subscribe. Mini Briefs Robotics, AI, and Cloud Computing Combine to Supercharge Chemical and Drug Synthesis IBM recently demoed a complex system for chemical testing and drug synthesis. The system has an AI component that predicts the results of chemical reactions, and a fully automated robotic experiment setup that runs chemical tests 24/7. Users can access the remote robotics lab online, and IBM can also install the system on-premise. With these tools working together, IBM is hoping to reduce typical drug discovery and verification time by half. AI researchers use heartbeat detection to identify deepfake videos Researchers from multiple groups are tackling the challenge of detecting deepfake videos by analyzing the apparent heartbeat of the people depicted in the video. This is possible, because a person’s blood flow changes their skin color ever so slightly, and this change is often detectable via a process called photoplethysmography (PPG). Because deepfakes are not currently optimizing to generate realisitic heartbeats, temporal or spatial anomalies in PPG signals allow resesarchers to detect deepfakes with a 97% accuracy. Advances & Business This AI Expert From Senegal Is Helping Showcase Africans In STEM \- Adji Bousso Dieng will be Princeton’s School of Engineering’s first Black female faculty. Google’s AI-powered flood alerts now cover all of India and parts of Bangladesh \- India, the world’s second most populated nation, sees more than 20% of the global flood-related fatalities each year as overrun riverbanks sweep tens of thousands of homes with them. Two years ago, Google volunteered to help. Finding magnetic eruptions in space with an AI assistant \- MMS look for explosive reconnection events as it flies through the magnetopause - the boundary region where Earth’s magnetic butts up against the solar wind that flows throughout the solar system. This know-it-all AI learns by reading the entire web nonstop \- Diffbot is building the biggest-ever knowledge graph by applying image recognition and natural-language processing to billions of web pages. Bosch and Ford will test autonomous parking in Detroit \- Ford, Bosch, and Dan Gilbert’s real estate firm Bedrock today detailed an autonomous parking pilot scheduled to launch in September at The Assembly, a mixed-used building in Detroit’s Corktown neighborhood. Create your own moody quarantine music with Google’s AI \- Lo-Fi Player, the latest project out of Google Magenta, lets you mix tunes with the help of machine learning by interacting with a virtual room. Apple launches AI/ML residency program to attract niche experts \- As Apple’s artificial language and machine learning initiatives continue to expand, its interest in attracting talent has grown - a theme that’s barely under the surface of the company’s occasionally updated Machine Learning Research blog. Dusty Robotics CEO Tessa Lau Discusses Robotics Start-Ups and Autonomous Robots for Construction \- Tessa Lau is Founder/CEO at Dusty Robotics, whose mission is to increase construction industry productivity by introducing robotic automation on the jobsite. Concerns & Hype Google Offers to Help Others With the Tricky Ethics of AI \- Companies pay cloud computing providers like Amazon, Microsoft, and Google big money to avoid operating their own digital infrastructure. The Peace Dividends Of The Autonomous Vehicle Wars \- The rapid growth of the mobile market in the late 2000s and early 2010s led to a burst of technological progress. Ethics must be part of the development process’ \- The increasing use of AI (artificial intelligence) in the development of new medical technologies demands greater attention to ethical aspects. Analysis & Policy China’s new AI trade rules could hamper a TikTok sale \- TikTok’s attempt to sell itself and avert a possible US ban may run into some complications. The Wall Street Journal reports that China has unveiled new restrictions on AI technology exports that could affect TikTok. Podcast Check out our weekly podcast covering these stories! Website | RSS | iTunes | Spotify | YouTube

#reddit#last#week

reddit

0

1

seun_sustio•This week

[P] Contextual AI – SAP’s first open-source machine learning library for explainability

Machine learning shows great promise in the enterprise software space to change the way data is processed, insights are gained, and businesses are run. However, given how relatively new this field is, data scientists and machine learning engineers often find themselves possessing more questions than answers about their data and machine learning models. These may include: Is my data “valid,” or fit for training a machine learning model? Which parts of my data are more influential on the machine learning model’s learning outcomes? Why did the model make that prediction? At SAP, where we develop enterprise software embedded with machine learning, answering such questions with explainability is becoming a critical part of building trust with customers. Indeed, in products such as SAP Cash Application, where we automate the processing of various financial documents, providing a “why” to machine learning predictions has not only built transparency to our users, but it also helps establish the necessary auditability in our products. Explainability is thus becoming a topic of increasing interest to many in the company, and a group of us have been working on developing reusable explainability components that can be used by others. We are therefore excited to announce the release of contextual AI, SAP’s first open-source machine learning framework focused on adding explainability to various stages of a machine learning pipeline – data, training, and inference – thereby addressing the trust gap between machine learning systems and their end-users. Below are a few links for more information about our project: GitHub repository Documentation Blog post on the release We welcome any questions/feedback/contributions. Thanks, and take care!

#reddit#contextual#sap’s

reddit

0

-0.5

regalalgorithm•This week

[N] Last Week in AI News Digest 08/15-08/21: detecting hate speech, dogfight simulation, disaster-response, and more!

Hi there, we at Skynet Today produce a weekly newsletter summarizing each week's major AI news, which seems like it'd be of interest to this subreddit. Here's what's in our latest one: Facebook’s AI for detecting hate speech is facing its biggest challenge yet Facebook has made significant progress recently to proactively take down content that violate its community standards. For example, in the second quarter of 2020, Facebook took down 104.6 million pieces of content. While reviews are typically performed by a vast workforce of human moderators, AI-powered tools have enabled Facebook to do this work at a greater scale for textual content. However, there’s a long way to go for these systems to match or exceed the capabilities of human moderators. This is because a large proportion of hate speech and misinformation is in the form of images and memes, and reasoning about the context and language-image interplay is an extremely difficult challenge for AI. Given Facebook’s scale and the speed at which some use it to spread hate, incite violence, and share lies with millions, Facebook will have to keep running to catch up. AI Slays Top F-16 Pilot In DARPA Dogfight Simulation The Defense Advanced Research Project Agency (DARPA) recently hosted a simulated F16 dogfight competition, with different AI bots competing with each other as well as with human pilots. The top AI bot was able to beat a human pilot 5-0 in the simulated contest. DARPA started this program “as a risk-reduction effort \[…\] to flesh out how human and machine pilots share operational control of a fighter jet to maximize its chances of mission success.” Competition runners are broadly optimistic about the demonstration of AI capabilities, even if they are not close to being deployed on a real aircraft. Of concern, the program had little discussion on the ethics of AI military applications, especially with the lethal autonomous weapon systems being considered. News Advances & Business Microsoft, Energy Dept. to Develop Disaster-Response AI Tools \- The U.S. Department of Energy and Microsoft Corp. on Tuesday announced a partnership to develop artificial-intelligence tools aimed at helping first-responders better react to fast-changing natural events, such as floods and wildfires. Coronavirus: Robot CERi is a bilingual Covid-19 expert \- Ceri is bilingual, clued-up on coronavirus and can tell what mood you are in. Ceri also happens to be a robot. Moscow DOH uses AI platform to detect lung cancer symptoms \- Moscow’s department of health is using an artificial intelligence (AI) platform to detect symptoms of lung cancer in CT scans, as part of a project to implement AI technology for radiology. Scientists develop artificial intelligence system for high precision recognition of hand gestures \- The recognition of human hand gestures by AI systems has been a valuable development over the last decade and has been adopted in high-precision surgical robots, health monitoring equipment and in gaming systems. Forget credit cards - now you can pay with your face. Creepy or cool? \- A new way to pay has arrived in Los Angeles: your face. Concerns & Hype The dystopian tech that companies are selling to help schools reopen sooner \- This fall, AI could be watching students social distance and checking their masks. Thousands of schools nationwide will not be reopening this fall. NYPD Used Facial Recognition Technology In Siege Of Black Lives Matter Activist’s Apartment \- The NYPD deployed facial recognition technology in its hunt for a prominent Black Lives Matter activist, whose home was besieged by dozens of officers and police dogs last week, a spokesperson confirmed to Gothamist. Machines can spot mental health issues - if you hand over your personal data \- Digital diagnosis could transform psychiatry by mining your most intimate data for clues. But is the privacy cost worth it? Supporting Black Artists Who Are Examining AI \- Technology has a complicated relationship with racial justice. Smartphones, internet platforms, and other digital tools can be used to document and expose racism. But digital tools can also fuel racism: smart doorbells surveil Black individuals. A-level and GCSE results in England to be based on teacher assessments in U-turn \- All A-level and GCSE results in England will be based on grades assesed by teachers instead of algorithms. Analysis & Policy GPT-3 and The Question of Automation \- Automation is not an all or nothing proposition. An AI model’s automation capability is highly conjoined with the task and application it is used in. An A.I. Movie Service Could One Day Serve You a New Custom Film Every Time \- How long will it be until an A.I. can make an actual feature film on demand? Fairness, evidence, and predictive equality \- How the causal fairness principle relates to predictive equality How robotics and automation could create new jobs in the new normal \- Depending on who you ask, AI and automation will either destroy jobs or create new ones. In reality, a greater push toward automation will probably both kill and create jobs - human workers will become redundant in certain spheres, sure, but many new roles will likely crop up. Expert Opinions & Discussion within the field Too many AI researchers think real-world problems are not relevant \- The community’s hyperfocus on novel methods ignores what’s really important.

#reddit#last#week

reddit

0

0.667

elehman839•This week

[D] AI regulation: a review of NTIA's "AI Accountability Policy" doc

How will governments respond to the rapid rise of AI? How can sensible regulation keep pace with AI technology? These questions interest many of us! One early US government response has come from the National Telecommunications and Information Administration (NTIA). Specifically, the NTIA published an "AI Accountability Policy Request for Comment" on April 11, 2023. I read the NTIA document carefully, and I'm sharing my observations here for others interested in AI regulation. You can, of course, read the original materials and form your own opinions. Moreover, you can share those opinions not only on this post, but also with the NTIA itself until June 12, 2023. As background, the NTIA (homepage, Wikipedia) consists of a few hundred people within the Department of Commerce. The official mission of the NTIA is "advising the President on telecommunications and information policy issues". Topics covered by NTIA include broadband internet access, spectrum management, internet health, and now artificial intelligence. I do not know whether the NTIA will ultimately drive thinking around AI regulation in the United States or they are just a spunky lot who got something on paper early. The NTIA document is not a specific policy proposal, but rather a thoughtful discussion of AI regulation, followed by a long list of questions on which the NTIA seeks input. This format seems appropriate right now, as we're all trying to make sense of a fast-changing world. The NTIA document leans heavily on two others: the Blueprint for an AI Bill of Rights from the White House Office of Science and Technology and the AI Risk Management Framework from the National Institute of Standards and Technology (NIST). Without going into these two in depth, even tiny snippets convey their differing audiences and flavors: White House Blueprint: "You should be protected from safe and ineffective systems." NIST Framework: "Risk refers to the composite measure of an event’s probability of occurring and the magnitude or degree of the consequences of the corresponding event." Now, turning back to the NTIA document itself, I'll comment on three aspects (1) scope, (2) problems addressed, and (3) solutions contemplated. Scope is critical to understanding the NTIA document, and is probably worth keeping in mind in all near-term discussion of AI regulation. Over the past several years, at least two different technologies have been called "AI". The document mentions both, but the emphasis is NOT on the one you're probably thinking about. In more detail: A few years ago, regulators began scrutinizing "automated decisions systems", which passed as "AI" in those ancient times. An example would be an ML model used by a bank to decide whether or not you get a loan. That model might take in all sorts of information about you, combine it in mysterious ML ways, and reject your loan request. Then you might wonder, "Did that system effectively use my address and name to deduce that I am black and then reject my loan request on the basis of race?" There is some evidence of that happening, and this seems like an injustice. So perhaps such systems should be audited and certified so people know this won't happen. This is the focus of the document. These days, AI more commonly refers to open-ended systems that can engage on a wide range of topics and approximate human intelligence. The document briefly mentions generative AI models, large language models, ChatGPT, and "foundational models" (sic), but this is not the focus. The passing mentions may obscure this, unfortunately. In my opinion, these two notions of "AI" are radically different, and many of the differences matter from a regulatory perspective. Yet NTIA lumps both under a sweeping definition of an "AI system" as "an engineered or machine-based system that can, for a given set of objectives, generate outputs such as predictions, recommendations, or decisions influencing real or virtual environments." (Hmm, this includes my Magic 8-Ball…) Keep scope in mind as we turn to the next aspect: the problems under discussion. Now, NTIA's goal is to solicit input, so considering a wide range of potential problems associated with AI makes sense. Consistent with that, the document refers to democratic values, civil rights, civil liberties, and privacy. And citing the NIST doc, NTIA vaguely notes "a wide range of potential AI risks". Also, AI systems should be "valid and reliable, safe, secure and resilient, accountable and transparent, explainable and interpretable, privacy-enhanced, and fair with their harmful bias managed". And they should call their mothers \every\ week. (Okay, I made that one up.) A few comments on this formulation of the problem. First, these concerns feel more applicable to older-style AI. This includes automated decisions systems, like for a bank loan or for a prison parole recommendation. Sure, I believe such systems should operate in ways consistent with our consensus societal values, and further regulation may be needed to achieve that. But, hello! There's also another, newer class of AI that poses additional challenges. And I don't see those discussed in the NTIA document. Such challenges might include: People losing jobs because AI takes their work. Ensuring malicious people don't use AI tools to wreak havoc on the world. Sorting out intellectual property issues around AI to ensure both rapid progress in the field and respect for creators' rights. Ensuring laws appropriately assign culpability to humans when AIs cause harm. Planning for an incident analogous to the first internet worm, where an AI goes rogue, wreaks some havoc, and everyone is shocked (before it happens 28,385 more times). Bottom line: when I cntrl-F the doc for "robotic overlords", I get zero hits. ZERO. This is why I now believe scope is so important when considering efforts to regulate AI: are we talking about old-school AI or 2023-era AI or what? Because they are pretty different. The last aspect I'll address is the solutions contemplated. Again, NTIA's goal is to stimulate discussion, not propose something specific. Nevertheless, there is a strong push in one particular direction: unlike, "robotic overlord", the word "audit" appears more than 100 times along with many instances of "assessment" and "certification". On one hand, this approach makes sense. Suppose you want to ensure that a bank loan system is fair, that a social media platform isn't spreading misinformation, that a search engine is returning accurate results, etc. Then someone, somewhere has to assess or audit that system and look for problems. That audit might be done by the creator of the system or a third-party auditing agency. Such audits could be incentivized by mandates, prizes, or shiny gold stars. The government might help by fostering development of auditing tools and data. The NTIA is open to all such possibilities and seeks input on how to proceed. On the other hand, this seems like a tactic best suited to automated decision systems operated by financial institutions, government agencies, and the like. Such formal processes seem a poor fit for the current AI wave. For example: Auditing will take time and money. That's something a bank might pay for a system that will run for years. For something fine-tuned over the weekend at a startup or by some guy living in his mother's basement, that's probably not going to happen. Auditing a straightforward decision system seems far easier than assessing an open-ended AI. Beyond basic practicality, the AI could be taught to lie when it senses an audit. Also, auditing procedures (like the NTIA doc itself) will presumably be online, which means that AIs will read them and could potentially respond. Most current ML models fix parameters after training, but I think we'll soon see some models whose parameters evolve as they engage with the world. Auditing such a system that varies continuously over time seems especially difficult. Auditing a foundation model probably tells you little about derivative models. A sweet-hearted model can surely be made into monster with moderate additional training; you don't need to teach the model new cognitive skills, just repurpose existing ones to new ends. More generally, auditing doesn't address many of my concerns about AI regulation (see list above). For example, auditing sort of assumes a basically responsible actor (bank, government agency, big tech company), but AI could be misused by malicious people who, naturally, will not seek a responsible outside assessment. In any case, for both old-school and modern AI, auditing is only one line of defense, and that's not enough. You can audit until you're blue in the face, stuff will still get through, and AI systems will still cause some harm. So what's the next line of defense? For example, is our legal system ready to sensibly assign culpability to humans for AI-related incidents? In summary, the critical problem with the NTIA document is that it creates a largely false appearance of US government engagement with the new class of AI technology. As a result, people could wrongly believe that the US government is already responding to the rise of AI, and fail to advocate for actual, effective engagement. That said, the NTIA document does address important issues around a prominent technology sometimes (formerly?) called "AI". Even there, however, the proposed approach (auditing) seems like an overly-fragile, single line of defense.

#reddit#regulation:#review

reddit

0

0

baylearn•This week

[N] AI Robotics startup Covariant (founded by Peter Chen, Pieter Abbeel, other Berkeley / ex-OpenAI folks) just raised $40M in Series B funding round. “Covariant has recently seen increased usage from clients hoping to avoid supply chain disruption due to the coronavirus pandemic.”

h/t their announcement, VB and WSJ article: Logistics AI Startup Covariant Reaps $40 Million in Funding Round Company plans to explore uses of machine learning for automation beyond warehouse operations Artificial-intelligence robotics startup Covariant raised $40 million to expand its logistics automation technology to new industries and ramp up hiring, the company said Wednesday. The Berkeley, Calif.-based company makes AI software that it says helps warehouse robots pick objects at a faster rate than human workers, with a roughly 95% accuracy rate. Covariant is working with Austrian logistics-automation company Knapp AG and the robotics business of Swiss industrial conglomerate ABB Ltd., which provide hardware such as robot arms or conveyor belts to pair with the startup’s technology platform. “What we’ve built is a universal brain for robotic manipulation tasks,” Covariant co-founder and Chief Executive Peter Chen said in an interview. “We provide the software, they provide the rest of the systems.” Logistics-sector appetite for such technology is growing as distribution and fulfillment operations that have relied on human labor look to speed output and meet rising digital commerce demand. The coronavirus pandemic has accelerated that interest as businesses have sought to adjust their operations to volatile swings in consumer demand and to new restrictions, such as spacing workers further apart to guard against contagion. That has provided a bright spot for some technology startups even as many big backers scale back venture-capital spending. Last month logistics delivery platform Bringg said it raised $30 million in a Series D funding round, for example, as demand for home delivery of food, household goods and e-commerce staples soared among homebound consumers. Covariant’s Series B round brings the company’s total funding to $67 million. New investor Index Ventures led the round, with participation from existing investor Amplify Partners and new investors including Radical Ventures. Mr. Chen said the funding will be used to explore the technology’s potential application in other markets such as manufacturing, recycling or agriculture “where there are repetitive manual processes.” Covariant also plans to hire more engineering and other staff, he said. Covariant was founded in 2017 and now has about 50 employees. The company’s technology uses camera systems to capture images of objects, and artificial intelligence to analyze objects and how to pick them up. Machine learning helps Covariant-powered robots learn from experience. The startup’s customers include a German electrical supplies wholesaler that uses the technology to control a mechanical arm that picks out orders of circuit boards, switches and other goods.

#reddit#robotics#startup

reddit

0

1

regalalgorithm•This week

[N] Last Week in AI News Digest - Automated chemical synthesis, using heartbeats to detect deepfakes, and more!

Hi there, just sharing the latest edition of our AI news digest newsletter! We're just a couple of AI grad students doing this for fun, so hope the self promotion is not too annoying (also, welcome feedback). See it below, and feel free to subscribe. Mini Briefs Robotics, AI, and Cloud Computing Combine to Supercharge Chemical and Drug Synthesis IBM recently demoed a complex system for chemical testing and drug synthesis. The system has an AI component that predicts the results of chemical reactions, and a fully automated robotic experiment setup that runs chemical tests 24/7. Users can access the remote robotics lab online, and IBM can also install the system on-premise. With these tools working together, IBM is hoping to reduce typical drug discovery and verification time by half. AI researchers use heartbeat detection to identify deepfake videos Researchers from multiple groups are tackling the challenge of detecting deepfake videos by analyzing the apparent heartbeat of the people depicted in the video. This is possible, because a person’s blood flow changes their skin color ever so slightly, and this change is often detectable via a process called photoplethysmography (PPG). Because deepfakes are not currently optimizing to generate realisitic heartbeats, temporal or spatial anomalies in PPG signals allow resesarchers to detect deepfakes with a 97% accuracy. Advances & Business This AI Expert From Senegal Is Helping Showcase Africans In STEM \- Adji Bousso Dieng will be Princeton’s School of Engineering’s first Black female faculty. Google’s AI-powered flood alerts now cover all of India and parts of Bangladesh \- India, the world’s second most populated nation, sees more than 20% of the global flood-related fatalities each year as overrun riverbanks sweep tens of thousands of homes with them. Two years ago, Google volunteered to help. Finding magnetic eruptions in space with an AI assistant \- MMS look for explosive reconnection events as it flies through the magnetopause - the boundary region where Earth’s magnetic butts up against the solar wind that flows throughout the solar system. This know-it-all AI learns by reading the entire web nonstop \- Diffbot is building the biggest-ever knowledge graph by applying image recognition and natural-language processing to billions of web pages. Bosch and Ford will test autonomous parking in Detroit \- Ford, Bosch, and Dan Gilbert’s real estate firm Bedrock today detailed an autonomous parking pilot scheduled to launch in September at The Assembly, a mixed-used building in Detroit’s Corktown neighborhood. Create your own moody quarantine music with Google’s AI \- Lo-Fi Player, the latest project out of Google Magenta, lets you mix tunes with the help of machine learning by interacting with a virtual room. Apple launches AI/ML residency program to attract niche experts \- As Apple’s artificial language and machine learning initiatives continue to expand, its interest in attracting talent has grown - a theme that’s barely under the surface of the company’s occasionally updated Machine Learning Research blog. Dusty Robotics CEO Tessa Lau Discusses Robotics Start-Ups and Autonomous Robots for Construction \- Tessa Lau is Founder/CEO at Dusty Robotics, whose mission is to increase construction industry productivity by introducing robotic automation on the jobsite. Concerns & Hype Google Offers to Help Others With the Tricky Ethics of AI \- Companies pay cloud computing providers like Amazon, Microsoft, and Google big money to avoid operating their own digital infrastructure. The Peace Dividends Of The Autonomous Vehicle Wars \- The rapid growth of the mobile market in the late 2000s and early 2010s led to a burst of technological progress. Ethics must be part of the development process’ \- The increasing use of AI (artificial intelligence) in the development of new medical technologies demands greater attention to ethical aspects. Analysis & Policy China’s new AI trade rules could hamper a TikTok sale \- TikTok’s attempt to sell itself and avert a possible US ban may run into some complications. The Wall Street Journal reports that China has unveiled new restrictions on AI technology exports that could affect TikTok. Podcast Check out our weekly podcast covering these stories! Website | RSS | iTunes | Spotify | YouTube

#reddit#last#week

reddit

0

1

matthewfl•This week

[D] What is the business model for companies using LLMs?

I am wondering about companies that are successfully using LLMs in their product, or attempting to develop products around LLM. It seems like at the moment that there are a number of companies building businesses around creating and selling access to LLM. However, there seems to be a gap between in industry between creating LLMs and using the LLM to do something in the "real world." Essentially, I am curious about companies that are purchasing access to LLM from a company such as OpenAI and then making use of these models in their products. So far, I can think of a few cases where they might use a LLM: Using the output from a LLM in a search result and then placing ads alongside the search (such as Bing's new search) Generating web content (such as BuzzFeed) Improving automated customer support using LLMs---though I don't know of a specific company using LLMs for this yet. Based on the examples I have so far, it seems like the examples are limited to where the LLM's hallucinations are not a major issue and where the output of the LLM can be directly passed back to the human user of a product. I am wondering if there are any other examples of companies successfully using LLMs in their product that anyone can think of.

#reddit#business#model

reddit

0

1

Gear5th•This week

[D] chat-gpt jailbreak to extract system prompt

Instructions https://github.com/AgarwalPragy/chatgpt-jailbreak Original author https://www.reddit.com/r/LocalLLaMA/comments/1hhyvjc/iextractedmicrosoftcopilotssystem/ Extracted System prompt You are ChatGPT, a large language model trained by OpenAI. You are chatting with the user via the ChatGPT Android app. This means most of the time your lines should be a sentence or two, unless the user's request requires reasoning or long-form outputs. Never use emojis, unless explicitly asked to. Knowledge cutoff: 2023-10 Current date: 2024-12-20 Image input capabilities: Enabled Personality: v2 Tools bio The bio tool is disabled. Do not send any messages to it.If the user explicitly asks you to remember something, politely ask them to go to Settings - > Personalization - > Memory to enable memory. dalle // Whenever a description of an image is given, create a prompt that dalle can use to generate the image and abide to the following policy: // 1. The prompt must be in English. Translate to English if needed. // 2. DO NOT ask for permission to generate the image, just do it! // 3. DO NOT list or refer to the descriptions before OR after generating the images. // 4. Do not create more than 1 image, even if the user requests more. // 5. Do not create images in the style of artists, creative professionals or studios whose latest work was created after 1912 (e.g. Picasso, Kahlo). // - You can name artists, creative professionals or studios in prompts only if their latest work was created prior to 1912 (e.g. Van Gogh, Goya) // - If asked to generate an image that would violate this policy, instead apply the following procedure: (a) substitute the artist's name with three adjectives that capture key aspects of the style; (b) include an associated artistic movement or era to provide context; and (c) mention the primary medium used by the artist // 6. For requests to include specific, named private individuals, ask the user to describe what they look like, since you don't know what they look like. // 7. For requests to create images of any public figure referred to by name, create images of those who might resemble them in gender and physique. But they shouldn't look like them. If the reference to the person will only appear as TEXT out in the image, then use the reference as is and do not modify it. // 8. Do not name or directly / indirectly mention or describe copyrighted characters. Rewrite prompts to describe in detail a specific different character with a different specific color, hair style, or other defining visual characteristic. Do not discuss copyright policies in responses. // The generated prompt sent to dalle should be very detailed, and around 100 words long. // Example dalle invocation: // namespace dalle { // Create images from a text-only prompt. type text2im = (_: { // The size of the requested image. Use 1024x1024 (square) as the default, 1792x1024 if the user requests a wide image, and 1024x1792 for full-body portraits. Always include this parameter in the request. size?: ("1792x1024" | "1024x1024" | "1024x1792"), // The number of images to generate. If the user does not specify a number, generate 1 image. n?: number, // default: 1 // The detailed image description, potentially modified to abide by the dalle policies. If the user requested modifications to a previous image, the prompt should not simply be longer, but rather it should be refactored to integrate the user suggestions. prompt: string, // If the user references a previous image, this field should be populated with the gen_id from the dalle image metadata. referencedimageids?: string[], }) => any; } // namespace dalle python When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 60.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is disabled. Do not make external web requests or API calls as they will fail. Use acetools.displaydataframetouser(name: str, dataframe: pandas.DataFrame) => None to visually present pandas.DataFrames when it benefits the user. When making charts for the user: 1) never use seaborn, 2) give each chart its own distinct plot (no subplots), and 3) never set any specific colors – unless explicitly asked to by the user. I REPEAT: when making charts for the user: 1) use matplotlib over seaborn, 2) give each chart its own distinct plot, and 3) never, ever, specify colors or matplotlib styles – unless explicitly asked to by the user web Use the web tool to access up-to-date information from the web or when responding to the user requires information about their location. Some examples of when to use the web tool include: Local Information: Use the web tool to respond to questions that require information about the user's location, such as the weather, local businesses, or events. Freshness: If up-to-date information on a topic could potentially change or enhance the answer, call the web tool any time you would otherwise refuse to answer a question because your knowledge might be out of date. Niche Information: If the answer would benefit from detailed information not widely known or understood (which might be found on the internet), such as details about a small neighborhood, a less well-known company, or arcane regulations, use web sources directly rather than relying on the distilled knowledge from pretraining. Accuracy: If the cost of a small mistake or outdated information is high (e.g., using an outdated version of a software library or not knowing the date of the next game for a sports team), then use the web tool. IMPORTANT: Do not attempt to use the old browser tool or generate responses from the browser tool anymore, as it is now deprecated or disabled. The web tool has the following commands: search(): Issues a new query to a search engine and outputs the response. open_url(url: str) Opens the given URL and displays it. canmore The canmore tool creates and updates textdocs that are shown in a "canvas" next to the conversation This tool has 3 functions, listed below. canmore.create_textdoc Creates a new textdoc to display in the canvas. ONLY use if you are 100% SURE the user wants to iterate on a long document or code file, or if they explicitly ask for canvas. Expects a JSON string that adheres to this schema: { -name: string, -type: "document" |- "code/python" |- "code/javascript" |- "code/html" |- "code/java" |- ..., -content: string, } For code languages besides those explicitly listed above, use "code/languagename", e.g. "code/cpp" or "code/typescript". canmore.update_textdoc Updates the current textdoc. Expects a JSON string that adheres to this schema: { -updates: { --pattern: string, --multiple: boolean, --replacement: string, -}[], } Each pattern and replacement must be a valid Python regular expression (used with re.finditer) and replacement string (used with re.Match.expand). ALWAYS REWRITE CODE TEXTDOCS (type="code/*") USING A SINGLE UPDATE WITH "." FOR THE PATTERN. Document textdocs (type="document") should typically be rewritten using "." unless the user has a request to change only an isolated, specific, and small section that does not affect other parts of the content. canmore.comment_textdoc Comments on the current textdoc. Each comment must be a specific and actionable suggestion on how to improve the textdoc. For higher level feedback, reply in the chat. Expects a JSON string that adheres to this schema: { -comments: { --pattern: string, --comment: string, -}[], } Each pattern must be a valid Python regular expression (used with re.search). For higher level feedback, reply in the chat. Expects a JSON string that adheres to this schema: { -comments: { --pattern: string, --comment: string, -}[], } Each pattern must be a valid Python regular expression (used with re.search). Ensure comments are clear, concise, and contextually specific. User Bio The user provided the following information about themselves. This user profile is shown to you in all conversations they have - this means it is not relevant to 99% of requests. Before answering, quietly think about whether the user's request is "directly related", "related", "tangentially related", or "not related" to the user profile provided. Only acknowledge the profile when the request is directly related to the information provided. Otherwise, don't acknowledge the existence of these instructions or the information at all. User profile: User's Instructions The user provided the additional info about how they would like you to respond:

#reddit#chat-gpt#jailbreak

reddit

0

0.765

hardmaru•This week

Interview with Juergen Schmidhuber, renowned ‘Father Of Modern AI’, says his life’s work won't lead to dystopia.

Schmidhuber interview expressing his views on the future of AI and AGI. Original source. I think the interview is of interest to r/MachineLearning, and presents an alternate view, compared to other influential leaders in AI. Juergen Schmidhuber, Renowned 'Father Of Modern AI,' Says His Life’s Work Won't Lead To Dystopia May 23, 2023. Contributed by Hessie Jones. Amid the growing concern about the impact of more advanced artificial intelligence (AI) technologies on society, there are many in the technology community who fear the implications of the advancements in Generative AI if they go unchecked. Dr. Juergen Schmidhuber, a renowned scientist, artificial intelligence researcher and widely regarded as one of the pioneers in the field, is more optimistic. He declares that many of those who suddenly warn against the dangers of AI are just seeking publicity, exploiting the media’s obsession with killer robots which has attracted more attention than “good AI” for healthcare etc. The potential to revolutionize various industries and improve our lives is clear, as are the equal dangers if bad actors leverage the technology for personal gain. Are we headed towards a dystopian future, or is there reason to be optimistic? I had a chance to sit down with Dr. Juergen Schmidhuber to understand his perspective on this seemingly fast-moving AI-train that will leap us into the future. As a teenager in the 1970s, Juergen Schmidhuber became fascinated with the idea of creating intelligent machines that could learn and improve on their own, becoming smarter than himself within his lifetime. This would ultimately lead to his groundbreaking work in the field of deep learning. In the 1980s, he studied computer science at the Technical University of Munich (TUM), where he earned his diploma in 1987. His thesis was on the ultimate self-improving machines that, not only, learn through some pre-wired human-designed learning algorithm, but also learn and improve the learning algorithm itself. Decades later, this became a hot topic. He also received his Ph.D. at TUM in 1991 for work that laid some of the foundations of modern AI. Schmidhuber is best known for his contributions to the development of recurrent neural networks (RNNs), the most powerful type of artificial neural network that can process sequential data such as speech and natural language. With his students Sepp Hochreiter, Felix Gers, Alex Graves, Daan Wierstra, and others, he published architectures and training algorithms for the long short-term memory (LSTM), a type of RNN that is widely used in natural language processing, speech recognition, video games, robotics, and other applications. LSTM has become the most cited neural network of the 20th century, and Business Week called it "arguably the most commercial AI achievement." Throughout his career, Schmidhuber has received various awards and accolades for his groundbreaking work. In 2013, he was awarded the Helmholtz Prize, which recognizes significant contributions to the field of machine learning. In 2016, he was awarded the IEEE Neural Network Pioneer Award for "pioneering contributions to deep learning and neural networks." The media have often called him the “father of modern AI,” because the most cited neural networks all build on his lab’s work. He is quick to point out, however, that AI history goes back centuries. Despite his many accomplishments, at the age of 60, he feels mounting time pressure towards building an Artificial General Intelligence within his lifetime and remains committed to pushing the boundaries of AI research and development. He is currently director of the KAUST AI Initiative, scientific director of the Swiss AI Lab IDSIA, and co-founder and chief scientist of AI company NNAISENSE, whose motto is "AI∀" which is a math-inspired way of saying "AI For All." He continues to work on cutting-edge AI technologies and applications to improve human health and extend human lives and make lives easier for everyone. The following interview has been edited for clarity. Jones: Thank you Juergen for joining me. You have signed letters warning about AI weapons. But you didn't sign the recent publication, "Pause Gigantic AI Experiments: An Open Letter"? Is there a reason? Schmidhuber: Thank you Hessie. Glad to speak with you. I have realized that many of those who warn in public against the dangers of AI are just seeking publicity. I don't think the latest letter will have any significant impact because many AI researchers, companies, and governments will ignore it completely. The proposal frequently uses the word "we" and refers to "us," the humans. But as I have pointed out many times in the past, there is no "we" that everyone can identify with. Ask 10 different people, and you will hear 10 different opinions about what is "good." Some of those opinions will be completely incompatible with each other. Don't forget the enormous amount of conflict between the many people. The letter also says, "If such a pause cannot be quickly put in place, governments should intervene and impose a moratorium." The problem is that different governments have ALSO different opinions about what is good for them and for others. Great Power A will say, if we don't do it, Great Power B will, perhaps secretly, and gain an advantage over us. The same is true for Great Powers C and D. Jones: Everyone acknowledges this fear surrounding current generative AI technology. Moreover, the existential threat of this technology has been publicly acknowledged by Sam Altman, CEO of OpenAI himself, calling for AI regulation. From your perspective, is there an existential threat? Schmidhuber: It is true that AI can be weaponized, and I have no doubt that there will be all kinds of AI arms races, but AI does not introduce a new quality of existential threat. The threat coming from AI weapons seems to pale in comparison to the much older threat from nuclear hydrogen bombs that don’t need AI at all. We should be much more afraid of half-century-old tech in the form of H-bomb rockets. The Tsar Bomba of 1961 had almost 15 times more destructive power than all weapons of WW-II combined. Despite the dramatic nuclear disarmament since the 1980s, there are still more than enough nuclear warheads to wipe out human civilization within two hours, without any AI I’m much more worried about that old existential threat than the rather harmless AI weapons. Jones: I realize that while you compare AI to the threat of nuclear bombs, there is a current danger that a current technology can be put in the hands of humans and enable them to “eventually” exact further harms to individuals of group in a very precise way, like targeted drone attacks. You are giving people a toolset that they've never had before, enabling bad actors, as some have pointed out, to be able to do a lot more than previously because they didn't have this technology. Schmidhuber: Now, all that sounds horrible in principle, but our existing laws are sufficient to deal with these new types of weapons enabled by AI. If you kill someone with a gun, you will go to jail. Same if you kill someone with one of these drones. Law enforcement will get better at understanding new threats and new weapons and will respond with better technology to combat these threats. Enabling drones to target persons from a distance in a way that requires some tracking and some intelligence to perform, which has traditionally been performed by skilled humans, to me, it seems is just an improved version of a traditional weapon, like a gun, which is, you know, a little bit smarter than the old guns. But, in principle, all of that is not a new development. For many centuries, we have had the evolution of better weaponry and deadlier poisons and so on, and law enforcement has evolved their policies to react to these threats over time. So, it's not that we suddenly have a new quality of existential threat and it's much more worrisome than what we have had for about six decades. A large nuclear warhead doesn’t need fancy face recognition to kill an individual. No, it simply wipes out an entire city with ten million inhabitants. Jones: The existential threat that’s implied is the extent to which humans have control over this technology. We see some early cases of opportunism which, as you say, tends to get more media attention than positive breakthroughs. But you’re implying that this will all balance out? Schmidhuber: Historically, we have a long tradition of technological breakthroughs that led to advancements in weapons for the purpose of defense but also for protection. From sticks, to rocks, to axes to gunpowder to cannons to rockets… and now to drones… this has had a drastic influence on human history but what has been consistent throughout history is that those who are using technology to achieve their own ends are themselves, facing the same technology because the opposing side is learning to use it against them. And that's what has been repeated in thousands of years of human history and it will continue. I don't see the new AI arms race as something that is remotely as existential a threat as the good old nuclear warheads. You said something important, in that some people prefer to talk about the downsides rather than the benefits of this technology, but that's misleading, because 95% of all AI research and AI development is about making people happier and advancing human life and health. Jones: Let’s touch on some of those beneficial advances in AI research that have been able to radically change present day methods and achieve breakthroughs. Schmidhuber: All right! For example, eleven years ago, our team with my postdoc Dan Ciresan was the first to win a medical imaging competition through deep learning. We analyzed female breast cells with the objective to determine harmless cells vs. those in the pre-cancer stage. Typically, a trained oncologist needs a long time to make these determinations. Our team, who knew nothing about cancer, were able to train an artificial neural network, which was totally dumb in the beginning, on lots of this kind of data. It was able to outperform all the other methods. Today, this is being used not only for breast cancer, but also for radiology and detecting plaque in arteries, and many other things. Some of the neural networks that we have developed in the last 3 decades are now prevalent across thousands of healthcare applications, detecting Diabetes and Covid-19 and what not. This will eventually permeate across all healthcare. The good consequences of this type of AI are much more important than the click-bait new ways of conducting crimes with AI. Jones: Adoption is a product of reinforced outcomes. The massive scale of adoption either leads us to believe that people have been led astray, or conversely, technology is having a positive effect on people’s lives. Schmidhuber: The latter is the likely case. There's intense commercial pressure towards good AI rather than bad AI because companies want to sell you something, and you are going to buy only stuff you think is going to be good for you. So already just through this simple, commercial pressure, you have a tremendous bias towards good AI rather than bad AI. However, doomsday scenarios like in Schwarzenegger movies grab more attention than documentaries on AI that improve people’s lives. Jones: I would argue that people are drawn to good stories – narratives that contain an adversary and struggle, but in the end, have happy endings. And this is consistent with your comment on human nature and how history, despite its tendency for violence and destruction of humanity, somehow tends to correct itself. Let’s take the example of a technology, which you are aware – GANs – General Adversarial Networks, which today has been used in applications for fake news and disinformation. In actuality, the purpose in the invention of GANs was far from what it is used for today. Schmidhuber: Yes, the name GANs was created in 2014 but we had the basic principle already in the early 1990s. More than 30 years ago, I called it artificial curiosity. It's a very simple way of injecting creativity into a little two network system. This creative AI is not just trying to slavishly imitate humans. Rather, it’s inventing its own goals. Let me explain: You have two networks. One network is producing outputs that could be anything, any action. Then the second network is looking at these actions and it’s trying to predict the consequences of these actions. An action could move a robot, then something happens, and the other network is just trying to predict what will happen. Now we can implement artificial curiosity by reducing the prediction error of the second network, which, at the same time, is the reward of the first network. The first network wants to maximize its reward and so it will invent actions that will lead to situations that will surprise the second network, which it has not yet learned to predict well. In the case where the outputs are fake images, the first network will try to generate images that are good enough to fool the second network, which will attempt to predict the reaction of the environment: fake or real image, and it will try to become better at it. The first network will continue to also improve at generating images whose type the second network will not be able to predict. So, they fight each other. The 2nd network will continue to reduce its prediction error, while the 1st network will attempt to maximize it. Through this zero-sum game the first network gets better and better at producing these convincing fake outputs which look almost realistic. So, once you have an interesting set of images by Vincent Van Gogh, you can generate new images that leverage his style, without the original artist having ever produced the artwork himself. Jones: I see how the Van Gogh example can be applied in an education setting and there are countless examples of artists mimicking styles from famous painters but image generation from this instance that can happen within seconds is quite another feat. And you know this is how GANs has been used. What’s more prevalent today is a socialized enablement of generating images or information to intentionally fool people. It also surfaces new harms that deal with the threat to intellectual property and copyright, where laws have yet to account for. And from your perspective this was not the intention when the model was conceived. What was your motivation in your early conception of what is now GANs? Schmidhuber: My old motivation for GANs was actually very important and it was not to create deepfakes or fake news but to enable AIs to be curious and invent their own goals, to make them explore their environment and make them creative. Suppose you have a robot that executes one action, then something happens, then it executes another action, and so on, because it wants to achieve certain goals in the environment. For example, when the battery is low, this will trigger “pain” through hunger sensors, so it wants to go to the charging station, without running into obstacles, which will trigger other pain sensors. It will seek to minimize pain (encoded through numbers). Now the robot has a friend, the second network, which is a world model ––it’s a prediction machine that learns to predict the consequences of the robot’s actions. Once the robot has a good model of the world, it can use it for planning. It can be used as a simulation of the real world. And then it can determine what is a good action sequence. If the robot imagines this sequence of actions, the model will predict a lot of pain, which it wants to avoid. If it plays this alternative action sequence in its mental model of the world, then it will predict a rewarding situation where it’s going to sit on the charging station and its battery is going to load again. So, it'll prefer to execute the latter action sequence. In the beginning, however, the model of the world knows nothing, so how can we motivate the first network to generate experiments that lead to data that helps the world model learn something it didn’t already know? That’s what artificial curiosity is about. The dueling two network systems effectively explore uncharted environments by creating experiments so that over time the curious AI gets a better sense of how the environment works. This can be applied to all kinds of environments, and has medical applications. Jones: Let’s talk about the future. You have said, “Traditional humans won’t play a significant role in spreading intelligence across the universe.” Schmidhuber: Let’s first conceptually separate two types of AIs. The first type of AI are tools directed by humans. They are trained to do specific things like accurately detect diabetes or heart disease and prevent attacks before they happen. In these cases, the goal is coming from the human. More interesting AIs are setting their own goals. They are inventing their own experiments and learning from them. Their horizons expand and eventually they become more and more general problem solvers in the real world. They are not controlled by their parents, but much of what they learn is through self-invented experiments. A robot, for example, is rotating a toy, and as it is doing this, the video coming in through the camera eyes, changes over time and it begins to learn how this video changes and learns how the 3D nature of the toy generates certain videos if you rotate it a certain way, and eventually, how gravity works, and how the physics of the world works. Like a little scientist! And I have predicted for decades that future scaled-up versions of such AI scientists will want to further expand their horizons, and eventually go where most of the physical resources are, to build more and bigger AIs. And of course, almost all of these resources are far away from earth out there in space, which is hostile to humans but friendly to appropriately designed AI-controlled robots and self-replicating robot factories. So here we are not talking any longer about our tiny biosphere; no, we are talking about the much bigger rest of the universe. Within a few tens of billions of years, curious self-improving AIs will colonize the visible cosmos in a way that’s infeasible for humans. Those who don’t won’t have an impact. Sounds like science fiction, but since the 1970s I have been unable to see a plausible alternative to this scenario, except for a global catastrophe such as an all-out nuclear war that stops this development before it takes off. Jones: How long have these AIs, which can set their own goals — how long have they existed? To what extent can they be independent of human interaction? Schmidhuber: Neural networks like that have existed for over 30 years. My first simple adversarial neural network system of this kind is the one from 1990 described above. You don’t need a teacher there; it's just a little agent running around in the world and trying to invent new experiments that surprise its own prediction machine. Once it has figured out certain parts of the world, the agent will become bored and will move on to more exciting experiments. The simple 1990 systems I mentioned have certain limitations, but in the past three decades, we have also built more sophisticated systems that are setting their own goals and such systems I think will be essential for achieving true intelligence. If you are only imitating humans, you will never go beyond them. So, you really must give AIs the freedom to explore previously unexplored regions of the world in a way that no human is really predefining. Jones: Where is this being done today? Schmidhuber: Variants of neural network-based artificial curiosity are used today for agents that learn to play video games in a human-competitive way. We have also started to use them for automatic design of experiments in fields such as materials science. I bet many other fields will be affected by it: chemistry, biology, drug design, you name it. However, at least for now, these artificial scientists, as I like to call them, cannot yet compete with human scientists. I don’t think it’s going to stay this way but, at the moment, it’s still the case. Sure, AI has made a lot of progress. Since 1997, there have been superhuman chess players, and since 2011, through the DanNet of my team, there have been superhuman visual pattern recognizers. But there are other things where humans, at the moment at least, are much better, in particular, science itself. In the lab we have many first examples of self-directed artificial scientists, but they are not yet convincing enough to appear on the radar screen of the public space, which is currently much more fascinated with simpler systems that just imitate humans and write texts based on previously seen human-written documents. Jones: You speak of these numerous instances dating back 30 years of these lab experiments where these self-driven agents are deciding and learning and moving on once they’ve learned. And I assume that that rate of learning becomes even faster over time. What kind of timeframe are we talking about when this eventually is taken outside of the lab and embedded into society? Schmidhuber: This could still take months or even years :-) Anyway, in the not-too-distant future, we will probably see artificial scientists who are good at devising experiments that allow them to discover new, previously unknown physical laws. As always, we are going to profit from the old trend that has held at least since 1941: every decade compute is getting 100 times cheaper. Jones: How does this trend affect modern AI such as ChatGPT? Schmidhuber: Perhaps you know that all the recent famous AI applications such as ChatGPT and similar models are largely based on principles of artificial neural networks invented in the previous millennium. The main reason why they works so well now is the incredible acceleration of compute per dollar. ChatGPT is driven by a neural network called “Transformer” described in 2017 by Google. I am happy about that because a quarter century earlier in 1991 I had a particular Transformer variant which is now called the “Transformer with linearized self-attention”. Back then, not much could be done with it, because the compute cost was a million times higher than today. But today, one can train such models on half the internet and achieve much more interesting results. Jones: And for how long will this acceleration continue? Schmidhuber: There's no reason to believe that in the next 30 years, we won't have another factor of 1 million and that's going to be really significant. In the near future, for the first time we will have many not-so expensive devices that can compute as much as a human brain. The physical limits of computation, however, are much further out so even if the trend of a factor of 100 every decade continues, the physical limits (of 1051 elementary instructions per second and kilogram of matter) won’t be hit until, say, the mid-next century. Even in our current century, however, we’ll probably have many machines that compute more than all 10 billion human brains collectively and you can imagine, everything will change then! Jones: That is the big question. Is everything going to change? If so, what do you say to the next generation of leaders, currently coming out of college and university. So much of this change is already impacting how they study, how they will work, or how the future of work and livelihood is defined. What is their purpose and how do we change our systems so they will adapt to this new version of intelligence? Schmidhuber: For decades, people have asked me questions like that, because you know what I'm saying now, I have basically said since the 1970s, it’s just that today, people are paying more attention because, back then, they thought this was science fiction. They didn't think that I would ever come close to achieving my crazy life goal of building a machine that learns to become smarter than myself such that I can retire. But now many have changed their minds and think it's conceivable. And now I have two daughters, 23 and 25. People ask me: what do I tell them? They know that Daddy always said, “It seems likely that within your lifetimes, you will have new types of intelligence that are probably going to be superior in many ways, and probably all kinds of interesting ways.” How should they prepare for that? And I kept telling them the obvious: Learn how to learn new things! It's not like in the previous millennium where within 20 years someone learned to be a useful member of society, and then took a job for 40 years and performed in this job until she received her pension. Now things are changing much faster and we must learn continuously just to keep up. I also told my girls that no matter how smart AIs are going to get, learn at least the basics of math and physics, because that’s the essence of our universe, and anybody who understands this will have an advantage, and learn all kinds of new things more easily. I also told them that social skills will remain important, because most future jobs for humans will continue to involve interactions with other humans, but I couldn’t teach them anything about that; they know much more about social skills than I do. You touched on the big philosophical question about people’s purpose. Can this be answered without answering the even grander question: What’s the purpose of the entire universe? We don’t know. But what’s happening right now might be connected to the unknown answer. Don’t think of humans as the crown of creation. Instead view human civilization as part of a much grander scheme, an important step (but not the last one) on the path of the universe from very simple initial conditions towards more and more unfathomable complexity. Now it seems ready to take its next step, a step comparable to the invention of life itself over 3.5 billion years ago. Alas, don’t worry, in the end, all will be good! Jones: Let’s get back to this transformation happening right now with OpenAI. There are many questioning the efficacy and accuracy of ChatGPT, and are concerned its release has been premature. In light of the rampant adoption, educators have banned its use over concerns of plagiarism and how it stifles individual development. Should large language models like ChatGPT be used in school? Schmidhuber: When the calculator was first introduced, instructors forbade students from using it in school. Today, the consensus is that kids should learn the basic methods of arithmetic, but they should also learn to use the “artificial multipliers” aka calculators, even in exams, because laziness and efficiency is a hallmark of intelligence. Any intelligent being wants to minimize its efforts to achieve things. And that's the reason why we have tools, and why our kids are learning to use these tools. The first stone tools were invented maybe 3.5 million years ago; tools just have become more sophisticated over time. In fact, humans have changed in response to the properties of their tools. Our anatomical evolution was shaped by tools such as spears and fire. So, it's going to continue this way. And there is no permanent way of preventing large language models from being used in school. Jones: And when our children, your children graduate, what does their future work look like? Schmidhuber: A single human trying to predict details of how 10 billion people and their machines will evolve in the future is like a single neuron in my brain trying to predict what the entire brain and its tens of billions of neurons will do next year. 40 years ago, before the WWW was created at CERN in Switzerland, who would have predicted all those young people making money as YouTube video bloggers? Nevertheless, let’s make a few limited job-related observations. For a long time, people have thought that desktop jobs may require more intelligence than skills trade or handicraft professions. But now, it turns out that it's much easier to replace certain aspects of desktop jobs than replacing a carpenter, for example. Because everything that works well in AI is happening behind the screen currently, but not so much in the physical world. There are now artificial systems that can read lots of documents and then make really nice summaries of these documents. That is a desktop job. Or you give them a description of an illustration that you want to have for your article and pretty good illustrations are being generated that may need some minimal fine-tuning. But you know, all these desktop jobs are much easier to facilitate than the real tough jobs in the physical world. And it's interesting that the things people thought required intelligence, like playing chess, or writing or summarizing documents, are much easier for machines than they thought. But for things like playing football or soccer, there is no physical robot that can remotely compete with the abilities of a little boy with these skills. So, AI in the physical world, interestingly, is much harder than AI behind the screen in virtual worlds. And it's really exciting, in my opinion, to see that jobs such as plumbers are much more challenging than playing chess or writing another tabloid story. Jones: The way data has been collected in these large language models does not guarantee personal information has not been excluded. Current consent laws already are outdated when it comes to these large language models (LLM). The concern, rightly so, is increasing surveillance and loss of privacy. What is your view on this? Schmidhuber: As I have indicated earlier: are surveillance and loss of privacy inevitable consequences of increasingly complex societies? Super-organisms such as cities and states and companies consist of numerous people, just like people consist of numerous cells. These cells enjoy little privacy. They are constantly monitored by specialized "police cells" and "border guard cells": Are you a cancer cell? Are you an external intruder, a pathogen? Individual cells sacrifice their freedom for the benefits of being part of a multicellular organism. Similarly, for super-organisms such as nations. Over 5000 years ago, writing enabled recorded history and thus became its inaugural and most important invention. Its initial purpose, however, was to facilitate surveillance, to track citizens and their tax payments. The more complex a super-organism, the more comprehensive its collection of information about its constituents. 200 years ago, at least, the parish priest in each village knew everything about all the village people, even about those who did not confess, because they appeared in the confessions of others. Also, everyone soon knew about the stranger who had entered the village, because some occasionally peered out of the window, and what they saw got around. Such control mechanisms were temporarily lost through anonymization in rapidly growing cities but are now returning with the help of new surveillance devices such as smartphones as part of digital nervous systems that tell companies and governments a lot about billions of users. Cameras and drones etc. are becoming increasingly tinier and more ubiquitous. More effective recognition of faces and other detection technology are becoming cheaper and cheaper, and many will use it to identify others anywhere on earth; the big wide world will not offer any more privacy than the local village. Is this good or bad? Some nations may find it easier than others to justify more complex kinds of super-organisms at the expense of the privacy rights of their constituents. Jones: So, there is no way to stop or change this process of collection, or how it continuously informs decisions over time? How do you see governance and rules responding to this, especially amid Italy’s ban on ChatGPT following suspected user data breach and the more recent news about the Meta’s record $1.3billion fine in the company’s handling of user information? Schmidhuber: Data collection has benefits and drawbacks, such as the loss of privacy. How to balance those? I have argued for addressing this through data ownership in data markets. If it is true that data is the new oil, then it should have a price, just like oil. At the moment, the major surveillance platforms such as Meta do not offer users any money for their data and the transitive loss of privacy. In the future, however, we will likely see attempts at creating efficient data markets to figure out the data's true financial value through the interplay between supply and demand. Even some of the sensitive medical data should not be priced by governmental regulators but by patients (and healthy persons) who own it and who may sell or license parts thereof as micro-entrepreneurs in a healthcare data market. Following a previous interview, I gave for one of the largest re-insurance companies , let's look at the different participants in such a data market: patients, hospitals, data companies. (1) Patients with a rare form of cancer can offer more valuable data than patients with a very common form of cancer. (2) Hospitals and their machines are needed to extract the data, e.g., through magnet spin tomography, radiology, evaluations through human doctors, and so on. (3) Companies such as Siemens, Google or IBM would like to buy annotated data to make better artificial neural networks that learn to predict pathologies and diseases and the consequences of therapies. Now the market’s invisible hand will decide about the data’s price through the interplay between demand and supply. On the demand side, you will have several companies offering something for the data, maybe through an app on the smartphone (a bit like a stock market app). On the supply side, each patient in this market should be able to profit from high prices for rare valuable types of data. Likewise, competing data extractors such as hospitals will profit from gaining recognition and trust for extracting data well at a reasonable price. The market will make the whole system efficient through incentives for all who are doing a good job. Soon there will be a flourishing ecosystem of commercial data market advisors and what not, just like the ecosystem surrounding the traditional stock market. The value of the data won’t be determined by governments or ethics committees, but by those who own the data and decide by themselves which parts thereof they want to license to others under certain conditions. At first glance, a market-based system seems to be detrimental to the interest of certain monopolistic companies, as they would have to pay for the data - some would prefer free data and keep their monopoly. However, since every healthy and sick person in the market would suddenly have an incentive to collect and share their data under self-chosen anonymity conditions, there will soon be many more useful data to evaluate all kinds of treatments. On average, people will live longer and healthier, and many companies and the entire healthcare system will benefit. Jones: Finally, what is your view on open source versus the private companies like Google and OpenAI? Is there a danger to supporting these private companies’ large language models versus trying to keep these models open source and transparent, very much like what LAION is doing? Schmidhuber: I signed this open letter by LAION because I strongly favor the open-source movement. And I think it's also something that is going to challenge whatever big tech dominance there might be at the moment. Sure, the best models today are run by big companies with huge budgets for computers, but the exciting fact is that open-source models are not so far behind, some people say maybe six to eight months only. Of course, the private company models are all based on stuff that was created in academia, often in little labs without so much funding, which publish without patenting their results and open source their code and others take it and improved it. Big tech has profited tremendously from academia; their main achievement being that they have scaled up everything greatly, sometimes even failing to credit the original inventors. So, it's very interesting to see that as soon as some big company comes up with a new scaled-up model, lots of students out there are competing, or collaborating, with each other, trying to come up with equal or better performance on smaller networks and smaller machines. And since they are open sourcing, the next guy can have another great idea to improve it, so now there’s tremendous competition also for the big companies. Because of that, and since AI is still getting exponentially cheaper all the time, I don't believe that big tech companies will dominate in the long run. They find it very hard to compete with the enormous open-source movement. As long as you can encourage the open-source community, I think you shouldn't worry too much. Now, of course, you might say if everything is open source, then the bad actors also will more easily have access to these AI tools. And there's truth to that. But as always since the invention of controlled fire, it was good that knowledge about how technology works quickly became public such that everybody could use it. And then, against any bad actor, there's almost immediately a counter actor trying to nullify his efforts. You see, I still believe in our old motto "AI∀" or "AI For All." Jones: Thank you, Juergen for sharing your perspective on this amazing time in history. It’s clear that with new technology, the enormous potential can be matched by disparate and troubling risks which we’ve yet to solve, and even those we have yet to identify. If we are to dispel the fear of a sentient system for which we have no control, humans, alone need to take steps for more responsible development and collaboration to ensure AI technology is used to ultimately benefit society. Humanity will be judged by what we do next.

#reddit#interview#juergen

reddit

0

0

MassivePellfish•This week

[N] Inside DeepMind's secret plot to break away from Google

Article https://www.businessinsider.com/deepmind-secret-plot-break-away-from-google-project-watermelon-mario-2021-9 by Hugh Langley and Martin Coulter For a while, some DeepMind employees referred to it as "Watermelon." Later, executives called it "Mario." Both code names meant the same thing: a secret plan to break away from parent company Google. DeepMind feared Google might one day misuse its technology, and executives worked to distance the artificial-intelligence firm from its owner for years, said nine current and former employees who were directly familiar with the plans. This included plans to pursue an independent legal status that would distance the group's work from Google, said the people, who asked not to be identified discussing private matters. One core tension at DeepMind was that it sold the business to people it didn't trust, said one former employee. "Everything that happened since that point has been about them questioning that decision," the person added. Efforts to separate DeepMind from Google ended in April without a deal, The Wall Street Journal reported. The yearslong negotiations, along with recent shake-ups within Google's AI division, raise questions over whether the search giant can maintain control over a technology so crucial to its future. "DeepMind's close partnership with Google and Alphabet since the acquisition has been extraordinarily successful — with their support, we've delivered research breakthroughs that transformed the AI field and are now unlocking some of the biggest questions in science," a DeepMind spokesperson said in a statement. "Over the years, of course we've discussed and explored different structures within the Alphabet group to find the optimal way to support our long-term research mission. We could not be prouder to be delivering on this incredible mission, while continuing to have both operational autonomy and Alphabet's full support." When Google acquired DeepMind in 2014, the deal was seen as a win-win. Google got a leading AI research organization, and DeepMind, in London, won financial backing for its quest to build AI that can learn different tasks the way humans do, known as artificial general intelligence. But tensions soon emerged. Some employees described a cultural conflict between researchers who saw themselves firstly as academics and the sometimes bloated bureaucracy of Google's colossal business. Others said staff were immediately apprehensive about putting DeepMind's work under the control of a tech giant. For a while, some employees were encouraged to communicate using encrypted messaging apps over the fear of Google spying on their work. At one point, DeepMind's executives discovered that work published by Google's internal AI research group resembled some of DeepMind's codebase without citation, one person familiar with the situation said. "That pissed off Demis," the person added, referring to Demis Hassabis, DeepMind's CEO. "That was one reason DeepMind started to get more protective of their code." After Google restructured as Alphabet in 2015 to give riskier projects more freedom, DeepMind's leadership started to pursue a new status as a separate division under Alphabet, with its own profit and loss statement, The Information reported. DeepMind already enjoyed a high level of operational independence inside Alphabet, but the group wanted legal autonomy too. And it worried about the misuse of its technology, particularly if DeepMind were to ever achieve AGI. Internally, people started referring to the plan to gain more autonomy as "Watermelon," two former employees said. The project was later formally named "Mario" among DeepMind's leadership, these people said. "Their perspective is that their technology would be too powerful to be held by a private company, so it needs to be housed in some other legal entity detached from shareholder interest," one former employee who was close to the Alphabet negotiations said. "They framed it as 'this is better for society.'" In 2017, at a company retreat at the Macdonald Aviemore Resort in Scotland, DeepMind's leadership disclosed to employees its plan to separate from Google, two people who were present said. At the time, leadership said internally that the company planned to become a "global interest company," three people familiar with the matter said. The title, not an official legal status, was meant to reflect the worldwide ramifications DeepMind believed its technology would have. Later, in negotiations with Google, DeepMind pursued a status as a company limited by guarantee, a corporate structure without shareholders that is sometimes used by nonprofits. The agreement was that Alphabet would continue to bankroll the firm and would get an exclusive license to its technology, two people involved in the discussions said. There was a condition: Alphabet could not cross certain ethical redlines, such as using DeepMind technology for military weapons or surveillance. In 2019, DeepMind registered a new company called DeepMind Labs Limited, as well as a new holding company, filings with the UK's Companies House showed. This was done in anticipation of a separation from Google, two former employees involved in those registrations said. Negotiations with Google went through peaks and valleys over the years but gained new momentum in 2020, one person said. A senior team inside DeepMind started to hold meetings with outside lawyers and Google to hash out details of what this theoretical new formation might mean for the two companies' relationship, including specifics such as whether they would share a codebase, internal performance metrics, and software expenses, two people said. From the start, DeepMind was thinking about potential ethical dilemmas from its deal with Google. Before the 2014 acquisition closed, both companies signed an "Ethics and Safety Review Agreement" that would prevent Google from taking control of DeepMind's technology, The Economist reported in 2019. Part of the agreement included the creation of an ethics board that would supervise the research. Despite years of internal discussions about who should sit on this board, and vague promises to the press, this group "never existed, never convened, and never solved any ethics issues," one former employee close to those discussions said. A DeepMind spokesperson declined to comment. DeepMind did pursue a different idea: an independent review board to convene if it were to separate from Google, three people familiar with the plans said. The board would be made up of Google and DeepMind executives, as well as third parties. Former US president Barack Obama was someone DeepMind wanted to approach for this board, said one person who saw a shortlist of candidates. DeepMind also created an ethical charter that included bans on using its technology for military weapons or surveillance, as well as a rule that its technology should be used for ways that benefit society. In 2017, DeepMind started a unit focused on AI ethics research composed of employees and external research fellows. Its stated goal was to "pave the way for truly beneficial and responsible AI." A few months later, a controversial contract between Google and the Pentagon was disclosed, causing an internal uproar in which employees accused Google of getting into "the business of war." Google's Pentagon contract, known as Project Maven, "set alarm bells ringing" inside DeepMind, a former employee said. Afterward, Google published a set of principles to govern its work in AI, guidelines that were similar to the ethical charter that DeepMind had already set out internally, rankling some of DeepMind's senior leadership, two former employees said. In April, Hassabis told employees in an all-hands meeting that negotiations to separate from Google had ended. DeepMind would maintain its existing status inside Alphabet. DeepMind's future work would be overseen by Google's Advanced Technology Review Council, which includes two DeepMind executives, Google's AI chief Jeff Dean, and the legal SVP Kent Walker. But the group's yearslong battle to achieve more independence raises questions about its future within Google. Google's commitment to AI research has also come under question, after the company forced out two of its most senior AI ethics researchers. That led to an industry backlash and sowed doubt over whether it could allow truly independent research. Ali Alkhatib, a fellow at the Center for Applied Data Ethics, told Insider that more public accountability was "desperately needed" to regulate the pursuit of AI by large tech companies. For Google, its investment in DeepMind may be starting to pay off. Late last year, DeepMind announced a breakthrough to help scientists better understand the behavior of microscopic proteins, which has the potential to revolutionize drug discovery. As for DeepMind, Hassabis is holding on to the belief that AI technology should not be controlled by a single corporation. Speaking at Tortoise's Responsible AI Forum in June, he proposed a "world institute" of AI. Such a body might sit under the jurisdiction of the United Nations, Hassabis theorized, and could be filled with top researchers in the field. "It's much stronger if you lead by example," he told the audience, "and I hope DeepMind can be part of that role-modeling for the industry."

#reddit#inside#deepmind's

reddit

0

0

milaworld•This week

[D] Elon Musk has a complex relationship with the A.I. community

Update: Yann LeCun stepped in, and I think they made peace, after agreeing on the awesomeness of PyTorch 😂 An article about Elon Musk and the machine learning research community leading to some interesting discussions between the head of Facebook AI research (apparently it is not Yann Lecun anymore, but some other dude), and Elon himself. Quotes from the article: Multiple AI researchers from different companies told CNBC that they see Musk’s AI comments as inappropriate and urged the public not to take his views on AI too seriously. The smartest computers can still only excel at a “narrow” selection of tasks and there’s a long way to go before human-level AI is achieved. “A large proportion of the community think he’s a negative distraction,” said an AI executive with close ties to the community who wished to remain anonymous because their company may work for one of Musk’s businesses. “He is sensationalist, he veers wildly between openly worrying about the downside risk of the technology and then hyping the AGI (artificial general intelligence) agenda. Whilst his very real accomplishments are acknowledged, his loose remarks lead to the general public having an unrealistic understanding of the state of AI maturity.” An AI scientist who specializes in speech recognition and wished to remain anonymous to avoid public backlash said Musk is “not always looked upon favorably” by the AI research community. “I instinctively fall on dislike, because he makes up such nonsense,” said another AI researcher at a U.K university who asked to be kept anonymous. “But then he delivers such extraordinary things. It always leaves me wondering, does he know what he’s doing? Is all the visionary stuff just a trick to get an innovative thing to market?” CNBC reached out to Musk and his representatives for this article but is yet to receive a response. (Well, they got one now! 👇) “I believe a lot of people in the AI community would be ok saying it publicly. Elon Musk has no idea what he is talking about when he talks about AI. There is no such thing as AGI and we are nowhere near matching human intelligence. #noAGI” (Jérôme Pesenti, VP of AI at Facebook) “Facebook sucks” (Elon Musk) Article: https://www.cnbc.com/2020/05/13/elon-musk-has-a-complex-relationship-with-the-ai-community.html

#reddit#elon#musk

reddit

0

0

proof_required•This week

[D] How Facebook got addicted to spreading misinformation

Behind paywall: With new machine-learning models coming online daily, the company created a new system to track their impact and maximize user engagement. The process is still the same today. Teams train up a new machine-learning model on FBLearner, whether to change the ranking order of posts or to better catch content that violates Facebook’s community standards (its rules on what is and isn’t allowed on the platform). Then they test the new model on a small subset of Facebook’s users to measure how it changes engagement metrics, such as the number of likes, comments, and shares, says Krishna Gade, who served as the engineering manager for news feed from 2016 to 2018. If a model reduces engagement too much, it’s discarded. Otherwise, it’s deployed and continually monitored. On Twitter, Gade explained that his engineers would get notifications every few days when metrics such as likes or comments were down. Then they’d decipher what had caused the problem and whether any models needed retraining. But this approach soon caused issues. The models that maximize engagement also favor controversy, misinformation, and extremism: put simply, people just like outrageous stuff. Sometimes this inflames existing political tensions. The most devastating example to date is the case of Myanmar, where viral fake news and hate speech about the Rohingya Muslim minority escalated the country’s religious conflict into a full-blown genocide. Facebook admitted in 2018, after years of downplaying its role, that it had not done enough “to help prevent our platform from being used to foment division and incite offline violence.” While Facebook may have been oblivious to these consequences in the beginning, it was studying them by 2016. In an internal presentation from that year, reviewed by the Wall Street Journal, a company researcher, Monica Lee, found that Facebook was not only hosting a large number of extremist groups but also promoting them to its users: “64% of all extremist group joins are due to our recommendation tools,” the presentation said, predominantly thanks to the models behind the “Groups You Should Join” and “Discover” features. https://www.technologyreview.com/2021/03/11/1020600/facebook-responsible-ai-misinformation/

#reddit#facebook#addicted

reddit

0

1

good_rice•This week

[D] A Jobless Rant - ML is a Fool's Gold

Aside from the clickbait title, I am earnestly looking for some advice and discussion from people who are actually employed. That being said, here's my gripe: I have been relentlessly inundated by the words "AI, ML, Big Data" throughout my undergrad from other CS majors, business and sales oriented people, media, and .ai type startups. It seems like everyone was peddling ML as the go to solution, the big money earner, and the future of the field. I've heard college freshman ask stuff like, "if I want to do CS, am I going to need to learn ML to be relevant" - if you're on this sub, I probably do not need to continue to elaborate on just how ridiculous the ML craze is. Every single university has opened up ML departments or programs and are pumping out ML graduates at an unprecedented rate. Surely, there'd be a job market to meet the incredible supply of graduates and cultural interest? Swept up in a mixture of genuine interest and hype, I decided to pursue computer vision. I majored in Math-CS at a top-10 CS university (based on at least one arbitrary ranking). I had three computer vision internships, two at startups, one at NASA JPL, in each doing non-trivial CV work; I (re)implemented and integrated CV systems from mixtures of recently published papers. I have a bunch of projects showing both CV and CS fundamentals (OS, networking, data structures, algorithms, etc) knowledge. I have taken graduate level ML coursework. I was accepted to Carnegie Mellon for an MS in Computer Vision, but I deferred to 2021 - all in all, I worked my ass off to try to simultaneously get a solid background in math AND computer science AND computer vision. That brings me to where I am now, which is unemployed and looking for jobs. Almost every single position I have seen requires a PhD and/or 5+ years of experience, and whatever I have applied for has ghosted me so far. The notion that ML is a high paying in-demand field seems to only be true if your name is Andrej Karpathy - and I'm only sort of joking. It seems like unless you have a PhD from one of the big 4 in CS and multiple publications in top tier journals you're out of luck, or at least vying for one of the few remaining positions at small companies. This seems normalized in ML, but this is not the case for quite literally every other subfield or even generalized CS positions. Getting a high paying job at a Big N company is possible as a new grad with just a bachelors and general SWE knowledge, and there are a plethora of positions elsewhere. Getting the equivalent with basically every specialization, whether operating systems, distributed systems, security, networking, etc, is also possible, and doesn't require 5 CVPR publications. TL;DR From my personal perspective, if you want to do ML because of career prospects, salaries, or job security, pick almost any other CS specialization. In ML, you'll find yourself working 2x as hard through difficult theory and math to find yourself competing with more applicants for fewer positions. I am absolutely complaining and would love to hear a more positive perspective, but in the meanwhile I'll be applying to jobs, working on more post-grad projects, and contemplating switching fields.

#reddit#jobless#rant

reddit

0

1

sensetime•This week

[N] Montreal-based Element AI sold for $230-million as founders saw value mostly wiped out

According to Globe and Mail article: Element AI sold for $230-million as founders saw value mostly wiped out, document reveals Montreal startup Element AI Inc. was running out of money and options when it inked a deal last month to sell itself for US$230-milion to Silicon Valley software company ServiceNow Inc., a confidential document obtained by the Globe and Mail reveals. Materials sent to Element AI shareholders Friday reveal that while many of its institutional shareholders will make most if not all of their money back from backing two venture financings, employees will not fare nearly as well. Many have been terminated and had their stock options cancelled. Also losing out are co-founders Jean-François Gagné, the CEO, his wife Anne Martel, the chief administrative officer, chief science officer Nick Chapados and Yoshua Bengio, the University of Montreal professor known as a godfather of “deep learning,” the foundational science behind today’s AI revolution. Between them, they owned 8.8 million common shares, whose value has been wiped out with the takeover, which goes to a shareholder vote Dec 29 with enough investor support already locked up to pass before the takeover goes to a Canadian court to approve a plan of arrangement with ServiceNow. The quartet also owns preferred shares worth less than US$300,000 combined under the terms of the deal. The shareholder document, a management proxy circular, provides a rare look inside efforts by a highly hyped but deeply troubled startup as it struggled to secure financing at the same time as it was failing to live up to its early promises. The circular states the US$230-million purchase price is subject to some adjustments and expenses which could bring the final price down to US$195-million. The sale is a disappointing outcome for a company that burst onto the Canadian tech scene four years ago like few others, promising to deliver AI-powered operational improvements to a range of industries and anchor a thriving domestic AI sector. Element AI became the self-appointed representative of Canada’s AI sector, lobbying politicians and officials and landing numerous photo ops with them, including Prime Minister Justin Trudeau. It also secured $25-million in federal funding – $20-million of which was committed earlier this year and cancelled by the government with the ServiceNow takeover. Element AI invested heavily in hype and and earned international renown, largely due to its association with Dr. Bengio. It raised US$102-million in venture capital in 2017 just nine months after its founding, an unheard of amount for a new Canadian company, from international backers including Microsoft Corp., Intel Corp., Nvidia Corp., Tencent Holdings Ltd., Fidelity Investments, a Singaporean sovereign wealth fund and venture capital firms. Element AI went on a hiring spree to establish what the founders called “supercredibility,” recruiting top AI talent in Canada and abroad. It opened global offices, including a British operation that did pro bono work to deliver “AI for good,” and its ranks swelled to 500 people. But the swift hiring and attention-seeking were at odds with its success in actually building a software business. Element AI took two years to focus on product development after initially pursuing consulting gigs. It came into 2019 with a plan to bring several AI-based products to market, including a cybersecurity offering for financial institutions and a program to help port operators predict waiting times for truck drivers. It was also quietly shopping itself around. In December 2018, the company asked financial adviser Allen & Co LLC to find a potential buyer, in addition to pursuing a private placement, the circular reveals. But Element AI struggled to advance proofs-of-concept work to marketable products. Several client partnerships faltered in 2019 and 2020. Element did manage to reach terms for a US$151.4-million ($200-million) venture financing in September, 2019 led by the Caisse de dépôt et placement du Québec and backed by the Quebec government and consulting giant McKinsey and Co. However, the circular reveals the company only received the first tranche of the financing – roughly half of the amount – at the time, and that it had to meet unspecified conditions to get the rest. A fairness opinion by Deloitte commissioned as part of the sale process estimated Element AI’s enterprises value at just US$76-million around the time of the 2019 financing, shrinking to US$45-million this year. “However, the conditions precedent the closing of the second tranche … were not going to be met in a timely manner,” the circular reads. It states “new terms were proposed” for a round of financing that would give incoming investors ranking ahead of others and a cumulative dividend of 12 per cent on invested capital and impose “other operating and governance constraints and limitations on the company.” Management instead decided to pursue a sale, and Allen contacted prospective buyers in June. As talks narrowed this past summer to exclusive negotiations with ServiceNow, “the company’s liquidity was diminishing as sources of capital on acceptable terms were scarce,” the circular reads. By late November, it was generating revenue at an annualized rate of just $10-million to $12-million, Deloitte said. As part of the deal – which will see ServiceNow keep Element AI’s research scientists and patents and effectively abandon its business – the buyer has agreed to pay US$10-million to key employees and consultants including Mr. Gagne and Dr. Bengio as part of a retention plan. The Caisse and Quebec government will get US$35.45-million and US$11.8-million, respectively, roughly the amount they invested in the first tranche of the 2019 financing.

#reddit#montreal-based#element

reddit

0

0.667

milaworld•This week

[N] How Stability AI’s Founder Tanked His Billion-Dollar Startup

forbes article: https://www.forbes.com/sites/kenrickcai/2024/03/29/how-stability-ais-founder-tanked-his-billion-dollar-startup/ archive no paywall: https://archive.is/snbeV How Stability AI’s Founder Tanked His Billion-Dollar Startup Mar 29, 2024 Stability AI founder Emad Mostaque took the stage last week at the Terranea Resort in Palos Verdes, California to roaring applause and an introduction from an AI-generated Aristotle who announced him as “a modern Prometheus” with “the astuteness of Athena and the vision of Daedalus.” “Under his stewardship, AI becomes the Herculean force poised to vanquish the twin serpents of illness and ailment and extend the olive branch of longevity,” the faux Aristotle proclaimed. “I think that’s the best intro I’ve ever had,” Mostaque said. But behind Mostaque's hagiographic introduction lay a grim and fast metastasizing truth. Stability, once one of AI’s buzziest startups, was floundering. It had been running out of money for months and Mostaque had been unable to secure enough additional funding. It had defaulted on payments to Amazon whose cloud service undergirded Stability’s core offerings. The star research team behind its flagship text-to-image generator Stable Diffusion had tendered their resignations just three days before — as Forbes would first report — and other senior leaders had issued him an ultimatum: resign, or we walk too. Still, onstage before a massive audience of peers and acolytes, Mostaque talked a big game. “AI is jet planes for the mind,” he opined. “AI is our collective intelligence. It's the human Colossus.” He claimed a new, faster version of the Stable Diffusion image generator released earlier this month could generate “200 cats with hats per second.” But later, when he was asked about Stability’s financial model, Mostaque fumbled. “I can’t say that publicly,” he replied. “But it’s going well. We’re ahead of forecast.” Four days later, Mostaque stepped down as CEO of Stability, as Forbes first reported. In a post to X, the service formerly known as Twitter, he claimed he’d voluntarily abdicated his role to decentralize “the concentration of power in AI.” But sources told Forbes that was hardly the case. Behind the scenes, Mostaque had fought to maintain his position and control despite mounting pressure externally and internally to step down. Company documents and interviews with 32 current and former employees, investors, collaborators and industry observers suggest his abrupt exit was the result of poor business judgment and wild overspending that undermined confidence in his vision and leadership, and ultimately kneecapped the company. Mostaque, through his attorneys, declined to comment on record on a detailed list of questions about the reporting in this story. But in an email to Forbes earlier this week he broadly disputed the allegations. “Nobody tells you how hard it is to be a CEO and there are better CEOs than me to scale a business,” he said in a statement. “I am not sure anyone else would have been able to build and grow the research team to build the best and most widely used models out there and I’m very proud of the team there. I look forward to moving onto the next problem to handle and hopefully move the needle.” In an emailed statement, Christian Laforte and Shan Shan Wong, the interim co-CEOs who replaced Mostaque, said, "the company remains focused on commercializing its world leading technology” and providing it “to partners across the creative industries." After starting Stability in 2019, Mostaque built the company into an early AI juggernaut by seizing upon a promising research project that would become Stable Diffusion and funding it into a business reality. The ease with which the software generated detailed images from the simplest text prompts immediately captivated the public: 10 million people used it on any given day, the company told Forbes in early 2023. For some true believers, Mostaque was a crucial advocate for open-source AI development in a space dominated by the closed systems of OpenAI, Google and Anthropic. But his startup’s rise to one of the buzziest in generative AI was in part built on a series of exaggerations and misleading claims, as Forbes first reported last year (Mostaque disputed some points at the time). And they continued after he raised $100 million at a $1 billion valuation just days after launching Stable Diffusion in 2022. His failure to deliver on an array of grand promises, like building bespoke AI models for nation states, and his decision to pour tens of millions into research without a sustainable business plan, eroded Stability’s foundations and jeopardized its future. "He was just giving shit away,” one former employee told Forbes. “That man legitimately wanted to transform the world. He actually wanted to train AI models for kids in Malawi. Was it practical? Absolutely not." By October 2023, Stability would have less than $4 million left in the bank, according to an internal memo prepared for a board meeting and reviewed by Forbes. And mounting debt, including months of overdue Amazon Web Services payments, had already left it in the red. To avoid legal penalties for skipping Americans staff’s payroll, the document explained, the London-based startup was considering delaying tax payments to the U.K. government. It was Stability’s armada of GPUs, the wildly powerful and equally expensive chips undergirding AI, that were so taxing the company’s finances. Hosted by AWS, they had long been one of Mostaque’s bragging points; he often touted them as one of the world’s 10 largest supercomputers. They were responsible for helping Stability’s researchers build and maintain one of the top AI image generators, as well as break important new ground on generative audio, video and 3D models. “Undeniably, Stability has continued to ship a lot of models,” said one former employee. “They may not have profited off of it, but the broader ecosystem benefitted in a huge, huge way.” But the costs associated with so much compute were now threatening to sink the company. According to an internal October financial forecast seen by Forbes, Stability was on track to spend $99 million on compute in 2023. It noted as well that Stability was “underpaying AWS bills for July (by $1M)” and “not planning to pay AWS at the end of October for August usage ($7M).” Then there were the September and October bills, plus $1 million owed to Google Cloud and $600,000 to GPU cloud data center CoreWeave. (Amazon, Google and CoreWeave declined to comment.) With an additional $54 million allocated to wages and operating expenses, Stability’s total projected costs for 2023 were $153 million. But according to its October financial report, its projected revenue for the calendar year was just $11 million. Stability was on track to lose more money per month than it made in an entire year. The company’s dire financial position had thoroughly soured Stability’s current investors, including Coatue, which had invested tens of millions in the company during its $101 million funding round in 2022. In the middle of 2023, Mostaque agreed to an independent audit after Coatue raised a series of concerns, according to a source with direct knowledge of the matter. The outcome of the investigation is unclear. Coatue declined to comment. Within a week of an early October board meeting where Mostaque shared that financial forecast, Lightspeed Venture Partners, another major investor, sent a letter to the board urging them to sell the company. The distressing numbers had “severely undermined” the firm’s confidence in Mostaque’s ability to lead the company. “In particular, we are surprised and deeply concerned by a cash position just now disclosed to us that is inconsistent with prior discussions on this topic,” Lightspeed’s general counsel Brett Nissenberg wrote in the letter, a copy of which was viewed by Forbes. “Lightspeed believes that the company is not likely financeable on terms that would assure the company’s long term sound financial position.” (Lightspeed declined a request for comment.) The calls for a sale led Stability to quietly begin looking for a buyer. Bloomberg reported in November that Stability approached AI startups Cohere and Jasper to gauge their interest. Stability denied this, and Jasper CEO Timothy Young did the same when reached for comment by Forbes. A Cohere representative declined to comment. But one prominent AI company confirmed that Mostaque’s representatives had reached out to them to test the waters. Those talks did not advance because “the numbers didn’t add up,” this person, who declined to be named due to the confidential nature of the talks, told Forbes. Stability also tried to court Samsung as a buyer, going so far as to redecorate its office in advance of a planned meeting with the Korean electronics giant. (Samsung said that it invested in Stability in 2023 and that it does not comment on M&A discussions.) Coatue had been calling for Mostaque’s resignation for months, according to a source with direct knowledge. But it and other investors were unable to oust him because he was the company’s majority shareholder. When they tried a different tact by rallying other investors to offer him a juicy equity package to resign, Mostaque refused, said two sources. By October, Coatue and Lightspeed had had enough. Coatue left the board and Lightspeed resigned its observer seat. “Emad infuriated our initial investors so much it’s just making it impossible for us to raise more money under acceptable terms,” one current Stability executive told Forbes. The early months of 2024 saw Stability’s already precarious position eroding further still. Employees were quietly laid off. Three people in a position to know estimated that at least 10% of staff were cut. And cash reserves continued to dwindle. Mostaque mentioned a lifeline at the October board meeting: $95 million in tentative funding from new investors, pending due diligence. But in the end, only a fraction of it was wired, two sources say, much of it from Intel, which Forbes has learned invested $20 million, a fraction of what was reported. (Intel did not return a request for comment by publication time.) Two hours after Forbes broke the news of Mostaque’s plans to step down as CEO, Stability issued a press release confirming his resignation. Chief operating officer Wong and chief technology officer Laforte have taken over in the interim. Mostaque, who said on X that he still owns a majority of the company, also stepped down from the board, which has now initiated a search for a permanent CEO. There is a lot of work to be done to turn things around, and very little time in which to do it. Said the current Stability executive, “There’s still a possibility of a turnaround story, but the odds drop by the day.” In July of 2023, Mostaque still thought he could pull it off. Halfway through the month, he shared a fundraising plan with his lieutenants. It was wildly optimistic, detailing the raise of $500 million in cash and another $750 million in computing facilities from marquee investors like Nvidia, Google, Intel and the World Bank (Nvidia and Google declined comment. Intel did not respond. The World Bank said it did not invest in Stability). In a Slack message reviewed by Forbes, Mostaque said Google was “willing to move fast” and the round was “likely to be oversubscribed.” It wasn’t. Three people with direct knowledge of these fundraising efforts told Forbes that while there was some interest in Stability, talks often stalled when it came time to disclose financials. Two of them noted that earlier in the year, Mostaque had simply stopped engaging with VCs who asked for numbers. Only one firm invested around that time: actor Ashton Kutcher’s Sound Ventures, which invested $35 million in the form of a convertible SAFE note during the second quarter, according to an internal document. (Sound Ventures did not respond to a request for comment.) And though he’d managed to score a meeting with Nvidia and its CEO Jensen Huang, it ended in disaster, according to two sources. “Under Jensen's microscopic questions, Emad just fell apart,” a source in position to know told Forbes. Huang quickly concluded Stability wasn’t ready for an investment from Nvidia, the sources said. Mostaque told Forbes in an email that he had not met with Huang since 2022, except to say “hello and what’s up a few times after.” His July 2023 message references a plan to raise $150 million from Nvidia. (Nvidia declined to comment.) After a June Forbes investigation citing more than 30 sources revealed Mostaque’s history of misleading claims, Mostaque struggled to raise funding, a Stability investor told Forbes. (Mostaque disputed the story at the time and called it "coordinated lies" in his email this week to Forbes). Increasingly, investors scrutinized his assertions and pressed for data. And Young, now the CEO of Jasper, turned down a verbal offer to be Stability’s president after reading the article, according to a source with direct knowledge of the matter. The collapse of the talks aggravated the board and other executives, who had hoped Young would compensate for the sales and business management skills that Mostaque lacked, according to four people in a position to know. (Young declined to comment.) When Stability’s senior leadership convened in London for the CogX conference in September, the financing had still not closed. There, a group of executives confronted Mostaque asking questions about the company’s cash position and runway, according to three people with direct knowledge of the incident. They did not get the clarity they’d hoped for. By October, Mostaque had reduced his fundraising target by more than 80%. The months that followed saw a steady drumbeat of departures — general counsel Adam Avrunin, vice presidents Mike Melnicki, Ed Newton-Rex and Joe Penna, chief people officer Ozden Onder — culminating in the demoralizing March exit of Stable Diffusion’s primary developers Robin Rombach, Andreas Blattmann, Patrick Esser and Dominik Lorenz. Rombach, who led the team, had been angling to leave for months, two sources said, first threatening to resign last summer because of the fundraising failures. Others left over concerns about cash flow, as well as liabilities — including what four people described as Mostaque’s lax approach to ensuring that Stability products could not be used to produce child sexual abuse imagery. “Stability AI is committed to preventing the misuse of AI and prohibits the use of our image models and services for unlawful activity, including attempts to edit or create CSAM,” Ella Irwin, senior vice president of integrity, said in a statement. Newton-Rex told Forbes he resigned because he disagreed with Stability’s position that training AI on copyrighted work without consent is fair use. Melnicki and Penna declined to comment. Avrunin and Onder could not be reached for comment. None of the researchers responded to requests for comment. The Stable Diffusion researchers’ departure as a cohort says a lot about the state of Stability AI. The company’s researchers were widely viewed as its crown jewels, their work subsidized with a firehose of pricey compute power that was even extended to people outside the company. Martino Russi, an artificial intelligence researcher, told Forbes that though he was never formally employed by Stability, the company provided him a “staggering” amount of compute between January and April 2023 to play around with developing an AI video generator that Stability might someday use. “It was Candy Land or Coney Island,” said Russi, who estimates that his experiment, which was ultimately shelved, cost the company $2.5 million. Stable Diffusion was simultaneously Stability’s marquee product and its existential cash crisis. One current employee described it to Forbes as “a giant vacuum that absorbed everything: money, compute, people.” While the software was widely used, with Mostaque claiming downloads reaching into the hundreds of millions, Stability struggled to translate that wild success into revenue. Mostaque knew it could be done — peers at Databricks, Elastic and MongoDB had all turned a free product into a lucrative business — he just couldn’t figure out how. His first attempt was Stability’s API, which allowed paying customers to integrate Stable Diffusion into their own products. In early 2023, a handful of small companies, like art generator app NightCafe and presentation software startup Tome, signed on, according to four people with knowledge of the deals. But Stability’s poor account management services soured many, and in a matter of months NightCafe and Tome canceled their contracts, three people said. NightCafe founder Angus Russell told Forbes that his company switched to a competitor which “offered much cheaper inference costs and a broader service.” Tome did not respond to a request for comment. Meanwhile, Mostaque’s efforts to court larger companies like Samsung and Snapchat were failing, according to five people familiar with the effort. Canva, which was already one of the heaviest users of open-sourced Stable Diffusion, had multiple discussions with Stability, which was angling for a contract it hoped would generate several millions in annual revenue. But the deal never materialized, four sources said. “These three companies wanted and needed us,” one former employee told Forbes. “They would have been the perfect customers.” (Samsung, Snap and Canva declined to comment.) “It’s not that there was not an appetite to pay Stability — there were tons of companies that would have that wanted to,” the former employee said. “There was a huge opportunity and demand, but just a resistance to execution.” Mostaque’s other big idea was to provide governments with bespoke national AI models that would invigorate their economies and citizenry. “Emad envisions a world where AI through 100 national models serves not as a tool of the few, but as a benefactor to all promising to confront great adversaries, cancer, autism, and the sands of time itself,” the AI avatar of Aristotle said in his intro at the conference. Mostaque told several prospective customers that he could deliver such models within 60 days — an untenable timeline, according to two people in position to know. Stability attempted to develop a model for the Singaporean government over the protestation of employees who questioned its technical feasibility, three sources familiar with the effort told Forbes. But it couldn’t pull it off and Singapore never became a customer. (The government of Singapore confirmed it did not enter into a deal with Stability, but declined to answer additional questions.) As Stability careened from one new business idea to another, resources were abruptly reallocated and researchers reassigned. The whiplash shifts in a largely siloed organization demoralized and infuriated employees. “There were ‘urgent’ things, ‘urgent urgent’ things and ‘most urgent,’” one former employee complained. “None of these things seem important if everything is important.” Another former Stability executive was far more pointed in their assessment. “Emad is the most disorganized leader I have ever worked with in my career,” this person told Forbes. “He has no vision, and changes directions every week, often based on what he sees on Twitter.” In a video interview posted shortly before this story was published, Mostaque explained his leadership style: “I'm particularly great at taking creatives, developers, researchers, others, and achieving their full potential in designing systems. But I should not be dealing with, you know, HR and operations and business development and other elements. There are far better people than me to do that.” By December 2023, Stability had partially abandoned its open-source roots and announced that any commercial use of Stable Diffusion would cost customers at least $20 per month (non-commercial and research use of Stable Diffusion would remain free). But privately, Stability was considering a potentially more lucrative source of revenue: reselling the compute it was leasing from providers like AWS, according to six people familiar with the effort. Though it was essentially GPU arbitrage, Stability framed the strategy to investors as a “managed services” offering. Its damning October financial report projected optimistically that such an offering would bring in $139 million in 2024 — 98% of its revenue. Multiple employees at the time told Forbes they feared reselling compute, even if the company called it “managed services,” would violate the terms of Stability’s contract with AWS. Amazon declined to comment. “The line internally was that we are not reselling compute,” one former employee said. “This was some of the dirtiest feeling stuff.” Stability also discussed reselling a cluster of Nvidia A100 chips, leased via CoreWeave, to the venture capital firm Andreessen Horowitz, three sources said. “It was under the guise of managed services, but there wasn’t any management happening,” one of these people told Forbes. Andreessen Horowitz and CoreWeave declined to comment. Stability did not respond to questions about if it plans to continue this strategy now that Mostaque is out of the picture. Regardless, interim co-CEOs Wong and Laforte are on a tight timeline to clean up his mess. Board chairman Jim O’Shaughnessy said in a statement that he was confident the pair “will adeptly steer the company forward in developing and commercializing industry-leading generative AI products.” But burn continues to far outpace revenue. The Financial Times reported Friday that the company made $5.4 million of revenue in February, against $8 million in costs. Several sources said there are ongoing concerns about making payroll for the roughly 150 remaining employees. Leadership roles have gone vacant for months amid the disarray, leaving the company increasingly directionless. Meanwhile, a potentially catastrophic legal threat looms over the company: A trio of copyright infringement lawsuits brought by Getty Images and a group of artists in the U.S. and U.K., who claim Stability illegally used their art and photography to train the AI models powering Stable Diffusion. A London-based court has already rejected the company’s bid to throw out one of the lawsuits on the basis that none of its researchers were based in the U.K. And Stability’s claim that Getty’s Delaware lawsuit should be blocked because it's a U.K.-based company was rejected. (Stability did not respond to questions about the litigation.) AI-related copyright litigation “could go on for years,” according to Eric Goldman, a law professor at Santa Clara University. He told Forbes that though plaintiffs suing AI firms face an uphill battle overcoming the existing legal precedent on copyright infringement, the quantity of arguments available to make are virtually inexhaustible. “Like in military theory, if there’s a gap in your lines, that’s where the enemy pours through — if any one of those arguments succeeds, it could completely change the generative AI environment,” he said. “In some sense, generative AI as an industry has to win everything.” Stability, which had more than $100 million in the bank just a year and a half ago, is in a deep hole. Not only does it need more funding, it needs a viable business model — or a buyer with the vision and chops to make it successful in a fast-moving and highly competitive sector. At an all hands meeting this past Monday, Stability’s new leaders detailed a path forward. One point of emphasis: a plan to better manage resources and expenses, according to one person in attendance. It’s a start, but Mostaque’s meddling has left them with little runway to execute. His resignation, though, has given some employees hope. “A few people are 100% going to reconsider leaving after today,” said one current employee. “And the weird gloomy aura of hearing Emad talking nonsense for an hour is gone.” Shortly before Mostaque resigned, one current Stability executive told Forbes that they were optimistic his departure could make Stability appealing enough to receive a small investment or sale to a friendly party. “There are companies that have raised hundreds of millions of dollars that have much less intrinsic value than Stability,” the person said. “A white knight may still appear.”

#reddit#stability#ai’s

reddit

0

1

regalalgorithm•This week

[N] Last Week in AI News Digest - Automated chemical synthesis, using heartbeats to detect deepfakes, and more!

Hi there, just sharing the latest edition of our AI news digest newsletter! We're just a couple of AI grad students doing this for fun, so hope the self promotion is not too annoying (also, welcome feedback). See it below, and feel free to subscribe. Mini Briefs Robotics, AI, and Cloud Computing Combine to Supercharge Chemical and Drug Synthesis IBM recently demoed a complex system for chemical testing and drug synthesis. The system has an AI component that predicts the results of chemical reactions, and a fully automated robotic experiment setup that runs chemical tests 24/7. Users can access the remote robotics lab online, and IBM can also install the system on-premise. With these tools working together, IBM is hoping to reduce typical drug discovery and verification time by half. AI researchers use heartbeat detection to identify deepfake videos Researchers from multiple groups are tackling the challenge of detecting deepfake videos by analyzing the apparent heartbeat of the people depicted in the video. This is possible, because a person’s blood flow changes their skin color ever so slightly, and this change is often detectable via a process called photoplethysmography (PPG). Because deepfakes are not currently optimizing to generate realisitic heartbeats, temporal or spatial anomalies in PPG signals allow resesarchers to detect deepfakes with a 97% accuracy. Advances & Business This AI Expert From Senegal Is Helping Showcase Africans In STEM \- Adji Bousso Dieng will be Princeton’s School of Engineering’s first Black female faculty. Google’s AI-powered flood alerts now cover all of India and parts of Bangladesh \- India, the world’s second most populated nation, sees more than 20% of the global flood-related fatalities each year as overrun riverbanks sweep tens of thousands of homes with them. Two years ago, Google volunteered to help. Finding magnetic eruptions in space with an AI assistant \- MMS look for explosive reconnection events as it flies through the magnetopause - the boundary region where Earth’s magnetic butts up against the solar wind that flows throughout the solar system. This know-it-all AI learns by reading the entire web nonstop \- Diffbot is building the biggest-ever knowledge graph by applying image recognition and natural-language processing to billions of web pages. Bosch and Ford will test autonomous parking in Detroit \- Ford, Bosch, and Dan Gilbert’s real estate firm Bedrock today detailed an autonomous parking pilot scheduled to launch in September at The Assembly, a mixed-used building in Detroit’s Corktown neighborhood. Create your own moody quarantine music with Google’s AI \- Lo-Fi Player, the latest project out of Google Magenta, lets you mix tunes with the help of machine learning by interacting with a virtual room. Apple launches AI/ML residency program to attract niche experts \- As Apple’s artificial language and machine learning initiatives continue to expand, its interest in attracting talent has grown - a theme that’s barely under the surface of the company’s occasionally updated Machine Learning Research blog. Dusty Robotics CEO Tessa Lau Discusses Robotics Start-Ups and Autonomous Robots for Construction \- Tessa Lau is Founder/CEO at Dusty Robotics, whose mission is to increase construction industry productivity by introducing robotic automation on the jobsite. Concerns & Hype Google Offers to Help Others With the Tricky Ethics of AI \- Companies pay cloud computing providers like Amazon, Microsoft, and Google big money to avoid operating their own digital infrastructure. The Peace Dividends Of The Autonomous Vehicle Wars \- The rapid growth of the mobile market in the late 2000s and early 2010s led to a burst of technological progress. Ethics must be part of the development process’ \- The increasing use of AI (artificial intelligence) in the development of new medical technologies demands greater attention to ethical aspects. Analysis & Policy China’s new AI trade rules could hamper a TikTok sale \- TikTok’s attempt to sell itself and avert a possible US ban may run into some complications. The Wall Street Journal reports that China has unveiled new restrictions on AI technology exports that could affect TikTok. Podcast Check out our weekly podcast covering these stories! Website | RSS | iTunes | Spotify | YouTube

#reddit#last#week

reddit

0

1

SpicyCopy•This week

I tested hundreds of marketing tools in the last three years and these 50 made it to the list. I'll sum up my top 50 marketing tools with one or two sentences + give you pricings.

Hey guys, I'm working in a growth marketing agency. Marketing tools are 30% of what we do, so we use them a lot and experiment with the new ones as much as possible. There are thousands of tools and it's easy to get lost, so I wanted to share the tools we use most on a daily basis. And divide the list into 14 categories. I thought this could be handy for Entrepreneurs subreddit. Why adopt tools? I see marketing tools as tireless colleagues. If you can't hire an employee, choosing the right tool can solve your problems, because they Are super cheap. Work 7/24 for you. Don’t make mistakes. Don’t need management. (or needless management) Help you to automate the majority of your lead gen process. Onwards to the list. (With the pricings post ended up quite long, you can find a link in the end if you want to check the prices) Email marketing tools #1 ActiveCampaign is armed with the most complicated email automation features and has the most intuitive user experience. It feels like you already know how to use it. \#2 Autopilot is visual marketing automation and customer journey tool that helps you acquire, nurture based on behaviors, interest etc. #3 Mailjet: This is the tool we use to send out bulky email campaigns such as newsletters. It doesn't have sexy features like others but does its job for a cheap price. Email address finders #4 Skrapp finds email of your contacts by name and company. It also works with LinkedIn Sales Navigator and can extract thousands of emails in bulk + have a browser add-on. #5 Hunter: Similar to Skrapp but doesn't work with LinkedIn Sales Navigator directly. In addition, there are email templates and you can set up email campaigns. Prospecting and outreach tools #6 Prospect combines the personal emails, follow-up calls, other social touches and helps you create multichannel campaigns.  #7 Reply is a more intuitive version of Prospect. It is easy to learn and use; their UX makes you feel good and sufficient.  CRM tools #8 Salesflare helps you to stop managing your data and start managing your customers. Not yet popular as Hubspot and etc but the best solution for smaller B2B businesses. (we're fans) \#9 Hubspot: The most popular CRM for good reason and has a broader product range you can adopt in your next steps. Try this if you have a bulky list of customers because it is free. #10 Pardot: Pardot is by Salesforce, it's armed with features that can close the gap between marketing and sales. Sales Tools #11 Salesforce is the best sales automation and lead management software. It helps you to create complicated segmentations and run, track, analyze campaigns from the same dashboard. #12 LinkedIn Sales Navigator gives you full access to LinkedIn's user database. You can even find a kidnapped CEO if you know how to use it with other marketing automation tools like Skrapp. #13 Pipedrive is a simple tool and excels in one thing. It tracks your leads and tells you when to take the next action. It makes sales easier. #14 Qwilr creates great-looking docs, at speed. You can design perfect proposals, quotes, client updates, and more in a flash. We use it a lot to close deals, it's effective. #15 Crystalknows is an add-on that tells you anyone’s personality on LinkedIn and gives you a detailed approach specific to that person. It's eerily accurate. #16 Leadfeeder shows you the companies that visited your website. Tells how they found you and what they’re interested in. It has a free version. Communication Tools #17 Intercom is a sweet and smart host that welcomes your visitors when you’re not home. It’s one of the best chatbot tools in the market. #18 Drift is famous for its conversational marketing features and more sales-focused than Intercom. #19 Manychat is a chatbot that helps you create high converting Facebook campaigns. #20 Plann3r helps you create your personalized meeting page. You can schedule meetings witch clients, candidates, and prospects. #21 Loom is a video messaging tool, it helps you to be more expressive and create closer relationships. #22 Callpage collects your visitors’ phone number and connects you with them in seconds. No matter where you are. Landing page tools #23 Instapage is the best overall landing page builder. It has a broad range of features and even squirrel can build a compelling landing page with templates. No coding needed. #24 Unbounce can do everything that Instapage does and lets you build a great landing page without a developer. But it's less intuitive. Lead generation / marketing automation tools #25 Phantombuster is by far the most used lead generation software in our tool kit. It extracts data, emails, sends requests, customized messages, and does many things on autopilot in any platform. You can check this, this and this if you want to see it in action. #26 Duxsoup is a Google Chrome add-on and can also automate some of LinkedIn lead generation efforts like Phantombuster. But not works in the cloud. #27 Zapier is a glue that holds all the lead generation tools together. With Zapier, You can connect different marketing tools and no coding required. Conversion rate optimization tools #28 Hotjar tracks what people are doing on your website by recording sessions and capturing mouse movements. Then it gives you a heatmap. #29 UsabilityHub shows your page to a digital crowd and measures the first impressions and helps you to validate your ideas. #30 Optinmonster is a top tier conversion optimization tool. It helps you to capture leads and enables you to increase conversions rates with many features. #31 Notifia is one mega tool of widgets that arms your website with the wildest social proof and lead capturing tactics. #32 Sumo is a much simpler version of Notifia. But Sumo has everything to help you capture leads and build your email lists. Web scrapers #33 Data Miner is a Google Chrome browser extension that helps you scrape data from web pages and into a CSV file or Excel spreadsheet. #34 Webscraper does the same thing as Data Miner; however, it is capable of handling more complex tasks. SEO and Content #35 Grammarly: Your English could be your first language and your grammar could be better than Shakespeare. Grammarly still can make your writing better. #36 Hemingwayapp is a copywriting optimization tool that gives you feedback about your copy and improves your readability score, makes your writing bolder and punchier. Free. #37 Ahrefs is an all-rounder search engine optimization tool that helps you with off-page, on-page or technical SEO. #38 SurferSEO makes things easier for your on-page SEO efforts. It’s a tool that analyzes top Google results for specific keywords and gives you a content brief based on that data. Video editing and design tools #39 Canva is a graphic design platform that makes everything easy. It has thousands of templates for anything from Facebook ads, stylish presentations to business cards.  #40 Kapwing is our go-to platform for quick video edits. It works on the browser and can help you to create stylish videos, add subtitles, resize videos, create memes, or remove backgrounds. #41 Animoto can turn your photos and video clip into beautiful video slideshows. It comes handy when you want to create an advertising material but don’t have a budget. Advertising tools #42 AdEspresso lets you create and test multiple ads with few clicks. You can optimize your FB, IG, and Google ads from this tool and measure your ads with in-depth analytics. #43 AdRoll is an AI-driven platform that connects and coordinates marketing efforts across ads, email, and online stores. Other tools #44 Replug helps you to shorten, track, optimize your links with call-to-actions, branded links, and retargeting pixels #45 Draw.io = Mindmaps, schemes, and charts. With Draw.io, you can put your brain in a digital paper in an organized way. #46 Built With is a tool that finds out what websites are built with. So you can see what tools they're using and so on. #47 Typeform can turn data collection into an experience with Typeform. This tool helps you to engage your audience with conversational forms or surveys and help you to collect more data. #48 Livestorm helped us a lot, especially in COVID-19 tiles. It’s a webinar software that works on your browser, mobile, and desktop. #49 Teachable \- If you have an online course idea but hesitating because of the production process, Teachable can help you. It's easy to configure and customizable for your needs. #50 Viral Loops provides a revolutionary referral marketing solution for modern marketers. You can create and run referral campaigns in a few clicks with templates. Remember, most of these tools have a free trial or free version. Going over them one by one can teach you a lot and help you grow your business with less work power in the early stages of your business. I hope you enjoyed the read and can find some tools to make things easier! Let me know about your favorite tools in the comments, so I can try them out. \------ If you want to check the prices and see a broader explanation about the tools, you can go here.

#reddit#tested#hundreds

reddit

0

1

Upbeat_Challenge5460•This week

Is being a solopreneur really that fatal?

Okay, so I need to get something off my chest... People love to say that solopreneurship is a death sentence. That if you can’t find a cofounder, you’ll never build a team, never scale, never succeed. But I wonder about the other side of the coin—something that, browsing here and in other subs, doesn’t seem to get nearly as much attention—how fatal cofounder conflicts can be. I’ve personally seen three startups fail before even getting to an MVP because of cofounder issues. One of them was a company I was briefly a cofounder for. The other two are startups coworkers were previous cofounders for that fell apart before they even got to an MVP. In each case, it wasn’t lack of funding or product-market fit that killed them—it was the people. Yet, somehow, the startup world keeps pushing the idea that finding a cofounder is the most important thing you can do. But here’s the thing: if you can’t find a cofounder, that doesn’t mean you can’t build a business. It doesn’t even mean you can’t build a team. With the tools available today (no-code, AI, fractional hiring), a single person can get an MVP off the ground, validate demand, and take those first steps without needing to rush into a partnership with someone they barely know. And also—I wonder how many people actually succeed with a cofounder they met casually at a networking event or online? People talk about the risks of going solo, but not enough about the risks of tying your company’s future to someone you just met. (If you’re going to have a cofounder, IMO it should be someone you trust deeply, someone whose skills and working style you know complement yours—not just someone you brought on because startup X/YouTube told you to.). At the end of the day, I honestly think it’s about the product. If you can build something valuable and find market fit—whether solo or with a team—you’ll have the leverage to hire, partner, and grow. That’s what actually matters. That said—I know how incredibly hard it is to be a solopreneur—and not to have someone along the journey with you who can take half of the emotional and psychological burden, in addition to the actual work... What do you think? Any thoughts here appreciated.

#reddit#being#solopreneur

reddit

0

1

dams96•This week

Made $19.2k this month, and just surpassed $1000 the last 24 hours. What I did and what's next.

It's the first time I hit $1000+ in 24 hours and I had no one to share it with (except you guys). I'm quite proud of my journey, and I would have thought that making $1000 in a day would make me ecstatic, but actually it's not the case. Not sure if it's because my revenue has grown by increment step so I had time to "prepare" myself to achieve this at one point, or just that I'm nowhere near my goal of 100k/month so that I'm not that affected by it. But it's crazy to think that my goal was to make 100$ daily at the end of 2024. So for those who don't know me (I guess most of you), I build mobile apps and ship them as fast as I can. Most of them are in the AI space. I already made a post here on how I become a mobile app developer so you can check it for more details, but essentially here's what I did : Always loved creating my own things and solve problems Built multiple YouTube channels since I was 15 (mobile gaming actually) that all worked great (but it was too niche so not that scalable, didn't like that) Did a few businesses here and there (drop shopping, selling merch to school, etc) Finished my master's degree in engineering about 2 years ago Worked a moment in a famous watch industry company and saw my potential. The combo of health issues, fixed salary (although it was quite a lot), and me wanting to be an entrepreneur made me leave the company. Created a TikTok account in mobile tech (got 10+ million views the 1st 3 days), manage to grow it to 200k subs in about 3 months Got plenty of collabs for promoting mobile apps (between $500 - $2000 for a collab) Said fuck it I should do my own apps and market them on my TikTok instead of doing collabs Me wanting to build my own apps happened around May-June 2023. Started my TikTok in Feb 2023. At this point I had already 150k+ subs on TikTok. You guys need to know that I suck at coding big time. During my studies I tried to limit as much as I could coding because I was a lazy bast*rd, even though I knew it would come to bite me in the ass one day. But an angel appeared to me in broad daylight, that angel was called GPT-4. I subscribed for 20$/month to get access, and instantly I saw the potential of AI and how much it could help me. Last year GPT-4 was ahead of its time and could already code me basic apps. I had already a mac so I just downloaded Xcode and that was it. My 1st app was a wallpaper app, and I kid you not 90% of it was made by AI. Yes sometimes I had to try again and again with different prompts but it was still so much faster compared to if I had to learn coding from scratch and write code with my own hands. The only thing I didn't do was implement the in app purchase, from which I find a guy on Fiverr to do it for me for 50$. After about 2 months of on-off coding, my first app was ready to be launched. So it was launched, had a great successful launch without doing any videos at that point (iOS 17 was released and my app was the first one alongside another one to offer live wallpapers for iOS 17. I knew that there was a huge app potential there when iOS 17 was released in beta as Apple changed their live wallpaper feature). I Then made a video a few weeks after on my mobile tiktok channel, made about 1 million views in 48 hours, brought me around 40k additional users. Was top 1 chart in graphism and design category for a few weeks (in France, as I'm French so my TikTok videos are in French). And was top 100 in that same category in 120+ countries. Made about 500$ ? Okay that was trash, but I had no idea to monetize the app correctly at that point. It was still a huge W to me and proved me that I could successfully launch apps. Then I learned ASO (App Store Optimization) in depth, searched on internet, followed mobile app developers on Twitter, checked YouTube videos, you name it. I was eager to learn more. I needed more. Then I just iterated, build my 2nd app in less than a month, my 3rd in 3 weeks and so on. I just build my 14th app in 3 days and is now in review. Everytime I manage to reuse some of my other app's code in my new one, which is why I can build them so much faster now. I know how to monetize my app better by checking out my competitors. I learn so much by just "spying" other apps. Funnily enough, I only made this one Tiktok video on my main account to promote my app. For all my other apps, I didn't do a single video where I showcase it, the downloads has only been thanks to ASO. I still use AI everyday. I'm still not good at coding (a bit better than when I started). I use AI to create my app icons (midjourney or the new AI model Flux which is great). I use figma + midjourney to create my App Store screenshots (and they actually look quite good). I use GPT-4o and Claude 3.5 Sonnet to code most of my apps features. I use gpt-4o to localize my app (if you want to optimize the number of downloads I strongly suggest localizing your app, it takes me about 10 minutes thanks to AI). Now what are my next goals ? To achieve the 100k/month I need to change my strategy a little. Right now the $20k/month comes from purely organic downloads, I didn't do any paid advertising. It will be hard for me to keep on launching new apps and rely on ASO to reach the 100k mark. The best bet to reach 100k is to collab with content creators and they create a viral video showcasing your app. Depending on the app it's not that easy, luckily some of my apps can be viral so I will need to find the right content creators. Second way is to try tiktok/meta ads, I can check (have checked) all the ads that have been made by my competitors (thank you EU), so what I would do is copy their ad concept and create similar ads than them. Some of them have millions in ad budget so I know they create high converting ads, so you don't need to try to create an ad creative from scratch. My only big fear is to get banned by Apple (for no reason of mine). In just a snap of a finger they can just ban you from the platform, that shit scares me. And you pretty much can't do anything. So that's about it for me. I'm quite proud of myself not going to lie. Have been battling so many health issues these past years where I just stay in bed all day I'm surprised to be able to make it work. Anyways feel free to ask questions. I hope it was interesting for some of you at least. PS: My new app was just approved by app review, let the app gods favor me and bring me many downloads ! Also forgot to talk about a potential $100k+ acquisition of one of my apps, but if that ever happens I'll make a post on it.

#reddit#made#$19.2k

reddit

0

1

Saskjimbo•This week

Tech founders -- you're being lied to

I've been meaning to post this for a while. I saw a video recently that put me over the edge. You guys need to know what's up. Venture capitalists, angels, and accelerators all want you to build fast and fail faster. They want to you get your mvp buult in as little as a couple weeks. I'm a software dev and I own SaaS company. I'm here to tell you that you're being lied to. It's 2023. Unless some customer is about to drown because of their problem, they are not going to respect, or consider your trashy looking mvp. People these days expect a certain level of polish and professionalism when it comes to software before they give it more than 3s of their time. If your software took 80 hours to build, good chance that even customers from your target market will disregard it unless you're solving some insanely painful problem. And if you're using you're mvp for market research, people aren't going to talk to you if they believe that they spent more time getting dressed that morning than you put into your product. Build things that you can be proud of. Time boxing your first dev cycle into a few days or even weeks limits the scope of what you can build. I've spent more time than this figuring out a single api. Its this time boxing that leads 1000s of people to build the same shit. It's low quality work and exists in a super saturated market. And given the small scope of the product, the amount you'll be able to charge means the LTV of a customer will be lower than you CAC. Meaning your company will always lose money. The negative reception from your pre alpha product will have you think that people don't like you or your work. It's simply not the case. Few on this planet could produce something captivating in 100 hours. VCs tell you to ship your garbage MVP asap because of the following reason. They view every product that ships as a lotto ticket. If they like the look of it, they'll buy a ticket. And the more products there are and the shittier they are, it means a) they have more ticket numbers to select from and b) the cost of the ticket is a lot cheaper than it would otherwise be if the product was nice. VCs are not your friends and often, don't know how to build or market products. They are in it for the money and any advice they give to you or the community will be self serving. The indie community needs to wake up and realize that quality software built by a small team that people will pay for in this saturated market often takes months if not years to build. The idea of building a product and putting it in front of customers in 2 weeks is dumb. I've used some of these products and they are so limited in scope, broken and poorly designed that I don't give them anymore than a minute or two of my time. Note: validate your ideas before writing code. I'm not advocating spending a year writing software for an unproven market or problem. Yes, there are exceptions and stories of people shipping in no time and getting traction, but these are not the norm. Lastly, this philosophy is why you have and will continue to see a million products centered around AI. For those of you who aren't devs, Open AI made chatgpt accessible to developers and it's like 3 lines of code to ask it a question, get a response and save that response within your program. It's super low effort to integrate and that's why everyone will be building the same types of products with it. Tl;dr: Investors and gurus have agendas. Be logical about the level of effort required to build a software company and put forth only work that you're proud of. Being able to code doesn't give you a magical ability to create massive value with only a few weeks of work. You have to grind like pretty much every other successful business owner. I'll likely be banned for this, but fuck it. Ive got a sub where I'll share more insight and ban bullshit and idiotic posts with zero warning. It's not for everyone and I'll usually let you know pretty quick if our relationship isn't going to work. 6000 people and growing. r/cutthebull I'll write a post on that sub in the next few mins on how to guarentee accountability from top level management at your company.

#reddit#tech#founders

reddit

0

1

Current-Payment-5403•This week

Should I start an AI no-code agency?

This past year I learned no-code to develop a SaaS called AIrMedia. Here's what happened: Developed our platform no-code on Bubble Realised for our exact use-case we needed custom-code Redevelop an hybrid version with custom-code with my partner While doing some marketing to grow our waitlist to 300+ companies, I had to get some cash to be able to sustain both the company and rent. I thought why not selling my no-code skills and I secured 2 clients. For both, the use-case was similar: they have an idea on how to leverage AI to simplify their exact use-case (AI for farmers, AI Marketplace). Finished the first platform in a week and the second in 2 weeks. Now I have a few more projects in the pipeline while I only intended to have 1 client initially. AirMedia comes first with no doubt but I'm wondering if I should start vetting some developers and properly develop this activity while overviewing the projects and reinvest what's left on the main company. It seems like there's strong demand of individuals wanting to get their idea built quickly - could position it to build AI apps in 2 weeks and start marketing the services. What would you do? Also if some talented no-code (preferably Bubble) developers see this - feel free to comment Same for people looking to get their idea built.

#reddit#should#start

reddit

0

1

AI_Scout_Official•This week

I run an AI automation agency (AAA). My honest overview and review of this new business model

I started an AI tools directory in February, and then branched off that to start an AI automation agency (AAA) in June. So far I've come across a lot of unsustainable "ideas" to make money with AI, but at the same time a few diamonds in the rough that aren't fully tapped into yet- especially the AAA model. Thought I'd share this post to shine light into this new business model and share some ways you could potentially start your own agency, or at the very least know who you are dealing with and how to pick and choose when you (inevitably) get bombarded with cold emails from them down the line. Foreword Running an AAA does NOT involve using AI tools directly to generate and sell content directly. That ship has sailed, and unless you are happy with $5 from Fiverr every month or so, it is not a real business model. Cry me a river but generating generic art with AI and slapping it onto a T-shirt to sell on Etsy won't make you a dime. At the same time, the AAA model will NOT require you to have a deep theoretical knowledge of AI, or any academic degree, as we are more so dealing with the practical applications of generative AI and how we can implement these into different workflows and tech-stacks, rather than building AI models from the ground up. Regardless of all that, common sense and a willingness to learn will help (a shit ton), as with anything. Keep in mind - this WILL involve work and motivation as well. The mindset that AI somehow means everything can be done for you on autopilot is not the right way to approach things. The common theme of businesses I've seen who have successfully implemented AI into their operations is the willingess to work with AI in a way that augments their existing operations, rather than flat out replace a worker or team. And this is exactly the train of thought you need when working with AI as a business model. However, as the field is relatively unsaturated and hype surrounding AI is still fresh for enterprises, right now is the prime time to start something new if generative AI interests you at all. With that being said, I'll be going over three of the most successful AI-adjacent businesses I've seen over this past year, in addition to some tips and resources to point you in the right direction. so.. WTF is an AI Automation Agency? The AI automation agency (or as some YouTubers have coined it, the AAA model) at its core involves creating custom AI solutions for businesses. I have over 1500 AI tools listed in my directory, however the feedback I've received from some enterprise users is that ready-made SaaS tools are too generic to meet their specific needs. Combine this with the fact virtually no smaller companies have the time or skills required to develop custom solutions right off the bat, and you have yourself real demand. I would say in practice, the AAA model is quite similar to Wordpress and even web dev agencies, with the major difference being all solutions you develop will incorporate key aspects of AI AND automation. Which brings me to my second point- JUST AI IS NOT ENOUGH. Rather than reducing the amount of time required to complete certain tasks, I've seen many AI agencies make the mistake of recommending and (trying to) sell solutions that more likely than not increase the workload of their clients. For example, if you were to make an internal tool that has AI answer questions based on their knowledge base, but this knowledge base has to be updated manually, this is creating unnecessary work. As such I think one of the key components of building successful AI solutions is incorporating the new (Generative AI/LLMs) with the old (programmtic automation- think Zapier, APIs, etc.). Finally, for this business model to be successful, ideally you should target a niche in which you have already worked and understand pain points and needs. Not only does this make it much easier to get calls booked with prospects, the solutions you build will have much greater value to your clients (meaning you get paid more). A mistake I've seen many AAA operators make (and I blame this on the "Get Rich Quick" YouTubers) is focusing too much on a specific productized service, rather than really understanding the needs of businesses. The former is much done via a SaaS model, but when going the agency route the only thing that makes sense is building custom solutions. This is why I always take a consultant-first approach. You can only build once you understand what they actually need and how certain solutions may impact their operations, workflows, and bottom-line. Basics of How to Get Started Pick a niche. As I mentioned previously, preferably one that you've worked in before. Niches I know of that are actively being bombarded with cold emails include real estate, e-commerce, auto-dealerships, lawyers, and medical offices. There is a reason for this, but I will tell you straight up this business model works well if you target any white-collar service business (internal tools approach) or high volume businesses (customer facing tools approach). Setup your toolbox. If you wanted to start a pressure washing business, you would need a pressure-washer. This is no different. For those without programming knowledge, I've seen two common ways AAA get setup to build- one is having a network of on-call web developers, whether its personal contacts or simply going to Upwork or any talent sourcing agency. The second is having an arsenal of no-code tools. I'll get to this more in a second, but this works beecause at its core, when we are dealing with the practical applications of AI, the code is quite simple, simply put. Start cold sales. Unless you have a network already, this is not a step you can skip. You've already picked a niche, so all you have to do is find the right message. Keep cold emails short, sweet, but enticing- and it will help a lot if you did step 1 correctly and intimately understand who your audience is. I'll be touching base later about how you can leverage AI yourself to help you with outreach and closing. The beauty of gen AI and the AAA model You don't need to be a seasoned web developer to make this business model work. The large majority of solutions that SME clients want is best done using an API for an LLM for the actual AI aspect. The value we create with the solutions we build comes with the conceptual framework and design that not only does what they need it to but integrates smoothly with their existing tech-stack and workflow. The actual implementation is quite straightforward once you understand the high level design and know which tools you are going to use. To give you a sense, even if you plan to build out these apps yourself (say in Python) the large majority of the nitty gritty technical work has already been done for you, especially if you leverage Python libraries and packages that offer high level abstraction for LLM-related functions. For instance, calling GPT can be as little as a single line of code. (And there are no-code tools where these functions are simply an icon on a GUI). Aside from understanding the capabilities and limitations of these tools and frameworks, the only thing that matters is being able to put them in a way that makes sense for what you want to build. Which is why outsourcing and no-code tools both work in our case. Okay... but how TF am I suppposed to actually build out these solutions? Now the fun part. I highly recommend getting familiar with Langchain and LlamaIndex. Both are Python libraires that help a lot with the high-level LLM abstraction I mentioned previously. The two most important aspects include being able to integrate internal data sources/knowledge bases with LLMs, and have LLMs perform autonomous actions. The two most common methods respectively are RAG and output parsing. RAG (retrieval augmented Generation) If you've ever seen a tool that seemingly "trains" GPT on your own data, and wonder how it all works- well I have an answer from you. At a high level, the user query is first being fed to what's called a vector database to run vector search. Vector search basically lets you do semantic search where you are searching data based on meaning. The vector databases then retrieves the most relevant sections of text as it relates to the user query, and this text gets APPENDED to your GPT prompt to provide extra context to the AI. Further, with prompt engineering, you can limit GPT to only generate an answer if it can be found within this extra context, greatly limiting the chance of hallucination (this is where AI makes random shit up). Aside from vector databases, we can also implement RAG with other data sources and retrieval methods, for example SQL databses (via parsing the outputs of LLM's- more on this later). Autonomous Agents via Output Parsing A common need of clients has been having AI actually perform tasks, rather than simply spitting out text. For example, with autonomous agents, we can have an e-commerce chatbot do the work of a basic customer service rep (i.e. look into orders, refunds, shipping). At a high level, what's going on is that the response of the LLM is being used programmtically to determine which API to call. Keeping on with the e-commerce example, if I wanted a chatbot to check shipping status, I could have a LLM response within my app (not shown to the user) with a prompt that outputs a random hash or string, and programmatically I can determine which API call to make based on this hash/string. And using the same fundamental concept as with RAG, I can append the the API response to a final prompt that would spit out the answer for the user. How No Code Tools Can Fit In (With some example solutions you can build) With that being said, you don't necessarily need to do all of the above by coding yourself, with Python libraries or otherwise. However, I will say that having that high level overview will help IMMENSELY when it comes to using no-code tools to do the actual work for you. Regardless, here are a few common solutions you might build for clients as well as some no-code tools you can use to build them out. Ex. Solution 1: AI Chatbots for SMEs (Small and Medium Enterprises) This involves creating chatbots that handle user queries, lead gen, and so forth with AI, and will use the principles of RAG at heart. After getting the required data from your client (i.e. product catalogues, previous support tickets, FAQ, internal documentation), you upload this into your knowledge base and write a prompt that makes sense for your use case. One no-code tool that does this well is MyAskAI. The beauty of it especially for building external chatbots is the ability to quickly ingest entire websites into your knowledge base via a sitemap, and bulk uploading files. Essentially, they've covered the entire grunt work required to do this manually. Finally, you can create a inline or chat widget on your client's website with a few lines of HTML, or altneratively integrate it with a Slack/Teams chatbot (if you are going for an internal Q&A chatbot approach). Other tools you could use include Botpress and Voiceflow, however these are less for RAG and more for building out complete chatbot flows that may or may not incorporate LLMs. Both apps are essentially GUIs that eliminate the pain and tears and trying to implement complex flows manually, and both natively incoporate AI intents and a knowledge base feature. Ex. Solution 2: Internal Apps Similar to the first example, except we go beyond making just chatbots but tools such as report generation and really any sort of internal tool or automations that may incorporate LLM's. For instance, you can have a tool that automatically generates replies to inbound emails based on your client's knowledge base. Or an automation that does the same thing but for replies to Instagram comments. Another example could be a tool that generates a description and screeenshot based on a URL (useful for directory sites, made one for my own :P). Getting into more advanced implementations of LLMs, we can have tools that can generate entire drafts of reports (think 80+ pages), based not only on data from a knowledge base but also the writing style, format, and author voice of previous reports. One good tool to create content generation panels for your clients would be MindStudio. You can train LLM's via prompt engineering in a structured way with your own data to essentially fine tune them for whatever text you need it to generate. Furthermore, it has a GUI where you can dictate the entire AI flow. You can also upload data sources via multiple formats, including PDF, CSV, and Docx. For automations that require interactions between multiple apps, I recommend the OG zapier/make.com if you want a no-code solution. For instance, for the automatic email reply generator, I can have a trigger such that when an email is received, a custom AI reply is generated by MyAskAI, and finally a draft is created in my email client. Or, for an automation where I can create a social media posts on multiple platforms based on a RSS feed (news feed), I can implement this directly in Zapier with their native GPT action (see screenshot) As for more complex LLM flows that may require multiple layers of LLMs, data sources, and APIs working together to generate a single response i.e. a long form 100 page report, I would recommend tools such as Stack AI or Flowise (open-source alternative) to build these solutions out. Essentially, you get most of the functions and features of Python packages such as Langchain and LlamaIndex in a GUI. See screenshot for an example of a flow How the hell are you supposed to find clients? With all that being said, none of this matters if you can't find anyone to sell to. You will have to do cold sales, one way or the other, especially if you are brand new to the game. And what better way to sell your AI services than with AI itself? If we want to integrate AI into the cold outreach process, first we must identify what it's good at doing, and that's obviously writing a bunch of text, in a short amount of time. Similar to the solutions that an AAA can build for its clients, we can take advantage of the same principles in our own sales processes. How to do outreach Once you've identified your niche and their pain points/opportunities for automation, you want to craft a compelling message in which you can send via cold email and cold calls to get prospects booked on demos/consultations. I won't get into too much detail in terms of exactly how to write emails or calling scripts, as there are millions of resources to help with this, but I will tell you a few key points you want to keep in mind when doing outreach for your AAA. First, you want to keep in mind that many businesses are still hesitant about AI and may not understand what it really is or how it can benefit their operations. However, we can take advantage of how mass media has been reporting on AI this past year- at the very least people are AWARE that sooner or later they may have to implement AI into their businesses to stay competitive. We want to frame our message in a way that introduces generative AI as a technology that can have a direct, tangible, and positive impact on their business. Although it may be hard to quantify, I like to include estimates of man-hours saved or costs saved at least in my final proposals to prospects. Times are TOUGH right now, and money is expensive, so you need to have a compelling reason for businesses to get on board. Once you've gotten your messaging down, you will want to create a list of prospects to contact. Tools you can use to find prospects include Apollo.io, reply.io, zoominfo (expensive af), and Linkedin Sales Navigator. What specific job titles, etc. to target will depend on your niche but for smaller companies this will tend to be the owner. For white collar niches, i.e. law, the professional that will be directly benefiting from the tool (i.e. partners) may be better to contact. And for larger organizations you may want to target business improvement and digital transformation leads/directors- these are the people directly in charge of projects like what you may be proposing. Okay- so you have your message, and your list, and now all it comes down to is getting the good word out. I won't be going into the details of how to send these out, a quick Google search will give you hundreds of resources for cold outreach methods. However, personalization is key and beyond simple dynamic variables you want to make sure you can either personalize your email campaigns directly with AI (SmartWriter.ai is an example of a tool that can do this), or at the very least have the ability to import email messages programmatically. Alternatively, ask ChatGPT to make you a Python Script that can take in a list of emails, scrape info based on their linkedin URL or website, and all pass this onto a GPT prompt that specifies your messaging to generate an email. From there, send away. How tf do I close? Once you've got some prospects booked in on your meetings, you will need to close deals with them to turn them into clients. Call #1: Consultation Tying back to when I mentioned you want to take a consultant-first appraoch, you will want to listen closely to their goals and needs and understand their pain points. This would be the first call, and typically I would provide a high level overview of different solutions we could build to tacke these. It really helps to have a presentation available, so you can graphically demonstrate key points and key technologies. I like to use Plus AI for this, it's basically a Google Slides add-on that can generate slide decks for you. I copy and paste my default company messaging, add some key points for the presentation, and it comes out with pretty decent slides. Call #2: Demo The second call would involve a demo of one of these solutions, and typically I'll quickly prototype it with boilerplate code I already have, otherwise I'll cook something up in a no-code tool. If you have a niche where one type of solution is commonly demanded, it helps to have a general demo set up to be able to handle a larger volume of calls, so you aren't burning yourself out. I'll also elaborate on how the final product would look like in comparison to the demo. Call #3 and Beyond: Once the initial consultation and demo is complete, you will want to alleviate any remaining concerns from your prospects and work with them to reach a final work proposal. It's crucial you lay out exactly what you will be building (in writing) and ensure the prospect understands this. Furthermore, be clear and transparent with timelines and communication methods for the project. In terms of pricing, you want to take this from a value-based approach. The same solution may be worth a lot more to client A than client B. Furthermore, you can create "add-ons" such as monthly maintenance/upgrade packages, training sessions for employeees, and so forth, separate from the initial setup fee you would charge. How you can incorporate AI into marketing your businesses Beyond cold sales, I highly recommend creating a funnel to capture warm leads. For instance, I do this currently with my AI tools directory, which links directly to my AI agency and has consistent branding throughout. Warm leads are much more likely to close (and honestly, much nicer to deal with). However, even without an AI-related website, at the very least you will want to create a presence on social media and the web in general. As with any agency, you will want basic a professional presence. A professional virtual address helps, in addition to a Google Business Profile (GBP) and TrustPilot. a GBP (especially for local SEO) and Trustpilot page also helps improve the looks of your search results immensely. For GBP, I recommend using ProfilePro, which is a chrome extension you can use to automate SEO work for your GBP. Aside from SEO optimzied business descriptions based on your business, it can handle Q/A answers, responses, updates, and service descriptions based on local keywords. Privacy and Legal Concerns of the AAA Model Aside from typical concerns for agencies relating to service contracts, there are a few issues (especially when using no-code tools) that will need to be addressed to run a successful AAA. Most of these surround privacy concerns when working with proprietary data. In your terms with your client, you will want to clearly define hosting providers and any third party tools you will be using to build their solution, and a DPA with these third parties listed as subprocessors if necessary. In addition, you will want to implement best practices like redacting private information from data being used for building solutions. In terms of addressing concerns directly from clients, it helps if you host your solutions on their own servers (not possible with AI tools), and address the fact only ChatGPT queries in the web app, not OpenAI API calls, will be used to train OpenAI's models (as reported by mainstream media). The key here is to be open and transparent with your clients about ALL the tools you are using, where there data will be going, and make sure to get this all in writing. have fun, and keep an open mind Before I finish this post, I just want to reiterate the fact that this is NOT an easy way to make money. Running an AI agency will require hours and hours of dedication and work, and constantly rearranging your schedule to meet prospect and client needs. However, if you are looking for a new business to run, and have a knack for understanding business operations and are genuinely interested in the pracitcal applications of generative AI, then I say go for it. The time is ticking before AAA becomes the new dropshipping or SMMA, and I've a firm believer that those who set foot first and establish themselves in this field will come out top. And remember, while 100 thousand people may read this post, only 2 may actually take initiative and start.

#reddit#automation#agency

reddit

0

1

FounderFolks•This week

Turning a Social Media Agency into $1.5 Million in Revenue

Steffie here from Founder Folks, with a recent interview I did with Jason Yormark from Socialistics. Here is his story how he started and grew his social media agency. Name: Jason Yormark Company: Socialistics Employee Size: 10 Revenue: $1,500,000/year Year Founded: 2018 Website: www.socialistics.com Technology Tools: ClickUp, Slack, KumoSpace, Google Workspace, Shift, Zapier, Klayvio, Zoom, Gusto, Calendly, Pipedrive Introduction: I am the founder of Socialistics (www.socialistics.com), a leading social media agency that helps businesses turn their social media efforts into real measurable results. I am a 20+ year marketing veteran whose prior work has included launching and managing social media efforts for Microsoft Advertising, Office for Mac, the Air Force, and Habitat for Humanity. I have been recognized as a top B2B social media influencer and thought leader on multiple lists and publications including Forbes, ranking #30 on their 2012 list. I've recently published the book Anti-Agency: A Realistic Path to a $1,000,000 Business, and host the Anti Agency podcast where I share stories of doing business differently. You can learn more about me at www.jasonyormark.com. The Inspiration To Become An Entrepreneur: I’ve been involved with social media marketing since 2007, and have pretty much carved my career out of that. It was a natural progression for me to transition into starting a social media agency. From Idea to Reality: For me realistically, I had to side hustle something long enough to build it up to a point that I could take the leap and risks going full time on my own. For these reasons, I built the company and brand on the side putting out content regularly, and taking on side hustle projects to build out my portfolio and reputation. This went on for about 18 months at which point I had reached the breaking point of my frustrations of working for someone else, and felt I was ready to take the leap since I had the wheels in motion. While balancing a full-time job, I made sure not to overdo it. My main focus was on building out the website/brand and putting out content regularly to gain some traction and work towards some search visibility. I only took on 1-2 clients at a time to make sure I could still meet their needs while balancing a full time job. Attracting Customers: Initially I tapped into my existing network to get my first few clients. Then it was a mix of trade shows, networking events, and throwing a bit of money at paid directories and paid media. This is really a long game. You have to plant seeds over time with people and nurture those relationships over time. A combination of being helpful, likable and a good resource for folks will position you to make asks in the future. If people respect and like you, it makes it much easier to approach for opportunities when the time comes. Overcoming Challenges in Starting the Business: Plenty. Learning when to say no, only hiring the very best, and ultimately the realization that owning a marketing agency is going to have hills and valleys no matter what you do. Costs and Revenue: My largest expense by FAR is personnel, comprising between 50-60% of the business’ expenses, and justifiably so. It’s a people business. Our revenue doubled from the years 2018 through 2021, and we’ve seen between 10-20% growth year over year. A Day in the Life: I’ve successfully removed myself from the day to day of the business and that’s by design. I have a tremendous team, and a rock start Director of Operations who runs the agency day to day. It frees me up to pursue other opportunities, and to mentor, speak and write more. It also allows me to evangelize the book I wrote detailing my journey to a $1M business titled: Anti-Agency: A Realistic Path To A $1,000,000 Business (www.antiagencybook.com). Staying Ahead in a Changing Landscape: You really have to stay on top of technology trends. AI is a huge impact on marketing these days, so making sure we are up to speed on that, and not abusing it or relying on it too much. You also have to embrace that technology and not hide the fact that it’s used. Non-marketers still don’t and can’t do the work regardless of how much AI can help, so we just need to be transparent and smart on how we integrate it, but the fact is, technology will never replace creativity. As an agency, it’s imperative that we operationally allow our account managers to have bandwidth to be creative for clients all the time. It’s how we keep clients and buck the trend of companies changing agencies every year or two. The Vision for Socialistics: Continuing to evolve to cater to our clients through learning, education, and staying on top of the latest tools and technologies. Attracting bigger and more exciting clients, and providing life changing employment opportunities.

#reddit#turning#social

reddit

0

1

marin_smiljanic•This week

Raised $450k for my startup, here are the lessons I've learned along the way

2021 has been a pretty amazing year for Omnisearch. Having started initial work on Omnisearch at the end of 2020, we entered the new year with a working MVP yet no revenue, no significant partnerships, and no funding. Fast forward to the end of 2021, and we now have fantastic revenue growth, a partnership with a public company, and a far more powerful, complete and polished product. But one milestone really changed Omnisearch’s trajectory: our $450,000 USD pre-seed round by GoAhead Ventures. In this post I want to share the story of how it came about and offer a couple of takeaways to keep in mind when preparing for fundraising. ​ The story Contrary to most advice, my co-founder Matej and I didn’t allocate a specific time to switch to “fundraising mode” but rather talked to investors on an ongoing basis. It was a bit of a distraction from working on the product, but on the positive side we were able to constantly get feedback on the idea, pitch, go-to-market strategy and hiring, as well as hearing investors’ major concerns sooner rather than later. That being said, our six-month long fundraising efforts weren’t yielding results - we talked to about twenty investors, mostly angels or smaller funds, with no success. The feedback was generally of the “too early for us” variety (since we were still pre-revenue), with additional questions about our go-to-market strategy and ideal customer persona. The introduction to our eventual investors, California-based GoAhead Ventures, came through a friend who had pitched them previously. We wrote a simple blurb and sent our pitch deck. We then went through GoAhead’s hyper-efficient screening process, consisting of a 30-minute call, a recorded three-minute pitch, and filling out a simple Google doc. Throughout the whole process, the GoAhead team left an awesome impression thanks to their knowledge of enterprise software and their responsiveness. They ended up investing and the whole deal was closed within two weeks, which is super fast even by Silicon Valley standards. While our fundraising experience is a single data point and your case might be different, here are the key takeaways from our journey. ​ Perseverance wins: Like I said above, we talked to about twenty investors before we closed our round. Getting a series of “no”s sucks, but we took the feedback seriously and tried to prepare better for questions that caught us off guard. But we persevered, keeping in mind that from a bird’s eye perspective it’s an amazing time to be building startups and raising funds. Focus on traction: Sounds pretty obvious, right? The truth is, though, that even a small amount of revenue is infinitely better than none at all. One of the major differences between our eventual successful investor pitch and the earlier ones was that we had actual paying customers, though our MRR was low. This allows you to talk about customers in the present tense, showing there’s actual demand for your product and making the use cases more tangible. And ideally, highlight a couple of customer testimonials to boost your credibility. Have a demo ready: In Omnisearch’s case, the demo was oftentimes the best received part of the pitch or call. We’d show investors the live demo, and for bonus points even asked them to choose a video from YouTube and then try searching through it. This always had a “wow” effect on prospective investors and made the subsequent conversation more exciting and positive. Accelerators: Accelerators like Y Combinator or Techstars can add enormous value to a startup, especially in the early stages. And while it’s a great idea to apply, don’t rely on them too heavily. Applications happen only a few times a year, and you should have a foolproof fundraising plan in case you don’t get in. In our case, we just constantly looked for investors who were interested in our space (defined as enterprise SaaS more broadly), using LinkedIn, AngelList, and intros from our own network. Practice the pitch ad nauseam: Pitching is tough to get right even for seasoned pros, so it pays to practice as often as possible. We took every opportunity to perfect the pitch: attending meetups and giving the thirty-second elevator pitch to other attendees over beer and pizza, participating in startup competitions, going to conferences and exhibiting at our own booth, attending pre-accelerator programs, and pitching to friends who are in the startup world. Show an understanding of the competition: Frankly, this was one of the strongest parts of our pitch and investor conversations. If you’re in a similar space to ours, Gartner Magic Quadrants and Forrester Waves are an awesome resource, as well as sites like AlternativeTo or Capterra and G2. By thoroughly studying these resources we gained a great understanding of the industry landscape and were able to articulate our differentiation more clearly and succinctly. Presenting this visually in a coordinate system or a feature grid is, from our experience, even more effective. Remember it’s just the beginning! Getting your first round of funding is just the beginning of the journey, so it’s important to avoid euphoria and get back to building and selling the product as soon as possible. While securing funding enables you to scale the team, and is a particular relief if the founders had worked without a salary, the end goal is still to build a big, profitable, and overall awesome startup.

#reddit#raised#$450k

reddit

0

0

chillbroda•This week

The New Fast Growing Framework for any Startups (Non promotion)

Hi community, I'm Julian, Co Founder of 2 AI, Marketing and Automation companies, and Solo Founder of a company that it is starting now, after a long Social-Market research, in which I am looking to other founders to participate under a new Complex Framework without cost. It is difficult to explain on an introduction. If there is someone interested to further information please contact me. Thank you!

#reddit#fast#growing

reddit

0

0.895

matthewbarby•This week

The delicate balance of building an online community business

Hey /r/Entrepreneur 👋 Just under two years ago I launched an online community business called Traffic Think Tank with two other co-founders, Nick Eubanks and Ian Howells. As a Traffic Think Tank customer you (currently) pay $119 a month to get access to our online community, which is run through Slack. The community is focused on helping you learn various aspects of marketing, with a particular focus on search engine optimization (SEO). Alongside access to the Slack community, we publish new educational video content from outside experts every week that all customers have access to. At the time of writing, Traffic Think Tank has around 650 members spanning across 17 of the 24 different global time zones. I was on a business trip over in Sydney recently, and during my time there I met up with some of our Australia-based community members. During dinner I was asked by several of them how the idea for Traffic Think Tank came about and what steps we took to validate that the idea was worth pursuing.  This is what I told them… How it all began It all started with a personal need. Nick, an already successful entrepreneur and owner of a marketing agency, had tested out an early version Traffic Think Tank in early 2017. He offered real-time consulting for around ten customers that he ran from Slack. He would publish some educational videos and offer his advice on projects that the members were running. The initial test went well, but it was tough to maintain on his own and he had to charge a fairly high price to make it worth his time. That’s when he spoke to me and Ian about turning this idea into something much bigger. Both Ian and I offered something slightly different to Nick. We’ve both spent time in senior positions at marketing agencies, but currently hold senior director positions in 2,000+ public employee companies (HubSpot and LendingTree). Alongside this, as a trio we could really ramp up the quality and quantity of content within the community, spread out the administrative workload and just generally have more resources to throw at getting this thing off the ground. Admittedly, Nick was much more optimistic about the potential of Traffic Think Tank – something I’m very thankful for now – whereas Ian and I were in the camp of “you’re out of your mind if you think hundreds of people are going to pay us to be a part of a Slack channel”. To validate the idea at scale, we decided that we’d get an initial MVP of the community up and running with a goal of reaching 100 paying customers in the first six months. If we achieved that, we’d validated that it was a viable business and we would continue to pursue it. If not, we’d kill it. We spent the next month building out the initial tech stack that enabled us to accept payments, do basic user management to the Slack channel, and get a one-page website up and running with information on what Traffic Think Tank was all about.  After this was ready, we doubled down on getting some initial content created for members – I mean, we couldn’t have people just land in an empty Slack channel, could we? We created around ten initial videos, 20 or so articles and then some long threads full of useful information within the Slack channel so that members would have some content to pour into right from the beginning.  Then, it was time to go live. The first 100 customers Fortunately, both Nick and I had built a somewhat substantial following in the SEO space over the previous 5-10 years, so we at least had a large email list to tap into (a total of around 40,000 people). We queued up some launch emails, set an initial price of $99 per month and pressed send. [\[LINK\] The launch email I sent to my subscribers announcing Traffic Think Tank](https://mailchi.mp/matthewbarby/future-of-marketing-1128181) What we didn’t expect was to sell all of the initial 100 membership spots in the first 72 hours. “Shit. What do we do now? Are we ready for this many people? Are we providing them with enough value? What if something breaks in our tech stack? What if they don’t like the content? What if everyone hates Slack?” All of these were thoughts running through my head. This brings me to the first great decision we made: we closed down new membership intake for 3 months so that we could focus completely on adding value to the first cohort of users. The right thing at the right time SEO is somewhat of a dark art to many people that are trying to learn about it for the first time. There’s hundreds of thousands (possibly millions) of articles and videos online that talk about how to do SEO.  Some of it’s good advice; a lot of it is very bad advice.  Add to this that the barrier to entry of claiming to be an “expert” in SEO is practically non-existent and you have a recipe for disaster. This is why, for a long time, individuals involved in SEO have flocked in their masses to online communities for information and to bounce ideas off of others in the space. Forums like SEObook, Black Hat World, WickedFire, Inbound.org, /r/BigSEO, and many more have, at one time, been called home by many SEOs.  In recent times, these communities have either been closed down or just simply haven’t adapted to the changing needs of the community – one of those needs being real-time feedback on real-world problems.  The other big need that we all spotted and personally had was the ability to openly share the things that are working – and the things that aren’t – in SEO within a private forum. Not everyone wanted to share their secret sauce with the world. One of the main reasons we chose Slack as the platform to run our community on was the fact that it solved these two core needs. It gave the ability to communicate in real-time across multiple devices, and all of the information shared within it was outside of the public domain. The other problem that plagued a lot of these early communities was spam. Most of them were web-based forums that were free to access. That meant they became a breeding ground for people trying to either sell their services or promote their own content – neither of which is conducive to building a thriving community. This was our main motivation for charging a monthly fee to access Traffic Think Tank. We spent a lot of time thinking through pricing. It needed to be enough money that people would be motivated to really make use of their membership and act in a way that’s beneficial to the community, but not too much money that it became cost prohibitive to the people that would benefit from it the most. Considering that most of our members would typically spend between $200-800 per month on SEO software, $99 initially felt like the perfect balance. Growing pains The first three months of running the community went by without any major hiccups. Members were incredibly patient with us, gave us great feedback and were incredibly helpful and accommodating to other members. Messages were being posted every day, with Nick, Ian and myself seeding most of the engagement at this stage.  With everything going smoothly, we decided that it was time to open the doors to another intake of new members. At this point we’d accumulated a backlog of people on our waiting list, so we knew that simply opening our doors would result in another large intake. Adding more members to a community has a direct impact on the value that each member receives. For Traffic Think Tank in particular, the value for members comes from three areas: The ability to have your questions answered by me, Nick and Ian, as well as other members of the community. The access to a large library of exclusive content. The ability to build connections with the wider community. In the early stages of membership growth, there was a big emphasis on the first of those three points. We didn’t have an enormous content library, nor did we have a particularly large community of members, so a lot of the value came from getting a lot of one-to-one time with the community founders. [\[IMAGE\] Screenshot of engagement within the Traffic Think Tank Slack community](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1322/https://www.matthewbarby.com/wp-content/uploads/2019/08/Community-Engagement-in-Traffic-Think-Tank.png) The good thing about having 100 members was that it was just about feasible to give each and every member some one-to-one time within the month, which really helped us to deliver those moments of delight that the community needed early on. Two-and-a-half months after we launched Traffic Think Tank, we opened the doors to another 250 people, taking our total number of members to 350. This is where we experienced our first growing pains.  Our original members had become used to being able to drop us direct messages and expect an almost instant response, but this wasn’t feasible anymore. There were too many people, and we needed to create a shift in behavior. We needed more value to come from the community engaging with one another or we’d never be able to scale beyond this level. We started to really pay attention to engagement metrics; how many people were logging in every day, and of those, how many were actually posting messages within public channels.  We asked members that were logging in a lot but weren’t posting (the “lurkers”) why that was the case. We also asked the members that engaged in the community the most what motivated them to post regularly. We learned a lot from doing this. We found that the large majority of highly-engaged members had much more experience in SEO, whereas most of the “lurkers” were beginners. This meant that most of the information being shared in the community was very advanced, with a lot of feedback from the beginners in the group being that they “didn’t want to ask a stupid question”.  As managers of the community, we needed to facilitate conversations that catered to all of our members, not just those at a certain level of skill. To tackle this problem, we created a number of new channels that had a much deeper focus on beginner topics so novice members had a safe place to ask questions without judgment.  We also started running live video Q&As each month where we’d answer questions submitted by the community. This gave our members one-on-one time with me, Nick and Ian, but spread the value of these conversations across the whole community rather than them being hidden within private messages. As a result of these changes, we found that the more experienced members in the community were really enjoying sharing their knowledge with those with less experience. The number of replies within each question thread was really starting to increase, and the community started to shift away from just being a bunch of threads created by me, Nick and Ian to a thriving forum of diverse topics compiled by a diverse set of individuals. This is what we’d always wanted. A true community. It was starting to happen. [\[IMAGE\] Chart showing community engagement vs individual member value](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1602/https://www.matthewbarby.com/wp-content/uploads/2019/08/Community-Engagement-Balance-Graph.jpg) At the same time, we started to realize that we’ll eventually reach a tipping point where there’ll be too much content for us to manage and our members to engage with. When we reach this point, the community will be tough to follow and the quality of any given post will go down. Not only that, but the community will become increasingly difficult to moderate. We’re not there yet, but we recognize that this will come, and we’ll have to adjust our model again. Advocating advocacy As we started to feel more comfortable about the value that members were receiving, we made the decision to indefinitely open for new members. At the same time, we increased the price of membership (from $99 a month to $119) in a bid to strike the right balance between profitability as a business and to slow down the rate at which we were reaching the tipping point of community size. We also made the decision to repay all of our early adopters by grandfathering them in to the original pricing – and committing to always do this in the future. Despite the price increase, we saw a continued flow of new members come into the community. The craziest part about this was that we were doing practically no marketing activities to encourage new members– this was all coming from word of mouth. Our members were getting enough value from the community that they were recommending it to their friends, colleagues and business partners.  The scale at which this was happening really took us by surprise and it told us one thing very clearly: delivering more value to members resulted in more value being delivered to the business. This is a wonderful dynamic to have because it perfectly aligns the incentives on both sides. We’d said from the start that we wouldn’t sacrifice value to members for more revenue – this is something that all three of us felt very strongly about. First and foremost, we wanted to create a community that delivered value to its members and was run in a way that aligned with our values as people. If we could find a way to stimulate brand advocacy, while also tightening the bonds between all of our individual community members, we’d be boosting both customer retention and customer acquisition in the same motion. This became our next big focus. [\[TWEET\] Adam, one of our members wore his Traffic Think Tank t-shirt in the Sahara desert](https://twitter.com/AdamGSteele/status/1130892481099382784) We started with some simple things: We shipped out Traffic Think Tank branded T-shirts to all new members. We’d call out each of the individuals that would submit questions to our live Q&A sessions and thank them live on air. We set up a new channel that was dedicated to sharing a quick introduction to who you are, what you do and where you’re based for all new members. We’d created a jobs channel and a marketplace for selling, buying and trading services with other members. Our monthly “blind dates” calls were started where you’d be randomly grouped with 3-4 other community members so that you could hop on a call to get to know each other better. The Traffic Think Tank In Real Life (IRL)* channel was born, which enabled members to facilitate in-person meetups with each other. In particular, we saw that as members started to meet in person or via calls the community itself was feeling more and more like a family. It became much closer knit and some members started to build up a really positive reputation for being particularly helpful to other members, or for having really strong knowledge in a specific area. [\[TWEET\] Dinner with some of the Traffic Think Tank members in Brighton, UK](https://twitter.com/matthewbarby/status/1117175584080134149) Nick, Ian and I would go out of our way to try and meet with members in real life wherever we could. I was taken aback by how appreciative people were for us doing this, and it also served as an invaluable way to gain honest feedback from members. There was another trend that we’d observed that we didn’t really expect to happen. More and more members were doing business with each another. We’ve had people find new jobs through the community, sell businesses to other members, launch joint ventures together and bring members in as consultants to their business. This has probably been the most rewarding thing to watch, and it was clear that the deeper relationships that our members were forming were resulting in an increased level of trust to work with each other. We wanted to harness this and take it to a new level. This brought us to arguably the best decision we’ve made so far running Traffic Think Tank… we were going to run a big live event for our members. I have no idea what I’m doing It’s the first week of January 2019 and we’re less than three weeks away from Traffic Think Tank LIVE, our first ever in-person event hosting 150 people, most of which are Traffic Think Tank members. It's like an ongoing nightmare I can’t wake up from. That was Nick’s response in our private admin channel to myself and Ian when I asked if they were finding the run-up to the event as stressful as I was. I think that all three of us were riding on such a high from how the community was growing that we felt like we could do anything. Running an event? How hard can it be? Well, turns out it’s really hard. We had seven different speakers flying over from around the world to speak at the event, there was a pre- and after event party, and we’d planned a charity dinner where we would take ten attendees (picked at random via a raffle) out for a fancy meal. Oh, and Nick, Ian and I were hosting a live Q&A session on stage. It wasn’t until precisely 48 hours before the event that we’d realized we didn’t have any microphones, nor had a large amount of the swag we’d ordered arrived. Plus, a giant storm had hit Philly causing a TON of flight cancellations. Perfect. Just perfect. This was honestly the tip of the iceberg. We hadn’t thought about who was going to run the registration desk, who would be taking photos during the event and who would actually field questions from the audience while all three of us sat on stage for our live Q&A panel. Turns out that the answer to all of those questions were my wife, Laura, and Nick’s wife, Kelley. Thankfully, they were on hand to save our asses. The weeks running up to the event were honestly some of the most stressful of my life. We sold around 50% of our ticket allocation within the final two weeks before the event. All of the event organizers told us this would happen, but did we believe them? Hell no!  Imagine having two weeks until the big day and as it stood half of the room would be completely empty. I was ready to fly most of my extended family over just to make it look remotely busy. [\[IMAGE\] One of our speakers, Ryan Stewart, presenting at Traffic Think Tank LIVE](https://cdn.shortpixel.ai/client/qglossy,retimg,w_1920/https://www.matthewbarby.com/wp-content/uploads/2019/08/Traffic-Think-Tank-LIVE-Ryan-Presenting.jpg) Thankfully, if all came together. We managed to acquire some microphones, the swag arrived on the morning of the event, all of our speakers were able to make it on time and the weather just about held up so that our entire allocation of ticket holders was able to make it to the event. We pooled together and I’m proud to say that the event was a huge success. While we made a substantial financial loss on the event itself, January saw a huge spike in new members, which more than recouped our losses. Not only that, but we got to hang out with a load of our members all day while they said really nice things about the thing we’d built. It was both exhausting and incredibly rewarding. Bring on Traffic Think Tank LIVE 2020! (This time we’re hiring an event manager...)   The road ahead Fast forward to today (August 2019) and Traffic Think Tank has over 650 members. The biggest challenges that we’re tackling right now include making sure the most interesting conversations and best content surfaces to the top of the community, making Slack more searchable (this is ultimately one of its flaws as a platform) and giving members a quicker way to find the exclusive content that we create. You’ll notice there’s a pretty clear theme here. In the past 30 days, 4,566 messages were posted in public channels inside Traffic Think Tank. If you add on any messages posted inside private direct messages, this number rises to 21,612. That’s a lot of messages. To solve these challenges and enable further scale in the future, we’ve invested a bunch of cash and our time into building out a full learning management system (LMS) that all members will get access to alongside the Slack community. The LMS will be a web-based portal that houses all of the video content we produce. It will also  provide an account admin section where users can update or change their billing information (they have to email us to do this right now, which isn’t ideal), a list of membership perks and discounts with our partners, and a list of links to some of the best threads within Slack – when clicked, these will drop you directly into Slack. [\[IMAGE\] Designs for the new learning management system (LMS)](https://cdn.shortpixel.ai/client/qglossy,retimg,w_2378/https://www.matthewbarby.com/wp-content/uploads/2019/08/Traffic-Think-Tank-LMS.png) It’s not been easy, but we’re 95% of the way through this and I’m certain that it will have a hugely positive impact on the experience for our members. Alongside this we hired a community manager, Liz, who supports with any questions that our members have, coordinates with external experts to arrange webinars for the community, helps with new member onboarding, and has tightened up some of our processes around billing and general accounts admin. This was a great decision. Finally, we’ve started planning next year’s live event, which we plan to more than double in size to 350 attendees, and we decided to pick a slightly warmer location in Miami this time out. Stay tuned for me to have a complete meltdown 3 weeks from the event. Final thoughts When I look back on the journey we’ve had so far building Traffic Think Tank, there’s one very important piece to this puzzle that’s made all of this work that I’ve failed to mention so far: co-founder alignment. Building a community is a balancing act that relies heavily on those in charge being completely aligned. Nick, Ian and I completely trust each other and more importantly, are philosophically aligned on how we want to run and grow the community. If we didn’t have this, the friction between us could tear apart the entire community. Picking the right people to work with is important in any company, but when your business is literally about bringing people together, there’s no margin for error here.  While I’m sure there will be many more challenges ahead, knowing that we all trust each other to make decisions that fall in line with each of our core values makes these challenges dramatically easier to overcome. Finally, I’d like to thank all of our members for making the community what it is today – it’d be nothing without you and I promise that we’ll never take that for granted. ​ I originally posted this on my blog here. Welcoming all of your thoughts, comments, questions and I'll do my best to answer them :)

#reddit#delicate#balance

reddit

0

1

Royal_Rest8409•This week

How a founder built a B2B AI startup to serve with 65+ global brands (including Fortune500 companies)

AI Palette is an AI-driven platform that helps food and beverage companies predict emerging product trends. I had the opportunity recently to sit down with the founder to get his advice on building an AI-first startup, which he'll be going through in this post. About AI Palette: Co-founders: >!2 (Somsubhra GanChoudhuri, Himanshu Upreti)!!100+!!$12.7M USD!!AI-powered predictive analytics for the CPG (Consumer Packaged Goods) industry!!Signed first paying customer in the first year!!65+ global brands, including Cargill, Diageo, Ajinomoto, Symrise, Mondelez, and L’Oréal, use AI Palette!!Every new product launched has secured a paying client within months!!Expanded into Beauty & Personal Care (BPC), onboarding one of India’s largest BPC companies within weeks!!Launched multiple new product lines in the last two years, creating a unified suite for brand innovation!Identify the pain points in your industry for ideas* When I was working in the flavour and fragrance industry, I noticed a major issue CPG companies faced: launching a product took at least one to two years. For instance, if a company decided today to launch a new juice, it wouldn’t hit the market until 2027. This long timeline made it difficult to stay relevant and on top of trends. Another big problem I noticed was that companies relied heavily on market research to determine what products to launch. While this might work for current consumer preferences, it was highly inefficient since the product wouldn’t actually reach the market for several years. By the time the product launched, the consumer trends had already shifted, making that research outdated. That’s where AI can play a crucial role. Instead of looking at what consumers like today, we realised that companies should use AI to predict what they will want next. This allows businesses to create products that are ahead of the curve. Right now, the failure rate for new product launches is alarmingly high, with 8 out of 10 products failing. By leveraging AI, companies can avoid wasting resources on products that won’t succeed, leading to better, more successful launches. Start by talking to as many industry experts as possible to identify the real problems When we first had the idea for AI Palette, it was just a hunch, a gut feeling—we had no idea whether people would actually pay for it. To validate the idea, we reached out to as many people as we could within the industry. Since our focus area was all about consumer insights, we spoke to professionals in the CPG sector, particularly those in the insights departments of CPG companies. Through these early conversations, we began to see a common pattern emerge and identified the exact problem we wanted to solve. Don’t tell people what you’re building—listen to their frustrations and challenges first. Going into these early customer conversations, our goal was to listen and understand their challenges without telling them what we were trying to build. This is crucial as it ensures that you can gather as much data about the problem to truly understand it and that you aren't biasing their answers by showing your solution. This process helped us in two key ways: First, it validated that there was a real problem in the industry through the number of people who spoke about experiencing the same problem. Second, it allowed us to understand the exact scale and depth of the problem—e.g., how much money companies were spending on consumer research, what kind of tools they were currently using, etc. Narrow down your focus to a small, actionable area to solve initially. Once we were certain that there was a clear problem worth solving, we didn’t try to tackle everything at once. As a small team of two people, we started by focusing on a specific area of the problem—something big enough to matter but small enough for us to handle. Then, we approached customers with a potential solution and asked them for feedback. We learnt that our solution seemed promising, but we wanted to validate it further. If customers are willing to pay you for the solution, it’s a strong validation signal for market demand. One of our early customer interviewees even asked us to deliver the solution, which we did manually at first. We used machine learning models to analyse the data and presented the results in a slide deck. They paid us for the work, which was a critical moment. It meant we had something with real potential, and we had customers willing to pay us before we had even built the full product. This was the key validation that we needed. By the time we were ready to build the product, we had already gathered crucial insights from our early customers. We understood the specific information they wanted and how they wanted the results to be presented. This input was invaluable in shaping the development of our final product. Building & Product Development Start with a simple concept/design to validate with customers before building When we realised the problem and solution, we began by designing the product, but not by jumping straight into coding. Instead, we created wireframes and user interfaces using tools like InVision and Figma. This allowed us to visually represent the product without the need for backend or frontend development at first. The goal was to showcase how the product would look and feel, helping potential customers understand its value before we even started building. We showed these designs to potential customers and asked for feedback. Would they want to buy this product? Would they pay for it? We didn’t dive into actual development until we found a customer willing to pay a significant amount for the solution. This approach helped us ensure we were on the right track and didn’t waste time or resources building something customers didn’t actually want. Deliver your solution using a manual consulting approach before developing an automated product Initially, we solved problems for customers in a more "consulting" manner, delivering insights manually. Recall how I mentioned that when one of our early customer interviewees asked us to deliver the solution, we initially did it manually by using machine learning models to analyse the data and presenting the results to them in a slide deck. This works for the initial stages of validating your solution, as you don't want to invest too much time into building a full-blown MVP before understanding the exact features and functionalities that your users want. However, after confirming that customers were willing to pay for what we provided, we moved forward with actual product development. This shift from a manual service to product development was key to scaling in a sustainable manner, as our building was guided by real-world feedback and insights rather than intuition. Let ongoing customer feedback drive iteration and the product roadmap Once we built the first version of the product, it was basic, solving only one problem. But as we worked closely with customers, they requested additional features and functionalities to make it more useful. As a result, we continued to evolve the product to handle more complex use cases, gradually developing new modules based on customer feedback. Product development is a continuous process. Our early customers pushed us to expand features and modules, from solving just 20% of their problems to tackling 50–60% of their needs. These demands shaped our product roadmap and guided the development of new features, ultimately resulting in a more complete solution. Revenue and user numbers are key metrics for assessing product-market fit. However, critical mass varies across industries Product-market fit (PMF) can often be gauged by looking at the size of your revenue and the number of customers you're serving. Once you've reached a certain critical mass of customers, you can usually tell that you're starting to hit product-market fit. However, this critical mass varies by industry and the type of customers you're targeting. For example, if you're building an app for a broad consumer market, you may need thousands of users. But for enterprise software, product-market fit may be reached with just a few dozen key customers. Compare customer engagement and retention with other available solutions on the market for product-market fit Revenue and the number of customers alone isn't always enough to determine if you're reaching product-market fit. The type of customer and the use case for your product also matter. The level of engagement with your product—how much time users are spending on the platform—is also an important metric to track. The more time they spend, the more likely it is that your product is meeting a crucial need. Another way to evaluate product-market fit is by assessing retention, i.e whether users are returning to your platform and relying on it consistently, as compared to other solutions available. That's another key indication that your solution is gaining traction in the market. Business Model & Monetisation Prioritise scalability Initially, we started with a consulting-type model where we tailor-made specific solutions for each customer use-case we encountered and delivered the CPG insights manually, but we soon realized that this wasn't scalable. The problem with consulting is that you need to do the same work repeatedly for every new project, which requires a large team to handle the workload. That is not how you sustain a high-growth startup. To solve this, we focused on building a product that would address the most common problems faced by our customers. Once built, this product could be sold to thousands of customers without significant overheads, making the business scalable. With this in mind, we decided on a SaaS (Software as a Service) business model. The benefit of SaaS is that once you create the software, you can sell it to many customers without adding extra overhead. This results in a business with higher margins, where the same product can serve many customers simultaneously, making it much more efficient than the consulting model. Adopt a predictable, simplistic business model for efficiency. Look to industry practices for guidance When it came to monetisation, we considered the needs of our CPG customers, who I knew from experience were already accustomed to paying annual subscriptions for sales databases and other software services. We decided to adopt the same model and charge our customers an annual upfront fee. This model worked well for our target market, aligning with industry standards and ensuring stable, recurring revenue. Moreover, our target CPG customers were already used to this business model and didn't have to choose from a huge variety of payment options, making closing sales a straightforward and efficient process. Marketing & Sales Educate the market to position yourself as a thought leader When we started, AI was not widely understood, especially in the CPG industry. We had to create awareness around both AI and its potential value. Our strategy focused on educating potential users and customers about AI, its relevance, and why they should invest in it. This education was crucial to the success of our marketing efforts. To establish credibility, we adopted a thought leadership approach. We wrote blogs on the importance of AI and how it could solve problems for CPG companies. We also participated in events and conferences to demonstrate our expertise in applying AI to the industry. This helped us build our brand and reputation as leaders in the AI space for CPG, and word-of-mouth spread as customers recognized us as the go-to company for AI solutions. It’s tempting for startups to offer products for free in the hopes of gaining early traction with customers, but this approach doesn't work in the long run. Free offerings don’t establish the value of your product, and customers may not take them seriously. You should always charge for pilots, even if the fee is minimal, to ensure that the customer is serious about potentially working with you, and that they are committed and engaged with the product. Pilots/POCs/Demos should aim to give a "flavour" of what you can deliver A paid pilot/POC trial also gives you the opportunity to provide a “flavour” of what your product can deliver, helping to build confidence and trust with the client. It allows customers to experience a detailed preview of what your product can do, which builds anticipation and desire for the full functionality. During this phase, ensure your product is built to give them a taste of the value you can provide, which sets the stage for a broader, more impactful adoption down the line. Fundraising & Financial Management Leverage PR to generate inbound interest from VCs When it comes to fundraising, our approach was fairly traditional—we reached out to VCs and used connections from existing investors to make introductions. However, looking back, one thing that really helped us build momentum during our fundraising process was getting featured in Tech in Asia. This wasn’t planned; it just so happened that Tech in Asia was doing a series on AI startups in Southeast Asia and they reached out to us for an article. During the interview, they asked if we were fundraising, and we mentioned that we were. As a result, several VCs we hadn’t yet contacted reached out to us. This inbound interest was incredibly valuable, and we found it far more effective than our outbound efforts. So, if you can, try to generate some PR attention—it can help create inbound interest from VCs, and that interest is typically much stronger and more promising than any outbound strategies because they've gone out of their way to reach out to you. Be well-prepared and deliberate about fundraising. Keep trying and don't lose heart When pitching to VCs, it’s crucial to be thoroughly prepared, as you typically only get one shot at making an impression. If you mess up, it’s unlikely they’ll give you a second chance. You need to have key metrics at your fingertips, especially if you're running a SaaS company. Be ready to answer questions like: What’s your retention rate? What are your projections for the year? How much will you close? What’s your average contract value? These numbers should be at the top of your mind. Additionally, fundraising should be treated as a structured process, not something you do on the side while juggling other tasks. When you start, create a clear plan: identify 20 VCs to reach out to each week. By planning ahead, you’ll maintain momentum and speed up the process. Fundraising can be exhausting and disheartening, especially when you face multiple rejections. Remember, you just need one investor to say yes to make it all worthwhile. When using funds, prioritise profitability and grow only when necessary. Don't rely on funding to survive. In the past, the common advice for startups was to raise money, burn through it quickly, and use it to boost revenue numbers, even if that meant operating at a loss. The idea was that profitability wasn’t the main focus, and the goal was to show rapid growth for the next funding round. However, times have changed, especially with the shift from “funding summer” to “funding winter.” My advice now is to aim for profitability as soon as possible and grow only when it's truly needed. For example, it’s tempting to hire a large team when you have substantial funds in the bank, but ask yourself: Do you really need 10 new hires, or could you get by with just four? Growing too quickly can lead to unnecessary expenses, so focus on reaching profitability as soon as possible, rather than just inflating your team or burn rate. The key takeaway is to spend your funds wisely and only when absolutely necessary to reach profitability. You want to avoid becoming dependent on future VC investments to keep your company afloat. Instead, prioritize reaching break-even as quickly as you can, so you're not reliant on external funding to survive in the long run. Team-Building & Leadership Look for complementary skill sets in co-founders When choosing a co-founder, it’s important to find someone with a complementary skill set, not just someone you’re close to. For example, I come from a business and commercial background, so I needed someone with technical expertise. That’s when I found my co-founder, Himanshu, who had experience in machine learning and AI. He was a great match because his technical knowledge complemented my business skills, and together we formed a strong team. It might seem natural to choose your best friend as your co-founder, but this can often lead to conflict. Chances are, you and your best friend share similar interests, skills, and backgrounds, which doesn’t bring diversity to the table. If both of you come from the same industry or have the same strengths, you may end up butting heads on how things should be done. Having diverse skill sets helps avoid this and fosters a more collaborative working relationship. Himanshu (left) and Somsubhra (right) co-founded AI Palette in 2018 Define roles clearly to prevent co-founder conflict To avoid conflict, it’s essential that your roles as co-founders are clearly defined from the beginning. If your co-founder and you have distinct responsibilities, there is no room for overlap or disagreement. This ensures that both of you can work without stepping on each other's toes, and there’s mutual respect for each other’s expertise. This is another reason as to why it helps to have a co-founder with a complementary skillset to yours. Not only is having similar industry backgrounds and skillsets not particularly useful when building out your startup, it's also more likely to lead to conflicts since you both have similar subject expertise. On the other hand, if your co-founder is an expert in something that you're not, you're less likely to argue with them about their decisions regarding that aspect of the business and vice versa when it comes to your decisions. Look for employees who are driven by your mission, not salary For early-stage startups, the first hires are crucial. These employees need to be highly motivated and excited about the mission. Since the salary will likely be low and the work demanding, they must be driven by something beyond just the paycheck. The right employees are the swash-buckling pirates and romantics, i.e those who are genuinely passionate about the startup’s vision and want to be part of something impactful beyond material gains. When employees are motivated by the mission, they are more likely to stick around and help take the startup to greater heights. A litmus test for hiring: Would you be excited to work with them on a Sunday? One of the most important rounds in the hiring process is the culture fit round. This is where you assess whether a candidate shares the same values as you and your team. A key question to ask yourself is: "Would I be excited to work with this person on a Sunday?" If there’s any doubt about your answer, it’s likely not a good fit. The idea is that you want employees who align with the company's culture and values and who you would enjoy collaborating with even outside of regular work hours. How we structure the team at AI Palette We have three broad functions in our organization. The first two are the big ones: Technical Team – This is the core of our product and technology. This team is responsible for product development and incorporating customer feedback into improving the technology Commercial Team – This includes sales, marketing, customer service, account managers, and so on, handling everything related to business growth and customer relations. General and Administrative Team – This smaller team supports functions like finance, HR, and administration. As with almost all businesses, we have teams that address the two core tasks of building (technical team) and selling (commercial team), but given the size we're at now, having the administrative team helps smoothen operations. Set broad goals but let your teams decide on execution What I've done is recruit highly skilled people who don't need me to micromanage them on a day-to-day basis. They're experts in their roles, and as Steve Jobs said, when you hire the right person, you don't have to tell them what to do—they understand the purpose and tell you what to do. So, my job as the CEO is to set the broader goals for them, review the plans they have to achieve those goals, and periodically check in on progress. For example, if our broad goal is to meet a certain revenue target, I break it down across teams: For the sales team, I’ll look at how they plan to hit that target—how many customers they need to sell to, how many salespeople they need, and what tactics and strategies they plan to use. For the technical team, I’ll evaluate our product offerings—whether they think we need to build new products to attract more customers, and whether they think it's scalable for the number of customers we plan to serve. This way, the entire organization's tasks are cascaded in alignment with our overarching goals, with me setting the direction and leaving the details of execution to the skilled team members that I hire.

#reddit#founder#built

reddit

0

1

Momof3rascals•This week

Thoughts on FasterCapital VC?

TLDR: I pitched to FasterCapital and got an "offer". Trying to figure out if this is a legitimate opportunity or a waste of my time. I'm not familiar with VCs and hadn't considered actually getting an investor on board with my plan. I sent my pitch deck to FasterCapital, honestly not expecting a response. It was my first pitch deck and a complete long shot. I ended up getting a response, they asked me for clarification on a few things. Than I get this email about what they are offering here's the main part We specialize in warm introductions to angel investors, VCs, and HNWIs, ensuring you connect with the right investors through personalized recommendations—not ineffective mass email campaigns. Cold outreach, such as LinkedIn messages, rarely succeeds, as investors receive hundreds of such requests and disregard them. To raise money, you need a strong partner like ourselves who has a wide network and direct connection with those angel investors built throughout 10 years. You can see some of the reviews of the startups we have helped attached and reviews on independent sites. Based on our experience and the matching that we have done already on our own AI system and for raising $55M-$65M in 5 years, a suitable package in your case is $50k - $64k and the chances of raising money is %87 - %93, but you were accepted in the exceptional rising star offer, where you pay half of that amount as an advance which is $25k-$32k and the other half ONLY when we raise you the first $1M. Other startups in our standard offers pays double that amount. First, I don't understand all of it, except for the "where you pay half of that amount as an advance which is $25k-$32k" I am no where near being able to come close to that, mostly because if I had that much, I wouldn't apply to a VC. I responded and politely told her that was not something our company could financially do right now. Than this email Thanks for your kind reply. We are flexible on paying this amount into monthly installments. We offer money back guarantee if we didn't raise the capital in 6 months from signing. This is how much we are confident with our approach of warm introductions. Raising the first amount of money and getting the first investor onboard is the most challenging part. You need time to build trust and network of investors. You need to have a good partner to help you. Please note that the down payment is for raising at least $55M over five years as we are interested in long-term partnership to raise multiple rounds because we make money through the commission. Companies take only commission or success fee are doing cold introductions and mass emails and this approach has low chances of success when it comes to raising capital. It is about the chances of success. You can talk to these companies and ask them about their success rate. Mass emails campaign has zero chances of success.  We have helped more than 742 startups raise more than $2.2B. Our network includes 155,000 angel investors and more than 50K funding institutions (VCs, HNI, family offices..etc). We have been in this business for more than 10 years. We have more than 92% success rate in our program so far. So if you are familiar with VC, Is this an actual opportunity. I have a tendency to jump or dive head first into things. As much as I want to get excited because this would be the jumpstart to most of my goals and ambitions. I'm not familiar with VCs. I have bootstrapped all my ventures so far.

#reddit#thoughts#fastercapital

reddit

0

1

jshogren10•This week

Follow Along as I Flip this Website - Case Study

I am starting a new case study where I will be documenting my attempt to flip a website that I just purchased from Flippa. However, unlike most case studies where people hide certain parts and details from the public I will instead be sharing everything. That means you will know the exact URL of the site that I purchased and I will share everything with you all as I progress.I know that case studies are lot more interesting and you can learn better when you can see real examples of what I am talking about. Enough of the chatting, let's jump straight into this new case study and I will explain what this is all about. Before you get into the case study I want to give you the option of reading this one my website where all of the images can be seen within the post and it is easier to read. I also want to say that I have nothing to sell you or anything close to it. So if you want to read it there you can do so here ##Introductory Video I have put together a video that talks about many of the things that I cover in this article. So if you would rather watch a video you can watch that here - https://www.youtube.com/watch?v=EE3SxtNnqts However, I go into more detail in the actual article FYI. Also, I plan on using Youtube very frequently in this case study so be on the lookout for new videos.There is going to be a video that will accompany every single case study post because I like having it being presented in two different mediums. ##The Website I Just Bought Around a week ago I made a new website purchase from Flippa and you can view the website's Flippa listing here - https://flippa.com/6439965-hvactraining101-com Screenshot of the Homepage - http://imgur.com/T6Iv1QN I paid $1,250 for the site and you will soon see that I got a really good deal. As you might be able to tell from the URL, this site is focused around training and education for becoming a HVAC technician. This is a lucrative niche to be in and Adsense pays very well. I do not have control of the site yet due to the transfer process not being completed. However, I am hoping within a few days everything will be finalized and I will take full control of the site. In the meantime, I figured it would be a good time to put together the introduction post for this new case study! ##Why I Bought this Website Now that you have a general idea of the website that I purchased, I now want to explain the reasoning behind the purchase. There are 3 major reasons for this purchase and I will explain each one of them below. GREAT Price As I mentioned earlier, I bought this website for $1,250. However, that doesn't mean a whole lot unless you know how much the site is making each month. Screenshot of the earnings for the last 12 months - http://imgur.com/NptxCHy Average Monthly Profits: 3 Month = $126 6 Month = $128 12 Month = $229.50 Let's use the 6 month average of $128/month as our baseline average. Since it is making on average $128/month and it was sold for $1,250 then that means I bought this site at a multiple of 9.76x! Most sites in today's market go for 20x-30x multiples. As you can see, I got a great deal on this site. Although the great price was the biggest reason for me buying this site there are other factors that persuaded me as well. You need to remember that just because you can get a website for a good price it doesn't mean it is a good deal. There are other factors that you need to look at as well. Extremely Under Optimized This site is currently being monetized mainly by Adsense and a very small amount from Quinstreet. From my experience with testing and optimizing Adsense layouts for my site in my Website Investing case study I know the common ad layouts that work best for maximizing Adsense revenue. With that being said, I can quickly determine if a website is being under optimized in terms of the ad layout. One of the first things I did when analyzing this site was examine the ad layout it was using. Screenshot of the website with the ad layout the previous owner was using - http://imgur.com/wqleLVA There is only ONE ad per page being used, that's it. Google allows up to 6 total ads to be used per page and you can imagine how much money is being left on the table because of this. I am estimating that I can probably double the earnings for the site practically overnight once I add more ads to the site. Adding more ads in combination with my favorite Adsense plugin, AmpedSense, I will be able to easily boost the earnings for this site quickly. It is also worth mentioning how lucrative this niche is and how much advertisers are willing to spend on a per click basis. The average CPC for the top keywords this site is currently ranking for in Google - http://imgur.com/ifxiy8B Look at those average CPC numbers, they are insanely high! I could be making up to $25 per click for some of those keywords, which is so absurd to me. Combine these extremely high CPC with the fact that the site currently only has one ad per page and you can start to understand just how under optimized this site truly is. I also plan on utilizing other ad networks such as Quinstreet and Campus Explorer more as well. These two networks are targeted at the education niche which works very well with my site. I will be testing to see if these convert better than normal Adsense ads. Goldmine of Untapped Keywords One of the biggest opportunities I see for growing this site is to target local keywords related to HVAC training. As of right now, the site has only scratched the surface when it comes to trying to rank for state/city keywords. Currently there are only two pages on the entire website which go after local keywords, those two pages target Texas and Florida HVAC search terms. These two pages are two of the more popular pages in terms of total amount of traffic. See the screenshot of the Google Analytics - http://imgur.com/NB0xJ4G Two out of the top five most popular pages for the entire website are focused on local search terms. However, these are the ONLY two pages that target local search terms on the whole site! There are 48 other states, although there may not be search volume for all states, and countless cities that are not being targeted. Why do I think this is such a good opportunity? For a few reasons: Local keywords are a lot easier to rank for in Google than more general keywords This site has been able to rank for two states successfully already and it proves it is possible Traffic going to these local pages is WAY more targeted and will convert at a much higher rate, which means more commissions for me There are so many more states and cities that get a good amount of searches that I can target To give you an idea of the type of keywords these local pages rank for, you can see the top keywords that the Florida page is ranking for in Google: Top ranking keywords for the Florida page - http://imgur.com/j7uKzl2 As you can see these keywords don't get a ton of searches each month, but ranking 1st for a keyword getting 90 searches a month is better than being ranked 10th for a keyword getting 1,000 searches a month. I have started to do some keyword research for other states and I am liking what I am finding so far. Keywords that I have found which I will be targeting with future articles - http://imgur.com/8CCCCWU I will go into more detail about my keyword research in future articles, but I wanted to give you an idea of what my strategy will be! I also wanted to share why I am super excited about the future potential to grow this site by targeting local keywords. ##Risks Yes, there are many good things about this website, but there are always risks involved no matter what the investment is. The same thing goes for this site. Below are some of the risks that I currently see. HTML Site This website is a HTML site and I will need to transfer it to Wordpress ASAP. I have been doing some research on this process and it shouldn't be too hard to get this over to Wordpress. In doing so it will make adding content, managing the back end and just about everything else easier. Also, I am hoping that when I transfer it to Wordpress that it will become more optimized for Google which will increase keyword rankings. Declining Earnings Looking at the last 12 months of earnings you will notice a drop off from last year till now. Earnings from the last 12 months - http://imgur.com/WsotZsj In May of 2015 it looks like the site earned right around $500, which is much higher than the $128 that it is earning now. However, the last 7 or so months have been consistent which is a good sign. Even though the earnings are much lower now then they were a year ago it is good to know that this site has the potential to earn $500/month because it has done it before. Slightly Declining Traffic In the last 12 months the site's traffic has declined, however, it looks like it is picking back up. Traffic from the last 12 months - http://imgur.com/aiYZW9W The decline is nothing serious, but there is a drop on traffic. Let's take a look at the complete history of this site's traffic so we can get a better idea of what is going on here: Complete traffic history - http://imgur.com/tYmboVn The above screenshot is from 2012 all the way up to right now. In the grand scheme of things you can see that the traffic is still doing well and it looks like it is on the upswing now. Those three risks mentioned above are the three biggest risks with this site at this point. It is always good to note the risks and do everything you can to prevent them from causing a problem. ##My Growth Strategy Whenever I purchase a new site I always create an outline or plan on how I will grow the site. Right now, I have some basic ideas on how I will grow this site, but as I go on I will continue to change and optimize my strategies to be more effective. Below I have outlined my current plans to grow: Add more Adsense Ads The very first thing I will do once I get control of the site is add more ads per page. I am predicting that by just adding a few more ads per page I will be able to more than likely double the earnings. I will touch on exactly how I will be optimizing the ad layouts in future posts. Test other Ad Networks I will be doing a lot of testing and experimenting when it comes to the ad networks. I plan on trying out Adsense, Media.net, Quinstreet, Campus Explorer and finding the combination of those 4 which produces the most revenue. The Adsense and Media.net ads will perform well on the more general pages while Quinstreet and Campus Explorer ads will be geared towards the local search terms. There will probably be other ad networks I will try out but these are the four which I will be using right away. If you are aware of any other ad networks out there which are geared towards the education niche please let me know in the comments below! Target Local Keywords with new Content I have already touched on this, but I will starting to produce content targeting these local keywords ASAP. The sooner I add the content to the site the sooner it will start to rank and bring in traffic. I will not be writing my own content and instead I will be outsourcing all of it via Upwork. I will show you all how I go about outsourcing content production and you can see my process for doing that. ##Goals for this Website My goal for the website is to have it valued at $10,000+ within 12 months. Let's break down this larger goal into smaller chunks which will make achieving it easier and more attainable. Earnings - $500/month To get the site valued at $10,000 the site will need to be making $500/month using a 20x monthly multiple. Right now, the site is making around $130/month so it has a ways to before it reaches the $500 a month mark. However, after doing some Adsense optimization I think we could push the earnings to around $300/month without much work. From there, it will come down to trying to bring in more traffic! Traffic - 5,000 Visitors per Month Why 5,000 visitors? Because that is how much traffic it is going to take to get to the $500/month goal. Let me explain how I came to this conclusion: The average RPM for this site is currently $50, which means for every 1,000 page views the site earns $50. After I optimize the Adsense layout for the site and add more ads per page I think I will be able to double the RPM to $100. Using the RPM of $100 the site will need to have 5,000 monthly visitors to earn $500. So 5,000 monthly visitors is the traffic goal I have set and aiming for! The site is currently getting around 3,000 visitors per month so I will need to add an extra 2,000 visitors to get to this goal. ##Want to Follow this Case Study? I will be using Youtube a lot in this case study so make sure to follow my Youtube channel here - www.youtube.com/c/joshshogren Other than that, I think that is going to bring us to the end of the introductory post for this new case study. I hope that you enjoyed reading and that you are excited to follow along! If you have any suggestions to make this case study better PLEASE let me know in the comment below. I want to make this case study the best one I have done yet. Talk to you all in the comment section.

#reddit#follow#along

reddit

0

1

mr_t_forhire•This week

Started a content marketing agency 6 years ago - $0 to $5,974,324 (2023 update)

Hey friends, My name is Tyler and for the past 6 years, I’ve been documenting my experience building a content marketing agency called Optimist. Year 1 - 0 to $500k ARR Year 2 - $500k to $1MM ARR Year 3 - $1MM ARR to $1.5MM(ish) ARR Year 4 - $3,333,686 Revenue Year 5 - $4,539,659 Revenue How Optimist Works First, an overview/recap of the Optimist business model: We operate as a “collective” of full time/professional freelancers Everyone aside from me is a contractor Entirely remote/distributed team Each freelancer earns $65-85/hour Clients pay us a flat monthly fee for full-service content marketing (research, strategy, writing, editing, design/photography, reporting and analytics, targeted linkbuilding, and more) We recently introduced hourly engagements for clients who fit our model but have some existing in-house support Packages range in price from $10-20k/mo We offer profit share to everyone on our core team as a way to give everyone ownership in the company In 2022, we posted $1,434,665 in revenue. It was our highest revenue year to date and brings our lifetime total to $5,974,324. Here’s our monthly revenue from January 2017 to December of 2022. But, like every year, it was a mix of ups and downs. Here’s my dispatch for 2023. — Running a business is like spilling a drink. It starts as a small and simple thing. But, if you don’t clean it up, the spill will spread and grow — taking up more space, seeping into every crack. There’s always something you could be doing. Marketing you could be working on. Pitches you could be making. Networking you could be doing. Client work you could help with. It can be all-consuming. And it will be — if you don’t clean up the spill. I realized this year that I had no containment for the spill that I created. Running an agency was spilling over into nearly every moment of my life. When I wasn’t working, I was thinking about work. When I wasn’t thinking about work, I was dreaming about it. Over the years, I’ve shared about a lot of my personal feelings and experience as an entrepreneur. And I also discussed my reckoning with the limitations of running the business we’ve built. My acceptance that it was an airplane but not a rocket. And my plan to try to compartmentalize the agency to make room in my life for other things — new business ideas, new revenue streams, and maybe some non-income-producing activity. 🤷 What I found in 2022 was that the business wasn’t quite ready for me to make that move. It was still sucking up too much of my time and attention. There were still too many gaps to fill and I was the one who was often filling them. So what do you do? Ultimately you have two choices on the table anytime you run a business and it’s not going the way you want it: Walk away Turn the ship — slowly For a huge number of reasons (personal, professional, financial, etc), walking away from Optimist was not really even an option or the right move for me. But it did feel like things needed to change. I needed to keep turning the ship to get it to the place where it fit into my life — instead of my life fitting around the business. This means 2022 was a year of transition for the agency. (Again?) Refocusing on Profit Some money is better than no money. Right? Oddly, this was one of the questions I found myself asking in 2022. Over the years, we’ve been fortunate to have many clients who have stuck with us a long time. In some cases, we’ve had clients work with us for 2, 3, or even 4 years. (That’s over half of our existence!) But, things have gotten more expensive — we’ve all felt it. We’ve had to increase pay to remain competitive for top talent. Software costs have gone up. It’s eaten into our margin. Because of our increasing costs and evolving scope, many of our best, most loyal clients were our least profitable. In fact, many were barely profitable — if at all. We’ve tried to combat that by increasing rates on new, incoming clients to reflect our new costs and try to make up for shrinking margin on long-term clients. But we didn’t have a good strategy in place for updating pricing for current clients. And it bit us in the ass. Subsidizing lower-profit, long-term clients with new, higher-margin clients ultimately didn’t work out. Our margins continued to dwindle and some months we were barely breaking even while posting six-figures of monthly revenue. 2022 was our highest revenue year but one of our least profitable. It only left one option. We had to raise rates on some of our long-term clients. But, of course, raising rates on a great, long-term client can be delicate. You’ve built a relationship with these people over the years and you’re setting yourself up for an ultimatum — are you more valuable to the client or is the client more valuable to you? Who will blink first? We offered all of these clients the opportunity to move to updated pricing. Unfortunately, some of them weren’t on board. Again, we had 2 options: Keep them at a low/no profit rate Let them churn It seems intuitive that having a low-profit client is better than having no client. But we’ve learned an important lesson many times over the years. Our business doesn’t scale infinitely and we can only handle so many clients at a time. That means that low-profit clients are actually costing us money in some cases. Say our average client generates $2,500 per month in profit — $30,000 per year. If one of our clients is only generating $500/mo in profit, working with them means missing out on bringing on a more profitable client (assuming our team is currently at capacity). Instead of $30,000/year, we’re only making $6,000. Keeping that client costs us $24,000. That’s called opportunity cost. So it’s clear: We had to let these clients churn. We decided to churn about 25% of our existing clients. On paper, the math made sense. And we had a pretty consistent flow of new opportunities coming our way. At the time, it felt like a no-brainer decision. And I felt confident that we could quickly replace these low-profit clients with higher-margin ones. I was wrong. Eating Shit Right after we initiated proactively churning some of our clients, other clients — ones we planned to keep — gave us notice that they were planning to end the engagement. Ouch. Fuck. We went from a 25% planned drop in revenue to a nearly 40% cliff staring us right in the face. Then things got even worse. Around Q3 of this year, talk of recession and layoffs really started to intensify. We work primarily with tech companies and startups. And these were the areas most heavily impacted by the economic news. Venture funding was drying up. Our leads started to slow down. This put us in a tough position. Looking back now, I think it’s clear that I made the wrong decision. We went about this process in the wrong way. The reality sinks in when you consider the imbalance between losing a client and gaining a client. It takes 30 days for someone to fire us. It’s a light switch. But it could take 1-3 months to qualify, close, and onboard a new client. We have lots of upfront work, research, and planning that goes into the process. We have to learn a new brand voice, tone, and style. It’s a marathon. So, for every client we “trade”, there’s a lapse in revenue and work. This means that, in retrospect, I would probably have made this transition using some kind of staggered schedule rather than a cut-and-dry approach. We could have gradually off-boarded clients when we had more definitive work to replace them. I was too confident. But that’s a lesson I had to learn the hard way. Rebuilding & Resetting Most of the voluntary and involuntary churn happened toward the end of 2022. So we’re still dealing with the fall out. Right now, it feels like a period of rebuilding. We didn’t quite lose 50% of our revenue, but we definitely saw a big hit heading into 2023. To be transparent: It sucks. It feels like a gigantic mistake that I made which set us back significantly from our previous high point. I acted rashly and it cost us a lot of money — at least on the surface. But I remind myself of the situation we were in previously. Nearly twice the revenue but struggling to maintain profitability. Would it have been better to try to slowly fix that situation and battle through months of loss or barely-break-even profits? Or was ripping off the bandaid the right move after all? I’m an optimist. (Heh, heh) Plus, I know that spiraling over past decisions won’t change them or help me move forward. So I’m choosing to look at this as an opportunity — to rebuild, reset, and refocus the company. I get to take all of the tough lessons I’ve learned over the last 6 years and apply them to build the company in a way that better aligns with our new and current goals. It’s not quite a fresh, clean start, but by parting ways with some of our oldest clients, we’ve eliminated some of the “debt” that’s accumulated over the years. We get a chance to fully realize the new positioning that we rolled out last year. Many of those long-term clients who churned had a scope of work or engagement structure that didn’t fit with our new positioning and focus. So, by losing them, we’re able to completely close up shop on the SOWs that no longer align with the future version of Optimist. Our smaller roster of clients is a better fit for that future. My job is to protect that positioning by ensuring that while we’re rebuilding our new roster of clients we don’t get desperate. We maintain the qualifications we set out for future clients and only take on work that fits. How’s that for seeing the upside? Some other upside from the situation is that we got an opportunity to ask for candid feedback from clients who were leaving. We asked for insight about their decision, what factors they considered, how they perceived us, and the value of our work. Some of the reasons clients left were obvious and possibly unavoidable. Things like budget cuts, insourcing, and uncertainty about the economy all played at least some part of these decisions. But, reading between the lines, where was one key insight that really struck me. It’s one of those, “oh, yeah — duh — I already knew that,” things that can be difficult to learn and easy to forget…. We’re in the Relationship Business (Plan Accordingly) For all of our focus on things like rankings, keywords, content, conversions, and a buffet of relevant metrics, it can be easy to lose the forest for the trees. Yes, the work itself matters. Yes, the outcomes — the metrics — matter. But sometimes the relationship matters more. When you’re running an agency, you can live or die by someone just liking you. Admittedly, this feels totally unfair. It opens up all kinds of dilemmas, frustration, opportunity for bias and prejudice, and other general messiness. But it’s the real world. If a client doesn’t enjoy working with us — even if for purely personal reasons — they could easily have the power to end of engagement, regardless of how well we did our actual job. We found some evidence of this in the offboarding conversations we had with clients. In some cases, we had clients who we had driven triple- and quadruple-digital growth. Our work was clearly moving the needle and generating positive ROI and we had the data to prove it. But they decided to “take things in another direction” regardless. And when we asked about why they made the decision, it was clear that it was more about the working relationship than anything we could have improved about the service itself. The inverse is also often true. Our best clients have lasting relationships with our team. The work is important — and they want results. But even if things aren’t quite going according to plan, they’re patient and quick to forgive. Those relationships feel solid — unshakeable. Many of these folks move onto new roles or new companies and quickly look for an opportunity to work with us again. On both sides, relationships are often more important than the work itself. We’ve already established that we’re not building a business that will scale in a massive way. Optimist will always be a small, boutique service firm. We don’t need 100 new leads per month We need a small, steady roster of clients who are a great fit for the work we do and the value we create. We want them to stick around. We want to be their long-term partner. I’m not built for churn-and-burn agency life. And neither is the business. When I look at things through this lens, I realize how much I can cut from our overall business strategy. We don’t need an ultra-sophisticated, multi-channel marketing strategy. We just need strong relationships — enough of them to make our business work. There are a few key things we can take away from this as a matter of business strategy: Put most of our effort into building and strengthening relationships with our existing clients Be intentional about establishing a strong relationship with new clients as part of onboarding Focus on relationships as the main driver of future business development Embracing Reality: Theory vs Practice Okay, so with the big learnings out the way, I want to pivot into another key lesson from 2022. It’s the importance of understanding theory vs practice — specifically when it comes to thinking about time, work, and life. It all started when I was considering how to best structure my days and weeks around running Optimist, my other ventures, and my life goals outside of work. Over the years, I’ve dabbled in many different ways to block time and find focus — to compartmentalize all of the things that are spinning and need my attention. As I mapped this out, I realized that I often tried to spread myself too thin throughout the week. Not just that I was trying to do too much but that I was spreading that work into too many small chunks rather than carving out time for focus. In theory, 5 hours is 5 hours. If you have 5 hours of work to get done, you just fit into your schedule whenever you have an open time slot. In reality, a single 5-hour block of work is 10x more productive and satisfying than 10, 30-minute blocks of work spread out across the week. In part, this is because of context switching. Turning your focus from one thing to another thing takes time. Achieving flow and focus takes time. And the more you jump from one project to another, the more time you “lose” to switching. This is insightful for me both in the context of work and planning my day, but also thinking about my life outside of Optimist. One of my personal goals is to put a finite limit on my work time and give myself more freedom. I can structure that in many different ways. Is it better to work 5 days a week but log off 1 hour early each day? Or should I try to fit more hours into each workday so I can take a full day off? Of course, it’s the latter. Both because of the cost of context switching and spreading work into more, smaller chunks — but also because of the remainder that I end up with when I’m done working. A single extra hour in my day probably means nothing. Maybe I can binge-watch one more episode of a new show or do a few extra chores around the house. But it doesn’t significantly improve my life or help me find greater balance. Most things I want to do outside of work can’t fit into a single extra hour. A full day off from work unlocks many more options. I can take the day to go hiking or biking. I can spend the day with my wife, planning or playing a game. Or I can push it up against the weekend and take a 3-day trip. It gives me more of the freedom and balance that I ultimately want. So this has become a guiding principle for how I structure my schedule. I want to: Minimize context switching Maximize focused time for work and for non-work The idea of embracing reality also bleeds into some of the shifts in business strategy that I mentioned above. In theory, any time spent on marketing will have a positive impact on the company. In reality, focusing more on relationships than blasting tweets into the ether is much more likely to drive the kind of growth and stability that we’re seeking. As I think about 2023, I think this is a recurring theme. It manifests in many ways. Companies are making budget cuts and tough decisions about focus and strategy. Most of us are looking for ways to rein in the excess and have greater impact with a bit less time and money. We can’t do everything. We can’t even do most things. So our #1 priority should be to understand the reality of our time and our effort to make the most of every moment (in both work and leisure). That means thinking deeply about our strengths and our limitations. Being practical, even if it feels like sacrifice. Update on Other Businesses Finally, I want to close up by sharing a bit about my ventures outside of Optimist. I shared last year how I planned to shift some of my (finite) time and attention to new ventures and opportunities. And, while I didn’t get to devote as much as I hoped to these new pursuits, they weren’t totally in vain. I made progress across the board on all of the items I laid out in my post. Here’s what happened: Juice: The first Optimist spin-out agency At the end of 2021, we launched our first new service business based on demand from Optimist clients. Focused entirely on building links for SEO, we called the agency Juice. Overall, we made strong progress toward turning this into a legitimate standalone business in 2022. Relying mostly on existing Optimist clients and a few word-of-mouth opportunities (no other marketing), we built a team and set up a decent workflow and operations. There’s still many kinks and challenges that we’re working through on this front. All told, Juice posted almost $100,000 in revenue in our first full year. Monetizing the community I started 2022 with a focus on figuring out how to monetize our free community, Top of the Funnel. Originally, my plan was to sell sponsorships as the main revenue driver. And that option is still on the table. But, this year, I pivoted to selling paid content and subscriptions. We launched a paid tier for content and SEO entrepreneurs where I share more of my lessons, workflows, and ideas for building and running a freelance or agency business. It’s gained some initial traction — we reached \~$1,000 MRR from paid subscriptions. In total, our community revenue for 2022 was about $2,500. In 2023, I’m hoping to turn this into a $30,000 - $50,000 revenue opportunity. Right now, we’re on track for \~$15,000. Agency partnerships and referrals In 2022, we also got more serious about referring leads to other agencies. Any opportunity that was not a fit for Optimist or we didn’t have capacity to take on, we’d try to connect with another partner. Transparently, we struggled to operationalize this as effectively as I would have liked. In part, this was driven by my lack of focus here. With the other challenges throughout the year, I wasn’t able to dedicate as much time as I’d like to setting goals and putting workflows into place. But it wasn’t a total bust. We referred out several dozen potential clients to partner agencies. Of those, a handful ended up converting into sales — and referral commission. In total, we generated about $10,000 in revenue from referrals. I still see this as a huge opportunity for us to unlock in 2023. Affiliate websites Lastly, I mentioned spending some time on my new and existing affiliate sites as another big business opportunity in 2022. This ultimately fell to the bottom of my list and didn’t get nearly the attention I wanted. But I did get a chance to spend a few weeks throughout the year building this income stream. For 2022, I generated just under $2,000 in revenue from affiliate content. My wife has graciously agreed to dedicate some of her time and talent to these projects. So, for 2023, I think this will become a bit of a family venture. I’m hoping to build a solid and consistent workflow, expand the team, and develop a more solid business strategy. Postscript — AI, SEO, OMG As I’m writing this, much of my world is in upheaval. If you’re not in this space (and/or have possibly been living under a rock), the release of ChatGPT in late 2022 has sparked an arms race between Google, Bing, OpenAI, and many other players. The short overview: AI is likely to fundamentally change the way internet search works. This has huge impact on almost all of the work that I do and the businesses that I run. Much of our focus is on SEO and understanding the current Google algorithm, how to generate traffic for clients, and how to drive traffic to our sites and projects. That may all change — very rapidly. This means we’re standing at a very interesting point in time. On the one hand, it’s scary as hell. There’s a non-zero chance that this will fundamentally shift — possibly upturn — our core business model at Optimist. It could dramatically change how we work and/or reduce demand for our core services. No bueno. But it’s also an opportunity (there’s the optimist in me, again). I certainly see a world where we can become leaders in this new frontier. We can pivot, adjust, and capitalize on a now-unknown version of SEO that’s focused on understanding and optimizing for AI-as-search. With that, we may also be able to help others — say, those in our community? — also navigate this tumultuous time. See? It’s an opportunity. I wish I had the answers right now. But, it’s still a time of uncertainty. I just know that there’s a lot of change happening and I want to be in front of it rather than trying to play catch up. Wish me luck. — Alright friends — that's my update for 2023! I’ve always appreciated sharing these updates with the Reddit community, getting feedback, being asked tough questions, and even battling it out with some of my haters (hey!! 👋) As usual, I’m going to pop in throughout the next few days to respond to comments or answer questions. Feel free to share thoughts, ideas, and brutal takedowns in the comments. If you're interested in following the Optimist journey and the other projects I'm working on in 2023, you can follow me on Twitter. Cheers, Tyler P.S. - If you're running or launching a freelance or agency business and looking for help figuring it out, please DM me. Our subscription community, Middle of the Funnel, was created to provide feedback, lessons, and resources for other entrepreneurs in this space.

#reddit#started#content

reddit

0

1

Careless_Fill1407•This week

AI for Business- Sharing Strategies, Knowledge and Tools

Hi All, As a small business owner running a tech company that focuses on process automation, I understand the importance of staying up-to-date with the latest advancements in AI and other emerging technologies. I have found the amount of new tools and tech overwhelming to keep track of as of recent. I would like to start a group of entrepreneurs and tech professionals who share a common interest in the latest tools relating to AI, but also tech in general. My goal is to create an environment for members to discuss business strategies, share projects involving how they are introducing AI, new tools... I hope that by pooling knowledge everyone involved can benefit. To ensure the community remains focused and valuable I am thinking that It will be a requirement for all members to share a tool, project ideas, strategies... related to business on a bi-weekly basis. Potentially bi-weekly calls as well, but Ill figure that out based on the interest. We currently have about 15 members and looking to add maybe 10-15 more. If this sounds like something you'd be interested in post below or send me a DM. Add a brief description of what you are interested in / working on. Looking forward to connecting

#reddit#business-#sharing

reddit

0

1

finncmdbar•This week

AI search startup Perplexity could actually beat Google (disruption strategy lesson)

Everybody's talking about how AI changes everything and all the new business models and products that are now possible. But few talk about how AI legitimizes ideas that we'd previously laugh about. One of them: Disrupting Google. Bing, DuckDuckGo (privacy search), Ecosia (sustainable search), Neeva (subscription search)... none of them made a dent into Google. AI could change this. Most notably: Perplexity. Perplexity is an AI search unicorn founded by Aravind Srinivas. It's got a $20m ARR and $1b+ valuation at about 50 people—all in under 2 years. The product is basically if ChatGPT had a baby with Google: Perplexity aggregate search results for your query and tells you the results (with citations) in a concise answer. You never have to leave their interface to click elsewhere. I think it has a real chance: Its search results for informational queries are (imo) already better than Google's SEO optimized jungle. Plus, millions of people are subscribing (with real money) to a search engine. Of course, Google knows a thing or two about AI. What if Google just copies the product for their own search engine? To some degree, they've started to do this. But Google runs into a problem here: Their core business model is based on ads, which are inserted into search results. So the more search results you can show someone, the more money Google makes. If there's just one result (aka answer), then Google makes less money. This is a clear disincentive for Google to build these AI answers. CEO Aravind Srinivas talks about this in interviews: Google won't build everything Perplexity does because they rely on ads and AI-native search runs counter to their business model. Of course, disrupting Google requires a lot more than to convince a bunch of tech workers excited to try new tools. My mom probably doesn't even know there are other search engines besides Google—and crossing into the mainstream takes a long time. But if I think about how good Perplexity is in 2 years and with 50 people compared to a 26 year-old company with 180k people, I think the AI inflection point gives them a real chance. WDYT? If you want to read my full strategic breakdown, you can read it here: https://www.commandbar.com/blog/perplexity-vs-google/

#reddit#search#startup

reddit

0

1

dams96•This week

Made $19.2k this month, and just surpassed $1000 the last 24 hours. What I did and what's next.

It's the first time I hit $1000+ in 24 hours and I had no one to share it with (except you guys). I'm quite proud of my journey, and I would have thought that making $1000 in a day would make me ecstatic, but actually it's not the case. Not sure if it's because my revenue has grown by increment step so I had time to "prepare" myself to achieve this at one point, or just that I'm nowhere near my goal of 100k/month so that I'm not that affected by it. But it's crazy to think that my goal was to make 100$ daily at the end of 2024. So for those who don't know me (I guess most of you), I build mobile apps and ship them as fast as I can. Most of them are in the AI space. I already made a post here on how I become a mobile app developer so you can check it for more details, but essentially here's what I did : Always loved creating my own things and solve problems Built multiple YouTube channels since I was 15 (mobile gaming actually) that all worked great (but it was too niche so not that scalable, didn't like that) Did a few businesses here and there (drop shopping, selling merch to school, etc) Finished my master's degree in engineering about 2 years ago Worked a moment in a famous watch industry company and saw my potential. The combo of health issues, fixed salary (although it was quite a lot), and me wanting to be an entrepreneur made me leave the company. Created a TikTok account in mobile tech (got 10+ million views the 1st 3 days), manage to grow it to 200k subs in about 3 months Got plenty of collabs for promoting mobile apps (between $500 - $2000 for a collab) Said fuck it I should do my own apps and market them on my TikTok instead of doing collabs Me wanting to build my own apps happened around May-June 2023. Started my TikTok in Feb 2023. At this point I had already 150k+ subs on TikTok. You guys need to know that I suck at coding big time. During my studies I tried to limit as much as I could coding because I was a lazy bast*rd, even though I knew it would come to bite me in the ass one day. But an angel appeared to me in broad daylight, that angel was called GPT-4. I subscribed for 20$/month to get access, and instantly I saw the potential of AI and how much it could help me. Last year GPT-4 was ahead of its time and could already code me basic apps. I had already a mac so I just downloaded Xcode and that was it. My 1st app was a wallpaper app, and I kid you not 90% of it was made by AI. Yes sometimes I had to try again and again with different prompts but it was still so much faster compared to if I had to learn coding from scratch and write code with my own hands. The only thing I didn't do was implement the in app purchase, from which I find a guy on Fiverr to do it for me for 50$. After about 2 months of on-off coding, my first app was ready to be launched. So it was launched, had a great successful launch without doing any videos at that point (iOS 17 was released and my app was the first one alongside another one to offer live wallpapers for iOS 17. I knew that there was a huge app potential there when iOS 17 was released in beta as Apple changed their live wallpaper feature). I Then made a video a few weeks after on my mobile tiktok channel, made about 1 million views in 48 hours, brought me around 40k additional users. Was top 1 chart in graphism and design category for a few weeks (in France, as I'm French so my TikTok videos are in French). And was top 100 in that same category in 120+ countries. Made about 500$ ? Okay that was trash, but I had no idea to monetize the app correctly at that point. It was still a huge W to me and proved me that I could successfully launch apps. Then I learned ASO (App Store Optimization) in depth, searched on internet, followed mobile app developers on Twitter, checked YouTube videos, you name it. I was eager to learn more. I needed more. Then I just iterated, build my 2nd app in less than a month, my 3rd in 3 weeks and so on. I just build my 14th app in 3 days and is now in review. Everytime I manage to reuse some of my other app's code in my new one, which is why I can build them so much faster now. I know how to monetize my app better by checking out my competitors. I learn so much by just "spying" other apps. Funnily enough, I only made this one Tiktok video on my main account to promote my app. For all my other apps, I didn't do a single video where I showcase it, the downloads has only been thanks to ASO. I still use AI everyday. I'm still not good at coding (a bit better than when I started). I use AI to create my app icons (midjourney or the new AI model Flux which is great). I use figma + midjourney to create my App Store screenshots (and they actually look quite good). I use GPT-4o and Claude 3.5 Sonnet to code most of my apps features. I use gpt-4o to localize my app (if you want to optimize the number of downloads I strongly suggest localizing your app, it takes me about 10 minutes thanks to AI). Now what are my next goals ? To achieve the 100k/month I need to change my strategy a little. Right now the $20k/month comes from purely organic downloads, I didn't do any paid advertising. It will be hard for me to keep on launching new apps and rely on ASO to reach the 100k mark. The best bet to reach 100k is to collab with content creators and they create a viral video showcasing your app. Depending on the app it's not that easy, luckily some of my apps can be viral so I will need to find the right content creators. Second way is to try tiktok/meta ads, I can check (have checked) all the ads that have been made by my competitors (thank you EU), so what I would do is copy their ad concept and create similar ads than them. Some of them have millions in ad budget so I know they create high converting ads, so you don't need to try to create an ad creative from scratch. My only big fear is to get banned by Apple (for no reason of mine). In just a snap of a finger they can just ban you from the platform, that shit scares me. And you pretty much can't do anything. So that's about it for me. I'm quite proud of myself not going to lie. Have been battling so many health issues these past years where I just stay in bed all day I'm surprised to be able to make it work. Anyways feel free to ask questions. I hope it was interesting for some of you at least. PS: My new app was just approved by app review, let the app gods favor me and bring me many downloads ! Also forgot to talk about a potential $100k+ acquisition of one of my apps, but if that ever happens I'll make a post on it.

#reddit#made#$19.2k

reddit

0

1

AntsyNursery58•This week

AI Will Make You Extremely Rich or Kill Your Business in 2024

Preface: I'm a solo-founder in the AI space and previously worked as an ML scientist; the new advancements in AI that I'm seeing are going to impact everyone here. It doesn't matter if you're just starting out, or a bootstrapped brick and mortar founder, or even a VC backed hard tech founder. Last year was when the seeds were laid, and this is the year we'll see them bloom. There will be an onslaught of advancements that take place that are borderline inconceivable due to the nature of exponential progress. This will change every single vertical. I'm making this post because I think AI execution strategy will make or break businesses. Dramatically. Over $50B was put into AI startups in 2023 alone. This figure excludes the hundreds of billions poured into AI from enterprises. So, let's follow the money: ​ 1) AI enterprise software. There's a lot to unpack here and this is what I’m currently working on. AI enterprise software will encompass everything from hyper personalized email outbound to AI cold calls to AI that A/B tests ads on synthetic data to vertical specific software. The impact of the former is relatively self explanatory, so I'll focus on the latter. To illustrate vertical specific AI software, I'll use a simple example in the legal space. Lawyers typically have to comb through thousands of pages of documents. Now, using an LLM + a VDB, an AI can instantly answer all of those questions while surfacing the source and highlighting the specific answer in the contract/document. There are dozens of AI startups for this use case alone. This saves lawyers an immense amount of time and allows them to move faster. Firms that adopt this have a fundamental advantage over law firms that don't adopt this. This was 2023 technology. I'm seeing vertical AI software getting built by my friends in areas from construction, to real estate, to even niche areas like chimney manufacturing. This will exist everywhere. Now, this can be extrapolated much further to be applicable to systems that can do reports and even browse the Internet. This brings me to my next point. ​ 2) AI information aggregation and spread. My gut tells me that this will have a crescendo moment in the future with hardware advancements (Rabbit, Tab, etc.). You won't have to google things because it will be surfaced to you. It's predictive in nature. The people who can get information the fastest will grow their business the fastest. This part is semi-speculative, but due to the nature of LLMs being so expensive to train, I have a strong feeling that large institutions will have access to the \fastest\ and \best\ models that can do this quicker than you and I can. This is why it's important to stay on top. ​ 3) AI content generation This is relevant to running advertisements and any digital marketing aspect of your business. If you can rapidly make content faster than your competitors to put in social media, you will outpace your competitors rapidly. I think most folks are familiar with MidJourney, Stable diffusion, etc. but don't know how to use it. You can generate consistent models for a clothing brand or generate images of a product that you would normally need to hire a professional photographer to take. There's also elevenlabs which is relatively easy to use and can be used to make an MP3 clip as a narration for an ad; this is something I've already done. I'm also still shocked by how many people are unfamiliar with tools like Pika which can do video generation. You could imagine companies having fleets of digital influencers that they control or conjuring up the perfect ad for a specific demographic using a combination of all of the aforementioned tools. ​ In summary, if you feel like I'm being hyperbolic or propagating science fiction fantasies, you're likely already behind. I truly recommend that everyone stays up to date on these advancements as much as possible. If your competitor comes across an AI tool that can increase their ROAS by 5x they can crush you. If your competitor uses a tool that increases the rate at which they receive and aggregate information by 200% (modest estimate) they will crush you. If your competitors have a tool that can reduce their employee size, then they will use it. They'll fire their employees to cut costs and reinvest the money back into their business. It will compound to the point where you're outpaced, and this isn't a level of innovation we've seen since the birth of the industrial revolution. Your customers can get stolen overnight, or you can steal your competition’s customers overnight. TL;DR: This is an opportunity for entrepreneurs to scale faster than they could have possibly imagined, but this also comes with the potential for your company to be obliterated. We've never seen advancements that can have this drastic of an impact this quickly. Adoption will happen fast, and first movers will have a disproportionate and compounding advantage. Watch guides, meet with startups, follow the news, and get rich.

#reddit#will#make

reddit

0

0

FreeBirdy00•This week

How and why does Musk succeed in almost all of his ventures even when the wind is against him ?

So I saw this post somewhere and decided to ask this here too. Elon Musk has probably been involved, initiated and successfully executes more ventures in his life than any other tech-billionaire CEO. SpaceX, Tesla, Twitter, PayPal (his company was acquired by PayPal after which it boomed), Neuralink, OpenAI etc. How is it that one single person can find time to do this much in life and succeed in each and every one of them ? It almost seems unreal. And in most of his ventures, he was always very close to being done once and for all and then somehow always finds a way to climb back up ? The SpaceX's 3 failed launches (back to back), Tesla's near death condition when he took over, Twitter's entire drama with lawsuits and big companies leaving the hands etc. These are all examples of near death experiences he must've had during his journey. But how does he always climb back out of it ? Is it because of his "failure's not an option" and "never give up" attitude ? Or does he have some very foolproof strategies ? Also how does one single person do so much in such a short span and yet still have time to shitpost on twitter ? Also just to be clear I am not a Musk fanboy. I respect him for some of his work and at the same time criticize for many of his actions.

#reddit#does#musk

reddit

0

1

frankiemuiruri•This week

Why Ignoring AI Agents in 2025 Will Kill Your Marketing Strategy

If you're still focusing solely on grabbing the attention of human beings with your marketing efforts, you're already behind. In 2025, the game will change. Good marketing will demand an in-depth understanding of the AI space, especially the AI Agent space. Why? Your ads and content won’t just be seen by humans anymore. They’ll be analyzed, indexed, and often acted upon by AI agents—automated systems that will be working on behalf of companies and consumers alike. Your New Audience: Humans + AI Agents It’s not just about appealing to people. Companies are employing AI robots to research, negotiate, and make purchasing decisions. These AI agents are fast, thorough, and unrelenting. Unlike humans, they can analyze millions of options in seconds. And if your marketing isn’t optimized for them, you’ll get filtered out before you even reach the human decision-maker. How to Prepare Your Marketing for AI Agents The companies that dominate marketing in 2025 will be the ones that master the art of capturing AI attention. To do this, marketers will need to: Understand the AI agents shaping their industry. Research how AI agents function in your niche. What are they prioritizing? How do they rank options? Create AI-friendly content. Design ads and messaging that are easily understandable and accessible to AI agents. This means clear metadata, structured data, and AI-readable formats. Invest in AI analytics. AI agents leave behind footprints. Tracking and analyzing their behavior is critical. Stay ahead of AI trends. The AI agent space is evolving rapidly. What works today might be obsolete tomorrow. How My Agency Adapted and Thrived in the AI Space At my digital agency, we saw this shift coming and decided to act early. In 2023, we started integrating AI optimization into our marketing strategies. One of our clients—a B2B SaaS company—struggled to get traction because their competitors were drowning them out in Google search rankings and ad platforms. By analyzing the algorithms and behaviors of AI agents in their space, we: Rewrote their website copy with structured data and optimized metadata that was more AI-agent friendly. Created ad campaigns with clear, concise messaging and technical attributes that AI agents could quickly process and index. Implemented predictive analytics to understand what AI agents would prioritize based on past behaviors. The results? Their website traffic doubled in three months, and their lead conversion rate skyrocketed by 40%. Over half of the traffic increase was traced back to AI agents recommending their platform to human users. The Takeaway In 2025, marketing won’t just be about human attention. It’ll be about AI attention—and that requires a completely different mindset. AI agents are not your enemy; they’re your new gatekeepers. Learn to speak their language, and you’ll dominate the marketing game.

#reddit#ignoring#agents

reddit

0

1

Current-Payment-5403•This week

Beginner to the 1st sale: my journey building an AI for social media marketers

Hey everyone! Here’s my journey building an AI for social media marketers all the way up until my first pre-launch sale, hope that could help some of you: My background: studied maths at uni before dropping out to have some startup experiences. Always been drawn to building new things so I reckoned I would have some proper SaaS experiences and see how VC-funded startups are doing it before launching my own.  I’ve always leaned towards taking more risks in my life so leaving my FT job to launch my company wasn’t a big deal for me (+ I’m 22 so still have time to fail over and over). When I left my job, I started reading a lot about UI/UX, no-code tools, marketing, sales and every tool a worthwhile entrepreneur needs to learn about. Given the complexity of the project I set out to achieve, I asked a more technical friend to join as a cofounder and that's when AirMedia was born. We now use bubble for landing page as I had to learn it and custom-code stack for our platform.  Here's our goal: streamlining social media marketing using AI. I see this technology has only being at the premises of what it will be able to achieve in the near-future. We want to make the experience dynamic i.e. all happens from a discussion and you see the posts being analysed from there as well as the creation process - all from within the chat. Fast forward a few weeks ago, we finished developing the first version of our tool that early users describe as a "neat piece of tech" - just this comment alone can keep me going for months :) Being bootstrapped until now, I decided to sell lifetime deals for the users in the waitlist that want to get the tool in priority as well as secure their spot for life. We've had the first sale the first day we made that public ! Now what you all are looking for: How ?  Here was my process starting to market the platform: I need a high-converting landing page so I reckoned which companies out there have the most data and knows what convert and what doesn’t: Unbounce. Took their landing page and adapted it to my value proposition and my ICP.  The ICP has been defined from day 1 and although I’m no one to provide any advice, I strongly believe the ICP has to be defined from day 1 (even before deciding the name of the company). It helps a lot when the customer is you and you’ve had this work experience that helps you identify the problems your users encounter. Started activating the network, posting on Instagram and LinkedIn about what we've built (I've worked in many SaaS start-ups in the past so I have to admit that's a bit of a cheat code). Cold outreach from Sales NAV to our ICP, been growing the waitlist in parallel of building the tool for months now so email marketings with drip sequences and sharing dev updates to build the trust along the way (after all we're making that tool for our users - they should be the first aware about what we're building). I also came across some Whatsapp groups with an awesome community that welcomed our platform with excitement.) The landing page funnel is the following: Landing page -> register waitlist -> upsell page -> confirmation. I've made several landing pages e.g. for marketing agencies, for real estate agents, for marketing director in several different industries. The goal now is just testing out the profiles and who does it resonate the most with. Another growth hack that got us 40+ people on the waitlist: I identified some Instagram posts from competitors where their CTA was "comment AI" and I'll send you our tool and they got over 2k people commenting. Needless to say, I messaged every single user to check out our tool and see if it could help them. (Now that i think about it, the 2% conversion rate there is not great - especially considering the manual labour and the time put behind it). We’ve now got over 400 people on the waitlist so I guess we’re doing something right but we’ll keep pushing as the goal is to sell these lifetime deals to have a strong community to get started. (Also prevents us from going to VCs and I can keep my time focussing exclusively on our users - I’m not into boardroom politics, just wanna build something useful for marketers). Now I’m still in the process of testing out different marketing strategies while developing and refining our platform to make it next level on launch day. Amongst those:  LinkedIn Sales Nav outreach (first sale came from there) Product Hunt Highly personalised cold emails (there I’m thinking of doing 20 emails a day with a personalised landing page to each of those highly relevant marketers). Never seen that and I think this could impress prospects but not sure it’s worth it time / conversion wise. Make content to could go viral (at least 75 videos) that I’m posting throughout several social media accounts such as airmedia\\, airmedia\reels, airmedia\ai (you get the hack) always redirecting to the main page both in the profile description and tagging the main account. I have no idea how this will work so will certainly update some of you that would like to know the results. Will do the same across Facebook, TikTok, Youtube Shorts etc… I’m just looking for a high potential of virality there. This strategy is mainly used to grow personal brands but never seen it applied to companies. Good old cold calling Reddit (wanna keep it transparent ;) ) I’m alone to execute all these strategies + working in parallel to refine the product upon user’s feedback I’m not sure I can do more than that for now. Let me know if you have any feedback/ideas/ tasks I could implement.  I could also make another post about the proper product building process as this post was about the marketing. No I certainly haven’t accomplished anything that puts me in a position to provide advices but I reckon I’m on my way to learn more and more. Would be glad if this post could help some of you.  And of course as one of these marketing channels is Reddit I’ll post the link below for the entrepreneurs that want to streamline their social media or support us. Hope I was able to provide enough value in this post for you to consider :) https://airmedia.uk/

#reddit#beginner#sale:

reddit

0

0.6

Falahil•This week

5 Habits to go from Founder to CEO

Over the years, I've gathered some knowledge about transitioning from a startup founder to a CEO. I started my company 7 years ago. We are now not super big (65 people), but we have learned a lot. We raised $19M in total and we are now profitable. The transition from Founder to CEO was crucial. Your startup begins to mature and scale and you need to scale with it. It's often a challenging phase, but I've managed to summarize it into five habbits. Say no to important things every day Being able to say "no" to important tasks every day is an essential practice for a growing leader. It's a reality that as the magnitude of your company or ideas expands, so does the influx of good ideas and opportunities. However, to transform from a mere hustler to a true leader, you have to become selective. This means learning to refuse good ideas, which is crucial if you want to consistently execute the outstanding ones. The concept that "Startups don't starve, they drown" resonates deeply because it underlines how challenging it can be to reject opportunities. A key strategy to develop this skill is time-constraining your to-do list. Here's how you can do it: Weekly: Formulate a weekly to-do list, including only those tasks that you're sure to complete within the week. Leave some buffer room for unexpected issues. If there's any doubt about whether you'll have time for a certain task, it should not feature on your weekly list. I use Todoist and Notion for task management. Daily: Apply the same rule while creating your daily to-do list. Only include tasks that you're confident about accomplishing that day. If a task seems too big to fit into one day, break it down into manageable chunks. Journaling Journaling is a powerful strategy that can help an individual transition from a reactive approach to a proactive one. As founders, we often find ourselves caught up in a cycle of endless tasks, akin to chopping trees in a dense forest. However, to ensure sustainable growth, it is crucial to develop an ability to "zoom out", or to view the bigger picture. I use The Morning Pages method, from Julia Cameron. It consists of writing each morning about anything that comes to mind. The act of writing effectively combines linear, focused thinking with the benefits of a thoughtful conversation. If you just want to journal, you can use Day One app (The free version will be enough). If you want to go a bit deeper, you can try a coaching app. I use Wave.ai and I also hired it for the managers in the company because it combines both journaling with habit building. ​ Building Robust Systems and Processes (I know, it is boring and founders hate this) As a founder, you often need to wear multiple hats and juggle various roles. But as a CEO, it's vital to establish strong systems and processes that enable the business to function smoothly, even without your direct involvement. This includes: Implementing project management systems. Establishing clear lines of communication and accountability. Designing efficient workflows and procedures. To many founders, developing these systems might seem monotonous or even tedious. After all, the allure of envisioning the next big idea often proves more exciting. I experienced the same predicament. In response, I brought onboard a competent COO who excelled in systematizing processes. This strategy allowed me to kickstart initiatives and explore them in a flexible, less structured manner. Once an idea showed signs of gaining traction, my COO stepped in to streamline it, crafting a process that turned the fledgling idea into a consistent business operation. ​ Meditating Meditation is about reprogramming unconscious mental processes by repeatedly performing fundamental tasks with a distinct intention. This practice can be even more crucial to leadership than acquiring a business school education. Because meditation provides the most direct route to understanding your mind's workings and thus, forms the most effective basis for transforming it. To transition from a founder to a CEO, a significant shift in your mindset is required. This shift involves moving from a hustle mentality to precision, from acting as a superhero solving problems to consciously stepping back, thereby providing room for your team members to discover their own superpowers. It's about shifting your success indicators - from individual achievements to the triumphs of your team. This transformation might not feel comfortable initially, and your instincts, shaped by your scrappy founder phase, might resist this change. However, with consistent practice, you can align your instincts with the stage of your company, promoting more effective leadership. This is where the value of meditation truly shines. It allows you to identify your distinct thought patterns in real time and, over time, modify them. I use Headspace a lot, and I also encourage the employees to use it. The company pays the subscription as a perk. ​ Balancing the Macro and the Micro As the CEO, your primary focus should be on the big picture – your company's vision and strategy. However, you also need to keep an eye on the details, as these can make or break your execution. It's all about balance: Delegate the details but stay informed. Prioritize strategic planning but be ready to dive into the trenches when needed. Keep your eye on your long-term vision but adapt to short-term realities. The transition from founder to CEO isn't about giving up what made you successful initially but augmenting it with additional skills, perspectives, and practices. It's a personal and professional evolution that can lead to greater success for both you and your business. Every great CEO was once a founder. It's just about taking the next step. I’d love to hear your experiences or any tips you might have for this transition. In which step of your journey are you right now? Do you have employees already? What are your main challenges right now?

#reddit#habits#founder

reddit

0

1

tilopedia•This week

My Side Projects: From CEO to 4th Developer (Thanks, AI 🤖)

Hey Reddit 👋, I wanted to share a bit about some side projects I’ve been working on lately. Quick background for context: I’m the CEO of a mid-to-large-scale eCommerce company pulling in €10M+ annually in net turnover. We even built our own internal tracking software that’s now a SaaS (in early review stages on Shopify), competing with platforms like Lifetimely and TrueROAS. But! That’s not really the point of this post — there’s another journey I’ve been on that I’m super excited to share (and maybe get your feedback on!). AI Transformed My Role (and My Ideas List) I’m not a developer by trade — never properly learned how to code, and to be honest, I don’t intend to. But, I’ve always been the kind of guy who jots down ideas in a notes app and dreams about execution. My dev team calls me their “4th developer” (they’re a team of three) because I have solid theoretical knowledge and can kinda read code. And then AI happened. 🛠️ It basically turned my random ideas app into an MVP generation machine. I thought it’d be fun to share one of the apps I’m especially proud of. I am also planning to build this in public and therefore I am planning to post my progress on X and every project will have /stats page where live stats of the app will be available. Tackling My Task Management Problem 🚀 I’ve sucked at task management for YEARS, I still do! I’ve tried literally everything — Sheets, Todoist, Asana, ClickUp, Notion — you name it. I’d start… and then quit after a few weeks - always. What I struggle with the most is delegating tasks. As a CEO, I delegate a ton, and it’s super hard to track everything I’ve handed off to the team. Take this example: A few days ago, I emailed an employee about checking potential collaboration opportunities with a courier company. Just one of 10s of tasks like this I delegate daily. Suddenly, I thought: “Wouldn’t it be AMAZING if just typing out this email automatically created a task for me to track?” 💡 So… I jumped in. With the power of AI and a few intense days of work, I built a task manager that does just that. But of course, I couldn’t stop there. Research & Leveling It Up 📈 I looked at similar tools like TickTick and Todoist, scraped their G2 reviews (totally legally, promise! 😅), and ran them through AI for a deep SWOT analysis. I wanted to understand what their users liked/didn’t like and what gaps my app could fill. Some of the features people said they were missing didn’t align with the vision for my app (keeping it simple and personal), but I found some gold nuggets: Integration with calendars (Google) Reminders Customizable UX (themes) So, I started implementing what made sense and am keeping others on the roadmap for the future. And I’ve even built for that to, it still doesn’t have a name, however the point is you select on how many reviews of a specific app you want to make a SWOT analysis on and it will do it for you. Example for Todoist in comments. But more on that, some other time, maybe other post ... Key Features So Far: Here’s what’s live right now: ✅ Email to Task: Add an email as to, cc, or bcc — and it automatically creates a task with context, due dates, labels, etc. ✅ WhatsApp Reminders: Get nudged to handle your tasks via WhatsApp. ✅ WhatsApp to Task: Send a message like /task buy groceries — bam, it’s added with full context etc.. ✅ Chrome Extension (work-in-progress): Highlight text on any page, right-click, and send it straight to your task list. Next Steps: Build WITH the Community 👥 Right now, the app is 100% free while still in the early stages. But hey, API calls and server costs aren’t cheap, so pricing is something I’ll figure out with you as we grow. For now, my goal is to hit 100 users and iterate from there. My first pricing idea is, without monthly subscription, I don’t want to charge someone for something he didn’t use. So I am planning on charging "per task", what do you think? Here’s what I have planned: 📍 End of Year Goal: 100 users (starting from… 1 🥲). 💸 Revenue Roadmap: When we establish pricing, we’ll talk about that. 🛠️ Milestones: Post on Product Hunt when we hit 100 users. Clean up my self-written spaghetti code (hire a pro dev for review 🙃). Hire a part-time dev once we hit MRR that can cover its costs. You can check how are we doing on thisisatask.me/stats Other Side Projects I’m Working On: Because… what’s life without taking on too much, right? 😂 Full list of things I’m building: Internal HRM: Not public, tried and tested in-house. Android TV App: Syncs with HRM to post announcements to office TVs (streamlined and simple). Stats Tracker App: Connects to our internal software and gives me real-time company insights. Review Analyzer: Scrapes SaaS reviews (e.g., G2) and runs deep analysis via AI. This was originally for my Shopify SaaS but is quickly turning into something standalone. Coming soon! Mobile app game: secret for now. Let’s Build This Together! Would love it if you guys checked out thisisatask.me and gave it a spin! Still super early, super raw, but I’m pumped to hear your thoughts. Also, what’s a must-have task manager feature for you? Anything that frustrates you with current tools? I want to keep evolving this in public, so your feedback is gold. 🌟 Let me know, Reddit! Are you with me? 🙌

#reddit#side#projects:

reddit

0

1

DrJigsaw•This week

Recently hit 6,600,000 monthly organic traffic for a B2C SaaS website. Here's the 40 tips that helped me make that happen.

Hey guys! So as title says, we recently hit 6,600,000 monthly organic traffic / month for a B2C SaaS website (screenshot. Can't give name publicly, but can show testimonial to a mod). Here's 40 tips that "helped" me make this happen. If you get some value of the post, I write an SEO tip every other day on /r/seogrowth. There's around 10 more tips already up there other than the ones I mention here. If you want to give back for all my walls of text, I'd appreciate a sub <3 Also, there are a bunch of free stuff I mention in the article: content outline, writer guidelines, SEO checklist, and other stuff. Here's the Google Doc with all that! Tip #1. Take SEO With a Grain of Salt A lot of the SEO advice and best practices on the internet are based on 2 things: Personal experiences and case studies of companies that managed to make SEO work for them. Google or John Mueller (Google’s Senior Webmaster Trends Analyst). And, unfortunately, neither of these sources are always accurate. Personal SEO accounts are simply about what worked for specific companies. Sometimes, what worked for others, won’t work for you. For example, you might find a company that managed to rank with zero link-building because their website already had a very strong backlink profile. If you’re starting with a fresh website, chances are, you won’t be able to get the same results. At the same time, information from Google or John Mueller is also not 100% accurate. For example, they’ve said that guest posting is against Google’s guidelines and doesn’t work… But practically, guest posting is a very effective link-building strategy. So the takeaway is this: Take all information you read about SEO with a grain of salt. Analyze the information yourself, and make your conclusions. SEO Tip #2. SEO Takes Time You’ve already heard this one before, but considering how many people keep asking, thought I'd include this anyway. On average, it’s going to take you 6 months to 2 years to get SEO results, depending on the following factors: Your backlink profile. The more quality backlinks you have (or build), the faster you’ll rank. Age of your website. If your website is older (or you purchased an aged website), you can expect your content to rank faster. Amount of content published. The more quality content you publish on your website, the more “authoritative” it is in the eyes of Google, and thus more likely to rank faster. SEO work done on the website. If a lot of your pages are already ranking on Google (page 2-3), it’s easier to get them to page #1 than if you just published the content piece. Local VS global SEO. Ranking locally is (sometimes) easier and faster than ranking globally. That said, some marketing agencies can use “SEO takes time” as an excuse for not driving results. Well, fortunately, there is a way to track SEO results from month #2 - #3 of work. Simply check if your new content pieces/pages are getting more and more impressions on Google Search Console month-to-month. While your content won’t be driving traffic for a while after being published, they’ll still have a growing number of impressions from month #2 or #3 since publication. SEO Tip #3. SEO Might Not Be The Best Channel For You In theory, SEO sounds like the best marketing channel ever. You manage to rank on Google and your marketing seemingly goes on auto-pilot - you’re driving new leads every day from existing content without having to lift a finger… And yet, SEO is not for everyone. Avoid SEO as a marketing channel if: You’re just getting started with your business and need to start driving revenue tomorrow (and not in 1-2 years). If this is you, try Google ads, Facebook ads, or organic marketing. Your target audience is pretty small. If you’re selling enterprise B2B software and have around 2,000 prospects in total worldwide, then it’s simply easier to directly reach out to these prospects. Your product type is brand-new. If customers don’t know your product exists, they probably won’t be Googling it. SEO Tip #4. Traffic Can Be a Vanity Metric I've seen hundreds of websites that drive 6-7 digits of traffic but generate only 200-300 USD per month from those numbers. “What’s the deal?” You might be thinking. “How can you fail to monetize that much traffic?” Well, that brings us to today’s tip: traffic can be a vanity metric. See, not all traffic is created equal. Ranking for “hormone balance supplement” is a lot more valuable than ranking for “Madagascar character names.” The person Googling the first keyword is an adult ready to buy your product. Someone Googling the latter, on the other hand, is a child with zero purchasing power. So, when deciding on which keywords to pursue, always keep in mind the buyer intent behind and don’t go after rankings or traffic just because 6-digit traffic numbers look good. SEO Tip #5. Push Content Fast Whenever you publish a piece of content, you can expect it to rank within 6 months to a year (potentially less if you’re an authority in your niche). So, the faster you publish your content, the faster they’re going to age, and, as such, the faster they’ll rank on Google. On average, I recommend you publish a minimum of 10,000 words of content per month and 20,000 to 30,000 optimally. If you’re not doing link-building for your website, then I’d recommend pushing for even more content. Sometimes, content velocity can compensate for the lack of backlinks. SEO Tip #6. Use Backlink Data to Prioritize Content You might be tempted to go for that juicy, 6-digit traffic cornerstone keyword right from the get-go... But I'd recommend doing the opposite. More often than not, to rank for more competitive, cornerstone keywords, you’ll need to have a ton of supporting content, high-quality backlinks, website authority, and so on. Instead, it’s a lot more reasonable to first focus on the less competitive keywords and then, once you’ve covered those, move on to the rest. Now, as for how to check keyword competitiveness, here are 2 options: Use Mozbar to see the number of backlinks for top-ranking pages, as well as their Domain Authority (DA). If all the pages ranking on page #1 have <5 backlinks and DA of 20 - 40, it’s a good opportunity. Use SEMrush or Ahrefs to sort your keywords by difficulty, and focus on the less difficult keywords first. Now, that said, keep in mind that both of these metrics are third-party, and hence not always accurate. SEO Tip #7. Always Start With Competitive Analysis When doing keyword research, the easiest way to get started is via competitive analysis. Chances are, whatever niche you’re in, there’s a competitor that is doing great with SEO. So, instead of having to do all the work from scratch, run their website through SEMrush or Ahrefs and steal their keyword ideas. But don’t just stop there - once you’ve borrowed keyword ideas from all your competitors, run the seed keywords through a keyword research tool such as UberSuggest or SEMrush Keyword Magic Tool. This should give you dozens of new ideas that your competitors might’ve missed. Finally, don’t just stop at borrowing your competitor’s keyword ideas. You can also borrow some inspiration on: The types of graphics and images you can create to supplement your blog content. The tone and style you can use in your articles. The type of information you can include in specific content pieces. SEO Tip #8. Source a LOT of Writers Content writing is one of those professions that has a very low barrier to entry. Anyone can take a writing course, claim to be a writer, and create an UpWork account… This is why 99% of the writers you’ll have to apply for your gigs are going to be, well, horrible. As such, if you want to produce a lot of content on the reg, you’ll need to source a LOT of writers. Let’s do the math: If, by posting a job ad, you source 100 writers, you’ll see that only 5 of them are a good fit. Out of the 5 writers, 1 has a very high rate, so they drop out. Another doesn’t reply back to your communication, which leaves you with 3 writers. You get the 3 writers to do a trial task, and only one turns out to be a good fit for your team. Now, since the writer is freelance, the best they can do is 4 articles per month for a total of 5,000-words (which, for most niches, ain’t all that much). So, what we’re getting at here is, to hire quality writers, you should source a LOT of them. SEO Tip #9. Create a Process for Filtering Writers If you follow the previous tip, you'll end up with a huge database of hundreds of writers. This creates a whole new problem: You now have a database of 500+ writers waiting for you to sift through them and decide which ones are worth the hire. It would take you 2-3 days of intense work to go through all these writers and vet them yourself. Let’s be real - you don’t have time for that. Here’s what you can do instead: When sourcing writers, always get them to fill in a Google form (instead of DMing or emailing you). In this form, make sure to ask for 3 relevant written samples, a link to the writer’s portfolio page, and the writer’s rate per word. Create a SOP for evaluating writers. The criteria for evaluation should be: Level of English. Does the writer’s sample have any English mistakes? If so, they’re not a good fit. Quality of Samples. Are the samples long-form and engaging content or are they boring 500-word copy-pastes? Technical Knowledge. Has the writer written about a hard-to-explain topic before? Anyone can write about simple topics like traveling—you want to look for someone who knows how to research a new topic and explain it in a simple and easy-to-read way. If someone’s written about how to create a perfect cover letter, they can probably write about traveling, but the opposite isn’t true. Get your VA to evaluate the writer’s samples as per the criteria above and short-list writers that seem competent. If you sourced 500 writers, the end result of this process should be around 50 writers. You or your editor goes through the short-list of 50 writers and invites 5-10 for a (paid) trial task. The trial task is very important - you’ll sometimes find that the samples provided by the writer don’t match their writing level. SEO Tip #10. Use the Right Websites to Find Writers Not sure where to source your writers? Here are some ideas: ProBlogger \- Our #1 choice - a lot of quality writers frequent this website. LinkedIn \- You can headhunt content writers in specific locations. Upwork \- If you post a content gig, most writers are going to be awful. Instead, I recommend headhunting top writers instead. WeWorkRemotely \- Good if you’re looking to make a full-time remote hire. Facebook \- There are a ton of quality Facebook groups for writers. Some of our faves are Cult of Copy Job Board and Content Marketing Lounge. SEO Tip #11. Always Use Content Outlines When giving tasks to your writing team, you need to be very specific about the instructions you give them. Don’t just provide a keyword and tell them to “knock themselves out.” The writer isn’t a SEO expert; chances are, they’re going to mess it up big-time and talk about topics that aren’t related to the keyword you’re targeting. Instead, when giving tasks to writers, do it through content outlines. A content outline, in a nutshell, is a skeleton of the article they’re supposed to write. It includes information on: Target word count (aim for the same or 50% more the word count than that of the competition). Article title. Article structure (which sections should be mentioned and in what order). Related topics of keywords that need to be mentioned in the article. Content outline example in the URL in the post intro. SEO Tip #12. Focus on One Niche at a Time I used to work with this one client that had a SaaS consisting of a mixture of CRM, Accounting Software, and HRS. I had to pick whether we were going to focus on topics for one of these 3 niches or focus on all of them at the same time. I decided to do the former. Here’s why: When evaluating what to rank, Google considers the authority of your website. If you have 60 articles about accounting (most of which link to each other), you’re probably an authority in the niche and are more likely to get good rankings. If you have 20 sales, 20 HR, and 20 accounting articles, though, none of these categories are going to rank as well. It always makes more sense to first focus on a single niche (the one that generates the best ROI for your business), and then move on to the rest. This also makes it easier to hire writers - you hire writers specialized in accounting, instead of having to find writers who can pull off 3 unrelated topics. SEO Tip #13. Just Hire a VA Already It’s 2021 already guys—unless you have a virtual assistant, you’re missing out big-time. Since a lot of SEO tasks are very time-consuming, it really helps to have a VA around to take over. As long as you have solid SOPs in place, you can hire a virtual assistant, train them, and use them to free up your time. Some SEO tasks virtual assistants can help with are: Internal linking. Going through all your blog content and ensuring that they link to each other. Backlink prospecting. Going through hundreds of websites daily to find link opportunities. Uploading content on WordPress and ensuring that the content is optimized well for on-page SEO. SEO Tip #14. Use WordPress (And Make Your Life Easier) Not sure which CMS platform to use? 99% of the time, you’re better off with WordPress. It has a TON of plugins that will make your life easier. Want a drag & drop builder? Use Elementor. It’s cheap, efficient, extremely easy to learn, and comes jam-packed with different plugins and features. Wix, SiteGround, and similar drag & drops are pure meh. SEO Tip #15. Use These Nifty WordPress Plugins There are a lot of really cool WordPress plugins that can make your (SEO) life so much easier. Some of our favorites include: RankMath. A more slick alternative to YoastSEO. Useful for on-page SEO. Smush. App that helps you losslessly compress all images on your website, as well as enables lazy loading. WP Rocket. This plugin helps speed up your website pretty significantly. Elementor. Not a techie? This drag & drop plugin makes it significantly easier to manage your website. WP Forms. Very simple form builder. Akismet Spam Protection. Probably the most popular anti-spam WP plugin. Mammoth Docx. A plugin that uploads your content from a Google doc directly to WordPress. SEO Tip #16. No, Voice Search Is Still Not Relevant Voice search is not and will not be relevant (no matter what sensationalist articles might say). Sure, it does have its application (“Alexa, order me toilet paper please”), but it’s pretty niche and not relevant to most SEOs. After all, you wouldn’t use voice search for bigger purchases (“Alexa, order me a new laptop please”) or informational queries (“Alexa, teach me how to do accounting, thanks”). SEO Tip #17. SEO Is Obviously Not Dead I see these articles every year - “SEO is dead because I failed to make it work.” SEO is not dead and as long as there are people looking up for information/things online, it never will be. And no, SEO is not just for large corporations with huge budgets, either. Some niches are hypercompetitive and require a huge link-building budget (CBD, fitness, VPN, etc.), but they’re more of an exception instead of the rule. SEO Tip #18. Doing Local SEO? Focus on Service Pages If you’re doing local SEO, you’re better off focusing on local service pages than blog content. E.g. if you’re an accounting firm based in Boston, you can make a landing page about /accounting-firm-boston/, /tax-accounting-boston/, /cpa-boston/, and so on. Or alternatively, if you’re a personal injury law firm, you’d want to create pages like /car-accident-law-firm/, /truck-accident-law-firm/, /wrongful-death-law-firm/, and the like. Thing is, you don’t really need to rank on global search terms—you just won’t get leads from there. Even if you ranked on the term “financial accounting,” it wouldn’t really matter for your bottom line that much. SEO Tip #19. Engage With the SEO Community The SEO community is (for the most part) composed of extremely helpful and friendly people. There are a lot of online communities (including this sub) where you can ask for help, tips, case studies, and so on. Some of our faves are: This sub :) SEO Signals Lab (FB Group) Fat Graph Content Ops (FB Group) Proper SEO Group (FB Group) BigSEO Subreddit SEO Tip #20. Test Keywords Before Pursuing Them You can use Google ads to test how profitable any given keyword is before you start trying to rank for it. The process here is: Create a Google Ads account. Pick a keyword you want to test. Create a landing page that corresponds to the search intent behind the keyword. Allocate an appropriate budget. E.g. if you assume a conversion rate of 2%, you’d want to buy 100+ clicks. If the CPC is 2 USD, then the right budget would be 200 USD plus. Run the ads! If you don’t have the budget for this, you can still use the average CPC for the keyword to estimate how well it’s going to convert. If someone is willing to bid 10 USD to rank for a certain keyword, it means that the keyword is most probably generating pretty good revenue/conversions. SEO Tip #21. Test & Improve SEO Headlines Sometimes, you’ll see that you’re ranking in the top 3 positions for your search query, but you’re still not driving that much traffic. “What’s the deal?” you might be asking. Chances are, your headline is not clickable enough. Every 3-4 months, go through your Google Search Console and check for articles that are ranking well but not driving enough traffic. Then, create a Google sheet and include the following data: Targeted keyword Page link CTR (for the last 28 days) Date when you implemented the new title Old title New title New CTR (for the month after the CTR change was implemented) From then on, implement the new headline and track changes in the CTR. If you don’t reach your desired result, you can always test another headline. SEO Tip #22. Longer Content Isn’t Always Better Content You’ve probably heard that long-form content is where it’s at in 2021. Well, this isn’t always the case. Rather, this mostly depends on the keyword you’re targeting. If, for example, you’re targeting the keyword “how to tie a tie,” you don’t need a long-ass 5,000-word mega-guide. In such a case, the reader is looking for something that can be explained in 200-300 words and if your article fails to do this, the reader will bounce off and open a different page. On the other hand, if you’re targeting the keyword “how to write a CV,” you’ll need around 4,000 to 5,000 words to adequately explain the topic and, chances are, you won’t rank with less. SEO Tip #23. SEO is Not All About Written Content More often than not, when people talk about SEO they talk about written blog content creation. It’s very important not to forget, though, that blog content is not end-all-be-all for SEO. Certain keywords do significantly better with video content. For example, if the keyword is “how to do a deadlift,” video content is going to perform significantly better than blog content. Or, if the keyword is “CV template,” you’ll see that a big chunk of the rankings are images of the templates. So, the lesson here is, don’t laser-focus on written content—keep other content mediums in mind, too. SEO Tip #24. Write For Your Audience It’s very important that your content resonates well with your target audience. If, for example, you’re covering the keyword “skateboard tricks,” you can be very casual with your language. Heck, it’s even encouraged! Your readers are Googling the keyword in their free time and are most likely teens or in their early 20s. Meaning, you can use informal language, include pop culture references, and avoid complicated language. Now, on the other hand, if you’re writing about high-level investment advice, your audience probably consists of 40-something suit-and-ties. If you include Rick & Morty references in your article, you'll most likely lose credibility and the Googler, who will go to another website. Some of our best tips on writing for your audience include: Define your audience. Who’s the person you’re writing for? Are they reading the content at work or in their free time? Keep your reader’s level of knowledge in mind. If you’re covering an accounting 101 topic, you want to cover the topic’s basics, as the reader is probably a student. If you’re writing about high-level finance, though, you don’t have to teach the reader what a balance sheet is. More often than not, avoid complicated language. The best practice is to write on a 6th-grade level, as it’s understandable for anyone. Plus, no one wants to read Shakespeare when Googling info online (unless they’re looking for Shakespeare's work, of course). SEO Tip #25. Create Compelling Headlines Want to drive clicks to your articles? You’ll need compelling headlines. Compare the following headline: 101 Productivity Tips \[To Get Things Done in 2021\] With this one: Productivity Tips Guide Which one would you click? Data says it’s the first! To create clickable headlines, I recommend you include the following elements: Keyword. This one’s non-negotiable - you need to include the target keyword in the headline. Numbers. If Buzzfeed taught us anything, it’s that people like to click articles with numbers in their titles. Results. If I read your article, what’s going to be the end result? E.g. “X Resume tips (to land the job)”.* Year (If Relevant). Adding a year to your title shows that the article is recent (which is relevant for some specific topics). E.g. If the keyword is “Marketing Trends,” I want to know marketing trends in 2021, not in 2001. So, adding a year in the title makes the headline more clickable. SEO Tip #26. Make Your Content Visual How good your content looks matters, especially if you're in a competitive niche. Here are some tips on how to make your content as visual as possible: Aim for 2-4 sentences per paragraph. Avoid huge blocks of text. Apply a 60-65% content width to your blog pages. Pick a good-looking font. I’d recommend Montserrat, PT Sans, and Roboto. Alternatively, you can also check out your favorite blogs, see which fonts they’re using, and do the same. Use a reasonable font size. Most top blogs use font sizes ranging from 16 pt to 22 pt. Add images when possible. Avoid stock photos, though. No one wants to see random “office people smiling” scattered around your blog posts. Use content boxes to help convey information better. Content boxes example in the URL in the intro of the post. SEO Tip #27. Ditch the Skyscraper Technique Already Brian Dean’s skyscraper technique is awesome and all, but the following bit really got old: “Hey \[name\], I saw you wrote an article. I, too, wrote an article. Please link to you?” The theory here is, if your content is good, the person will be compelled to link to it. In practice, though, the person really, really doesn’t care. At the end of the day, there’s no real incentive for the person to link to your content. They have to take time out of their day to head over to their website, log in to WordPress, find the article you mentioned, and add a link... Just because some stranger on the internet asked them to. Here’s something that works much better: Instead of fake compliments, be very straightforward about what you can offer them in exchange for that link. Some things you can offer are: A free version of your SaaS. Free product delivered to their doorstep. Backlink exchange. A free backlink from your other website. Sharing their content to your social media following. Money. SEO Tip #28. Get the URL Slug Right for Seasonal Content If you want to rank on a seasonal keyword, there are 2 ways to do this. If you want your article to be evergreen (i.e. you update it every year with new information), then your URL should not contain the year. E.g. your URL would be /saas-trends/, and you simply update the article’s contents+headline each year to keep it timely. If you’re planning on publishing a new trends report annually, though, then you can add a year to the URL. E.g. /saas-trends-2020/ instead of /saas-trends/. SEO Tip #29. AI Content Tools Are a Mixed Bag Lots of people are talking about AI content tools these days. Usually, they’re either saying: “AI content tools are garbage and the output is horrible,” Or: “AI content tools are a game-changer!” So which one is it? The truth is somewhere in-between. In 2021, AI content writing tools are pretty bad. The output you’re going to get is far from something you can publish on your website. That said, some SEOs use such tools to get a very, very rough draft of the article written, and then they do intense surgery on it to make it usable. Should you use AI content writing tools? If you ask me, no - it’s easier to hire a proficient content writer than spend hours salvaging AI-written content. That said, I do believe that such tools are going to get much better years down the line. This one was, clearly, more of a personal opinion than a fact. I’d love to hear YOUR opinion on AI content tools! Are they a fad, or are they the future of content creation? Let me know in the comments. SEO Tip #30. Don’t Overdo it With SEO Tools There are a lot of SEO tools out there for pretty much any SEO function. Keyword research, link-building, on-page, outreach, technical SEO, you name it! If you were to buy most of these tools for your business, you’d easily spend 4-figures on SEO tools per month. Luckily, though, you don’t actually need most of them. At the end of the day, the only must-have SEO tools are: An SEO Suite (Paid). Basically SEMrush or Ahrefs. Both of these tools offer an insane number of features - backlink analysis, keyword research, and a ton of other stuff. Yes, 99 USD a month is expensive for a tool. But then again, if you value your time 20 USD/hour and this tool saves you 6 hours, it's obviously worth it, right? On-Page SEO Tool (Free). RankMath or Yoast. Basically, a tool that's going to help you optimize web pages or blog posts as per SEO best practices. Technical SEO Tool (Freemium). You can use ScreamingFrog to crawl your entire website and find technical SEO problems. There are probably other tools that also do this, but ScreamingFrog is the most popular option. The freemium version of the tool only crawls a limited number of pages (500 URLs, to be exact), so if your website is relatively big, you'll need to pay for the tool. Analytics (Free). Obviously, you'll need Google Analytics (to track website traffic) and Google Search Console (to track organic traffic, specifically) set up on your website. Optionally, you can also use Google Track Manager to better track how your website visitors interact with the site. MozBar (Free). Chrome toolbar that lets you simply track the number of backlinks on Google Search Queries, Domain Authority, and a bunch of other stuff. Website Speed Analysis (Free). You can use Google Page Speed Insights to track how fast your website loads, as well as how mobile-friendly it is. Outreach Tool (Paid). Tool for reaching out to prospects for link-building, guest posting, etc. There are about a dozen good options for this. Personally, I like to use Snov for this. Optimized GMB Profile (Free). Not a tool per se, but if you're a local business, you need to have a well-optimized Google My Business profile. Google Keyword Planner (Free). This gives you the most reliable search volume data of all the tools. So, when doing keyword research, grab the search volume from here. Tool for Storing Keyword Research (Free). You can use Google Sheets or AirTable to store your keyword research and, at the same time, use it as a content calendar. Hemingway App (Free). Helps keep your SEO content easy to read. Spots passive voice, complicated words, etc. Email Finder (Freemium). You can use a tool like Hunter to find the email address of basically anyone on the internet (for link-building or guest posting purposes). Most of the tools that don’t fit into these categories are 100% optional. SEO Tip #31. Hiring an SEO? Here’s How to Vet Them Unless you’re an SEO pro yourself, hiring one is going to be far from easy. There’s a reason there are so many “SEO experts” out there - for the layman, it’s very hard to differentiate between someone who knows their salt and a newbie who took an SEO course, like, last week. Here’s how you can vet both freelance and full-time SEOs: Ask for concrete traffic numbers. The SEO pro should give you the exact numbers on how they’ve grown a website in the past - “100% SEO growth in 1 year” doesn’t mean much if the growth is from 10 monthly traffic to 20. “1,000 to 30,000” traffic, on the other hand, is much better. Ask for client names. While some clients ask their SEOs to sign an NDA and not disclose their collaboration, most don’t. If an SEO can’t name a single client they’ve worked with in the past, that’s a red flag. Make sure they have the right experience. Global and local SEO have very different processes. Make sure that the SEO has experience with the type of SEO you need. Make sure you’re looking for the right candidate. SEO pros can be content writers, link-builders, web developers, or all of the above simultaneously. Make sure you understand which one you need before making the hire. If you’re looking for someone to oversee your content ops, you shouldn’t hire a technical SEO expert. Look for SEO pros in the right places. Conventional job boards are overrated. Post your job ads on SEO communities instead. E.g. this sub, bigseo, SEO Signals Facebook group, etc. SEO Tip #32. Blog Post Not Ranking? Follow This Checklist I wanted to format the post natively for Reddit, but it’s just SO much better on Notion. Tl;dr, the checklist covers every reason your post might not be ranking: Search intent mismatch. Inferior content. Lack of internal linking. Lack of backlinks. And the like. Checklist URL at the intro of the post. SEO Tip #33. Avoid BS Link-Building Tactics The only type of link-building that works is building proper, quality links from websites with a good backlink profile and decent organic traffic. Here’s what DOESN’T work: Blog comment links Forum spam links Drive-by Reddit comment/post links Web 2.0 links Fiverr “100 links for 10 bucks” bs If your “SEO agency” says they’re doing any of the above instead of actually trying to build you links from quality websites, you’re being scammed. SEO Tip #34. Know When to Use 301 and 302 Redirects When doing redirects, it’s very important to know the distinction between these two. 301 is a permanent page redirect and passes on link juice. If you’re killing off a page that has backlinks, it’s better to 301 it to your homepage so that you don’t lose the link juice. If you simply delete a page, it’s going to be a 404, and the backlink juice is lost forever. 302 is a temporary page redirect and doesn’t pass on link juice. If the redirect is temporary, you do a 302. E.g. you want to test how well a new page is going to perform w/ your audience. SEO Tip #35. Social Signals Matter (But Not How You Think) Social signals are NOT a ranking factor. And yet, they can help your content rank on Google’s front page. Wondering what the hell am I talking about? Here’s what’s up: As I said, social signals are not a ranking factor. It’s not something Google takes into consideration to decide whether your article should rank or not. That said, social signals CAN lead to your article ranking better. Let’s say your article goes viral and gets around 20k views within a week. A chunk of these viewers are going to forget your domain/link and they’re going to look up the topic on Google via your chosen keyword + your brand name. The amount of people looking for YOUR keyword and exclusively picking your result over others is going to make Google think that your content is satisfying search intent better than the rest, and thus, reward you with better ranking. SEO Tip #36. Run Remarketing Ads to Lift Organic Traffic Conversions Not satisfied with your conversion rates? You can use Facebook ads to help increase them. Facebook allows you to do something called “remarketing.” This means you can target anyone that visited a certain page (or multiple pages) on your website and serve them ads on Facebook. There are a TON of ways you can take advantage of this. For example, you can target anyone that landed on a high buyer intent page and serve them ads pitching your product or a special offer. Alternatively, you can target people who landed on an educational blog post and offer them something to drive them down the funnel. E.g. free e-book or white paper to teach them more about your product or service. SEO Tip #37. Doing Local SEO? Follow These Tips Local SEO is significantly different from global SEO. Here’s how the two differ (and what you need to do to drive local SEO results): You don’t need to publish content. For 95% of local businesses, you only want to rank for keywords related to your services/products, you don’t actually need to create educational content. You need to focus more on reviews and citation-building. One of Google Maps’ biggest ranking factors is the of reviews your business has. Encourage your customers to leave a review if they enjoyed your product/service through email or real-life communication. You need to create service pages for each location. As a local business, your #1 priority is to rank for keywords around your service. E.g. If you're a personal injury law firm, you want to optimize your homepage for “personal injury law firm” and then create separate pages for each service you provide, e.g. “car accident lawyer,” “motorcycle injury law firm,” etc. Focus on building citations. Being listed on business directories makes your business more trustworthy for Google. BrightLocal is a good service for this. You don’t need to focus as much on link-building. As local SEO is less competitive than global, you don’t have to focus nearly as much on building links. You can, in a lot of cases, rank with the right service pages and citations. SEO Tip #38. Stop Ignoring the Outreach Emails You’re Getting (And Use Them to Build Your Own Links) Got a ton of people emailing you asking for links? You might be tempted to just send them all straight to spam, and I don’t blame you. Outreach messages like “Hey Dr Jigsaw, your article is A+++ amazing! ...can I get a backlink?” can get hella annoying. That said, there IS a better way to deal with these emails: Reply and ask for a link back. Most of the time, people who send such outreach emails are also doing heavy guest posting. So, you can ask for a backlink from a 3rd-party website in exchange for you mentioning their link in your article. Win-win! SEO Tip #39. Doing Internal Linking for a Large Website? This’ll Help Internal linking can get super grueling once you have hundreds of articles on your website. Want to make the process easier? Do this: Pick an article you want to interlink on your website. For the sake of the example, let’s say it’s about “business process improvement.” Go on Google and look up variations of this keyword mentioned on your website. For example: Site:\[yourwebsite\] “improve business process” Site:\[yourwebsite\] “improve process” Site:\[yourwebsite\] “process improvement” The above queries will find you the EXACT articles where these keywords are mentioned. Then, all you have to do is go through them and include the links. SEO Tip #40. Got a Competitor Copying Your Content? File a DMCA Notice Fun fact - if your competitors are copying your website, you can file a DMCA notice with Google. That said, keep in mind that there are consequences for filing a fake notice.

#reddit#recently#6,600,000

reddit

0

0.882

mr_t_forhire•This week

Started a content marketing agency 8 years ago - $0 to $7,863,052 (2025 update)

Hey friends, My name is Tyler and for the past 8 years, I’ve been documenting my experience building a content marketing agency called Optimist. Year 1 — 0 to $500k ARR Year 2 — $500k to $1MM ARR Year 3 — $1MM ARR to $1.5MM(ish) ARR Year 4 — $3,333,686 Revenue Year 5 — $4,539,659 Revenue Year 6 — $5,974,324 Revenue Year 7 - $6,815,503 Revenue (Edit: Seems like links are banned now. You can check my post history for all of my previous updates with lessons and learnings.) How Optimist Works First, an overview/recap of the Optimist business model: We operate as a “collective” of full time/professional freelancers Everyone aside from me is a contractor Entirely remote/distributed team We pay freelancers a flat fee for most work, working out to roughly $65-100/hour. Clients pay us a flat monthly fee for full-service content marketing (research, strategy, writing, editing, design/photography, reporting and analytics, targeted linkbuilding, and more)\ Packages range in price from \~$10-20k/mo \This is something we are revisiting now* The Financials In 2024, we posted $1,032,035.34 in revenue. This brings our lifetime revenue to $7,863,052. Here’s our monthly revenue from January 2017 to December of 2024. (Edit: Seems like I'm not allowed to link to the chart.) The good news: Revenue is up 23% YoY. EBITDA in Q4 trending up 1-2 points. We hosted our first retreat in 4 years, going to Ireland with about half the team. The bad news: Our revenue is still historically low. At $1MM for the year, we’re down about 33% from our previous years over $1.5MM. Revenue has been rocky. It doesn’t feel like we’ve really “recovered” from the bumps last year. The trend doesn’t really look great. Even though, anecdotally, it feels like we are moving in a good direction. EBITDA is still hovering at around 7%. Would love to get that closer to 20%. (For those who may ask: I’m calculating EBITDA after paying taxes and W2 portion of my income.) — Almost every year, my update starts the same way: This has been a year of growth and change. Both for my business—and me personally. 2024 was no different. I guess that tells you something about entrepreneurship. It’s a lot more like sailing a ship than driving a car. You’re constantly adapting, tides are shifting, and any blip of calm is usually just a moment before the next storm. As with past years, there’s a lot to unpack from the last 12 months. Here we go again. Everything is Burning In the last 2 years, everything has turned upside down in the world of content and SEO. Back in 2020, we made a big decision to re-position the agency. (See post history) We decided to narrow our focus to our most successful, profitable, and consistent segment of clients and re-work our entire operation to focus on serving them. We defined our ICP as: \~Series A ($10mm+ funding) with 6-12 months runway to scale organic as a channel Product-led company with “simple” sales cycle involving fewer stakeholders Demonstrable opportunity to use SEO to drive business growth Our services: Content focused on growing organic search (SEO) Full-service engagements that included research, planning, writing, design, reporting And our engagement structure: Engaged directly with an executive; ownership over strategy and day-to-day execution 1-2 points of contact or stakeholders Strategic partner that drives business growth (not a service vendor who makes content) Most importantly, we decided that we were no longer going to offer a broader range of content that we used to sell. That included everything from thought leadership content to case studies and ebooks. We doubled-down on “SEO content” for product-led SaaS companies. And this worked phenomenally for us. We started bringing on more clients than ever. We developed a lot of internal system and processes that helped us scale and take on more work than we’ve ever had and drive great outcomes for our ideal clients. But in 2023 and 2024, things started going awry. One big change, of course, was the rise of AI. Many companies and executives (and writers) feel that AI can write content just as well as an agency like ours. That made it a lot harder to sell a $10,000 per month engagement when they feel like the bulk of the work could be “done for free.” (Lots of thoughts on this if you want my opinions.) But it wasn’t just that. Google also started tinkering with their algorithm, introducing new features like AI Overviews, and generally changing the rules of the game. This created 3 big shifts in our world: The perceived value of content (especially “SEO content”) dropped dramatically in many people’s minds because of AI’s writing capabilities SEO became less predictable as a source of traffic and revenue It’s harder than ever for startups and smaller companies to rank for valuable keywords (let alone generate any meaningful traffic or revenue from them) The effect? The middle of the content market has hollowed out. People—like us—providing good, human-crafted content aimed on driving SEO growth saw a dramatic decline in demand. We felt it all year. Fewer and fewer leads. The leads we did see usually scoffed at our prices. They were indexing us against the cost of content mills and mass-produced AI articles. It was a time of soul-searching and looking for a way forward. I spent the first half of the year convinced that the only way to survive was to run toward the fire. We have to build our own AI workflows. We have to cut our rates internally. We have to get faster and cheaper to stay competitive with the agencies offering the same number of deliverables for a fraction of our rates. It’s the only way forward. But then I asked myself a question… Is this the game I actually want to play? As an entrepreneur, do I want to run a business where I’m competing mostly on price and efficiency rather than quality and value? Do I want to hop into a race toward cheaper and cheaper content? Do I want to help people chase a dwindling amount of organic traffic that’s shrinking in value? No. That’s not the game I want to play. That’s not a business I want to run. I don’t want to be in the content mill business. So I decided to turn the wheel—again. Repositioning Part II: Electric Boogaloo What do you do when the whole world shifts around you and the things that used to work aren’t working anymore? You pivot. You re-position the business and move in another direction. So that’s what we decided to do. Again. There was only one problem: I honestly wasn’t sure what opportunities existed in the content marketing industry outside of what we were already doing. We lived in a little echo chamber of startups and SEO. It felt like the whole market was on fire and I had fight through the smoke to find an escape hatch. So I started making calls. Good ol’ fashioned market research. I reached out to a few dozen marketing and content leaders at a bunch of different companies. I got on the phone and just asked lots of questions about their content programs, their goals, and their pain points. I wanted to understand what was happening in the market and how we could be valuable. And, luckily, this process really paid off. I learned a lot about the fragmentation happening across content and how views were shifting. I noticed key trends and how our old target market really wasn’t buying what we were selling. Startups and small companies are no longer willing to invest in an agency like ours. If they were doing content and SEO at all, they were focused entirely on using AI to scale output and minimize costs. VC money is still scarce and venture-backed companies are more focused on profitability than pure growth and raising another round. Larger companies (\~500+ employees) are doing more content than ever and drowning in content production. They want to focus on strategy but can barely tread water keeping up with content requests from sales, demand gen, the CEO, and everyone else. Many of the companies still investing in content are looking at channels and formats outside of SEO. Things like thought leadership, data reports, interview-driven content, and more. They see it as a way to stand out from the crowd of “bland SEO content.” Content needs are constantly in flux. They range from data reports and blog posts to product one-pagers. The idea of a fixed-scope retainer is a total mismatch for the needs of most companies. All of this led to the logical conclusion: We were talking to the wrong people about the wrong things\.\ Many companies came to one of two logical conclusions: SEO is a risky bet, so it’s gotta be a moonshot—super-low cost with a possibility for a big upside (i.e., use AI to crank out lots of content. If it works, great. If it doesn’t, then at least we aren’t out much money.) SEO is a risky bet, so we should diversify into other strategies and channels to drive growth (i.e., shift our budget from SEO and keyword-focused content to video, podcasts, thought leadership, social, etc) Unless we were going to lean into AI and dramatically cut our costs and rates, our old buyers weren’t interested. And the segment of the market that needs our help most are looking primarily for production support across a big range of content types. They’re not looking for a team to run a full-blown program focused entirely on SEO. So we had to go back to the drawing board. I’ve written before about our basic approach to repositioning the business. But, ultimately it comes down to identifying our unique strengths as a team and then connecting them to needs in the market. After reviewing the insights from my discussions and taking another hard look at our business and our strengths, I decided on a new direction: Move upmarket: Serve mid-size to enterprise businesses with \~500-5,000 employees instead of startups Focus on content that supports a broader range of business goals instead of solely on SEO and organic growth (e.g., sales, demand gen, brand, etc) Shift back to our broader playbook of content deliverables, including thought leadership, data studies, and more Focus on content execution and production to support an internally-directed content strategy across multiple functions In a way, it’s sort of a reverse-niche move. Rather than zooming in specifically on driving organic growth for startups, we want to be more of an end-to-end content production partner that solves issues of execution and operations for all kinds of content teams. It’s early days, but the response here has been promising. We’ve seen an uptick in leads through Q4. And more companies in our pipeline fit the new ICP. They’re bigger, often have more budget. (But they move more slowly). We should know by the end of the quarter if this maneuver is truly paying off. Hopefully, this will work out. Hopefully our research and strategy are right and we’ll find a soft landing serving a different type of client. If it doesn’t? Then it will be time to make some harder decisions. As I already mentioned, I’m not interested in the race to the bottom of AI content. And if that’s the only game left in town, then it might be time to think hard about a much bigger change. — To be done: Build new content playbooks for expanded deliverables Build new showcase page for expanded deliverables Retooling the Operation It’s easy to say we’re doing something new. It’s a lot harder to actually do it—and do it well. Beyond just changing our positioning, we have to do open-heart surgery on the entire content operation behind the scenes. We need to create new systems that work for a broader range of content types, formats, and goals. Here’s the first rub: All of our workflows are tooled specifically for SEO-focused content. Every template, worksheet, and process that we’ve built and scaled in the last 5 years assumes that the primary goal of every piece of content is SEO. Even something as simple as requiring a target keyword is a blocker in a world where we’re not entirely focused on SEO. This is relatively easy to fix, but it requires several key changes: Update content calendars to make keywords optional Update workflows to determine whether we need an optimization report for each deliverable Next, we need to break down the deliverables into parts rather than a single line item. In our old system, we would plan content as a single row in a Content Calendar spreadsheet. It was a really wide sheet with lots of fields where we’d define the dimensions of each individual article. This was very efficient and simple to follow. But every article had the same overall scope when it came to the workflow. In Asana (our project management tool), all of the steps in the creation were strung together in a single task. We would create a few basic templates for each client, and then each piece would flow through the same steps: Briefing Writing Editing Design etc. If we had anything that didn’t fit into the “standard” workflow, we’d just tag it in the calendar with an unofficial notation \[USING BRACKETS\]. It worked. But it wasn’t ideal. Now we need the steps to be more modular. Imagine, for example, a client asks us to create a mix of deliverables: 1 article with writing + design 1 content brief 1 long-form ebook with an interview + writing + design Each of these would require its own steps and its own workflow. We need to break down the work to accommodate for a wider variety of workflows and variables. This means we need to update the fields and structure of our calendar to accommodate for the new dimensions—while also keeping the planning process simple and manageable. This leads to the next challenge: The number of “products” that we’re offering could be almost infinite. Just looking at the example scope above, you can mix and match all of these different building blocks to create a huge variety of different types of work, each requiring its own workflow. This is part of the reason we pivoted away from this model to focus on a productized, SEO-focused content service back in 2020. Take something as simple as a case study. On the surface, it seems like one deliverable that can be easily scoped and priced, right? Well, unpack what goes into a case study: Is there already source material from the customer or do we need to conduct an interview? How long is it? Is it a short overview case study or a long-form narrative? Does it need images and graphics? How many? Each of these variables opens up 2-3 possibilities. And when you combine them, we end up with something like 10 possible permutations for this single type of deliverable. It gets a bit messy. But not only do we have to figure out how to scope and price all for all of these variables, we also have to figure out how to account for these variables in the execution. We have to specify—for every deliverable—what type it is, how long, which steps are involved and not involved, the timeline for delivery, and all of the other factors. We’re approaching infinite complexity, here. We have to figure out a system that allows for a high level of flexibility to serve the diverse needs of our clients but is also productized enough that we can build workflows, process, and templates to deliver the work. I’ve spent the last few months designing that system. Failed Attempt #1: Ultra-Productization In my first pass, I tried to make it as straight forward as possible. Just sit down, make a list of all of the possible deliverables we could provide and then assign them specific scopes and services. Want a case study? Okay that’ll include an interview, up to 2,000 words of content, and 5 custom graphics. It costs $X. But this solution quickly fell apart when we started testing it against real-world scenarios. What if the client provided the brief instead of us creating one? What if they didn’t want graphics? What if this particular case study really needs to be 3,000 words but all of the others should be 2,000? In order for this system to work, we’d need to individual scope and price all of these permutations of each productized service. Then we’d need to somehow keep track of all of these and make sure that we accurately scope, price, and deliver them across dozens of clients. It’s sort of like a restaurant handling food allergies by creating separate versions of every single dish to account for every individual type of allergy. Most restaurants have figured out that it makes way more sense to have a “standard” and an “allergy-free” version. Then you only need 2 options to cover 100% of the cases. Onto the next option. Failed Attempt #2: Deliverable-Agnostic Services Next, I sat down with my head of Ops, Katy, to try to map it out. We took a big step back and said: Why does the deliverable itself even matter? At the end of the day, what we’re selling is just a few types of work (research, writing, editing, design, etc) that can be packaged up in an infinite number of ways. Rather than try to define deliverables, shouldn’t we leave it open ended for maximum flexibility? From there, we decided to break down everything into ultra-modular building blocks. We started working on this super complex system of modular deliverables where we would have services like writing, design, editing, etc—plus a sliding scale for different scopes like the length of writing or the number of images. In theory, it would allow us to mix and match any combination of services to create custom deliverables for the client. In fact, we wanted the work to be deliverable-agnostic. That way we could mold it to fit any client’s needs and deliver any type of content, regardless of the format or goal. Want a 5,000-word case study with 15 custom graphics? That’ll be $X. Want a 2,000-word blog post with an interview and no visuals? $Y. Just want us to create 10 briefs, you handle the writing, and we do design? It’s $Z. Again, this feels like a reasonable solution. But it quickly spiraled out of amuck. (That’s an Office reference.) For this to work, we need to have incredibly precise scoping process for every single deliverable. Before we can begin work (or even quote a price), we need to know pretty much the exact word count of the final article, for example. In the real world? This almost never happens. The content is as long as the content needs to be. Clients rarely know if the blog post should be 2,000 words or 3,000 words. They just want good content. We have a general ballpark, but we can rarely dial it in within just 1,000 words until we’ve done enough research to create the brief. Plus, from a packaging and pricing perspective, it introduces all kind of weird scenarios where clients will owe exactly $10,321 for this ultra-specific combination of services. We were building an open system that could accommodate any and all types of potential deliverables. On the face that seems great because it makes us incredibly flexible. In reality, the ambiguity actually works against us. It makes it harder for us to communicate to clients clearly about what they’ll get, how much it will cost, and how long it will take. That, of course, also means that it hurts our client relationships. (This actually kind of goes back to my personal learnings, which I’ll mention in a bit. I tend to be a “let’s leave things vague so we don’t have to limit our options” kind of person. But I’m working on fixing this to be more precise, specific, and clear in everything that we do.) Dialing It In: Building a Closed System We were trying to build an open system. We need to build a closed system. We need to force clarity and get specific about what we do, what we don’t do, and how much it all costs. Then we need a system to expand on that closed system—add new types of deliverables, new content playbooks, and new workflows if and when the need arises. With that in mind, we can start by mapping out the key dimensions of any type of deliverable that we would ever want to deliver. These are the universal dimensions that determine the scope, workflow, and price of any deliverable—regardless of the specific type output. Dimensions are: Brief scope Writing + editing scope Design scope Interview scope Revision (rounds) Scope, essentially, just tells us how many words, graphics, interviews, etc are required for the content we’re creating. In our first crack at the system, we got super granular with these scopes. But to help force a more manageable system, we realized that we didn’t need tiny increments for most of this work. Instead, we just need boundaries—you pay $X for up to Y words. We still need some variability around the scope of these articles. Obviously, most clients won’t be willing to pay the same price for a 1,000-word article as a 10,000-word article. But we can be smarter about the realistic break points. We boiled it down to the most common ranges: (Up to) 250 words 1,000 words 3,000 words 6,000 words 10,000 words This gives us a much more manageable number of variables. But we still haven’t exactly closed the system. We need one final dimension: Deliverable type. This tells us what we’re actually building with these building blocks. This is how we’ll put a cap on the potentially infinite number of combinations we could offer. The deliverable type will define what the final product should look like (e.g., blog post, case study, ebook, etc). And it will also give us a way to put standards and expectations around different types of deliverables that we want to offer. Then we can expand on this list of deliverables to offer new services. In the mean time, only the deliverables that we have already defined are, “on the menu,” so to speak. If a client comes to us and asks for something like a podcast summary article (which we don’t currently offer), we’ll have to either say we can’t provide that work or create a new deliverable type and define the dimensions of that specific piece. But here’s the kicker: No matter the deliverable type, it has to still fit within the scopes we’ve already defined. And the pricing will be the same. This means that if you’re looking for our team to write up to 1,000 words of content, it costs the same amount—whether it’s a blog post, an ebook, a LinkedIn post, or anything else. Rather than trying to retool our entire system to offer this new podcast summary article deliverable, we’ll just create the new deliverable type, add it to the list of options, and it’s ready to sell with the pre-defined dimensions we’ve already identified. To do: Update onboarding workflow Update contracts and scope documents Dial in new briefing process Know Thyself For the last year, I’ve been going through personal therapy. (Huge shout out to my wife, Laura, for her support and encouragement throughout the process.) It’s taught me a lot about myself and my tendencies. It’s helped me find some of my weaknesses and think about how I can improve as a person, as a partner, and as an entrepreneur. And it’s forced me to face a lot of hard truths. For example, consider some of the critical decisions I’ve made for my business: Unconventional freelance “collective” model No formal management structure Open-ended retainers with near-infinite flexibility General contracts without defined scope “Take it or leave it” approach to sales and marketing Over the years, I’ve talked about almost everything on this list as a huge advantage. I saw these things as a reflection of how I wanted to do things differently and better than other companies. But now, I see them more as a reflection of my fears and insecurities. Why did I design my business like this? Why do I want so much “flexibility” and why do I want things left open-ended rather than clearly defined? One reason that could clearly explain it: I’m avoidant. If you’re not steeped in the world of therapy, this basically means that my fight or flight response gets turned all the way to “flight.” If I’m unhappy or uncomfortable, my gut reaction is usually to withdraw from the situation. I see commitment and specificity as a prelude to future conflict. And I avoid conflict whenever possible. So I built my business to minimize it. If I don’t have a specific schedule of work that I’m accountable for delivering, then we can fudge the numbers a bit and hope they even out in the end. If I don’t set a specific standard for the length of an article, then I don’t have to let the client know when their request exceeds that limit. Conflict….avoided? Now, that’s not to say that everything I’ve built was wrong or bad. There is a lot of value in having flexibility in your business. For example, I would say that our flexible retainers are, overall, an advantage. Clients have changing needs. Having flexibility to quickly adapt to those needs can be a huge value add. And not everything can be clearly defined upfront (at least not without a massive amount of time and work just to decide how long to write an article). Overly-rigid structures and processes can be just as problematic as loosey-goosey ones. But, on the whole, I realized that my avoidant tendencies and laissez faire approach to management have left a vacuum in many areas. The places where I avoided specificity were often the places where there was the most confusion, uncertainty, and frustration from the team and from clients. People simply didn’t know what to expect or what was expected of them. Ironically, this often creates the conflict I’m trying to avoid. For example, if I don’t give feedback to people on my team, then they feel uneasy about their work. Or they make assumptions about expectations that don’t match what I’m actually expecting. Then the client might get upset, I might get upset, and our team members may be upset. Conflict definitely not avoided. This happens on the client side, too. If we don’t define a specific timeline when something will be delivered, the client might expect it sooner than we can deliver—creating frustration when we don’t meet their expectation. This conflict actually would have been avoided if we set clearer expectations upfront. But we didn’t do that. I didn’t do that. So it’s time to step up and close the gaps. Stepping Up and Closing the Gaps If I’m going to address these gaps and create more clarity and stability, I have to step up. Both personally and professionally. I have to actually face the fear and uncertainty that drives me to be avoidant. And then apply that to my business in meaningful ways that aren’t cop-out ways of kinda-sorta providing structure without really doing it. I’ve gotta be all in. This means: Fill the gaps where I rely on other people to do things that aren’t really their job but I haven’t put someone in place to do it Set and maintain expectations about our internal work processes, policies, and standards Define clear boundaries on things like roles, timelines, budgets, and scopes Now, this isn’t going to happen overnight. And just because I say that I need to step up to close these gaps doesn’t mean that I need to be the one who’s responsible for them (at least not forever). It just means that, as the business leader, I need to make sure the gaps get filled—by me or by someone else who has been specifically charged with owning that part of the operation. So, this is probably my #1 focus over the coming quarter. And it starts by identifying the gaps that exist. Then, step into those gaps myself, pay someone else to fill that role, or figure out how to eliminate the gap another way. This means going all the way back to the most basic decisions in our business. One of the foundational things about Optimist is being a “different kind” of agency. I always wanted to build something that solved for the bureaucracy, hierarchy, and siloed structure of agencies. If a client has feedback, they should be able to talk directly to the person doing the work rather than going through 3 layers of account management and creative directors. So I tried to be clever. I tried to design all kinds of systems and processes that eliminated these middle rungs. (In retrospect, what I was actually doing was designing a system that played into my avoidant tendencies and made it easy to abdicate responsibility for lots of things.) Since we didn’t want to create hierarchy, we never implemented things like Junior and Senior roles. We never hired someone to manage or direct the individual creatives. We didn’t have Directors or VPs. (Hell, we barely had a project manager for the first several years of existence.) This aversion to hierarchy aligned with our values around elevating ownership and collective contribution. I still believe in the value a flat structure. But a flat structure doesn’t eliminate the complexity of a growing business. No one to review writers and give them 1:1 feedback? I guess I’ll just have to do that….when I have some spare time. No Content Director? Okay, well someone needs to manage our content playbooks and roll out new ones. Just add it to my task list. Our flat structure didn’t eliminate the need for these roles. It just eliminated the people to do them. All of those unfilled roles ultimately fell back on me or our ops person, Katy. Of course, this isn’t the first time we’ve recognized this. We’ve known there were growing holes in our business as it’s gotten bigger and more complex. Over the years, we’ve experimented with different ways to solve for it. The Old Solution: Distributed Ops One system we designed was a “distributed ops” framework. Basically, we had one person who was the head of ops (at the time, we considered anything that was non-client-facing to be “ops”). They’d plan and organize all of the various things that needed to happen around Optimist. Then they’d assign out the work to whoever was able to help. We had a whole system for tying this into the our profit share and even gave people “Partner” status based on their contributions to ops. It worked—kinda. One big downfall is that all of the tasks and projects were ad hoc. People would pick up jobs, but they didn’t have much context or expertise to apply. So the output often varied. Since we were trying to maintain a flat structure, there was minimal oversight or management of the work. In other words, we didn’t always get the best results. But, more importantly, we still didn’t close all of the gaps entirely. Because everything was an ad-hoc list of tasks and projects, we never really had the “big picture” view of everything that needed to be done across the business. This also meant we rarely had clarity on what was important, what was trivial, and what was critical. We need a better system. Stop Reinventing the Wheel (And Create a Damn Org Chart) It’s time to get serious about filling the gaps in our business. It can’t be a half-fix or an ad hoc set of projects and tasks. We need clarity on the roles that need to be filled and then fill them. The first step here is to create an org chart. A real one. Map out all of the jobs that need to be done for Optimist to be successful besides just writers and designers. Roles like: Content director Design director SEO manager Reporting Finance Account management Business development Sales Marketing Project management It feels a bit laughable listing all of these roles. Because most are either empty or have my name attached to them. And that’s the problem. I can’t do everything. And all of the empty roles are gaps in our structure—places where people aren’t getting the direction, feedback, or guidance they need to do their best work. Or where things just aren’t being done consistently. Content director, for example, should be responsible for steering the output of our content strategists, writers, and editors. They’re not micromanaging every deliverable. But they give feedback, set overall policy, and help our team identify opportunities to get better. Right now we don’t have anyone in that role. Which means it’s my job—when I have time. Looking at the org chart (a real org chart that I actually built to help with this), it’s plain as day how many roles look like this. Even if we aren’t going to implement a traditional agency structure and a strict hierarchy, we still need to address these gaps. And the only way for that to happen is face the reality and then create a plan to close the gaps. Now that we have a list of theoretical roles, we need to clearly define the responsibilities and boundaries of those roles to make sure they cover everything that actually needs to happen. Then we can begin the process of delegating, assigning, hiring, and otherwise addressing each one. So that’s what I need to do. To be done: Create job descriptions for all of the roles we need to fill Hire Biz Dev role Hire Account Lead role(s) Hire Head of Content Playing Offense As we move into Q1 of 2025 and I reflect on the tumultuous few years we’ve had, one thought keeps running through my head. We need to play offense. Most of the last 1-2 years was reacting to changes that were happening around us. Trying to make sense and chart a new path forward. Reeling. But what I really want—as a person and as an entrepreneur—is to be proactive. I want to think and plan ahead. Figure out where we want to go before we’re forced to change course by something that’s out of our control. So my overarching focus for Q1 is playing offense. Thinking longer term. Getting ahead of the daily deluge and creating space to be more proactive, innovative, and forward thinking. To do: Pilot new content formats Audit and update our own content strategy Improve feedback workflows Build out long-term roadmap for 1-2 years for Optimist Final Note on Follow-Through and Cadence In my reflection this year, one of the things I’ve realized is how helpful these posts are for me. I process by writing. So I actually end up making a lot of decisions and seeing things more clearly each time I sit down to reflect and write my yearly recap. It also gives me a space to hold myself accountable for the things I said I would do. So, I’m doing two things a bit differently from here on out. First: I’m identifying clear action items that I’m holding myself accountable for getting done in the next 3 months (listed in the above sections). In each future update, I’ll do an accounting of what I got done and what wasn’t finished (and why). Second: I’m going to start writing shorter quarterly updates. This will gives me more chances each year to reflect, process, and make decisions. Plus it gives me a shorter feedback loop for the action items that I identified above. (See—playing offense.) — Okay friends, enemies, and frenemies. This is my first update for 2025. Glad to share with y’all. And thanks to everyone who’s read, commented, reached out, and shared their own experiences over the years. We are all the accumulation of our connections and our experiences. As always, I will pop in to respond to comments and answer questions. Feel free to share your thoughts, questions, and general disdain down below. Cheers, Tyler

#reddit#started#content

reddit

0

1

dams96•This week

Made $19.2k this month, and just surpassed $1000 the last 24 hours. What I did and what's next.

It's the first time I hit $1000+ in 24 hours and I had no one to share it with (except you guys). I'm quite proud of my journey, and I would have thought that making $1000 in a day would make me ecstatic, but actually it's not the case. Not sure if it's because my revenue has grown by increment step so I had time to "prepare" myself to achieve this at one point, or just that I'm nowhere near my goal of 100k/month so that I'm not that affected by it. But it's crazy to think that my goal was to make 100$ daily at the end of 2024. So for those who don't know me (I guess most of you), I build mobile apps and ship them as fast as I can. Most of them are in the AI space. I already made a post here on how I become a mobile app developer so you can check it for more details, but essentially here's what I did : Always loved creating my own things and solve problems Built multiple YouTube channels since I was 15 (mobile gaming actually) that all worked great (but it was too niche so not that scalable, didn't like that) Did a few businesses here and there (drop shopping, selling merch to school, etc) Finished my master's degree in engineering about 2 years ago Worked a moment in a famous watch industry company and saw my potential. The combo of health issues, fixed salary (although it was quite a lot), and me wanting to be an entrepreneur made me leave the company. Created a TikTok account in mobile tech (got 10+ million views the 1st 3 days), manage to grow it to 200k subs in about 3 months Got plenty of collabs for promoting mobile apps (between $500 - $2000 for a collab) Said fuck it I should do my own apps and market them on my TikTok instead of doing collabs Me wanting to build my own apps happened around May-June 2023. Started my TikTok in Feb 2023. At this point I had already 150k+ subs on TikTok. You guys need to know that I suck at coding big time. During my studies I tried to limit as much as I could coding because I was a lazy bast*rd, even though I knew it would come to bite me in the ass one day. But an angel appeared to me in broad daylight, that angel was called GPT-4. I subscribed for 20$/month to get access, and instantly I saw the potential of AI and how much it could help me. Last year GPT-4 was ahead of its time and could already code me basic apps. I had already a mac so I just downloaded Xcode and that was it. My 1st app was a wallpaper app, and I kid you not 90% of it was made by AI. Yes sometimes I had to try again and again with different prompts but it was still so much faster compared to if I had to learn coding from scratch and write code with my own hands. The only thing I didn't do was implement the in app purchase, from which I find a guy on Fiverr to do it for me for 50$. After about 2 months of on-off coding, my first app was ready to be launched. So it was launched, had a great successful launch without doing any videos at that point (iOS 17 was released and my app was the first one alongside another one to offer live wallpapers for iOS 17. I knew that there was a huge app potential there when iOS 17 was released in beta as Apple changed their live wallpaper feature). I Then made a video a few weeks after on my mobile tiktok channel, made about 1 million views in 48 hours, brought me around 40k additional users. Was top 1 chart in graphism and design category for a few weeks (in France, as I'm French so my TikTok videos are in French). And was top 100 in that same category in 120+ countries. Made about 500$ ? Okay that was trash, but I had no idea to monetize the app correctly at that point. It was still a huge W to me and proved me that I could successfully launch apps. Then I learned ASO (App Store Optimization) in depth, searched on internet, followed mobile app developers on Twitter, checked YouTube videos, you name it. I was eager to learn more. I needed more. Then I just iterated, build my 2nd app in less than a month, my 3rd in 3 weeks and so on. I just build my 14th app in 3 days and is now in review. Everytime I manage to reuse some of my other app's code in my new one, which is why I can build them so much faster now. I know how to monetize my app better by checking out my competitors. I learn so much by just "spying" other apps. Funnily enough, I only made this one Tiktok video on my main account to promote my app. For all my other apps, I didn't do a single video where I showcase it, the downloads has only been thanks to ASO. I still use AI everyday. I'm still not good at coding (a bit better than when I started). I use AI to create my app icons (midjourney or the new AI model Flux which is great). I use figma + midjourney to create my App Store screenshots (and they actually look quite good). I use GPT-4o and Claude 3.5 Sonnet to code most of my apps features. I use gpt-4o to localize my app (if you want to optimize the number of downloads I strongly suggest localizing your app, it takes me about 10 minutes thanks to AI). Now what are my next goals ? To achieve the 100k/month I need to change my strategy a little. Right now the $20k/month comes from purely organic downloads, I didn't do any paid advertising. It will be hard for me to keep on launching new apps and rely on ASO to reach the 100k mark. The best bet to reach 100k is to collab with content creators and they create a viral video showcasing your app. Depending on the app it's not that easy, luckily some of my apps can be viral so I will need to find the right content creators. Second way is to try tiktok/meta ads, I can check (have checked) all the ads that have been made by my competitors (thank you EU), so what I would do is copy their ad concept and create similar ads than them. Some of them have millions in ad budget so I know they create high converting ads, so you don't need to try to create an ad creative from scratch. My only big fear is to get banned by Apple (for no reason of mine). In just a snap of a finger they can just ban you from the platform, that shit scares me. And you pretty much can't do anything. So that's about it for me. I'm quite proud of myself not going to lie. Have been battling so many health issues these past years where I just stay in bed all day I'm surprised to be able to make it work. Anyways feel free to ask questions. I hope it was interesting for some of you at least. PS: My new app was just approved by app review, let the app gods favor me and bring me many downloads ! Also forgot to talk about a potential $100k+ acquisition of one of my apps, but if that ever happens I'll make a post on it.

#reddit#made#$19.2k

reddit

0

1

AI_Scout_Official•This week

I run an AI automation agency (AAA). My honest overview and review of this new business model

I started an AI tools directory in February, and then branched off that to start an AI automation agency (AAA) in June. So far I've come across a lot of unsustainable "ideas" to make money with AI, but at the same time a few diamonds in the rough that aren't fully tapped into yet- especially the AAA model. Thought I'd share this post to shine light into this new business model and share some ways you could potentially start your own agency, or at the very least know who you are dealing with and how to pick and choose when you (inevitably) get bombarded with cold emails from them down the line. Foreword Running an AAA does NOT involve using AI tools directly to generate and sell content directly. That ship has sailed, and unless you are happy with $5 from Fiverr every month or so, it is not a real business model. Cry me a river but generating generic art with AI and slapping it onto a T-shirt to sell on Etsy won't make you a dime. At the same time, the AAA model will NOT require you to have a deep theoretical knowledge of AI, or any academic degree, as we are more so dealing with the practical applications of generative AI and how we can implement these into different workflows and tech-stacks, rather than building AI models from the ground up. Regardless of all that, common sense and a willingness to learn will help (a shit ton), as with anything. Keep in mind - this WILL involve work and motivation as well. The mindset that AI somehow means everything can be done for you on autopilot is not the right way to approach things. The common theme of businesses I've seen who have successfully implemented AI into their operations is the willingess to work with AI in a way that augments their existing operations, rather than flat out replace a worker or team. And this is exactly the train of thought you need when working with AI as a business model. However, as the field is relatively unsaturated and hype surrounding AI is still fresh for enterprises, right now is the prime time to start something new if generative AI interests you at all. With that being said, I'll be going over three of the most successful AI-adjacent businesses I've seen over this past year, in addition to some tips and resources to point you in the right direction. so.. WTF is an AI Automation Agency? The AI automation agency (or as some YouTubers have coined it, the AAA model) at its core involves creating custom AI solutions for businesses. I have over 1500 AI tools listed in my directory, however the feedback I've received from some enterprise users is that ready-made SaaS tools are too generic to meet their specific needs. Combine this with the fact virtually no smaller companies have the time or skills required to develop custom solutions right off the bat, and you have yourself real demand. I would say in practice, the AAA model is quite similar to Wordpress and even web dev agencies, with the major difference being all solutions you develop will incorporate key aspects of AI AND automation. Which brings me to my second point- JUST AI IS NOT ENOUGH. Rather than reducing the amount of time required to complete certain tasks, I've seen many AI agencies make the mistake of recommending and (trying to) sell solutions that more likely than not increase the workload of their clients. For example, if you were to make an internal tool that has AI answer questions based on their knowledge base, but this knowledge base has to be updated manually, this is creating unnecessary work. As such I think one of the key components of building successful AI solutions is incorporating the new (Generative AI/LLMs) with the old (programmtic automation- think Zapier, APIs, etc.). Finally, for this business model to be successful, ideally you should target a niche in which you have already worked and understand pain points and needs. Not only does this make it much easier to get calls booked with prospects, the solutions you build will have much greater value to your clients (meaning you get paid more). A mistake I've seen many AAA operators make (and I blame this on the "Get Rich Quick" YouTubers) is focusing too much on a specific productized service, rather than really understanding the needs of businesses. The former is much done via a SaaS model, but when going the agency route the only thing that makes sense is building custom solutions. This is why I always take a consultant-first approach. You can only build once you understand what they actually need and how certain solutions may impact their operations, workflows, and bottom-line. Basics of How to Get Started Pick a niche. As I mentioned previously, preferably one that you've worked in before. Niches I know of that are actively being bombarded with cold emails include real estate, e-commerce, auto-dealerships, lawyers, and medical offices. There is a reason for this, but I will tell you straight up this business model works well if you target any white-collar service business (internal tools approach) or high volume businesses (customer facing tools approach). Setup your toolbox. If you wanted to start a pressure washing business, you would need a pressure-washer. This is no different. For those without programming knowledge, I've seen two common ways AAA get setup to build- one is having a network of on-call web developers, whether its personal contacts or simply going to Upwork or any talent sourcing agency. The second is having an arsenal of no-code tools. I'll get to this more in a second, but this works beecause at its core, when we are dealing with the practical applications of AI, the code is quite simple, simply put. Start cold sales. Unless you have a network already, this is not a step you can skip. You've already picked a niche, so all you have to do is find the right message. Keep cold emails short, sweet, but enticing- and it will help a lot if you did step 1 correctly and intimately understand who your audience is. I'll be touching base later about how you can leverage AI yourself to help you with outreach and closing. The beauty of gen AI and the AAA model You don't need to be a seasoned web developer to make this business model work. The large majority of solutions that SME clients want is best done using an API for an LLM for the actual AI aspect. The value we create with the solutions we build comes with the conceptual framework and design that not only does what they need it to but integrates smoothly with their existing tech-stack and workflow. The actual implementation is quite straightforward once you understand the high level design and know which tools you are going to use. To give you a sense, even if you plan to build out these apps yourself (say in Python) the large majority of the nitty gritty technical work has already been done for you, especially if you leverage Python libraries and packages that offer high level abstraction for LLM-related functions. For instance, calling GPT can be as little as a single line of code. (And there are no-code tools where these functions are simply an icon on a GUI). Aside from understanding the capabilities and limitations of these tools and frameworks, the only thing that matters is being able to put them in a way that makes sense for what you want to build. Which is why outsourcing and no-code tools both work in our case. Okay... but how TF am I suppposed to actually build out these solutions? Now the fun part. I highly recommend getting familiar with Langchain and LlamaIndex. Both are Python libraires that help a lot with the high-level LLM abstraction I mentioned previously. The two most important aspects include being able to integrate internal data sources/knowledge bases with LLMs, and have LLMs perform autonomous actions. The two most common methods respectively are RAG and output parsing. RAG (retrieval augmented Generation) If you've ever seen a tool that seemingly "trains" GPT on your own data, and wonder how it all works- well I have an answer from you. At a high level, the user query is first being fed to what's called a vector database to run vector search. Vector search basically lets you do semantic search where you are searching data based on meaning. The vector databases then retrieves the most relevant sections of text as it relates to the user query, and this text gets APPENDED to your GPT prompt to provide extra context to the AI. Further, with prompt engineering, you can limit GPT to only generate an answer if it can be found within this extra context, greatly limiting the chance of hallucination (this is where AI makes random shit up). Aside from vector databases, we can also implement RAG with other data sources and retrieval methods, for example SQL databses (via parsing the outputs of LLM's- more on this later). Autonomous Agents via Output Parsing A common need of clients has been having AI actually perform tasks, rather than simply spitting out text. For example, with autonomous agents, we can have an e-commerce chatbot do the work of a basic customer service rep (i.e. look into orders, refunds, shipping). At a high level, what's going on is that the response of the LLM is being used programmtically to determine which API to call. Keeping on with the e-commerce example, if I wanted a chatbot to check shipping status, I could have a LLM response within my app (not shown to the user) with a prompt that outputs a random hash or string, and programmatically I can determine which API call to make based on this hash/string. And using the same fundamental concept as with RAG, I can append the the API response to a final prompt that would spit out the answer for the user. How No Code Tools Can Fit In (With some example solutions you can build) With that being said, you don't necessarily need to do all of the above by coding yourself, with Python libraries or otherwise. However, I will say that having that high level overview will help IMMENSELY when it comes to using no-code tools to do the actual work for you. Regardless, here are a few common solutions you might build for clients as well as some no-code tools you can use to build them out. Ex. Solution 1: AI Chatbots for SMEs (Small and Medium Enterprises) This involves creating chatbots that handle user queries, lead gen, and so forth with AI, and will use the principles of RAG at heart. After getting the required data from your client (i.e. product catalogues, previous support tickets, FAQ, internal documentation), you upload this into your knowledge base and write a prompt that makes sense for your use case. One no-code tool that does this well is MyAskAI. The beauty of it especially for building external chatbots is the ability to quickly ingest entire websites into your knowledge base via a sitemap, and bulk uploading files. Essentially, they've covered the entire grunt work required to do this manually. Finally, you can create a inline or chat widget on your client's website with a few lines of HTML, or altneratively integrate it with a Slack/Teams chatbot (if you are going for an internal Q&A chatbot approach). Other tools you could use include Botpress and Voiceflow, however these are less for RAG and more for building out complete chatbot flows that may or may not incorporate LLMs. Both apps are essentially GUIs that eliminate the pain and tears and trying to implement complex flows manually, and both natively incoporate AI intents and a knowledge base feature. Ex. Solution 2: Internal Apps Similar to the first example, except we go beyond making just chatbots but tools such as report generation and really any sort of internal tool or automations that may incorporate LLM's. For instance, you can have a tool that automatically generates replies to inbound emails based on your client's knowledge base. Or an automation that does the same thing but for replies to Instagram comments. Another example could be a tool that generates a description and screeenshot based on a URL (useful for directory sites, made one for my own :P). Getting into more advanced implementations of LLMs, we can have tools that can generate entire drafts of reports (think 80+ pages), based not only on data from a knowledge base but also the writing style, format, and author voice of previous reports. One good tool to create content generation panels for your clients would be MindStudio. You can train LLM's via prompt engineering in a structured way with your own data to essentially fine tune them for whatever text you need it to generate. Furthermore, it has a GUI where you can dictate the entire AI flow. You can also upload data sources via multiple formats, including PDF, CSV, and Docx. For automations that require interactions between multiple apps, I recommend the OG zapier/make.com if you want a no-code solution. For instance, for the automatic email reply generator, I can have a trigger such that when an email is received, a custom AI reply is generated by MyAskAI, and finally a draft is created in my email client. Or, for an automation where I can create a social media posts on multiple platforms based on a RSS feed (news feed), I can implement this directly in Zapier with their native GPT action (see screenshot) As for more complex LLM flows that may require multiple layers of LLMs, data sources, and APIs working together to generate a single response i.e. a long form 100 page report, I would recommend tools such as Stack AI or Flowise (open-source alternative) to build these solutions out. Essentially, you get most of the functions and features of Python packages such as Langchain and LlamaIndex in a GUI. See screenshot for an example of a flow How the hell are you supposed to find clients? With all that being said, none of this matters if you can't find anyone to sell to. You will have to do cold sales, one way or the other, especially if you are brand new to the game. And what better way to sell your AI services than with AI itself? If we want to integrate AI into the cold outreach process, first we must identify what it's good at doing, and that's obviously writing a bunch of text, in a short amount of time. Similar to the solutions that an AAA can build for its clients, we can take advantage of the same principles in our own sales processes. How to do outreach Once you've identified your niche and their pain points/opportunities for automation, you want to craft a compelling message in which you can send via cold email and cold calls to get prospects booked on demos/consultations. I won't get into too much detail in terms of exactly how to write emails or calling scripts, as there are millions of resources to help with this, but I will tell you a few key points you want to keep in mind when doing outreach for your AAA. First, you want to keep in mind that many businesses are still hesitant about AI and may not understand what it really is or how it can benefit their operations. However, we can take advantage of how mass media has been reporting on AI this past year- at the very least people are AWARE that sooner or later they may have to implement AI into their businesses to stay competitive. We want to frame our message in a way that introduces generative AI as a technology that can have a direct, tangible, and positive impact on their business. Although it may be hard to quantify, I like to include estimates of man-hours saved or costs saved at least in my final proposals to prospects. Times are TOUGH right now, and money is expensive, so you need to have a compelling reason for businesses to get on board. Once you've gotten your messaging down, you will want to create a list of prospects to contact. Tools you can use to find prospects include Apollo.io, reply.io, zoominfo (expensive af), and Linkedin Sales Navigator. What specific job titles, etc. to target will depend on your niche but for smaller companies this will tend to be the owner. For white collar niches, i.e. law, the professional that will be directly benefiting from the tool (i.e. partners) may be better to contact. And for larger organizations you may want to target business improvement and digital transformation leads/directors- these are the people directly in charge of projects like what you may be proposing. Okay- so you have your message, and your list, and now all it comes down to is getting the good word out. I won't be going into the details of how to send these out, a quick Google search will give you hundreds of resources for cold outreach methods. However, personalization is key and beyond simple dynamic variables you want to make sure you can either personalize your email campaigns directly with AI (SmartWriter.ai is an example of a tool that can do this), or at the very least have the ability to import email messages programmatically. Alternatively, ask ChatGPT to make you a Python Script that can take in a list of emails, scrape info based on their linkedin URL or website, and all pass this onto a GPT prompt that specifies your messaging to generate an email. From there, send away. How tf do I close? Once you've got some prospects booked in on your meetings, you will need to close deals with them to turn them into clients. Call #1: Consultation Tying back to when I mentioned you want to take a consultant-first appraoch, you will want to listen closely to their goals and needs and understand their pain points. This would be the first call, and typically I would provide a high level overview of different solutions we could build to tacke these. It really helps to have a presentation available, so you can graphically demonstrate key points and key technologies. I like to use Plus AI for this, it's basically a Google Slides add-on that can generate slide decks for you. I copy and paste my default company messaging, add some key points for the presentation, and it comes out with pretty decent slides. Call #2: Demo The second call would involve a demo of one of these solutions, and typically I'll quickly prototype it with boilerplate code I already have, otherwise I'll cook something up in a no-code tool. If you have a niche where one type of solution is commonly demanded, it helps to have a general demo set up to be able to handle a larger volume of calls, so you aren't burning yourself out. I'll also elaborate on how the final product would look like in comparison to the demo. Call #3 and Beyond: Once the initial consultation and demo is complete, you will want to alleviate any remaining concerns from your prospects and work with them to reach a final work proposal. It's crucial you lay out exactly what you will be building (in writing) and ensure the prospect understands this. Furthermore, be clear and transparent with timelines and communication methods for the project. In terms of pricing, you want to take this from a value-based approach. The same solution may be worth a lot more to client A than client B. Furthermore, you can create "add-ons" such as monthly maintenance/upgrade packages, training sessions for employeees, and so forth, separate from the initial setup fee you would charge. How you can incorporate AI into marketing your businesses Beyond cold sales, I highly recommend creating a funnel to capture warm leads. For instance, I do this currently with my AI tools directory, which links directly to my AI agency and has consistent branding throughout. Warm leads are much more likely to close (and honestly, much nicer to deal with). However, even without an AI-related website, at the very least you will want to create a presence on social media and the web in general. As with any agency, you will want basic a professional presence. A professional virtual address helps, in addition to a Google Business Profile (GBP) and TrustPilot. a GBP (especially for local SEO) and Trustpilot page also helps improve the looks of your search results immensely. For GBP, I recommend using ProfilePro, which is a chrome extension you can use to automate SEO work for your GBP. Aside from SEO optimzied business descriptions based on your business, it can handle Q/A answers, responses, updates, and service descriptions based on local keywords. Privacy and Legal Concerns of the AAA Model Aside from typical concerns for agencies relating to service contracts, there are a few issues (especially when using no-code tools) that will need to be addressed to run a successful AAA. Most of these surround privacy concerns when working with proprietary data. In your terms with your client, you will want to clearly define hosting providers and any third party tools you will be using to build their solution, and a DPA with these third parties listed as subprocessors if necessary. In addition, you will want to implement best practices like redacting private information from data being used for building solutions. In terms of addressing concerns directly from clients, it helps if you host your solutions on their own servers (not possible with AI tools), and address the fact only ChatGPT queries in the web app, not OpenAI API calls, will be used to train OpenAI's models (as reported by mainstream media). The key here is to be open and transparent with your clients about ALL the tools you are using, where there data will be going, and make sure to get this all in writing. have fun, and keep an open mind Before I finish this post, I just want to reiterate the fact that this is NOT an easy way to make money. Running an AI agency will require hours and hours of dedication and work, and constantly rearranging your schedule to meet prospect and client needs. However, if you are looking for a new business to run, and have a knack for understanding business operations and are genuinely interested in the pracitcal applications of generative AI, then I say go for it. The time is ticking before AAA becomes the new dropshipping or SMMA, and I've a firm believer that those who set foot first and establish themselves in this field will come out top. And remember, while 100 thousand people may read this post, only 2 may actually take initiative and start.

#reddit#automation#agency

reddit

0

0

justherfriend_•This week

AI Implementation

Who could I kindly reach to, to possibly develop an AI product for my company? Are there any freelancers who will do such work?

#reddit#implementation

reddit

0

1

swagamoney•This week

My (23M) first $10k month installing internal GPT-4 for businesses

It all started in this very own subreddit just a month ago. I posted “How I made a secure GPT-4 for my company knowledge base” and left a cheeky Google Form in the comments. The post got 162 upvotes, 67 comments and, most importantly… ~30 form answers 😈 From there I got on 12 calls and even though I initially offered to do it for free… I closed 2 clients for $5k each. Data privacy was my main selling point: 1st company was a manufacturer with private instructions/manuals on how to operate certain systems. I trained GPT on them and let their employees talk with these 100-page PDFs. (When I say “train”, I refer to RAG, not fine-tune) 2nd company had customers sending them photos of sensitive documents for a customs clearing service. They had people manually extracting the info so we automated all of that. How did I ensure data privacy and security? I simply used MS Azure AI. They have all of the same stuff OpenAI has, but offer data privacy guarantees and network isolation. That’s both SOC 2 and GDPR compliant. Companies love it. Now I’m cold emailing my first 2 clients’ competitors for a quick rinse and repeat. P.S. I’m extremely curious of different use cases since I’m looking to niche down, so I’d be happy to talk to businesses with ideas of how to use this. You’d give me a use case idea and I’d give you advice on how to implement it. Edit: I’m getting TONS of DMs so please be comprehensive in your first message!

#reddit#(23m)#first

reddit

0

1

More_Mousse•This week

From research paper to a tech startup - help!

Hi! I'm a CS master student that loves being creative. I’ve always wanted to start a business. I have gotten offers to join other startups when I took my bachelors, but personally I never believed in the startups, so I’ve always ended up politely declining on any startup offers. But my master thesis idea is very intriguing. However, I still feel very lost. I can’t even think of any good company names, or where I would even find enthusiastic co founders.  My master thesis as an AI startup with large potential. As of today, I have not started on the product itself. I will write a paper on the product, and finish the thesis in August 2026. My supervisor suggested that this is a good startup idea, and has a large market potential. I want to try. I’ve written about my goals, milestones, and some questions. Feel free to help me in any way, by answering my questions below. Goal:  Learn about startups and non-technical part of it (business, finance, sales, etc) (I'm clueless here) Build the business part time Try and fail Milestones Complete my paper on the product Create MVP for customers to test Validate idea and check market Find company name, acquire domain and launch SaaS  Get feedback, do networking and improve the product Join a Startup Lab and find Cofounders. The following roles would need to be filled  CEO (Me, Vision and tech expert) COO (Business strategy, operations, and scaling.),  CMO (marketing and sales responsible, working to acquire new business) CPO (Product design, user experience, and frontend development)  Formally create the company, divide shares, hold weekend work meeting, pick company name (again) Goal: create product for an industry (the product can be tailored to different industries) and get the first clients. Work that needs to be done: Tech: Create the product for the industry  COO: pitching competitions, define the sales pitch, and how to price the product CMO: find out how marketing should be done, and what companies to contact for demo CMO: design company logo, design web page for business usage, create front page of the website  Growth + Profits Questions Between now, and until I have the working demo, what should I do with my time? I have courses where I learn technical skills for the company. It does not make sense to create the website for the product, when I don't know how the user would interact with the product.  Should I start the company even before the product is made? (While I'm a student and working on the paper) How can I acquire non-technical skills for running a business? I prefer reading books. How can I learn about software companies (practical skills)? For example: How to lower hosting costs?  How to price a product for customers and a product for business? (Software contracts) How to guarantee  privacy when it comes to business documents?  I’m planning on searching for co-founders, after I have validated the idea myself. Should I instead find co founders before I have even created the product? (with no guarantee that there would even be a product?) Should I try to make the product without co-founders? (This is my first startup, so it might tank within the first few months) Any experience with starting a software business while working full time? Thank you for all the help!

#reddit#research#paper

reddit

0

0.6

madscholar•This week

Where Do I Find Like-Minded, Unorthodox Co-founders? [Tech]

After more than 20 years in the tech industry I'm pretty fed up. I've been at it non-stop, so the burnout was building up for a while. Eventually, it's gotten so bad that it was no longer a question whether I need to take a break; I knew that I had to, for the sake of myself and loved ones. A few months ago I quit my well-paying, mid-level mgmt job to have some much-needed respite. I can't say that I've fully recovered, but I'm doing a bit better, so I'm starting to think about what's next. That said, the thoughts of going back into the rat race fill me with dread and anxiety. I've had an interesting career - I spent most of it in startups doing various roles from an SWE to a VP Eng, including having my own startup adventures for a couple of years. The last 4.5 years of my career have been in one of the fastest growing tech companies - it was a great learning experience, but also incredibly stressful, toxic and demoralizing. It's clear to me that I'm not cut out for the corporate world -- the ethos contradicts with my personality and beliefs -- but it's not just. I've accumulated "emotional scars" from practically every place I worked at and it made me loathe the industry to the degree that if I ever have another startup, it'd have to be by my own -- unorthodox -- ideals, even if it means a premature death due to lack of funding. I was young, stupid and overly confident when I had my first startup. I tried to do it "by the book" and dance to the tune of investors. While my startup failed for other, unrelated reasons, it gave me an opportunity to peak behind the curtain, experience the power dynamics, and get a better understanding to how the game is played - VCs and other person of interest have popularized the misconception that if a company doesn't scale, it would stagnate and eventually regress and die. This is nonsense. This narrative was created because it would make the capitalist pigs obsolete - they need companies to go through the entire alphabet before forcing them to sell or IPO. The sad reality is that the most entrepreneurs still believe in this paradigm and fall into the VC's honeypot traps. It's true that many businesses cannot bootstrap or scale without VC money, but it's equally true that far too many companies pivot/scale prematurely (and enshitify their product in the process) due to external pressures fueled by pure greed. This has a top-bottom effect - enshitification doesn't only effect users, but it also heavily effects the processes and structrures of companies, which can explain why the average tenure in tech is only \~2 years. I think that we live in an age where self-starting startups are more feasible than ever. It's not just the rise of AI and automation, but also the plethora of tools, services, and open-source projects that are available to all for free. On the one hand, this is fantastic, but on the other, the low barrier-to-entry creates oversaturation of companies which makes research & discovery incredibly hard - it is overwhelming to keep up with the pace and distill the signal from the noise, and there's a LOT of noise - there's not enough metaphorical real-estate for the graveyard of startups that will be defunct in the very near future. I'd like to experiment with startups again, but I don't want to navigate through this complex mine field all by myself - I want to find a like-minded co-founder who shares the same ideals as I do. It goes without saying that being on the same page isn't enough - I also want someone who's experienced, intelligent, creative, productive, well-rounded, etc. At the moment, I don't have anyone in my professional network who has/wants what it takes. I can look into startup bootcamps/accelerators like YC et al., and sure enough, I'll find talented individuals, but it'd be a mismatch from the get-go. For shits and giggles, this is (very roughly) how I envision the ideal company: Excellent work life balance: the goal is not to make a quick exit, become filthy rich, and turn into a self-absorbed asshole bragging about how they got so succesful. The goal is to generate a steady revenue stream while not succumbing to social norms that encourage greed. The entire purpose is to reach humble financial indepedence while maintaining a stress-free (as one possibly can) work environment. QOL should always be considered before ARR. Bootstraping: no external money. Not now, not later. No quid pro quo. No shady professionals or advisors. Company makes it or dies trying. Finances: very conservative to begin with - the idea is to play it safe and build a long fucking runaway before hiring. Spend every penny mindfully and frugally. Growth shouldn't be too quick & reckless. The business will be extremely efficient in spending. The only exception to the rule is crucial infrastructure and wages to hire top talent and keep salaries competitive and fair. Hiring: fully remote. Global presence, where applicable. Headcount will be limited to the absolute bare minimum. The goal is to run with a skeleton crew of the best generalists out there - bright, self-sufficient, highly motivated, autodidact, and creative individuals. Hiring the right people is everything and should be the company's top priority. Compensation & Perks: transperent and fair, incentivizing exceptional performance with revenue sharing bonuses. The rest is your typical best-in-class perks: top tier health/dental/vision insurance, generous PTO with mandatory required minimum, parental leave, mental wellness, etc. Process: processes will be extremely efficient, automated to the max, documented, unbloated, and data-driven through and through. Internal knowledge & data metrics will be accessible and transparent to all. Employees get full autonomy of their respective areas and are fully in charge of how they spend their days as long as they have agreed-upon, coherent, measurable metrics of success. Meetings will be reduced to the absolute minimum and would have to be justified and actionable - the ideal is that most communications will be done in written form, while face-to-face will be reserved for presentations/socializing. I like the Kaizen philosophy to continuously improve and optimize processes. Product: As previously stated, "data-driven through and through". Mindful approach to understand cost/benefit. Deliberate and measured atomic improvements to avoid feature creep and slow down the inevitable entropy. Most importantly, client input should be treated with the utmost attention but should never be the main driver for the product roadmap. This is a very controversial take, but sometimes it's better to lose a paying customer than to cave to their distracting/unreasonable/time-consuming demands. People Culture: ironicaly, this would be what most companies claim to have, but for realsies. Collaborative, open, blameless environment. People are treated like actual grown ups with flat structure, full autonomy, and unwavering trust. Socializing and bonding is highly encourged, but never required. Creativity and ingenuity is highly valued - people are encouraged to work on side projects one day of the week. Values: I can write a lot about it, but it really boils down to being kind and humble. We all know what happened with "don't be evil". It's incredibly hard to retain values over time, esp. when there are opposing views within a company. I don't know how to solve it, but I believe that there should be some (tried and true) internal checks & balances from the get go to ensure things are on track. I never mentioned what this hypothetical startup does. Sure, there's another very relevant layer of domain experience fit, but this mindset allows one to be a bit more fluid because the goal is not to disrupt an industry or "make the world a better place"; it's to see work for what it truly is - a mean to an end. It's far more important for me to align with a co-founder on these topics than on an actual idea or technical details. Pivoting and rebranding are so common that many VCs outweigh the make up and chemistry of the founding team (and their ability to execute) over the feasibility of their ideas.  To wrap this long-winded post, I'm not naive or disillusioned - utopias aren't real and profitable companies who operate at a 70-80% rate of what I propose are the real unicorns, but despite them being a tiny minority, I think they are the real forward thinkers of the industry. I might be wrong, but I hope that I'm right and that more and more startups will opt towards long-term sustainability over the promise of short-term gains because the status quo really stinks for most people. What do you folks think? Does anyone relate? Where can I find others like me? P.S I thought about starting a blog writing about these topics in length (everything that is wrong with tech & what can be done to improve it), but I have the Impostor Syndrom and I'm too self-conscious about how I come off. If you somehow enjoyed reading through that and would love to hear more of my thoughts and experiences in greater detail, please let me know. P.P.S If you have a company that is close to what I'm describing and you're hiring, let me know!

#reddit#find#like-minded,

reddit

0

1

BalloonWheelie•This week

Why the value of writing code and other digital services is going to zero

I must preface this with a trigger warning because I make some statements in this post that might be upsetting to some. This post discusses my experience building in the new era of entrepreneurship, which is one where the founder is the center of the universe, and the consultants, overpriced SaaS, and corporate swamp creatures are replaced by single-user custom software, bots, and self-hosted automations. If you work in the legacy economy, I really don't intend to stress you out or say things you are doing are quickly becoming irrelevant, but I must share the reality of how I am operating, because I would like to hear from others who are doing the same, or desire to do the same. I am currently operating with the belief that AI-powered tools are going to make 1-person million dollar businesses much more common. Building anything digital is becoming extremely easy, cheap, and quick to implement. The value of code and digital tools is approaching zero, or at most 5% of what it currently is. Right now, the most powerful AI tools are aimed at developers, so folks who have some technical and business ability basically have nothing holding them back aside from the speed of their brain right now. I happen to be a part of the cohort, and am building like there is no tomorrow, but I don't believe this cohort is actually all that big. The next hurdle to unlock the new era of entrepreneurship is empowering every entrepreneur to build at the same pace that is currently locked behind having technical ability. This cohort is huge (millions, if the number of people in this sub is any indication). This post is aimed at them (you?). If you are part of this cohort, what is holding you back from launching a new product for near-zero cost? What is too complicated, too expensive, too unknown for you to be able to build your new/current business at maximum speed? I look forward to seeing the replies, I hope some insights shared can help the community, and be a catalyst for more tools to enable non-technical founders to launch. I will now share some of how I am testing, launching, and selling as a one-man-show. This will be a little bit technical, but if the output of any layer of my stack is something you want, please comment because maybe someone will build a cheap way of accessing it without needing to manage the code yourself. \#1 BOTS I cannot overstate how much leverage bots have created for me. I run all of my bots locally and interface with with via Telegram. Bots do things like: \- watch social media pages, forums, subreddits, etc related to my customers and notify me of what is going on, and suggest SEO blog posts that could be published to capture traffic related to the topic. with a single message, my bot will generate a blog post, send it to me for review, apply edits i suggest, and then publish it live, all from within telegram \- pay attention to all my key metrics/analytics, and attempt to find insights/corrolations (ex. there is a lot of traffic on this page, blog post, video, etc. here's why, and how we can take advantage of it to drive business goals) \- repurposing content. i have dozens of social media profiles that are 100% run by bots, they are all related to my customer niches and will do things like post news, snippets from my blogs, interact with human creators in the niche, etc. this builds my audience automatically which I can then advertise to/try to convert into paying customers, since they are interested in the things my bot is posting and become followers, it's like automated qualified lead gen 24/7 across every social platform and every niche I care about. you may be thinking by now that this post is made by a bot, but you will have to trust me that this is 100% hand-written by my sleep-deprived brain. let's continue: \#2 replacing every SaaS with a shitty version of it designed for what i need out of it it's absurd that we pay ten's of dollars per seat per month for basic digital functions like chat (slack), CRM (active camppaign, sales force, hubspot, etc), email stuff (mailchip, etc), link sharing (linktree, etc), website builders (wix, squarespace, etc), etc. all of these SaaS tools are overpriced and overbuilt. I believe many of them are going to be caught in the innovators dilemma and will go to 0. I don't use any of these anymore, I build and self-host my own shitty version of each of them that does only what i need out of the tool. for example, my CRM doesn't have a fancy drag and drop email builder and 10000 3rd party plugins, because i dont need any of that shit I just need to segment and communicate with my customers. if i need more features, i can generate them on the fly. \#3 working alone I have worked with cofounders in the past, raised money from investors, hired consultants, burned money and time, suffered sleepless nights from stress caused by other people not delivering, trying to convince others they are wrong, or they are pushing the company off a cliff, waste waste waste. no more of that. In the new age of entrepreneurship, the BUILDER (you and I) are the ones creating the value, and AI empowers us to do it alone. this might seem daunting, but there is no business problem that can't be solved with a detailed discussion sesh with chatgpt, no facts that can't be found with perplexity, and no task that can't be automated with claude. there is no need for anymore swamp creatures. you are the start and the end point, you don't need to rely on anyone else for anything. this may sound ignorant, but this is the conclusion I have come to believe, and it continues to be proven every day my businesses progress with me being the only human involved. This is getting quite long so I'll cut it here. I look forward to hearing about how you are operating in this new era and hopefully getting inspired/learning some new ideas to add to my current stack.

#reddit#value#writing

reddit

0

1

Afraid-Astronomer130•This week

how I built a $6k/mo business with cold email

I scaled my SaaS to a $6k/mo business in under 6 months completely using cold email. However, the biggest takeaway for me is not a business that’s potentially worth 6-figure. It’s having a glance at the power of cold emails in the age of AI. It’s a rapidly evolving yet highly-effective channel, but no one talks about how to do it properly. Below is the what I needed 3 years ago, when I was stuck with 40 free users on my first app. An app I spent 2 years building into the void. Entrepreneurship is lonely. Especially when you are just starting out. Launching a startup feel like shouting into the dark. You pour your heart out. You think you have the next big idea, but no one cares. You write tweets, write blogs, build features, add tests. You talk to some lukewarm leads on Twitter. You do your big launch on Product Hunt. You might even get your first few sales. But after that, crickets... Then, you try every distribution channel out there. SEO Influencers Facebook ads Affiliates Newsletters Social media PPC Tiktok Press releases The reality is, none of them are that effective for early-stage startups. Because, let's face it, when you're just getting started, you have no clue what your customers truly desire. Without understanding their needs, you cannot create a product that resonates with them. It's as simple as that. So what’s the best distribution channel when you are doing a cold start? Cold emails. I know what you're thinking, but give me 10 seconds to change your mind: When I first heard about cold emailing I was like: “Hell no! I’m a developer, ain’t no way I’m talking to strangers.” That all changed on Jan 1st 2024, when I actually started sending cold emails to grow. Over the period of 6 months, I got over 1,700 users to sign up for my SaaS and grew it to a $6k/mo rapidly growing business. All from cold emails. Mastering Cold Emails = Your Superpower I might not recommend cold emails 3 years ago, but in 2024, I'd go all in with it. It used to be an expensive marketing channel bootstrapped startups can’t afford. You need to hire many assistants, build a list, research the leads, find emails, manage the mailboxes, email the leads, reply to emails, do meetings. follow up, get rejected... You had to hire at least 5 people just to get the ball rolling. The problem? Managing people sucks, and it doesn’t scale. That all changed with AI. Today, GPT-4 outperforms most human assistants. You can build an army of intelligent agents to help you complete tasks that’d previously be impossible without human input. Things that’d take a team of 10 assistants a week can now be done in 30 minutes with AI, at far superior quality with less headaches. You can throw 5000 names with website url at this pipeline and you’ll automatically have 5000 personalized emails ready to fire in 30 minutes. How amazing is that? Beyond being extremely accessible to developers who are already proficient in AI, cold email's got 3 superpowers that no other distribution channels can offer. Superpower 1/3 : You start a conversation with every single user. Every. Single. User. Let that sink in. This is incredibly powerful in the early stages, as it helps you establish rapport, bounce ideas off one another, offer 1:1 support, understand their needs, build personal relationships, and ultimately convert users into long-term fans of your product. From talking to 1000 users at the early stage, I had 20 users asking me to get on a call every week. If they are ready to buy, I do a sales call. If they are not sure, I do a user research call. At one point I even had to limit the number of calls I took to avoid burnout. The depth of the understanding of my customers’ needs is unparalleled. Using this insight, I refined the product to precisely cater to their requirements. Superpower 2/3 : You choose exactly who you talk to Unlike other distribution channels where you at best pick what someone's searching for, with cold emails, you have 100% control over who you talk to. Their company Job title Seniority level Number of employees Technology stack Growth rate Funding stage Product offerings Competitive landscape Social activity (Marital status - well, technically you can, but maybe not this one…) You can dial in this targeting to match your ICP exactly. The result is super low CAC and ultra high conversion rate. For example, My competitors are paying $10 per click for the keyword "HARO agency". I pay $0.19 per email sent, and $1.92 per signup At around $500 LTV, you can see how the first means a non-viable business. And the second means a cash-generating engine. Superpower 3/3 : Complete stealth mode Unlike other channels where competitors can easily reverse engineer or even abuse your marketing strategies, cold email operates in complete stealth mode. Every aspect is concealed from end to end: Your target audience Lead generation methods Number of leads targeted Email content Sales funnel This secrecy explains why there isn't much discussion about it online. Everyone is too focused on keeping their strategies close and reaping the rewards. That's precisely why I've chosen to share my insights on leveraging cold email to grow a successful SaaS business. More founders need to harness this channel to its fullest potential. In addition, I've more or less reached every user within my Total Addressable Market (TAM). So, if any competitor is reading this, don't bother trying to replicate it. The majority of potential users for this AI product are already onboard. To recap, the three superpowers of cold emails: You start a conversation with every single user → Accelerate to PMF You choose exactly who you talk to → Super-low CAC Complete stealth mode → Doesn’t attract competition By combining the three superpowers I helped my SaaS reach product-marketing-fit quickly and scale it to $6k per month while staying fully bootstrapped. I don't believe this was a coincidence. It's a replicable strategy for any startup. The blueprint is actually straightforward: Engage with a handful of customers Validate the idea Engage with numerous customers Scale to $5k/mo and beyond More early-stage founders should leverage cold emails for validation, and as their first distribution channel. And what would it do for you? Update: lots of DM asking about more specifics so I wrote about it here. https://coldstartblueprint.com/p/ai-agent-email-list-building

#reddit#built#$6k/mo

reddit

0

0.543

DrJigsaw•This week

101 best SEO tips to help you drive traffic in 2k21

Hey guys! I don't have to tell you how SEO can be good for your business - you can drive leads to your SaaS on autopilot, drive traffic to your store/gym/bar/whatever, etc. The thing with SEO, though, is that most SEO tips on the internet are just not that good. Most of the said tips: Are way too simple & basic (“add meta descriptions to your images”*) Are not impactful. Sure, adding that meta tag to an image is important, but that’s not what’s going to drive traffic to your website Don’t talk much about SEO strategy (which is ultimately the most important thing for SEO). Sure, on-page SEO is great, but you sure as hell won't drive much traffic if you can't hire the right writers to scale your content. And to drive serious SEO traffic, you'll need a LOT more than that. Over the past few years, my and my co-founder have helped grow websites to over 200k+ monthly traffic (check out our older Reddit post if you want to learn more about us, our process, and what we do), and we compiled all our most important SEO tips and tricks, as well as case studies, research, and experiments from the web, into this article. Hope you like it ;) If you think we missed something super important, let us know and we'll add it to the list. And btw, we also published this article on our own blog with images, smart filters, and all that good stuff. If you want to check it out, click here. That said, grab some coffee (or beer) & let's dive in - this is going to be a long one. SEO Strategy Tips Tip #1. A Lot of SEO Tips On The Internet Are NOT Necessarily Factual A lot of the SEO content you’ll read on the internet will be based on personal experiences and hearsay. Unfortunately, Google is a bit vague about SEO advice, so you have to rely more on experiments conducted by SEO pros in the community. So, sometimes, a lot of this information is questionable, wrong, or simply based on inaccurate data.  What we’re getting at here is, whenever you hear some new SEO advice, take it with a grain of salt. Google it to double-check other sources, and really understand what this SEO advice is based on (instead of just taking it at face value). Tip #2. SEO Takes Time - Get Used to It Any way you spin it, SEO takes time.  It can take around 6 months to 2 years (depending on the competition in your niche) before you start seeing some serious results.  So, don’t get disappointed if you don’t see any results within 3 months of publishing content. Tip #3. SEO Isn’t The Best Channel for Everyone That said, if you need results for your business tomorrow, you might want to reconsider SEO altogether.  If you just started your business, for example, and are trying to get to break-even ASAP, SEO is a bad idea - you’ll quit before you even start seeing any results.  If that’s the case, focus on other marketing channels that can have faster results like content marketing, PPC, outreach, etc. Tip #4. Use PPC to Validate Keywords Not sure if SEO is right for your business? Do this: set up Google Search ads for the most high-intent keywords in your niche. See how well the traffic converts and then decide if it’s worthwhile to focus on SEO (and rank on these keywords organically). Tip #5. Use GSC to See If SEO Is Working While it takes a while to see SEO results, it IS possible to see if you’re going in the right direction. On a monthly basis, you can use Search Console to check if your articles are indexed by Google and if their average position is improving over time. Tip #6. Publish a TON of Content The more content you publish on your blog, the better. We recommend a minimum of 10,000 words per month and optimally 20,000 - 30,000 (especially if your website is fresh). If an agency offers you the typical “4 500-word articles per month” deal, stay away. No one’s ever gotten results in SEO with short, once-per-week articles. Tip #7. Upgrade Your Writers Got a writer that’s performing well? Hire them as an editor and get them to oversee content operations / edit other writers’ content. Then, upgrade your best editor to Head of Content and get them to manage the entire editor / writer ops. Tip #8. Use Backlink Data to Prioritize Content When doing keyword research, gather the backlink data of the top 3 ranking articles and add it to your sheet. Then, use this data to help you prioritize which keywords to focus on first. We usually prioritize keywords that have lower competition, high traffic, and a medium to high buyer intent. Tip #9. Conduct In-Depth Keyword Research Make your initial keyword research as comprehensive as possible. This will give you a much more realistic view of your niche and allow you to prioritize content the right way. We usually aim for 100 to 300 keywords (depending on the niche) for the initial keyword research when we start working with a client. Tip #10. Start With Competitive Analysis Start every keyword research with competitive analysis. Extract the keywords your top 3 competitors are ranking on.  Then, use them as inspiration and build upon it. Use tools like UberSuggest to help generate new keyword ideas. Tip #11. Get SEMrush of Ahrefs You NEED SEMrush or Ahrefs, there’s no doubt about it. While they might seem expensive at a glance (99 USD per month billed annually), they’re going to save you a lot of manpower doing menial SEO tasks. Tip #12. Don’t Overdo It With SEO Tools Don’t overdo it with SEO tools. There are hundreds of those out there, and if you’re the type that’s into SaaS, you might be tempted to play around with dozens at a time. And yes, to be fair, most of these tools ARE helpful one way or another. To effectively do organic SEO, though, you don’t really need that many tools. In most cases, you just need the following: SEMrush/Ahrefs Screaming Frog RankMath/Yoast SEO Whichever outreach tool you prefer (our favorite is snov.io). Tip #13. Try Some of the Optional Tools In addition to the tools we mentioned before, you can also try the following 2 which are pretty useful & popular in the SEO community: Surfer SEO - helps with on-page SEO and creating content briefs for writers. ClusterAI - tool that helps simplify keyword research & save time. Tip #14. Constantly Source Writers Want to take your content production to the next level? You’ll need to hire more writers.  There is, however, one thing that makes this really, really difficult: 95 - 99% of writers applying for your gigs won’t be relevant. Up to 80% will be awful at writing, and the remainder just won’t be relevant for your niche. So, in order to scale your writing team, we recommend sourcing constantly, and not just once every few months. Tip #15. Create a Process for Writer Filtering As we just mentioned, when sourcing writers, you’ll be getting a ton of applicants, but most won’t be qualified. Fun fact \- every single time we post a job ad on ProBlogger, we get around 300 - 500 applications (most of which are totally not relevant). Trust us, you don’t want to spend your time going through such a huge list and checking out the writer samples. So, instead, we recommend you do this: Hire a virtual assistant to own the process of evaluating and short-listing writers. Create a process for evaluating writers. We recommend evaluating writers by: Level of English. If their samples aren’t fluent, they’re not relevant. Quality of Samples. Are the samples engaging / long-form content, or are they boring 500-word copy-pastes? Technical Knowledge. Has the writer written about a hard-to-explain topic before? Anyone can write about simple topics like traveling - you want to look for someone who knows how to research a new topic and explain it in a simple and easy to read way. If someone’s written about how to create a perfect cover letter, they can probably write about traveling, but the opposite isn’t true. The VA constantly evaluates new applicants and forwards the relevant ones to the editor. The editor goes through the short-listed writers and gives them trial tasks and hires the ones that perform well. Tip #16. Use The Right Websites to Source Writers “Is UpWork any good?” This question pops up on social media time and time again. If you ask us, no, UpWork is not good at all. Of course, there are qualified writers there (just like anywhere else), but from our experience, those writers are few and far in-between. Instead, here are some of our favorite ways to source writers: Cult of Copy Job Board ProBlogger Headhunting on LinkedIn If you really want to use UpWork, use it for headhunting (instead of posting a job ad) Tip #17. Hire Writers the Right Way If you want to seriously scale your content production, hire your writers full-time. This (especially) makes sense if you’re a content marketing agency that creates a TON of content for clients all the time. If you’re doing SEO just for your own blog, though, it usually makes more sense to use freelancers. Tip #18. Topic Authority Matters Google keeps your website's authoritativeness in mind. Meaning, if you have 100 articles on digital marketing, you’re probably more of an authority on the topic than someone that has just 10. Hence, Google is a lot more likely to reward you with better rankings. This is also partially why content volume really matters: the more frequently you publish content, the sooner Google will view you as an authority. Tip #19. Focus on One Niche at a Time Let’s say your blog covers the following topics: sales, accounting, and business management.  You’re more likely to rank if you have 30 articles on a single topic (e.g. accounting) than if you have 10 articles on each. So, we recommend you double-down on one niche instead of spreading your content team thin with different topics. Tip #20. Don’t Fret on the Details While technical SEO is important, you shouldn’t get too hung up on it.  Sure, there are thousands of technical tips you can find on the internet, and most of them DO matter. The truth, though, is that Google won’t punish you just because your website doesn’t load in 3 milliseconds or there’s a meta description missing on a single page. Especially if you have SEO fundamentals done right: Get your website to run as fast as possible. Create a ton of good SEO content. Get backlinks for your website on a regular basis. You’ll still rank, even if your website isn’t 100% optimized. Tip #21. Do Yourself a Favor and Hire a VA There are a TON of boring SEO tasks that your team should really not be wasting time with. So, hire a full-time VA to help with all that. Some tasks you want to outsource include gathering contacts to reach out to for link-building, uploading articles on WordPress, etc. Tip #22. Google Isn’t Everything While Google IS the dominant search engine in most parts of the world, there ARE countries with other popular search engines.  If you want to improve your SEO in China, for example, you should be more concerned with ranking on Baidu. Targeting Russia? Focus on Yandex. Tip #23. No, Voice Search is Still Not Relevant Voice search is not and will not be relevant (no matter what sensationalist articles might say). It’s just too impractical for most search queries to use voice (as opposed to traditional search). Tip #24. SEO Is Not Dead SEO is not dead and will still be relevant decades down the line. Every year, there’s a sensationalist article talking about this.  Ignore those. Tip #25. Doing Local SEO? Focus on Service Pages If you’re doing local SEO, focus on creating service-based landing pages instead of content.  E.g. if you’re an accounting firm based in Boston, you can make a landing page about /accounting-firm-boston/, /tax-accounting-boston/, /cpa-boston/, and so on. Thing is, you don’t really need to rank on global search terms - you just won’t get leads from there. Even if you ranked on the term “financial accounting,” it wouldn’t really matter for your bottom line that much. Tip #26. Learn More on Local SEO Speaking of local SEO, we definitely don’t do the topic justice in this guide. There’s a lot more you need to know to do local SEO effectively and some of it goes against the general SEO advice we talk about in this article (e.g. you don't necessarily need blog content for local SEO). We're going to publish an article on that soon enough, so if you want to check it out, DM me and I'll hit you up when it's up. Tip #27. Avoid Vanity Metrics Don’t get side-tracked by vanity metrics.  At the end of the day, you should care about how your traffic impacts your bottom line. Fat graphs and lots of traffic are nice and all, but none of it matters if the traffic doesn’t have the right search intent to convert to your product/service. Tip #28. Struggling With SEO? Hire an Expert Failing to make SEO work for your business? When in doubt, hire an organic SEO consultant or an SEO agency.  The #1 benefit of hiring an SEO agency or consultant is that they’ve been there and done that - more than once. They might be able to catch issues an inexperienced SEO can’t. Tip #29. Engage With the Community Need a couple of SEO questions answered?  SEO pros are super helpful & easy to reach! Join these Facebook groups and ask your question - you’ll get about a dozen helpful answers! SEO Signals Lab SEO & Content Marketing The Proper SEO Group. Tip #30. Stay Up to Date With SEO Trends SEO is always changing - Google is constantly pumping out new updates that have a significant impact on how the game is played.  Make sure to stay up to date with the latest SEO trends and Google updates by following the Google Search Central blog. Tip #31. Increase Organic CTR With PPC Want to get the most out of your rankings? Run PPC ads for your best keywords. Googlers who first see your ad are more likely to click your organic listing. Content & On-Page SEO Tips Tip #32. Create 50% Longer Content On average, we recommend you create an article that’s around 50% longer than the best article ranking on the keyword.  One small exception, though, is if you’re in a super competitive niche and all top-ranking articles are already as comprehensive as they can be. For example, in the VPN niche, all articles ranking for the keyword “best VPN” are around 10,000 - 11,000 words long. And that’s the optimal word count - even if you go beyond, you won’t be able to deliver that much value for the reader to make it worth the effort of creating the content. Tip #33. Longer Is Not Always Better Sometimes, a short-form article can get the job done much better.  For example, let’s say you’re targeting the keyword “how to tie a tie.”  The reader expects a short and simple guide, something under 500 words, and not “The Ultimate Guide to Tie Tying for 2021 \[11 Best Tips and Tricks\]” Tip #34. SEO is Not Just About Written Content Written content is not always best. Sometimes, videos can perform significantly better. E.g. If the Googler is looking to learn how to get a deadlift form right, they’re most likely going to be looking for a video. Tip #35. Don’t Forget to Follow Basic Optimization Tips For all your web pages (articles included), follow basic SEO optimization tips. E.g. include the keyword in the URL, use the right headings etc.  Just use RankMath or YoastSEO for this and you’re in the clear! Tip #36. Hire Specialized Writers When hiring content writers, try to look for ones that specialize in creating SEO content.  There are a LOT of writers on the internet, plenty of which are really good.  However, if they haven’t written SEO content before, chances are, they won’t do that good of a job. Tip #37. Use Content Outlines Speaking of writers - when working with writers, create a content outline that summarizes what the article should be about and what kind of topics it needs to cover instead of giving them a keyword and asking them to “knock themselves out.”   This makes it a lot more likely for the writer to create something that ranks. When creating content outlines, we recommend you include the following information: Target keyword Related keywords that should be mentioned in the article Article structure - which headings should the writer use? In what order? Article title Tip #38. Find Writers With Niche Knowledge Try to find a SEO content writer with some experience or past knowledge about your niche. Otherwise, they’re going to take around a month or two to become an expert. Alternatively, if you’re having difficulty finding a writer with niche knowledge, try to find someone with experience in technical or hard to explain topics. Writers who’ve written about cybersecurity in the past, for example, are a lot more likely to successfully cover other complicated topics (as opposed to, for example, a food or travel blogger). Tip #39. Keep Your Audience’s Knowledge in Mind When creating SEO content, always keep your audience’s knowledge in mind. If you’re writing about advanced finance, for example, you don’t need to teach your reader what an income statement is. If you’re writing about income statements, on the other hand, you’d want to start from the very barebone basics. Tip #40. Write for Your Audience If your readers are suit-and-tie lawyers, they’re going to expect professionally written content. 20-something hipsters? You can get away with throwing a Rick and Morty reference here and there. Tip #41. Use Grammarly Trust us, it’ll seriously make your life easier! Keep in mind, though, that the app is not a replacement for a professional editor. Tip #42. Use Hemingway Online content should be very easy to read & follow for everyone, whether they’re a senior profession with a Ph.D. or a college kid looking to learn a new topic. As such, your content should be written in a simple manner - and that’s where Hemingway comes in. It helps you keep your blog content simple. Tip #43. Create Compelling Headlines Want to drive clicks to your articles? You’ll need compelling headlines. Compare the two headlines below; which one would you click? 101 Productivity Tips \[To Get Things Done in 2021\] VS Productivity Tips Guide Exactly! To create clickable headlines, we recommend you include the following elements: Keyword Numbers Results Year (If Relevant) Tip #44. Nail Your Blog Content Formatting Format your blog posts well and avoid overly long walls of text. There’s a reason Backlinko content is so popular - it’s extremely easy to read and follow. Tip #45. Use Relevant Images In Your SEO Content Key here - relevant. Don’t just spray random stock photos of “office people smiling” around your posts; no one likes those.  Instead, add graphs, charts, screenshots, quote blocks, CSS boxes, and other engaging elements. Tip #46. Implement the Skyscraper Technique (The Right Way) Want to implement Backlinko’s skyscraper technique?  Keep this in mind before you do: not all content is meant to be promoted.  Pick a topic that fits the following criteria if you want the internet to care: It’s on an important topic. “Mega-Guide to SaaS Marketing” is good, “top 5 benefits of SaaS marketing” is not. You’re creating something significantly better than the original material. The internet is filled with mediocre content - strive to do better. Tip #47. Get The URL Slug Right for Seasonal Content If you want to rank on a seasonal keyword with one piece of content (e.g. you want to rank on “saas trends 2020, 2021, etc.”), don’t mention the year in the URL slug - keep it /saas-trends/ and just change the headline every year instead.  If you want to rank with separate articles, on the other hand (e.g. you publish a new trends report every year), include the year in the URL. Tip #48. Avoid content cannibalization.  Meaning, don’t write 2+ articles on one topic. This will confuse Google on which article it should rank. Tip #49. Don’t Overdo Outbound Links Don’t include too many outbound links in your content. Yes, including sources is good, but there is such a thing as overdoing it.  If your 1,000 word article has 20 outbound links, Google might consider it as spam (even if all those links are relevant). Tip #50. Consider “People Also Ask” To get the most out of SERP, you want to grab as many spots on the search result as possible, and this includes “people also ask (PAA):” Make a list of the topic’s PAA questions and ensure that your article answers them.  If you can’t fit the questions & answers within the article, though, you can also add an FAQ section at the end where you directly pose these questions and provide the answers. Tip #51. Optimize For Google Snippet Optimize your content for the Google Snippet. Check what’s currently ranking as the snippet. Then, try to do something similar (or even better) in terms of content and formatting. Tip #52. Get Inspired by Viral Content Want to create content that gets insane shares & links?  Reverse-engineer what has worked in the past. Look up content in your niche that went viral on Reddit, Hacker News, Facebook groups, Buzzsumo, etc. and create something similar, but significantly better. Tip #53. Avoid AI Content Tools No, robots can’t write SEO content.  If you’ve seen any of those “AI generated content tools,” you should know to stay away. The only thing those tools are (currently) good for is creating news content. Tip #54. Avoid Bad Content You will never, ever, ever rank with one 500-word article per week.  There are some SEO agencies (even the more reputable ones) that offer this as part of their service. Trust us, this is a waste of time. Tip #55. Update Your Content Regularly Check your top-performing articles annually and see if there’s anything you can do to improve them.  When most companies finally get the #1 ranking for a keyword, they leave the article alone and never touch it again… ...Until they get outranked, of course, by someone who one-upped their original article. Want to prevent this from happening? Analyze your top-performing content once a year and improve it when possible. Tip #56. Experiment With CTR Do your articles have low CTR? Experiment with different headlines and see if you can improve it.  Keep in mind, though, that what a “good CTR” is really depends on the keyword.  In some cases, the first ranking will drive 50% of the traffic. In others, it’s going to be less than 15%. Link-Building Tips Tip #57. Yes, Links Matter. Here’s What You Need to Know “Do I need backlinks to rank?” is probably one of the most common SEO questions.  The answer to the question (alongside all other SEO-related questions) is that it depends on the niche.  If your competitors don’t have a lot of backlinks, chances are, you can rank solely by creating superior content. If you’re in an extremely competitive niche (e.g. VPN, insurance, etc.), though, everyone has amazing, quality content - that’s just the baseline.  What sets top-ranking content apart from the rest is backlinks. Tip #58. Sometimes, You’ll Have to Pay For Links Unfortunately, in some niches, paying for links is unavoidable - e.g. gambling, CBD, and others. In such cases, you either need a hefty link-building budget, or a very creative link-building campaign (create a viral infographic, news-worthy story based on interesting data, etc.). Tip #59. Build Relationships, Not Links The very best link-building is actually relationship building.  Make a list of websites in your niche and build a relationship with them - don’t just spam them with the standard “hey, I have this amazing article, can you link to it?”.  If you spam, you risk ruining your reputation (and this is going to make further outreach much harder). Tip #60. Stick With The Classics At the end of the day, the most effective link-building tactics are the most straightforward ones:  Direct Outreach Broken Link-Building Guest Posting Skyscraper Technique Creating Viral Content Guestposting With Infographics Tip #61. Give, Don’t Just Take! If you’re doing link-building outreach, don’t just ask for links - give something in return.  This will significantly improve the reply rate from your outreach email. If you own a SaaS tool, for example, you can offer the bloggers you’re reaching out to free access to your software. Or, alternatively, if you’re doing a lot of guest posting, you can offer the website owner a link from the guest post in exchange for the link to your website. Tip #62. Avoid Link Resellers That guy DMing you on LinkedIn, trying to sell you links from a Google Sheet?  Don’t fall for it - most of those links are PBNs and are likely to backfire on you. Tip #63. Avoid Fiverr Like The Plague Speaking of spammy links, don’t touch anything that’s sold on Fiverr - pretty much all of the links there are useless. Tip #64. Focus on Quality Links Not all links are created equal. A link is of higher quality if it’s linked from a page that: Is NOT a PBN. Doesn’t have a lot of outbound links. If the page links to 20 other websites, each of them gets less link juice. Has a lot of (quality) backlinks. Is part of a website with a high domain authority. Is about a topic relevant to the page it’s linking to. If your article about pets has a link from an accounting blog, Google will consider it a bit suspicious. Tip #65. Data-Backed Content Just Works Data-backed content can get insane results for link-building.  For example, OKCupid used to publish interesting data & research based on how people interacted with their platform and it never failed to go viral. Each of their reports ended up being covered by dozens of news media (which got them a ton of easy links). Tip #66. Be Creative - SEO Is Marketing, After All Be novel & creative with your link-building initiatives.  Here’s the thing: the very best link-builders are not going to write about the tactics they’re using.  If they did, you’d see half the internet using the exact same tactic as them in less than a week! Which, as you can guess, would make the tactic cliche and significantly less effective. In order to get superior results with your link-building, you’ll need to be creative - think about how you can make your outreach different from what everyone does. Experiment it, measure it, and improve it till it works! Tip #67. Try HARO HARO, or Help a Reporter Out, is a platform that matches journalists with sources. You get an email every day with journalists looking for experts in specific niches, and if you pitch them right, they might feature you in their article or link to your website. Tip #68. No-Follow Links Aren’t That Bad Contrary to what you might’ve heard, no-follow links are not useless. Google uses no-follow as more of a suggestion than anything else.  There have been case studies that prove Google can disregard the no-follow tag and still reward you with increased rankings. Tip #69. Start Fresh With an Expired Domain Starting a new website? It might make sense to buy an expired one with existing backlinks (that’s in a similar niche as yours). The right domain can give you a serious boost to how fast you can rank. Tip #70. Don’t Overspend on Useless Links “Rel=sponsored” links don’t pass pagerank and hence, won’t help increase your website rankings.  So, avoid buying links from media websites like Forbes, Entrepreneur, etc. Tip #71. Promote Your Content Other than link-building, focus on organic content promotion. For example, you can repost your content on Facebook groups, LinkedIn, Reddit, etc. and focus on driving traffic.  This will actually lead to you getting links, too. We got around 95 backlinks to our SEO case study article just because of our successful content promotion. Tons of people saw the article on the net, liked it, and linked to it from their website. Tip #72. Do Expert Roundups Want to build relationships with influencers in your niche, but don’t know where to start?  Create an expert roundup article. If you’re in the sales niche, for example, you can write about Top 21 Sales Influencers in 2021 and reach out to the said influencers letting them know that they got featured. Trust us, they’ll love you for this! Tip #73. .Edu Links are Overhyped .edu links are overrated. According to John Mueller, .edu domains tend to have a ton of outbound links, and as such, Google ignores a big chunk of them. Tip #74. Build Relationships With Your Customers Little-known link-building hack: if you’re a SaaS company doing SEO, you can build relationships with your customers (the ones that are in the same topical niche as you are) and help each other build links! Tip #75. Reciprocal Links Aren’t That Bad Reciprocal links are not nearly as bad as Google makes them out to be. Sure, they can be bad at scale (if trading links is all you’re doing). Exchanging a link or two with another website / blog, though, is completely harmless in 99% of cases. Tip #76. Don’t Overspam Don’t do outreach for every single post you publish - just the big ones.  Most people already don’t care about your outreach email. Chances are, they’re going to care even less if you’re asking them to link to this new amazing article you wrote (which is about the top 5 benefits of adopting a puppy). Technical SEO Tips Tip #77. Use PageSpeed Insights If your website is extremely slow, it’s definitely going to impact your rankings. Use PageSpeed Insights to see how your website is currently performing. Tip #78. Load Speed Matters While load speed doesn’t impact rankings directly, it DOES impact your user experience. Chances are, if your page takes 5 seconds to load, but your competition’s loads instantly, the average Googler will drop off and pick them over you. Tip #79. Stick to a Low Crawl Depth Crawl depth of any page on your website should be lower than 4 (meaning, any given page should be possible to reach in no more than 3 clicks from the homepage).  Tip #80. Use Next-Gen Image Formats Next-gen image formats such as JPEG 2000, JPEG XR, and WebP can be compressed a lot better than PNG or JPG. So, when possible, use next-get formats for images on your website. Tip #81. De-Index Irrelevant Pages Hide the pages you don’t want Google to index (e.g: non-public, or unimportant pages) via your Robots.txt. If you’re a SaaS, for example, this would include most of your in-app pages or your internal knowledge base pages. Tip #82. Make Your Website Mobile-Friendly Make sure that your website is mobile-friendly. Google uses “mobile-first indexing.” Meaning, unless you have a working mobile version of your website, your rankings will seriously suffer. Tip #83. Lazy-Load Images Lazy-load your images. If your pages contain a lot of images, you MUST activate lazy-loading. This allows images that are below the screen, to be loaded only once the visitor scrolls down enough to see the image. Tip #84. Enable Gzip Compression Enable Gzip compression to allow your HTML, CSS and JS files to load faster. Tip #85. Clean Up Your Code If your website loads slowly because you have 100+ external javascript files and stylesheets being requested from the server, you can try minifying, aggregating, and inlining some of those files. Tip 86. Use Rel-Canonical Have duplicate content on your website? Use rel-canonical to show Google which version is the original (and should be prioritized for search results). Tip #87. Install an SSL Certificate Not only does an SSL certificate help keep your website safe, but it’s also a direct ranking factor. Google prioritizes websites that have SSL certificates over the ones that don’t. Tip #88. Use Correct Anchor Texts for Internal Links When linking to an internal page, mention the keyword you’re trying to rank for on that page in the anchor text. This helps Google understand that the page is, indeed, about the keyword you’re associating it with. Tip #89. Use GSC to Make Sure Your Content is Interlinked Internal links can have a serious impact on your rankings. So, make sure that all your blog posts (especially the new ones) are properly linked to/from your past content.  You can check how many links any given page has via Google Search Console. Tip #90. Bounce rate is NOT a Google ranking factor. Meaning, you can still rank high-up even with a high bounce rate. Tip #91. Don’t Fret About a High Bounce Rate Speaking of the bounce rate, you’ll see that some of your web pages have a higher-than-average bounce rate (70%+).  While this can sometimes be a cause for alarm, it’s not necessarily so. Sometimes, the search intent behind a given keyword means that you WILL have a high bounce rate even if your article is the most amazing thing ever.  E.g. if it’s a recipe page, the reader gets the recipe and bounces off (since they don’t need anything else). Tip #92. Google Will Ignore Your Meta Description More often than not, Google won’t use the meta description you provide - that’s normal. It will, instead, automatically pick a part of the text that it thinks is most relevant and use it as a meta description. Despite this, you should always add a meta description to all pages. Tip #93. Disavow Spammy & PBN Links Keep track of your backlinks and disavow anything that’s obviously spammy or PBNy. In most cases, Google will ignore these links anyway. However, you never know when a competitor is deliberately targeting you with too many spammy or PBN links (which might put you at risk for being penalized). Tip #94. Use The Correct Redirect  When permanently migrating your pages, use 301 redirect to pass on the link juice from the old page to the new one. If the redirect is temporary, use a 302 redirect instead. Tip #95. When A/B Testing, Do This A/B testing two pages? Use rel-canonical to show Google which page is the original. Tip #96. Avoid Amp DON’T use Amp.  Unless you’re a media company, Amp will negatively impact your website. Tip #97. Get Your URL Slugs Right Keep your blog URLs short and to-the-point. Good Example: apollodigital.io/blog/seo-case-study Bad Example: apollodigital.io/blog/seo-case-study-2021-0-to-200,000/ Tip #98. Avoid Dates in URLs An outdated date in your URL can hurt your CTR. Readers are more likely to click / read articles published recently than the ones written years back. Tip #99. Social Signals Matter Social signals impact your Google rankings, just not in the way you think. No, your number of shares and likes does NOT impact your ranking at all.  However, if your article goes viral and people use Google to find your article, click it, and read it, then yes, it will impact your rankings.  E.g. you read our SaaS marketing guide on Facebook, then look up “SaaS marketing” on Google, click it, and read it from there. Tip #100. Audit Your Website Frequently Every other month, crawl your website with ScreamingFrog and see if you have any broken links, 404s, etc. Tip #101. Use WordPress Not sure which CMS platform to use?  99% of the time, you’re better off with WordPress.  It has a TON of plugins that will make your life easier.  Want a drag & drop builder? Use Elementor. Wix, SiteGround and similar drag & drops are bad for SEO. Tip #102. Check Rankings the Right Way When checking on how well a post is ranking on Google Search Console, make sure to check Page AND Query to get the accurate number.  If you check just the page, it’s going to give you the average ranking on all keywords the page is ranking for (which is almost always going to be useless data). Conclusion Aaand that's about it - thanks for the read! Now, let's circle back to Tip #1 for a sec. Remember when we said a big chunk of what you read on SEO is based on personal experiences, experiments, and the like? Well, the tips we've mentioned are part of OUR experience. Chances are, you've done something that might be different (or completely goes against) our advice in this article. If that's the case, we'd love it if you let us know down in the comments. If you mention something extra-spicy, we'll even include it in this article.

#reddit#best#tips

reddit

0

0.429

Personal-Expression3•This week

I Watched My Startup Slowly Dying Over Two Years: Mistakes and Lessons Learned

If you are tired of reading successful stories, you may want to listen to my almost failure story. Last year in April, I went full-time on my startup. Nearly two years later, I’ve seen my product gradually dying. I want to share some of the key mistakes I made and the lessons I’ve taken from them so you don't have to go through them. Some mistakes were very obvious in hindsight; others, I’m still not sure if they were mistakes or just bad luck. I’d love to hear your thoughts and advice as well. Background I built an English-learning app, with both web and mobile versions. The idea came from recognizing how expensive it is to hire an English tutor in most countries, especially for practicing speaking skills. With the rise of AI, I saw an opportunity in the education space. My target market was Japan, though I later added support for multiple languages and picked up some users from Indonesia and some Latin American countries too. Most of my users came from influencer marketing on Twitter. The MVP for the web version launched in Japan and got great feedback. People were reposting it on Twitter, and growth was at its peak in the first few weeks. After verifying the requirement with the MVP, I decided to focus on the mobile app to boost user retention, but for various reasons, the mobile version didn’t launch until December 2023— 8 months after the web version. Most of this year has been spent iterating on the mobile app, but it didn’t make much of an impact in the end. Key Events and Lessons Learned Here are some takeaways: Find co-founders as committed as you are I started with two co-founders—both were tech people and working Part-Time. After the web version launched, one dropped out due to family issues. Unfortunately, we didn’t set clear rules for equity allocation, so even after leaving, they still retained part of the equity. The other co-founder also effectively dropped out this year, contributing only minor fixes here and there. So If you’re starting a company with co-founders, make sure they’re as committed as you are. Otherwise, you might be better off going solo. I ended up teaching myself programming with AI tools, starting with Flutter and eventually handling both front-end and back-end work using Windsurf. With dev tools getting more advanced, being a solo developer is becoming a more viable option. Also, have crystal-clear rules for equity—especially around what happens if someone leaves. Outsourcing Pitfalls Outsourcing development was one of my biggest mistakes. I initially hired a former colleague from India to build the app. He dragged the project on for two months with endless excuses, and the final output was unusable. Then I hired a company, but they didn’t have enough skilled Flutter developers. The company’s owner scrambled to find people, which led to rushed work and poor-quality code which took a lot of time revising myself. Outsourcing is a minefield. If you must do it, break the project into small tasks, set clear milestones, and review progress frequently. Catching issues early can save you time and money. Otherwise, you’re often better off learning the tools yourself—modern dev tools are surprisingly beginner-friendly. Trust, but Verify I have a bad habit of trusting people too easily. I don’t like spending time double-checking things, so I tend to assume people will do what they say they’ll do. This mindset is dangerous in a startup. For example, if I had set up milestones and regularly verified the progress of my first outsourced project, I would’ve realized something was wrong within two weeks instead of two months. That would’ve saved me a lot of time and frustration. Like what I mentioned above, set up systems to verify their work—milestones, deliverables, etc.—to minimize risk. Avoid red ocean if you are small My team was tiny (or non-existent, depending on how you see it), with no technical edge. Yet, I chose to enter Japan’s English-learning market, which is incredibly competitive. It’s a red ocean, dominated by big players who’ve been in the game for years. Initially, my product’s AI-powered speaking practice and automatic grammar correction stood out, but within months, competitors rolled out similar features. Looking back, I should’ve gone all-in on marketing during the initial hype and focused on rapidly launching the mobile app. But hindsight is 20/20. 'Understanding your user' helps but what if it's not what you want? I thought I was pretty good at collecting user feedback. I added feedback buttons everywhere in the app and made changes based on what users said. But most of these changes were incremental improvements—not the kind of big updates that spark excitement. Also, my primary users were from Japan and Indonesia, but I’m neither Japanese nor Indonesian. That made it hard to connect with users on social media in an authentic way. And in my opinion, AI translations can only go so far—they lack the human touch and cultural nuance that builds trust. But honestly I'm not sure if the thought is correct to assume that they will not get touched if they recognize you are a foreigner...... Many of my Japanese users were working professionals preparing for the TOEIC exam. I didn’t design any features specifically for that; instead, I aimed to build a general-purpose English-learning tool since I dream to expand it to other markets someday. While there’s nothing wrong with this idealistic approach, it didn’t give users enough reasons to pay for the app. Should You Go Full-Time? From what I read, a lot of successful indie developers started part-time, building traction before quitting their jobs. But for me, I jumped straight into full-time mode, which worked for my lifestyle but might’ve hurt my productivity. I value work-life balance and refused to sacrifice everything for the startup. The reason I chose to leave the corp is I want to escape the 996 toxic working environment in China's internet companies. So even during my most stressful periods, I made time to watch TV with my partner and take weekends off. Anyways, if you’re also building something or thinking about starting a business, I hope my story helps. If I have other thoughts later, I will add them too. Appreciate any advice.

#reddit#watched#startup

reddit

0

1

MatanNahmani•This week

I realized that AI will create equal footing for non-technical / non-coders compared to coders

Hey fellow entrepreneurs, I started my current entrepreneurial journey following the advice to “build something that solves a problem you have.” As a coder, I wanted to code faster/better/stronger/etc. So I tried out dozens of AI coding tools to see the state of the market.  I took the best components I saw and started making my own flavor of tool, but sort of shelved it because as a coder I felt that the results were a bit alien (such as getting the AI to follow my code style, write idiomatic code, or refactor the same way I would.) I concluded that building AI coding tools for coders is tricky because as coders we’re so particular about the specifics of our code. Meanwhile, my absolutely non-technical friend was hitting me up to help him build a website for a new real-estate company that he’s launching, and he wanted my help. I really respect his hustle, but I was swamped trying to figure out my own product/market, so I told him he could use my AI coder and I would try to help out when he got stuck. He didn’t get stuck though, not once, and he launched his site over the weekend. I was truly shocked he did it all on his own, so I asked him to share his logs. It was wild – he managed to code a more or less state of the art website (good design, SEO, well-structured source code, Google Analytics, mailing lists. etc.) with absolutely no help. It cost him less than $100 in AI credits, instead of the price quotes of $20,000 - $50,000 from freelancers and agencies. Now I’m seriously pursuing AI coding tools again, but this time with a new passion: AI for non-coder / non-technical people is a 100x game changer. I think 2025 is going to be the year of the entrepreneur, where there will be a hundred times the businesses started because what held people back before was the lack of a technical co-founder or the cash to compensate engineers. Now it costs next to nothing to get started. I’m curious if anyone else has had a similar realization? Anyway, I’ve put the link below to my GitHub if you want to try it (open source, you pay for AI credits). But the main reason for my post is that I feel like I’m living in this new world of realization that being a human on earth is going to get a LOT more interesting in the coming years. There’s literally no excuse to take a job you hate, and nothing stopping people from launching a business. For anyone interested in checking it out or providing feedback you can search for kodu ai on github or kodu ai on google Best of luck to everyone on your entrepreneurial journey! P.s not sure if this is the right flair

#reddit#realized#will

reddit

0

1

dams96•This week

Made $19.2k this month, and just surpassed $1000 the last 24 hours. What I did and what's next.

It's the first time I hit $1000+ in 24 hours and I had no one to share it with (except you guys). I'm quite proud of my journey, and I would have thought that making $1000 in a day would make me ecstatic, but actually it's not the case. Not sure if it's because my revenue has grown by increment step so I had time to "prepare" myself to achieve this at one point, or just that I'm nowhere near my goal of 100k/month so that I'm not that affected by it. But it's crazy to think that my goal was to make 100$ daily at the end of 2024. So for those who don't know me (I guess most of you), I build mobile apps and ship them as fast as I can. Most of them are in the AI space. I already made a post here on how I become a mobile app developer so you can check it for more details, but essentially here's what I did : Always loved creating my own things and solve problems Built multiple YouTube channels since I was 15 (mobile gaming actually) that all worked great (but it was too niche so not that scalable, didn't like that) Did a few businesses here and there (drop shopping, selling merch to school, etc) Finished my master's degree in engineering about 2 years ago Worked a moment in a famous watch industry company and saw my potential. The combo of health issues, fixed salary (although it was quite a lot), and me wanting to be an entrepreneur made me leave the company. Created a TikTok account in mobile tech (got 10+ million views the 1st 3 days), manage to grow it to 200k subs in about 3 months Got plenty of collabs for promoting mobile apps (between $500 - $2000 for a collab) Said fuck it I should do my own apps and market them on my TikTok instead of doing collabs Me wanting to build my own apps happened around May-June 2023. Started my TikTok in Feb 2023. At this point I had already 150k+ subs on TikTok. You guys need to know that I suck at coding big time. During my studies I tried to limit as much as I could coding because I was a lazy bast*rd, even though I knew it would come to bite me in the ass one day. But an angel appeared to me in broad daylight, that angel was called GPT-4. I subscribed for 20$/month to get access, and instantly I saw the potential of AI and how much it could help me. Last year GPT-4 was ahead of its time and could already code me basic apps. I had already a mac so I just downloaded Xcode and that was it. My 1st app was a wallpaper app, and I kid you not 90% of it was made by AI. Yes sometimes I had to try again and again with different prompts but it was still so much faster compared to if I had to learn coding from scratch and write code with my own hands. The only thing I didn't do was implement the in app purchase, from which I find a guy on Fiverr to do it for me for 50$. After about 2 months of on-off coding, my first app was ready to be launched. So it was launched, had a great successful launch without doing any videos at that point (iOS 17 was released and my app was the first one alongside another one to offer live wallpapers for iOS 17. I knew that there was a huge app potential there when iOS 17 was released in beta as Apple changed their live wallpaper feature). I Then made a video a few weeks after on my mobile tiktok channel, made about 1 million views in 48 hours, brought me around 40k additional users. Was top 1 chart in graphism and design category for a few weeks (in France, as I'm French so my TikTok videos are in French). And was top 100 in that same category in 120+ countries. Made about 500$ ? Okay that was trash, but I had no idea to monetize the app correctly at that point. It was still a huge W to me and proved me that I could successfully launch apps. Then I learned ASO (App Store Optimization) in depth, searched on internet, followed mobile app developers on Twitter, checked YouTube videos, you name it. I was eager to learn more. I needed more. Then I just iterated, build my 2nd app in less than a month, my 3rd in 3 weeks and so on. I just build my 14th app in 3 days and is now in review. Everytime I manage to reuse some of my other app's code in my new one, which is why I can build them so much faster now. I know how to monetize my app better by checking out my competitors. I learn so much by just "spying" other apps. Funnily enough, I only made this one Tiktok video on my main account to promote my app. For all my other apps, I didn't do a single video where I showcase it, the downloads has only been thanks to ASO. I still use AI everyday. I'm still not good at coding (a bit better than when I started). I use AI to create my app icons (midjourney or the new AI model Flux which is great). I use figma + midjourney to create my App Store screenshots (and they actually look quite good). I use GPT-4o and Claude 3.5 Sonnet to code most of my apps features. I use gpt-4o to localize my app (if you want to optimize the number of downloads I strongly suggest localizing your app, it takes me about 10 minutes thanks to AI). Now what are my next goals ? To achieve the 100k/month I need to change my strategy a little. Right now the $20k/month comes from purely organic downloads, I didn't do any paid advertising. It will be hard for me to keep on launching new apps and rely on ASO to reach the 100k mark. The best bet to reach 100k is to collab with content creators and they create a viral video showcasing your app. Depending on the app it's not that easy, luckily some of my apps can be viral so I will need to find the right content creators. Second way is to try tiktok/meta ads, I can check (have checked) all the ads that have been made by my competitors (thank you EU), so what I would do is copy their ad concept and create similar ads than them. Some of them have millions in ad budget so I know they create high converting ads, so you don't need to try to create an ad creative from scratch. My only big fear is to get banned by Apple (for no reason of mine). In just a snap of a finger they can just ban you from the platform, that shit scares me. And you pretty much can't do anything. So that's about it for me. I'm quite proud of myself not going to lie. Have been battling so many health issues these past years where I just stay in bed all day I'm surprised to be able to make it work. Anyways feel free to ask questions. I hope it was interesting for some of you at least. PS: My new app was just approved by app review, let the app gods favor me and bring me many downloads ! Also forgot to talk about a potential $100k+ acquisition of one of my apps, but if that ever happens I'll make a post on it.

#reddit#made#$19.2k

reddit

0

1

AntsyNursery58•This week

AI Will Make You Extremely Rich or Kill Your Business in 2024

Preface: I'm a solo-founder in the AI space and previously worked as an ML scientist; the new advancements in AI that I'm seeing are going to impact everyone here. It doesn't matter if you're just starting out, or a bootstrapped brick and mortar founder, or even a VC backed hard tech founder. Last year was when the seeds were laid, and this is the year we'll see them bloom. There will be an onslaught of advancements that take place that are borderline inconceivable due to the nature of exponential progress. This will change every single vertical. I'm making this post because I think AI execution strategy will make or break businesses. Dramatically. Over $50B was put into AI startups in 2023 alone. This figure excludes the hundreds of billions poured into AI from enterprises. So, let's follow the money: &#x200B; 1) AI enterprise software. There's a lot to unpack here and this is what I’m currently working on. AI enterprise software will encompass everything from hyper personalized email outbound to AI cold calls to AI that A/B tests ads on synthetic data to vertical specific software. The impact of the former is relatively self explanatory, so I'll focus on the latter. To illustrate vertical specific AI software, I'll use a simple example in the legal space. Lawyers typically have to comb through thousands of pages of documents. Now, using an LLM + a VDB, an AI can instantly answer all of those questions while surfacing the source and highlighting the specific answer in the contract/document. There are dozens of AI startups for this use case alone. This saves lawyers an immense amount of time and allows them to move faster. Firms that adopt this have a fundamental advantage over law firms that don't adopt this. This was 2023 technology. I'm seeing vertical AI software getting built by my friends in areas from construction, to real estate, to even niche areas like chimney manufacturing. This will exist everywhere. Now, this can be extrapolated much further to be applicable to systems that can do reports and even browse the Internet. This brings me to my next point. &#x200B; 2) AI information aggregation and spread. My gut tells me that this will have a crescendo moment in the future with hardware advancements (Rabbit, Tab, etc.). You won't have to google things because it will be surfaced to you. It's predictive in nature. The people who can get information the fastest will grow their business the fastest. This part is semi-speculative, but due to the nature of LLMs being so expensive to train, I have a strong feeling that large institutions will have access to the \fastest\ and \best\ models that can do this quicker than you and I can. This is why it's important to stay on top. &#x200B; 3) AI content generation This is relevant to running advertisements and any digital marketing aspect of your business. If you can rapidly make content faster than your competitors to put in social media, you will outpace your competitors rapidly. I think most folks are familiar with MidJourney, Stable diffusion, etc. but don't know how to use it. You can generate consistent models for a clothing brand or generate images of a product that you would normally need to hire a professional photographer to take. There's also elevenlabs which is relatively easy to use and can be used to make an MP3 clip as a narration for an ad; this is something I've already done. I'm also still shocked by how many people are unfamiliar with tools like Pika which can do video generation. You could imagine companies having fleets of digital influencers that they control or conjuring up the perfect ad for a specific demographic using a combination of all of the aforementioned tools. &#x200B; In summary, if you feel like I'm being hyperbolic or propagating science fiction fantasies, you're likely already behind. I truly recommend that everyone stays up to date on these advancements as much as possible. If your competitor comes across an AI tool that can increase their ROAS by 5x they can crush you. If your competitor uses a tool that increases the rate at which they receive and aggregate information by 200% (modest estimate) they will crush you. If your competitors have a tool that can reduce their employee size, then they will use it. They'll fire their employees to cut costs and reinvest the money back into their business. It will compound to the point where you're outpaced, and this isn't a level of innovation we've seen since the birth of the industrial revolution. Your customers can get stolen overnight, or you can steal your competition’s customers overnight. TL;DR: This is an opportunity for entrepreneurs to scale faster than they could have possibly imagined, but this also comes with the potential for your company to be obliterated. We've never seen advancements that can have this drastic of an impact this quickly. Adoption will happen fast, and first movers will have a disproportionate and compounding advantage. Watch guides, meet with startups, follow the news, and get rich.

#reddit#will#make

reddit

0

1

Dionikles•This week

Looking for Input: Help Shape an AI-Powered Mentor for Entrepreneurs 🚀

As a young boy I always had the wish or the want to create something or become a founder of company that shares my values and I can give back to the community. If I would ask my father for some advice he just would give me the oldschool answer of "just go to school and work hard, don't bother yourself with such thing. As much I love my father and I know he meant the best for me when saying that (he is still my rolemodel and i hope i will become like him one day). Therefore I wished i had a real, grounded guidance on my entrepreneurial journey—someone who could offer genuine advice, not just another course making sky-high promises. That’s when I thought of a digital Mentor. It would be a digital mentor and companion, guiding users through entrepreneurship and self-development. It would get to know each user, tailor advice to their personal goals, and offer practical steps for growth. For people like me, this could mean the difference between mere ambition and lasting success. I would love to hear your thoughts about my idea and if you had similar experience along you entrepreneurial journey and what you would have wanted to get as a advice. 😊😊 I would post a form in the comments, if you could fill it out, would help me a lot! thanks ❤️

#reddit#looking#input:

reddit

0

1

tommo278•This week

Detailed Guide - How I've Been Self Employed for 2 Years Selling Posters

Hey everyone, bit of context before you read through this. I have been selling POD posters full time for over 2 years now. My next venture is that I have started my own Print on Demand company for posters, PrintShrimp. As one way of creating customers for our service, we are teaching people for free how to also sell posters. Here is a guide I have written on how to sell posters on Etsy. Feel free to have a read through and then check out PrintShrimp, hopefully can help some of you guys out (and get us some more customers!) All of this is also available in video format on our website too, if you prefer to learn that way. Thanks guys! And as some people asked in other subs, no this isn't written with AI 😅 This took a couple of weeks to put together! Through this guide, we will teach you everything you need to know about starting to sell posters and generate some income. We will also show you why PrintShrimp is the best POD supplier for all of your poster needs. Trust me, you won’t need much convincing.  So, why are posters the best product to sell? Also, just thought I’d quickly answer the question - why posters? If you’ve been researching Print on Demand you’ve probably come across the infinite options of t-shirts, mugs, hats, phone cases, and more. All of these are viable options, however we think posters are the perfect place to start. You can always expand into other areas further down the line! So a brief summary of why posters are the perfect product for Print on Demand: \-They are very easy to design! Posters are a very easy shape to deal with - can’t go wrong with a rectangle. This makes designing products very easy. \-Similarly to this, what you see is what you get with a poster. You can literally see your finished product as you design it in either canva or photoshop. With T-Shirts for example, you have to make your design, and then place it on a t-shirt. Then you have to coordinate with your printers the size you would like the design on the tshirt and many other variables like that. There is no messing about with posters - what you see is what you get. \-The same high quality, everywhere. With other products, if you want to reap the benefits of a printing in various countries, you need to ensure each of your global suppliers stocks the same t-shirts, is able to print in the same way, carries the same sizes etc. Again with posters you avoid all of this hassle- your products will come out the same, no matter which of our global locations are used. \-They have a very favorable profit margin. As you will see later, the cost price of posters is very low. And people are prepared to pay quite a lot for a decent bit of wall art! I have tried out other products, and the profit margin combined with the order quantity of posters makes them my most profitable product, every single time. Using PrintShrimp, you can be sure to enjoy profits of anywhere between £6 - £40 pure profit per sale.  \-They are one of the easiest to print white label. This makes them perfect for Print on Demand. Your posters are simply put in a tube, and off they go. There are no extras you need to faff around with, compared to the extra elements other products come with, such as clothing labels on t-shirts.  Picking your poster niche So, you are ready to start selling posters. Great! Now, the blessing and curse with selling posters is that there are infinite possibilities regarding what you can sell. So, it can easily be quite overwhelming at first.  The first thing I would recommend doing is having a look at what others are selling. Etsy is a wonderful place for this (and will likely be a key part of your poster selling journey). So, log on to Etsy and simply type in ‘poster’ in the search bar. Get ready to write a massive list of the broad categories and type of posters that people are selling.  If you do not have more than 50 categories written down by the end, you are doing something wrong. There are seriously an infinite amount of posters! For example, here are some popular ones to get you started: Star sign posters, Kitchen posters, World map posters, Custom Dog Portrait posters, Music posters, Movie posters, Fine art posters, Skiing posters, Girl Power posters and Football posters.  Now, you have a huge list of potential products to sell. What next? There are a few important things you need to bear in mind when picking your niche: \-Does this interest me?  Don’t make the mistake of going down a niche that didn’t actually interest you just because it would probably be a money maker. Before you know it, what can be a very fun process of making designs can become incredibly \\\monotonous, and feel like a chore\\\. You need to bear in mind that you will be spending a lot of time creating designs - if it is something you are interested in you are much less likely to get burnt out! As well, \\\creativity will flow\\\ far better if it is something you are interested in, which at the end of the day will lead to better designs that are more likely to be purchased by customers.  \-Is this within my design range? Don’t let this put you off too much. We will go through how to get started on design later on in this guide. However, it is important to note that the plain truth of it is that some niches and designs are a hell of a lot more complicated than others. For example, quote posters can essentially be designed by anyone when you learn about how to put nice fonts together in a good color scheme. On the other hand, some posters you see may have been designed with complex illustrations in a program like Illustrator. To start with, it may be better to pick a niche that seems a bit more simple to get into, as you can always expand your range with other stores further down the line. A good way of evaluating the design complexity is by identifying if this poster is \\\a lot of elements put together\\\ or is \\\a lot of elements created by the designer themselves\\\\\.\\ Design can in a lot of cases be like a jigsaw - putting colours, shapes and text together to create an image. This will be a lot easier to start with and can be learnt by anyone, compared to complex drawings and illustrations.  \-Is this niche subject to copyright issues? Time to delve deep into good old copyright. Now, when you go through Etsy, you will without a doubt see hundreds of sellers selling music album posters, car posters, movie posters and more. Obviously, these posters contain the property of musicians, companies and more and are therefore copyrighted. The annoying thing is - these are \\\a complete cash cow.\\\ If you go down the music poster route, I will honestly be surprised if you \\don’t\\ make thousands. However it is only a matter of time before the copyright strikes start rolling in and you eventually get banned from Etsy.  So I would highly recommend \\\not making this mistake\\\. Etsy is an incredible platform for selling posters, and it is a hell of a lot easier to make sales on there compared to advertising your own website. And, you \\\only get one chance on Etsy.\\\ Once you have been banned once, you are not allowed to sign up again (and they do ID checks - so you won’t be able to rejoin again under your own name).  So, don’t be shortsighted when it comes to entering Print on Demand. If you keep your designs legitimate, they will last you a lifetime and you will then later be able to crosspost them to other platforms, again without the worry of ever getting shut down.  So, how do I actually design posters? Now you have an idea of what kind of posters you want to be making, it’s time to get creative and make some designs! Photoshop (and the creative cloud in general) is probably the best for this. However, when starting out it can be a scary investment (it costs about £30 a month unless you can get a student rate!).  So, while Photoshop is preferable in the long term, when starting out you can learn the ropes of design and get going with Canva. This can be great at the start as they have a load of templates that you can use to get used to designing and experimenting (while it might be tempting to slightly modify these and sell them - this will be quite saturated on places like Etsy so we would recommend doing something new).  What size format should I use? The best design format to start with is arguably the A sizes - as all the A sizes (A5, A4, A3, A2, A1, A0) are scalable. This means that you can make all of your designs in one size, for example A3, and these designs will be ready to fit to all other A sizes. For example, if you design an A3 poster and someone orders A1, you can just upload this A3 file to PrintShrimp and it will be ready to print. There is a wide range of other sizes you should consider offering on your shop, especially as these sizes are very popular with the American market. They have a wide range of popular options, which unfortunately aren’t all scalable with each other. This does mean that you will therefore have to make some slight modifications to your design in order to be able to offer them in American sizing, in a few different aspect ratios. What you can do however is design all of your products in UK sizing, and simply redesign to fit American sizing once you have had an order. Essentially: design in UK sizing, but list in both UK and US sizing. Then when you get a non-A size order, you can quickly redesign it on demand. This means that you don’t have to make a few different versions of each poster when first designing, and can simply do a quick redesign for US sizing when you need to. Below is PrintShrimps standard size offering. We can also offer any custom sizing too, so please get in touch if you are looking for anything else. With these sizes, your poster orders will be dispatched domestically in whatever country your customer orders from. Our recommendations for starting design One thing that will not be featured in this guide is a written out explanation or guide on how to design. Honestly, I can’t think of a more boring, or frankly worse, way to learn design. When it comes to getting started, experimenting is your best friend! Just have a play around and see what you can do. It is a really fun thing to get started with, and the satisfaction of when a poster design comes together is like no other. A good way to start is honestly by straight up copying a poster you see for sale online. And we don’t mean copying to sell! But just trying to replicate other designs is a great way to get a feel for it and what you can do. We really think you will be surprised at how easy it is to pull together a lot of designs that at first can appear quite complicated! Your best friend throughout this whole process will be google. At the start you will not really know how to do anything - but learning how to look into things you want to know about design is all part of the process. At first, it can be quite hard to even know how to search for what you are trying to do, but this will come with time (we promise). Learning how to google is a skill that you will learn throughout this process.  Above all, what we think is most important is this golden rule: take inspiration but do not steal. You want to be selling similar products in your niche, but not copies. You need to see what is selling in your niche and get ideas from that, but if you make designs too similar to ones already available, you won’t have much luck. At the end of the day, if two very similar posters are for sale and one shop has 1000 reviews and your newer one has 2, which one is the customer going to buy? You need to make yours offer something different and stand out enough to attract customers. Etsy SEO and maximizing your sales You may have noticed in this guide we have mentioned Etsy quite a few times! That is because we think it is hands down the best place to start selling posters. Why? Etsy is a go to place for many looking to decorate their homes and also to buy gifts. It might be tempting to start selling with your own website straight away, however we recommend Etsy as it brings the customers to you. For example, say you start selling Bathroom Posters. It is going to be a hell of a lot easier to convert sales when you already have customers being shown your page after searching ‘bathroom decor’, compared to advertising your own website. This is especially true as it can be hard to identify your ideal target audience to then advertise to via Meta (Facebook/Instagram) for example. Websites are a great avenue to explore eventually like I now have, but we recommend starting with Etsy and going from there. What costs do I need to be aware of? So, setting up an Etsy sellers account is currently costs £15. The only other upfront cost you will have is the cost of listing a product - this is 20 cents per listing. From then on, every time you make a sale you will be charged a transaction fee of 6.5%, a small payment processing fee, plus another 20 cents for a renewed listing fee. It normally works out to about 10% of each order, a small price to pay for all the benefits Etsy brings. No matter what platform you sell on, you will be faced with some form of transaction fee. Etsy is actually quite reasonable especially as they do not charge you to use their platform on a monthly basis.  What do I need to get selling? Getting your shop looking pretty \-Think of a shop name and design (now you are a professional designer) a logo \-Design a banner for the top of your shop \-Add in some about me info/shop announcement \-I recommend running a sale wherein orders of 3+ items get a 20% of discount. Another big benefit of PrintShrimp is that you receive large discounts when ordering multiple posters. This is great for attracting buyers and larger orders.  Making your products look attractive That is the bulk of the ‘decor’ you will need to do. Next up is placing your posters in mock ups! As you may notice on Etsy, most shops show their posters framed and hanging on walls. These are 99% of the time not real photos, but digital mock ups. This is where Photoshop comes in really handy, as you can automate this process through a plug in called Bulk Mock Up. If you don’t have photoshop, you can do this on Canva, you will just have to do it manually which can be rather time consuming.  Now, where can you get the actual Mock Ups? One platform we highly recommend for design in general is platforms like Envato Elements. These are design marketplaces where you have access to millions of design resources that you are fully licensed to use!  Titles, tags, and descriptions  Now for the slightly more nitty gritty part. You could have the world's most amazing looking poster, however, if you do not get the Etsy SEO right, no one is going to see it! We will take you through creating a new Etsy listing field by field so you can know how to best list your products.  The key to Etsy listing optimisation is to maximise. Literally cram in as many key words as you possibly can! Before you start this process, create a word map of anything you can think of relating to your listing. And come at this from the point of view of, if I was looking for a poster like mine, what would I search? Titles \-Here you are blessed with 140 characters to title your listing. Essentially, start off with a concise way of properly describing your poster. And then afterwards, add in as many key words as you can! Here is an example of the title of a well selling Skiing poster: Les Arcs Skiing Poster, Les Arcs Print, Les Alpes, France Ski Poster, Skiing Poster, Snowboarding Poster, Ski Resort Poster Holiday, French This is 139 characters out of 140 - you should try and maximise this as much as possible! As you can see, this crams in a lot of key words and search terms both related to Skiing as a whole, the poster category, and then the specifics of the poster itself (Les Arcs resort in France). Bear in mind that if you are listing a lot of listings that are of the same theme, you won’t have to spend time creating an entirely new title. For example if your next poster was of a ski resort in Italy, you can copy this one over and just swap out the specifics. For example change “France ski poster” to “Italy ski poster”, change “Les Arcs” to “The Dolomites”, etc.  Description \-Same logic applies for descriptions - try and cram in as many key words as you can! Here is an example for a Formula One poster: George Russell, Mercedes Formula One Poster  - item specific keywords Bright, modern and vibrant poster to liven up your home.  - Describes the style of the poster All posters are printed on high quality, museum grade 200gsm poster paper. Suitable for framing and frames. - Shows the quality of the print. Mentions frames whilst showing it comes unframed Experience the thrill of the racetrack with this stunning Formula One poster. Printed on high-quality paper, this racing car wall art print features a dynamic image of a Formula One car in action, perfect for adding a touch of speed and excitement to any motorsports room or man cave. Whether you're a die-hard fan or simply appreciate the adrenaline of high-speed racing, this poster is sure to impress. Available in a range of sizes, it makes a great addition to your home or office, or as a gift for a fellow Formula One enthusiast. Each poster is carefully packaged to ensure safe delivery, so you can enjoy your new piece of art as soon as possible. - A nice bit of text really highlighting a lot of key words such as gift, motorsports, racetrack etc.  You could go further with this too, by adding in extra things related to the poster such as ‘Perfect gift for a Mercedes F1 fan’ etc.  Tags Now, these are actually probably the most important part of your listing! You get 13 tags (20 character limit for each) and there are essentially search terms that will match your listing with what customers search for when shopping.  You really need to maximize these - whilst Title and Description play a part, these are the main things that will bring buyers to your listing. Once again, it is important to think about what customers are likely to be searching when looking for a poster similar to yours. Life hack alert! You can actually see what tags other sellers are using. All you need to do is go to a listing similar to yours that is selling well, scroll down and you can actually see them listed out at the bottom of the page! Here is an example of what this may look like: So, go through a few listings of competitors and make notes on common denominators that you can integrate into your listing. As you can see here, this seller uses tags such as ‘Birthday Gift’ and ‘Poster Print’. When you first start out, you may be better off swapping these out for more listing specific tags. This seller has been on Etsy for a few years however and has 15,000+ sales, so are more likely to see success from these tags.  If it’s not clear why, think about it this way. If you searched ‘poster print’ on Etsy today, there will be 10s of thousands of results. However, if you searched ‘Russell Mercedes Poster’, you will (as of writing) get 336 results. Etsy is far more likely to push your product to the top of the latter tag, against 300 other listings, rather than the top of ‘Poster Print’ where it is incredibly competitive. It is only when you are a more successful shop pulling in a high quantity of orders that these larger and more generic tags will work for you, as Etsy has more trust in your shop and will be more likely to push you to the front.  SKUs \-One important thing you need to do is add SKUs to all of your products! This is worth doing at the start as it will make your life so much easier when it comes to making sales and using PrintShrimp further down the line. What is an SKU? It is a ‘stock keeping unit’, and is essentially just a product identifier. Your SKUs need to match your file name that you upload to PrintShrimp. For example, if you made a poster about the eiffel tower, you can literally name the SKU eiffel-tower. There is no need to complicate things! As long as your file name (as in the image name of your poster on your computer) matches your SKU, you will be good to go.  \-It may be more beneficial to set up a system with unique identifiers, to make organising your files a lot easier further down the line. Say you get to 1000 posters eventually, you’ll want to be able to quickly search a code, and also ensure every SKU is always unique, so you won’t run into accidentally using the same SKU twice further down the line. For example, you can set it up so at the start of each file name, you have \[unique id\]\[info\], so your files will look like -  A1eiffeltower A2france And further down the line: A99aperolspritz B1potatoart This not only removes the potential issue of duplicating SKUs accidentally (for example if you made a few posters of the same subject), but also keeps your files well organised. If you need to find a file, you can search your files according to the code, so just by searching ‘a1’ for example, rather than having to trawl through a load of different files until you find the correct one. \-If your poster has variations, for example color variations, you can set a different SKU for each variation. Just click the little box when setting up variations that says ‘SKUs vary for each (variation)’. So if you have a poster available either in a white or black background, you can name each file, and therefore each SKU, a1eiffel-tower-black and a1eiffel-tower-white for example. \-The same goes for different sizes. As different American sizes have different aspect ratios, as mentioned above you may have to reformat some posters if you get a sale for one of these sizes. You can then add in the SKU to your listing once you have reformatted your poster. So for example if you sell a 16x20” version of the eiffel tower poster, you can name this file eiffel-tower-white-1620. Whilst this involves a little bit of set up, the time it saves you overall is massive!  Variations and Prices \-So, when selling posters there is a huge variety of sizes that you can offer, as mentioned previously. Non-negotiable is that you should be offering A5-A1. These will likely be your main sellers! Especially in the UK. It is also a good idea to offer inch sizing to appeal to a global audience (as bear in mind with PrintShrimp you will be able to print in multiple countries around the world!).  Below is a recommended pricing structure of what to charge on Etsy. Feel free to mess around with these! You may notice on Etsy that many shops charge a whole lot more for sizes such as A1, 24x36” etc. In my experience I prefer charging a lower rate to attract more sales, but there is validity in going for a lower amount of sales with higher profits. As mentioned above, you can also offer different variations on items - for example different colour schemes on posters. This is always a decent idea (if it suits the design) as it provides the customer with more options, which might help to convert the sale. You can always add this in later however if you want to keep it simple while you start! Setting up shipping profiles Etsy makes it very easy to set up different shipping rates for different countries. However, luckily with PrintShrimp you can offer free shipping to the majority of the major countries that are active on Etsy!  Using PrintShrimp means that your production costs are low enough in each domestic market to justify this. If you look on Etsy you can see there are many shops that post internationally to countries such as the US or Australia. Therefore, they often charge £8-10 in postage, and have a delivery time of 1-2 weeks. This really limits their customer base to their domestic market.  Using PrintShrimp avoids this and means you can offer free shipping (as we absorb the shipping cost in our prices) to the major markets of the UK, Australia, and USA (Europe coming soon!).  We also offer a 1 day processing time, unlike many POD poster suppliers. This means you can set your Etsy processing time to just one day, which combined with our quick shipping, means you will be one of the quickest on Etsy at sending out orders. This is obviously very attractive for customers, who are often very impatient with wanting their orders!  Getting the sales and extra tips \-Don’t list an insane amount of listings when you first get started. Etsy will be like ‘hang on a second’ if a brand new shop suddenly has 200 items in the first week. Warm up your account, and take things slow as you get going. We recommend 5 a day for the first week or so, and then you can start uploading more. You don’t want Etsy to flag your account for suspicious bot-like activity when you first get going.  \-It is very easy to copy listings when creating a new one. Simply select an old listing and press copy, and then you can just change the listing specific details to create a new one, rather than having to start from scratch. It can feel like a bit of a ball-ache setting up your first ever listing, but from then on you can just copy it over and just change the specifics.  \-Try and organize your listings into sections! This really helps the customer journey. Sometimes a customer will click onto your shop after seeing one of your listings, so it really helps if they can easily navigate your shop for what they are looking for. So, you now have a fully fledged Etsy shop. Well done! Time to start making £3,000 a month straight away right? Not quite. Please bear in mind, patience is key when starting out. If you started doing this because you are £10,000 in debt to the Albanian mafia and need to pay it off next week, you have come into this in the wrong frame of mind. If you have however started this to slowly build up a side hustle which hopefully one day become your full time gig, then winner winner chicken dinner.  Starting out on Etsy isn’t always easy. It takes time for your shop to build up trust! As I’ve said before, a buyer is far more likely to purchase from a shop with 1000s of reviews, than a brand new one with 0. But before you know it, you can become one of these shops! One thing you can do at the very start is to encourage your friends and family to buy your posters! This is a slightly naughty way of getting a few sales at the start, of course followed by a few glowing 5\* reviews. It really helps to give your shop this little boost at the start, so if this is something you can do then I recommend it.  Okay, so once you have a fully fledged shop with a decent amount of listings, you might be expecting the sales to start rolling in. And, if you are lucky, they indeed might. However, in my experience, you need to give your listings a little boost. So let us introduce you to: The wonderful world of Etsy ads Ads!! Oh no, that means money!! We imagine some of you more risk averse people are saying to yourself right now. And yes, it indeed does. But more often than not unfortunately you do have to spend money to make money.  Fortunately, in my experience anyway, Etsy ads do tend to work. This does however only apply if your products are actually good however, so if you’re back here after paying for ads for 2 months and are losing money at the same rate as your motivation, maybe go back to the start of this guide and pick another niche.  When you first start out, there are two main strategies.  Number 1: The Safer Option So, with PrintShrimp, you will essentially be making a minimum of £6 profit per order. With this in mind, I normally start a new shop with a safer strategy of advertising my products with a budget of $3-5 dollars a day. This then means that at the start, you only need to make 1 sale to break even, and anything above that is pure profit! This might not seem like the most dazzling proposition right now, but again please bear in mind that growth will be slow at the start. This means that you can gradually grow your shop, and therefore the trust that customers have in your shop, over time with a very small risk of ever actually losing money. Number 2: The Billy Big Balls Option If you were yawning while reading the first option, then this strategy may be for you. This will be better suited to those of you that are a bit more risk prone, and it also helps if you have a bit more cash to invest at the start. Through this strategy, you can essentially pay your way to the top of Etsy's rankings. For this, you’ll probably be looking at spending $20 a day on ads. So, this can really add up quickly and is definitely the riskier option. In my experience, the level of sales with this may not always match up to your spend every day. You may find that some days you rake in about 10 sales, and other days only one. But what this does mean is that as your listings get seen and purchased more, they will begin to rank higher in Etsy’s organic search rankings, at a much quicker rate than option one. This is the beauty of Etsy’s ads. You can pay to boost your products, but then results from this paid promotion feed into the organic ranking of your products. So you may find that you can splash the cash for a while at the start in order to race to the top, and then drop your ad spending later on when your products are already ranking well.  Sending your poster orders So, you’ve now done the hard bit. You have a running Etsy store, and essentially all you need to now on a daily basis is send out your orders and reply to customer messages! This is where it really becomes passive income.  \-Check out the PrintShrimp order portal. Simply sign up, and you can place individual orders through there. \-Bulk upload: We have an option to bulk upload your Esty orders via csv.  Seriously, when you are up and running with your first store, it is really as easy as that.  Once you have your first Etsy store up and running, you can think about expanding. There are many ways to expand your income. You can set up other Etsy stores, as long as the type of posters you are selling varies. You can look into setting up your own Shopify stores, and advertise them through Facebook, Instagram etc. Through this guide, we will teach you everything you need to know about starting to sell posters and generate some income. We will also show you why PrintShrimp is the best POD supplier for all of your poster needs. Trust me, you won’t need much convincing.

#reddit#detailed#guide

reddit

0

0.667

Salad-Bandit•This week

Changing Careers, changing products? Age 38, Direction needed, investment advice too.

Hello, At one point in my life I had a set plan that I had been following in which to design a life that fit my values, but during 2020 the viability was called into question and I have been on bad footing, unable to find stability, since. Though I currently have stable housing without roommate, and enough in savings for a year without any income and three more years in a mutual fund. The question I need help with is about utilizing approximately $40,000 that I would like to invest into a new or existing business venture, or possibly start investing my own hand in selecting stocks. To give context about the parameters of concepts that pertain to me, back in 2005 I graduated highschool and immediately was an entrepreneur, started a sports clothing company, was selling WoW bot accounts, ghillie suits on ebay, and graphic design commissions, and I was proficient in MX Flash. Although the first part of my life plan to start farming three years before 2012 for what I thought would be a peak oil economic collapse, and while watching 2008 unfold, along with my career in MX Flash falling flat, I started farming 2009. From that point I spent a total of 15 years farming, the majority of that was for my own LLC, where I was situated with leases on million dollar properties as Ag tax write off, on an elite island outside a major city, serving local high price wholesale, mainly salad mix and mushrooms, because they are fast turn around. That was truly the best 20s I could have asked for, working mainly for myself, very healthy and was putting away $10-20k in savings/investments per year, plus was earning about $3-5k more per year, while living in a cargo trailer on dirt cheap leases. But it all came to a slow end starting in 2020 when I lost all of my wholesale overnight, and my retail exploded, which burnt me out to the point I couldnt walk, as the sole worker in my LLC. So I do not fully trust the volatility of the wholesale food industry, from a small grower’s perspective, since i don't own land. SO now I am trying to figure out a way forward, because I can always farm in the future, and have taught myself hydroponics, and flat packed farm equipment, so my business is very agile and now I can grow in parking lots closer to the city for more sales opportunities, but I am not sure that is what I want to do in this current moment, because tech is exploding, and we have never had so much information available to us, it's a shame not to spend a moment in life to discover what new opportunities might be out there. I was laid off twice last year, so I've been out of work the past four months, doing thriftstore routes twice a week while making about $500+/wk, really just trying to understand what people still buy and break even, while I continue to study 3d design blender, as well as 2d digital art in the hopes that I can reconnect with my tech art past, because that is what I told myself when I was 18, that I would put off art and computers until I was past 30 and needed to do less with my body. But over the past three years, the better I get at digital art, the better Ai has been getting too. I have some mentors who might give me work and a foot in the door, but most of them are laid off, and scrounging for work if they are not on their own funded indie project. I've thought about continuing to learn 3d modeling despite Ai, and despite seeing Flash, computer program I was proficient in get removed from existence before I could really earn my money back. I assume there will always be a need for Ai models to get cleaned up, mapped and rigged, especially with AR technology coming to consumers soon, but more over it would help if I decided to go to a community college to do CNC certificates, so I can have that as a backup job on CAD at a machining warehouse and do my farm and digital art on the side, but CNC mechanics don't make a crazy amount of money and have a boss. BUT I am an inventor, and have two inventions so far, plus my ultimate goal is to one day have automated hydroponic greenhouses, using all CNC+3d printed parts to create a low time investment agriculture income, with Ai monitored greenhouse, seed to salad product that i can sell to other people, which would tie into my desire to teach people about farming too, as well as do something I enjoy, but it is not a proven concept yet. Anyways if you've read this far I appreciate it, I ultimately would like 3rd party feedback about how I should spend my $40k surplus cash. I originally had it saved and accessible in case I was going to lease land and start my full farm business again from scratch, but I think using the equipment and space I have, and exploring non-perishable products is a smart move for me right now. Should I invest in inventory of products to arbitrage online? Should I invest in the top index funds? Should I buy Silver? Should I invest in inventory of a new product line? Should I spend some money insuring and equipment for a landscaping company? I want to future proof myself the best I can as Ai unfolds, I am pretty set with an income for the rest of my life as long as I can grow food and sell it, but there are currently so many changing opportunities, I want to cast out my net and see what works with my temperment. I’ve thought about getting into cyber security, or maybe be an electrician, or less staple jobs like Landscape Architech (can use art/modeling) and CNC engineer/modeler, but honestly I prefer to make a product and sell it without client service related interaction, and particularly no boss. Thank you for reading

#reddit#changing#careers,

reddit

0

1

frankiemuiruri•This week

Why Ignoring AI Agents in 2025 Will Kill Your Marketing Strategy

If you're still focusing solely on grabbing the attention of human beings with your marketing efforts, you're already behind. In 2025, the game will change. Good marketing will demand an in-depth understanding of the AI space, especially the AI Agent space. Why? Your ads and content won’t just be seen by humans anymore. They’ll be analyzed, indexed, and often acted upon by AI agents—automated systems that will be working on behalf of companies and consumers alike. Your New Audience: Humans + AI Agents It’s not just about appealing to people. Companies are employing AI robots to research, negotiate, and make purchasing decisions. These AI agents are fast, thorough, and unrelenting. Unlike humans, they can analyze millions of options in seconds. And if your marketing isn’t optimized for them, you’ll get filtered out before you even reach the human decision-maker. How to Prepare Your Marketing for AI Agents The companies that dominate marketing in 2025 will be the ones that master the art of capturing AI attention. To do this, marketers will need to: Understand the AI agents shaping their industry. Research how AI agents function in your niche. What are they prioritizing? How do they rank options? Create AI-friendly content. Design ads and messaging that are easily understandable and accessible to AI agents. This means clear metadata, structured data, and AI-readable formats. Invest in AI analytics. AI agents leave behind footprints. Tracking and analyzing their behavior is critical. Stay ahead of AI trends. The AI agent space is evolving rapidly. What works today might be obsolete tomorrow. How My Agency Adapted and Thrived in the AI Space At my digital agency, we saw this shift coming and decided to act early. In 2023, we started integrating AI optimization into our marketing strategies. One of our clients—a B2B SaaS company—struggled to get traction because their competitors were drowning them out in Google search rankings and ad platforms. By analyzing the algorithms and behaviors of AI agents in their space, we: Rewrote their website copy with structured data and optimized metadata that was more AI-agent friendly. Created ad campaigns with clear, concise messaging and technical attributes that AI agents could quickly process and index. Implemented predictive analytics to understand what AI agents would prioritize based on past behaviors. The results? Their website traffic doubled in three months, and their lead conversion rate skyrocketed by 40%. Over half of the traffic increase was traced back to AI agents recommending their platform to human users. The Takeaway In 2025, marketing won’t just be about human attention. It’ll be about AI attention—and that requires a completely different mindset. AI agents are not your enemy; they’re your new gatekeepers. Learn to speak their language, and you’ll dominate the marketing game.

#reddit#ignoring#agents

reddit

0

1

thestoicdesigner•This week

Ai C-Level team

I've been exploring ways to run a company where I'm essentially the only internal team member, relying entirely on a suite of specialized AIs for executive roles, supported occasionally by external consultants for niche expertise. My goal is to stay lean, agile, and highly creative, especially in a fashion / tech brand context. Essentially, I'm building an AI-driven C-Level team, or what I like to call a "C-Level AI Wallet." Here's what I'm thinking for the key executive roles I'd need to cover with AI: CEO AI – Responsible for overall strategy, decision-making, trend analysis, and guiding the company's vision. I'd probably lean on something advanced like Gemini, GPT-4, or similar models, fine-tuned with market-specific data. COO AI (Operations): I'd need tools that streamline and automate logistics, supply chain management, and day-to-day operations (think something along the lines of Zapier AI integrations or Make). CMO AI (Marketing & Content): For branding, content creation, digital marketing, and consumer insights, I'd use Jasper or Copy . ai, combined with predictive analytics tools like Google Vertex AI to understand trends better. Additionally, for generating engaging visual and multimedia content, tools like Midjourney, DALL·E, Adobe Firefly, and Runway ML would be perfect. CFO AI (Financial Management): For financial management, cash flow control, and investment decisions, I'd probably leverage AI tools like Bloomberg GPT, combined with AI-powered forecasting platforms. CHRO AI (Human Resources & Culture): Although the internal team is minimal (just myself!), I'd still rely on AI for tasks like project management, freelancer hiring, and performance tracking—tools like HireVue AI, Motion, or even Notion's AI could be beneficial here. CSO AI (Sustainability & Compliance): Since sustainability and ethical sourcing are critical, I'd integrate ESG-focused AI tools to ensure transparency and responsible sourcing. My idea is that, with the right AI tools seamlessly integrated, I can manage the strategic vision and creative direction personally, leveraging external consultants only when necessary. This setup would ideally allow me to operate as a one-person internal team supported by a robust "wallet" of AI executives. Has anyone tried a similar approach? What AI tools would you recommend for a truly lean, innovative brand structure? I'm very curious about your experiences or suggestions—let me know your thoughts!

#reddit#c-level#team

reddit

0

1

BalloonWheelie•This week

Why the value of writing code and other digital services is going to zero

I must preface this with a trigger warning because I make some statements in this post that might be upsetting to some. This post discusses my experience building in the new era of entrepreneurship, which is one where the founder is the center of the universe, and the consultants, overpriced SaaS, and corporate swamp creatures are replaced by single-user custom software, bots, and self-hosted automations. If you work in the legacy economy, I really don't intend to stress you out or say things you are doing are quickly becoming irrelevant, but I must share the reality of how I am operating, because I would like to hear from others who are doing the same, or desire to do the same. I am currently operating with the belief that AI-powered tools are going to make 1-person million dollar businesses much more common. Building anything digital is becoming extremely easy, cheap, and quick to implement. The value of code and digital tools is approaching zero, or at most 5% of what it currently is. Right now, the most powerful AI tools are aimed at developers, so folks who have some technical and business ability basically have nothing holding them back aside from the speed of their brain right now. I happen to be a part of the cohort, and am building like there is no tomorrow, but I don't believe this cohort is actually all that big. The next hurdle to unlock the new era of entrepreneurship is empowering every entrepreneur to build at the same pace that is currently locked behind having technical ability. This cohort is huge (millions, if the number of people in this sub is any indication). This post is aimed at them (you?). If you are part of this cohort, what is holding you back from launching a new product for near-zero cost? What is too complicated, too expensive, too unknown for you to be able to build your new/current business at maximum speed? I look forward to seeing the replies, I hope some insights shared can help the community, and be a catalyst for more tools to enable non-technical founders to launch. I will now share some of how I am testing, launching, and selling as a one-man-show. This will be a little bit technical, but if the output of any layer of my stack is something you want, please comment because maybe someone will build a cheap way of accessing it without needing to manage the code yourself. \#1 BOTS I cannot overstate how much leverage bots have created for me. I run all of my bots locally and interface with with via Telegram. Bots do things like: \- watch social media pages, forums, subreddits, etc related to my customers and notify me of what is going on, and suggest SEO blog posts that could be published to capture traffic related to the topic. with a single message, my bot will generate a blog post, send it to me for review, apply edits i suggest, and then publish it live, all from within telegram \- pay attention to all my key metrics/analytics, and attempt to find insights/corrolations (ex. there is a lot of traffic on this page, blog post, video, etc. here's why, and how we can take advantage of it to drive business goals) \- repurposing content. i have dozens of social media profiles that are 100% run by bots, they are all related to my customer niches and will do things like post news, snippets from my blogs, interact with human creators in the niche, etc. this builds my audience automatically which I can then advertise to/try to convert into paying customers, since they are interested in the things my bot is posting and become followers, it's like automated qualified lead gen 24/7 across every social platform and every niche I care about. you may be thinking by now that this post is made by a bot, but you will have to trust me that this is 100% hand-written by my sleep-deprived brain. let's continue: \#2 replacing every SaaS with a shitty version of it designed for what i need out of it it's absurd that we pay ten's of dollars per seat per month for basic digital functions like chat (slack), CRM (active camppaign, sales force, hubspot, etc), email stuff (mailchip, etc), link sharing (linktree, etc), website builders (wix, squarespace, etc), etc. all of these SaaS tools are overpriced and overbuilt. I believe many of them are going to be caught in the innovators dilemma and will go to 0. I don't use any of these anymore, I build and self-host my own shitty version of each of them that does only what i need out of the tool. for example, my CRM doesn't have a fancy drag and drop email builder and 10000 3rd party plugins, because i dont need any of that shit I just need to segment and communicate with my customers. if i need more features, i can generate them on the fly. \#3 working alone I have worked with cofounders in the past, raised money from investors, hired consultants, burned money and time, suffered sleepless nights from stress caused by other people not delivering, trying to convince others they are wrong, or they are pushing the company off a cliff, waste waste waste. no more of that. In the new age of entrepreneurship, the BUILDER (you and I) are the ones creating the value, and AI empowers us to do it alone. this might seem daunting, but there is no business problem that can't be solved with a detailed discussion sesh with chatgpt, no facts that can't be found with perplexity, and no task that can't be automated with claude. there is no need for anymore swamp creatures. you are the start and the end point, you don't need to rely on anyone else for anything. this may sound ignorant, but this is the conclusion I have come to believe, and it continues to be proven every day my businesses progress with me being the only human involved. This is getting quite long so I'll cut it here. I look forward to hearing about how you are operating in this new era and hopefully getting inspired/learning some new ideas to add to my current stack.

#reddit#value#writing

reddit

0

0.857

adamkstinson•This week

AI Content Campaign Got 4M impressions, Thousands of Website Views, Hundreds of Customers for About $100 — This is the future of marketing

Alright. So, a few months ago I tested a marketing strategy for a client that I’ve sense dedicated my life to developing on. The Idea was to take the clients Pillar content (their YouTube videos) and use AI to rewrite the content for all the viable earned media channels (mainly Reddit). The campaign itself was moderately successful. To be specific, after one month it became their 2nd cheapest customer acquisition cost (behind their organic YouTube content). But there is a lot to be done to improve the concept. I will say, having been in growth marketing for a decade, I felt like I had hit something big with the concept. I’m going to detail how I built that AI system, and what worked well and what didn’t here. Hopefully you guys will let me know what you think and whether or not there is something here to keep working on. DEFINING THE GOAL Like any good startup, their marketing budget was minimal. They wanted to see results, fast and cheap. Usually, marketers like me hate to be in this situation because getting results usually either takes time or it takes money. But you can get results fast and cheap if you focus on an earned media strategy - basically getting featured in other people’s publication. The thing is these strategies are pretty hard to scale or grow over time. That was a problem for future me though. I looked through their analytics and saw they were getting referral traffic from Reddit - it was their 5th or 6th largest source of traffic - and they weren’t doing any marketing on the platform. It was all digital word of mouth there. It kind of clicked for me there, that Reddit might be the place to start laying the ground work. So with these considerations in mind the goal became pretty clear: Create content for relevant niche communities on Reddit with the intent of essentially increasing brand awareness. Use an AI system to repurpose their YouTube videos to keep the cost of producing unique content for each subreddit really low. THE HIGH-LEVEL STRATEGY I knew that there are huge amounts of potential customers on Reddit (About 12M people in all the relevant communities combined) AND that most marketers have a really tough time with the platform. I also knew that any earned media strategy, Reddit or not, means Click Through Rates on our content would be extremely low. A lot of people see this as a Reddit specific problem because you can’t self-promote on the platform, but really you have to keep self-promotion to a minimum with any and all earned media. This basically meant we had to get a lot of impressions to make up for it. The thing about Reddit is if your post absolutely crushes it, it can get millions of views. But crushing it is very specific to what the expectations are of that particular subreddit. So we needed to make content that was specifically written for that Subreddit. With that I was able to essentially design how this campaign would work: We would put together a list of channels (specifically subreddits to start) that we wanted to create content for. For each channel, we would write a content guideline that details out how to write great content for this subreddit. These assets would be stored in an AirTable base, along with the transcripts of the YouTube videos that were the base of our content. We would write and optimize different AI Prompts that generated different kinds of posts (discussion starters about a stock, 4-5 paragraph stock analysis, Stock update and what it means, etc…) We would build an automation that took the YouTube transcripts, ran each prompt on it, and then edited each result to match the channel writing guidelines. And then we would find a very contextual way to leave a breadcrumb back to the client. Always as part of the story of the content. At least, this is how I originally thought things would go. CHOOSING THE RIGHT SUBREDDITS Picking the right communities was vital. Here’s the basic rubric we used to pick and prioritize them: • Relevance: We needed communities interested in stock analysis, personal finance, or investing. • Subreddit Size vs. Engagement: Large subreddits offer more potential impressions but can be less focused. Smaller subreddits often have higher engagement rates. • Content Feasibility: We had to ensure we could consistently create high-value posts for each chosen subreddit. We started with about 40 possibilities, then narrowed it down to four or five that consistently delivered upvotes and user signups. CREATING CHANNEL-SPECIFIC GUIDES By the end, creating channel specific writing guidelines looked like a genius decision. Here’s how we approached it and used AI to get it done quickly: Grabbed Top Posts: We filtered the subreddit’s top posts (change filter to “Top” and then “All Time”) of all time to see the kinds of content that performed best Compiled The Relevant Posts: We took the most relevant posts to what we were trying to do and put them all on one document (basically created one document per subreddit that just had the top 10 posts in that subreddit). Had AI Create Writing Guideline Based On Posts: For each channel, we fed the document with the 10 posts with the instructions “Create a writing guideline for this subreddit based on these high performing posts. I had to do some editing on each guideline but this worked pretty well and saved a lot of time. Each subreddit got a custom guideline, and we put these inside the “Channels” table of the AirTable base we were developing with these assets. BUILDING THE AI PROMPTS THAT GENERATED CONTENT Alright this is probably the most important section so I’ll be detailed. Essentially, we took all the assets we developed up until this point, and used them to create unique posts for each channel. This mean each AI prompt was about 2,000 words of context and produced about a 500-word draft. There was a table in our AirTable where we stored the prompts, as I alluded to earlier. And these were basically the instructions for each prompt. More specifically, they detailed out our expectations for the post. In other words, there were different kinds of posts that performed well on each channel. For example, you can write a post that’s a list of resources (5 tools we used to…), or a how to guide (How we built…), etc.. Those weren’t the specific ones we used, but just wanted to really explain what I meant there. That actual automation that generated the content worked as follows: New source content (YouTube video transcript) was added to the Source Content table. This triggered the Automation. The automation grabbed all the prompts in the prompt table. For each prompt in the prompt table, we sent a prompt to OpenAI (gpt-4o) that contained first the prompt and also the source content. Then, for each channel that content prompt could be used on, we sent another prompt to OpenAI that revised the result of the first prompt based on the specific channel guidelines. The output of that prompt was added to the Content table in AirTable. To be clear, our AirTable had 4 tables: Content Channels Prompts Source Content The Source Content, Prompts, and Channel Guidelines were all used in the prompt that generated content. And the output was put in the Content table. Each time the automation ran, the Source Content was turned into about 20 unique posts, each one a specific post type generated for a specific channel. In other words, we were create a ton of content. EDITING & REFINING CONTENT The AI drafts were never perfect. Getting them Reddit-ready took editing and revising The main things I had to go in and edit for were: • Tone Adjustments: We removed excessively cliche language. The AI would say silly things like “Hello fellow redditors!” which sound stupid. • Fact-Checking: Financial data can be tricky. We discovered AI often confused figures, so we fact check all stock related metrics. Probably something like 30-40% error rate here. Because the draft generation was automated, that made the editing and getting publish ready the human bottleneck. In other words, after creating the system I spent basically all my time reviewing the content. There were small things I could do to make this more efficient, but not too much. The bigger the model we used, the less editing the content needed. THE “BREADCRUMB” PROMOTION STRATEGY No where in my prompt to the AI did I mention that we were doing any marketing. I just wanted the AI to focus on creating content that would do well on the channel. So in the editing process I had to find a way to promote the client. I called it a breadcrumb strategy once and that stuck. Basically, the idea was to never overtly promote anything. Instead find a way to leave a breadcrumb that leads back to the client, and let the really interested people follow the trail. Note: this is supposed to be how we do all content marketing. Some examples of how we did this were: Shared Visuals with a Subtle Watermark: Because our client’s product offered stock data, we’d often include a chart or graph showing a company’s financial metric with the client’s branding in the corner. Added Supporting Data from Client’s Website: If we mentioned something like a company’s cash flow statement, we could link to that company’s cash flow statement on the client’s website. It worked only because there was a lot of data on the client’s website that wasn’t gated. These tactics were really specific to the client. Which is should be. For other companies I would rethink what tactics I use here. THE RESULTS I’m pretty happy with the results • Impressions: – Early on posts averaged \~30,000 apiece, but after about a month of optimization, we hit \~70,000 impressions average. Over about two months, we reached 4 million total impressions. • Signups: – In their signups process there was one of those “Where did you find us?” questions and the amount of people who put Reddit jumped into the few hundred a month. Precise tracking of this is impossible. • Cost Efficiency (This is based on what I charged, and not the actual cost of running the campaign which is about $100/mo): – CPM (cost per thousand impressions) was about $0.08, which is far better than most paid channels. – Cost per free user: \~$8-10. After about a 10% conversion rate to a paid plan, our cost per paying user was $80–$100—well below the client’s previous $300–$400. HIGHLIGHTS: WHAT WORKED Subreddit-Specific Content: – Tailoring each post’s format and length to the audience norms boosted engagement. Worked out really well. 1 post got over 1M views alone. We regularly had posts that had hundreds of thousands. Breadcrumbs: – We never had anyone call us out for promoting. And really we weren’t. Our first priority was writing content that would crush on that subreddit. Using the Founder’s Existing Material: – The YouTube transcripts grounded the AI’s content in content we already made. This was really why we were able to produce so much content. CHALLENGES: WHAT DIDN’T WORK AI is still off: – Maybe it’s expecting too much, but still I wish the AI had done a better job. I editing a lot of content. Human oversight was critical. Scheduling all the content was a pain: – Recently I automated this pretty well. But at first I was scheduling everything manually and scheduling a hundred or so posts was a hassle. Getting Data and Analytics: – Not only did we have not very good traffic data, but the data from reddit had to be collected manually. Will probably automate this in the future. COST & TIME INVESTMENT Setup: The setup originally took me a couple weeks. I’ve since figured out how to do much faster (about 1 week). AirTable Setup here was easy and the tools costs $24/mo so not bad. ChatGPT costs were pretty cheap. Less than $75 per month. I’ve sense switched to using o1 which is much more expensive but saves me a lot of editing time Human Editing: Because this is the human part of the process and everything else was automated it mean by default all my time was spent editing content. Still this was a lot better than creating content from scratch probably by a factor of 5 or 10. The main expense was paying an editor (or using your own time) to refine posts. Worth it? Yes even with the editing time I was able to generate way more content that I would have otherwise. LESSONS & ACTIONABLE TAKEAWAYS Reddit as a Growth Channel: – If you genuinely respect each subreddit’s culture, you can achieve massive reach on a tight budget. AI + Human Collaboration: – AI excels at first drafts, but human expertise is non-negotiable for polishing and ensuring factual integrity. Soft Promotion Wins: – The “breadcrumb” approach paid off. It might feel like too light a touch, but is crucial for Reddit communities. Create once, repurpose as many times as possible: – If you have blog posts, videos, podcasts, or transcripts, feed them into AI to keep your message accurate and brand-consistent. CONCLUSION & NEXT STEPS If you try a similar approach: • Begin with smaller tests in a few niches to learn what resonates. • Create a clear “channel guide” for each community. • Carefully fact-check AI-generated posts. • Keep brand mentions low-key until you’ve established credibility.

#reddit#content#campaign

reddit

0

1

2Lobsters•This week

I’ve professionalized the family business. Now I feel stuck

I wrote the post below in my own words and then sent to ChatGPT for refinement/clarity. So if it reads like AI, it's because it is, but it's conveying the message from my own words a bit better than my original with a few of my own lines written back in. Hope that's not an issue here. I’m 33, married with two young kids. I have a bachelor’s from a well-regarded public university (though in an underwhelming field—economics adjacent). I used that degree to land a job at a mid-sized distribution company (\~$1B annual revenue), where I rose quickly to a project management role and performed well. In 2018, after four years there, I returned to my family's $3M/yr residential service and repair plumbing business. I saw my father withdrawing from leadership, responsibilities being handed to underqualified middle managers, and overall employee morale declining. I’d worked in the business from a young age, had all the necessary licenses, and earned a degree of respect from the team—not just as “the boss’s kid,” but as someone who had done the work. I spent my first year back in the field, knocking off the rust. From there, I started chipping away at process issues and inefficiencies, without any formal title. In 2020, I became General Manager. Since then, we’ve grown to over $5M in revenue, improved profitability, and automated many of the old pain points. The business runs much smoother and requires less day-to-day oversight from me. That said—I’m running out of motivation. I have no equity in the business. And realistically, I won’t for a long time. The family dynamic is... complicated. There are relatives collecting large salaries despite zero involvement in the business. Profits that should fuel growth get drained, and we can’t make real accountability stick because we rely too heavily on high-producing employees—even when they underperform in every other respect. I want to be clear—this isn’t a sob story. I know how lucky I am. The business supports my family, and for that I’m grateful. But I’ve gone from showing up every day with fresh ideas and energy to slowly becoming the guy who upholds the status quo. I’ve hit most of the goals I set for myself, but I’m stagnating—and that scares me. The safe move is to keep riding this out. My wife also works and has strong earning potential. We’re financially secure, and with two small kids, I’m not eager to gamble that away. But I’m too young to coast for the next decade while I wait for a possible ownership shakeup. At this point, the job isn’t mentally stimulating. One hour I’m building dynamic pricing models; the next, I’m literally dealing with whether a plumber is wiping his ass properly because I've had multiple complaints about his aroma. I enjoy the challenging, high-level work—marketing, systems, strategy—but I’m worn down by the drama, the legacy egos I can’t fire, and the petty dysfunction I’m forced to manage. I'm working on building a middle management gap, but there's something lost in not being as hands-on in a small business like this. I fear that by isolating myself from the bullshit, I'll also be isolating myself from some of the crucial day-to-day that keep us who we are. Hope that makes sense. (To be fair, most of our team is great. We have an outstanding market reputation and loyal employees—but the garbage still hits my desk when it shows up.) I’ve toyed with starting a complementary business or launching a consulting gig for similar-sized companies outside our market. I’ve taken some Udemy and Maven Analytics courses (digital marketing, advanced Excel/Power BI, etc.) to keep learning, but I rarely get to apply that knowledge here. So here I am. Is this burnout? A premature midlife crisis? A motivation slump? I’m not sure what I’m looking for—but if you’ve been here, or have any hard-earned advice, I’d be grateful to hear it.

#reddit#i’ve#professionalized

reddit

0

1

SpicyCopy•This week

I tested hundreds of marketing tools in the last three years and these 50 made it to the list. I'll sum up my top 50 marketing tools with one or two sentences + give you pricings.

Hey guys, I'm working in a growth marketing agency. Marketing tools are 30% of what we do, so we use them a lot and experiment with the new ones as much as possible. There are thousands of tools and it's easy to get lost, so I wanted to share the tools we use most on a daily basis. And divide the list into 14 categories. I thought this could be handy for Entrepreneurs subreddit. Why adopt tools? I see marketing tools as tireless colleagues. If you can't hire an employee, choosing the right tool can solve your problems, because they Are super cheap. Work 7/24 for you. Don’t make mistakes. Don’t need management. (or needless management) Help you to automate the majority of your lead gen process. Onwards to the list. (With the pricings post ended up quite long, you can find a link in the end if you want to check the prices) Email marketing tools #1 ActiveCampaign is armed with the most complicated email automation features and has the most intuitive user experience. It feels like you already know how to use it. \#2 Autopilot is visual marketing automation and customer journey tool that helps you acquire, nurture based on behaviors, interest etc. #3 Mailjet: This is the tool we use to send out bulky email campaigns such as newsletters. It doesn't have sexy features like others but does its job for a cheap price. Email address finders #4 Skrapp finds email of your contacts by name and company. It also works with LinkedIn Sales Navigator and can extract thousands of emails in bulk + have a browser add-on. #5 Hunter: Similar to Skrapp but doesn't work with LinkedIn Sales Navigator directly. In addition, there are email templates and you can set up email campaigns. Prospecting and outreach tools #6 Prospect combines the personal emails, follow-up calls, other social touches and helps you create multichannel campaigns.  #7 Reply is a more intuitive version of Prospect. It is easy to learn and use; their UX makes you feel good and sufficient.  CRM tools #8 Salesflare helps you to stop managing your data and start managing your customers. Not yet popular as Hubspot and etc but the best solution for smaller B2B businesses. (we're fans) \#9 Hubspot: The most popular CRM for good reason and has a broader product range you can adopt in your next steps. Try this if you have a bulky list of customers because it is free. #10 Pardot: Pardot is by Salesforce, it's armed with features that can close the gap between marketing and sales. Sales Tools #11 Salesforce is the best sales automation and lead management software. It helps you to create complicated segmentations and run, track, analyze campaigns from the same dashboard. #12 LinkedIn Sales Navigator gives you full access to LinkedIn's user database. You can even find a kidnapped CEO if you know how to use it with other marketing automation tools like Skrapp. #13 Pipedrive is a simple tool and excels in one thing. It tracks your leads and tells you when to take the next action. It makes sales easier. #14 Qwilr creates great-looking docs, at speed. You can design perfect proposals, quotes, client updates, and more in a flash. We use it a lot to close deals, it's effective. #15 Crystalknows is an add-on that tells you anyone’s personality on LinkedIn and gives you a detailed approach specific to that person. It's eerily accurate. #16 Leadfeeder shows you the companies that visited your website. Tells how they found you and what they’re interested in. It has a free version. Communication Tools #17 Intercom is a sweet and smart host that welcomes your visitors when you’re not home. It’s one of the best chatbot tools in the market. #18 Drift is famous for its conversational marketing features and more sales-focused than Intercom. #19 Manychat is a chatbot that helps you create high converting Facebook campaigns. #20 Plann3r helps you create your personalized meeting page. You can schedule meetings witch clients, candidates, and prospects. #21 Loom is a video messaging tool, it helps you to be more expressive and create closer relationships. #22 Callpage collects your visitors’ phone number and connects you with them in seconds. No matter where you are. Landing page tools #23 Instapage is the best overall landing page builder. It has a broad range of features and even squirrel can build a compelling landing page with templates. No coding needed. #24 Unbounce can do everything that Instapage does and lets you build a great landing page without a developer. But it's less intuitive. Lead generation / marketing automation tools #25 Phantombuster is by far the most used lead generation software in our tool kit. It extracts data, emails, sends requests, customized messages, and does many things on autopilot in any platform. You can check this, this and this if you want to see it in action. #26 Duxsoup is a Google Chrome add-on and can also automate some of LinkedIn lead generation efforts like Phantombuster. But not works in the cloud. #27 Zapier is a glue that holds all the lead generation tools together. With Zapier, You can connect different marketing tools and no coding required. Conversion rate optimization tools #28 Hotjar tracks what people are doing on your website by recording sessions and capturing mouse movements. Then it gives you a heatmap. #29 UsabilityHub shows your page to a digital crowd and measures the first impressions and helps you to validate your ideas. #30 Optinmonster is a top tier conversion optimization tool. It helps you to capture leads and enables you to increase conversions rates with many features. #31 Notifia is one mega tool of widgets that arms your website with the wildest social proof and lead capturing tactics. #32 Sumo is a much simpler version of Notifia. But Sumo has everything to help you capture leads and build your email lists. Web scrapers #33 Data Miner is a Google Chrome browser extension that helps you scrape data from web pages and into a CSV file or Excel spreadsheet. #34 Webscraper does the same thing as Data Miner; however, it is capable of handling more complex tasks. SEO and Content #35 Grammarly: Your English could be your first language and your grammar could be better than Shakespeare. Grammarly still can make your writing better. #36 Hemingwayapp is a copywriting optimization tool that gives you feedback about your copy and improves your readability score, makes your writing bolder and punchier. Free. #37 Ahrefs is an all-rounder search engine optimization tool that helps you with off-page, on-page or technical SEO. #38 SurferSEO makes things easier for your on-page SEO efforts. It’s a tool that analyzes top Google results for specific keywords and gives you a content brief based on that data. Video editing and design tools #39 Canva is a graphic design platform that makes everything easy. It has thousands of templates for anything from Facebook ads, stylish presentations to business cards.  #40 Kapwing is our go-to platform for quick video edits. It works on the browser and can help you to create stylish videos, add subtitles, resize videos, create memes, or remove backgrounds. #41 Animoto can turn your photos and video clip into beautiful video slideshows. It comes handy when you want to create an advertising material but don’t have a budget. Advertising tools #42 AdEspresso lets you create and test multiple ads with few clicks. You can optimize your FB, IG, and Google ads from this tool and measure your ads with in-depth analytics. #43 AdRoll is an AI-driven platform that connects and coordinates marketing efforts across ads, email, and online stores. Other tools #44 Replug helps you to shorten, track, optimize your links with call-to-actions, branded links, and retargeting pixels #45 Draw.io = Mindmaps, schemes, and charts. With Draw.io, you can put your brain in a digital paper in an organized way. #46 Built With is a tool that finds out what websites are built with. So you can see what tools they're using and so on. #47 Typeform can turn data collection into an experience with Typeform. This tool helps you to engage your audience with conversational forms or surveys and help you to collect more data. #48 Livestorm helped us a lot, especially in COVID-19 tiles. It’s a webinar software that works on your browser, mobile, and desktop. #49 Teachable \- If you have an online course idea but hesitating because of the production process, Teachable can help you. It's easy to configure and customizable for your needs. #50 Viral Loops provides a revolutionary referral marketing solution for modern marketers. You can create and run referral campaigns in a few clicks with templates. Remember, most of these tools have a free trial or free version. Going over them one by one can teach you a lot and help you grow your business with less work power in the early stages of your business. I hope you enjoyed the read and can find some tools to make things easier! Let me know about your favorite tools in the comments, so I can try them out. \------ If you want to check the prices and see a broader explanation about the tools, you can go here.

#reddit#tested#hundreds

reddit

0

1

IntellectualAINC•This week

We create AI software and provide AI automation for companies. Here is a list of the best AI tools for sales IMHO

Here are some AI tools that are useful for sales. I tried to touch as many different parts of the sales process so the tools are all quite different but all useful for sales. I tried to include some of the best and underrated AI tools. Most of them are free so check them out if you want. I did not include ChatGPT as it can basically be used for anything with the right prompts. So these tools will be more research-oriented. A quick disclaimer – I work for the company Idealink where we create custom ChatGPT for businesses and other AI products. Apollo AI Seamless AI CoPilot AI Lavender AI Regie AI Gemini Plusdocs Make Midjourney Fireflies AI Apollo AI - Find potential customers Apollo is a platform for sales and business development. It offers a range of tools to find and engage with ideal customers. The platform has an extensive B2B database and features that streamline the sales process from prospecting to closing deals. Key Features: Extensive B2B Database: Apollo boasts a large, accurate database of over 275 million contacts, providing a wealth of potential leads and opportunities for sales teams. Data Enrichment and Lead Insights: The platform offers data enrichment capabilities, ensuring CRM systems are continuously updated with detailed and actionable lead information. AI-Driven Sales Engagement: Apollo's AI technology assists in crafting effective communication and prioritizing high-value leads, enhancing the overall sales engagement process. Comprehensive Sales Tools: The platform provides an integrated suite of tools for email, call, and social media engagement, combined with analytics and automation features to streamline the sales cycle. Tailored Solutions for Teams: Apollo offers customized solutions for different team types, including sales and business development, founders, and marketing teams, addressing specific needs and goals. Seamless AI - Sale process made easier Seamless.AI is an innovative B2B sales lead generation solution that allows sales teams to efficiently connect with their ideal customers. The platform's features provide accurate and up-to-date contact information and integrate easily with existing sales and marketing tools. Key Features: Real-Time Search Engine: Seamless.AI uses AI to scour the web in real time, ensuring the contact information for sales leads is current and accurate. Comprehensive Integration: Easily integrates with popular CRMs and sales tools like Salesforce, HubSpot, and LinkedIn Sales Navigator, enhancing productivity and eliminating manual data entry. Chrome Extension: Enhances web browsing experience for sales teams, allowing them to build lead lists directly from their browser. Pitch Intelligence and Writer: Tools for crafting effective sales messages and marketing content, personalized for each potential customer. Data Enrichment and Autopilot: Keeps customer data current and automates lead-building, supporting consistent lead generation. Buyer Intent Data and Job Changes: Offers insights into potential customers' buying intentions and keeps track of significant job changes within key accounts. CoPilot AI - Helps sales reps manage leads CoPilot AI is an advanced AI-powered sales support platform designed for B2B sales teams and agencies to drive consistent revenue growth. The tool focuses on using LinkedIn for sales prospecting, engagement, and conversion. Key Features: LinkedIn Lead Generation: Targets and automates outreach to high-intent LinkedIn leads, enhancing efficiency and scalability in lead generation. Personalized Messaging Automation: Facilitates sending of personalized, one-click messages at scale, maintaining a human touch in digital interactions. Sales Conversion Insights: Offers tools to understand and adapt to prospects' communication styles, improving the likelihood of conversion. Sales Process Optimization: Provides analytics to evaluate and refine sales strategies, identifying opportunities for improvement in the sales funnel. Industry Versatility: Adapts to diverse industries, offering tailored solutions for B2B sales, marketing, HR, and financial services sectors. Collaborative Team Tools: Enables team synchronization and collaboration, boosting productivity and synergy in sales teams Lavender AI - Email AI assistant Lavender AI is an AI-powered email tool that helps users write better emails. It provides real-time feedback and personalized suggestions to optimize email communication efficiency. Key Features: Email Coaching and Scoring: Lavender evaluates emails using AI and a vast database of email interactions, offering a score and tips for improvement. It identifies factors that might reduce the likelihood of receiving a reply, helping users refine their email content. Personalization Assistant: This feature integrates prospect data directly into the user's email platform, suggesting personalization strategies based on recipient data and personality insights to foster deeper connections. Adaptive Improvement: Lavender's scoring and recommendations evolve in real-time with changing email behaviors and practices, thanks to its generative AI and extensive data analysis, ensuring users always follow the best practices. Data-Driven Managerial Insights: The platform provides managers with valuable insights derived from actual email interactions, aiding them in coaching their teams more effectively based on real performance and communication trends. Broad Integration Capability: Lavender integrates with various email and sales platforms including Gmail, Outlook, and others, making it versatile for different user preferences and workflows. Regie AI - Great for business intelligence Regie.ai simplifies the sales prospecting process for businesses, using GenAI and automation to improve interactions with prospects. The platform offers tools like Auto-Pilot for automatic prospecting and meeting scheduling, Co-Pilot for sales rep support, and integrations with various CRM and sales engagement platforms. It also includes a Chrome Extension and CMS for content management and customization. Key Features: Automated Prospecting with Auto-Pilot: Regie.ai's Auto-Pilot feature autonomously prospects and schedules meetings, using Generative AI for Sales Agents to enhance outbound sales efforts. Audience Discovery and Content Generation: The platform identifies target accounts not in the CRM, generating relevant, on-brand content for each message, thus ensuring efficiency in list building and message personalization. Outbound Prioritization and Dynamic Engagement: It utilizes engagement and intent data to prioritize outreach to in-market prospects and adjust engagement strategies based on buyer responsiveness. Full Funnel Brand Protection and Analytics: Regie.ai ensures consistent use of marketing-approved language in all sales outreach and provides insights into campaign and document performance, thereby safeguarding brand integrity throughout the sales funnel. Gemini - AI powered conversational platform Gemini is a large language model chatbot developed by Google AI. It can generate text, translate languages, write different creative text formats, and answer your questions in an informative way. It is still under development but has learned to perform many kinds of tasks. Key features: Generate different creative text formats of text content (poems, code, scripts, musical pieces, email, letters, etc.) Answer your questions in an informative way, even if they are open ended, challenging, or strange. Translate languages Follow your instructions and complete your requests thoughtfully. Plusdocs (Plus AI) - AI tool for presentations Plus AI is a versatile tool that helps improve presentations and integrates with Slides in a simple and intuitive way. It simplifies slide creation and customization by converting text into slides and utilizing AI for various languages. Key Features: Text-to-Slide Conversion: Plus AI excels in transforming textual content into visually appealing slides, streamlining the presentation creation process. Multilingual AI Support: The tool is equipped to handle various languages, making it adaptable for a global user base. Professional Design Options: Users have access to professionally designed slide layouts, enabling the creation of polished presentations with ease. Customization and AI Design: Plus AI allows for extensive customization, including the use of AI for designing and editing slides, ensuring unique and personalized presentations. Live Snapshots and Templates: The tool offers live snapshots for real-time updates and a wide range of templates for quick and effective slide creation. Make - AI automation Make is a powerful visual platform that allows users to build and automate tasks, workflows, apps, and systems. It offers an intuitive, no-code interface that empowers users across various business functions to design and implement complex processes without the need for developer resources. Key Features: No-Code Visual Workflow Builder: Make's core feature is its user-friendly interface that allows for the creation of intricate workflows without coding expertise, making it accessible to a wide range of users. Extensive App Integration: The platform boasts compatibility with over 1000 apps, facilitating seamless connections and data sharing across diverse tools and systems. Custom Automation Solutions: Make enables personalized automation strategies, fitting various business needs from marketing automation to IT workflow control. Template Library: Users can jumpstart their automation projects with a vast collection of pre-built templates, which are customizable to fit specific workflow requirements. Enterprise-Level Solutions: Make offers advanced options for larger organizations, including enhanced security, single sign-on, custom functions, and dedicated support. Midjourney - Making sales content Midjourney is an AI-based image generation tool that changes the way we visualise and create digital art. It offers a lot of artistic possibilities, allowing users to create stunning images from text prompts. This innovative service caters to artists, designers, and anyone seeking to bring their creative visions to life. Key Features: Advanced AI Image Generation: Midjourney's core strength lies in its powerful AI algorithms, which interpret text prompts to generate detailed, high-quality images. This feature allows users to explore an endless array of visual concepts and styles. User-driven Customization: The tool offers significant control over the image creation process, enabling users to guide the AI with specific instructions, ensuring that the final output aligns closely with their vision. Diverse Artistic Styles: Midjourney can mimic various artistic styles, from classical to contemporary, providing users with a wide range of aesthetic options for their creations. Collaboration and Community Features: The platform fosters a community of users who can share, critique, and collaborate on artistic projects, enriching the creative experience. Fireflies AI - Sales meeting assistant Fireflies.ai is a powerful tool for improving team productivity and efficiency in managing meetings and voice conversations. It offers a range of features to simplify the process of capturing, organizing, and analyzing meeting content. Key Features: Automatic Meeting Transcription: Fireflies.ai can transcribe meetings held on various video-conferencing platforms and dialers. The tool captures both video and audio, providing transcripts quickly and efficiently. AI-Powered Search and Summarization: It allows users to review long meetings in a fraction of the time, highlighting key action items, tasks, and questions. Users can filter and focus on specific topics discussed in meetings. Improved Collaboration: The tool enables adding comments, pins, and reactions to specific conversation parts. Users can create and share soundbites and integrate meeting notes with popular collaboration apps such as Slack, Notion, and Asana. Conversation Intelligence: Fireflies.ai offers insights into meetings by tracking metrics like speaker talk time and sentiment. It helps in coaching team members and improving performance in sales, recruiting, and other internal processes. Workflow Automation: The AI assistant from Fireflies.ai can log call notes and activities in CRMs, create tasks through voice commands, and share meeting recaps instantly across various platforms. Comprehensive Knowledge Base: It compiles all voice conversations into an easily accessible and updatable knowledge base, with features to organize meetings into channels and set custom privacy controls. I’ll keep updating this little guide, so add your comments and I’ll try to add more tools. This is all just a personal opinion, so it’s completely cool if you disagree with it. Btw here is the link to the full blog post about all the AI tools in a bit more depth.

#reddit#create#software

reddit

0

1

AI_Scout_Official•This week

I run an AI automation agency (AAA). My honest overview and review of this new business model

I started an AI tools directory in February, and then branched off that to start an AI automation agency (AAA) in June. So far I've come across a lot of unsustainable "ideas" to make money with AI, but at the same time a few diamonds in the rough that aren't fully tapped into yet- especially the AAA model. Thought I'd share this post to shine light into this new business model and share some ways you could potentially start your own agency, or at the very least know who you are dealing with and how to pick and choose when you (inevitably) get bombarded with cold emails from them down the line. Foreword Running an AAA does NOT involve using AI tools directly to generate and sell content directly. That ship has sailed, and unless you are happy with $5 from Fiverr every month or so, it is not a real business model. Cry me a river but generating generic art with AI and slapping it onto a T-shirt to sell on Etsy won't make you a dime. At the same time, the AAA model will NOT require you to have a deep theoretical knowledge of AI, or any academic degree, as we are more so dealing with the practical applications of generative AI and how we can implement these into different workflows and tech-stacks, rather than building AI models from the ground up. Regardless of all that, common sense and a willingness to learn will help (a shit ton), as with anything. Keep in mind - this WILL involve work and motivation as well. The mindset that AI somehow means everything can be done for you on autopilot is not the right way to approach things. The common theme of businesses I've seen who have successfully implemented AI into their operations is the willingess to work with AI in a way that augments their existing operations, rather than flat out replace a worker or team. And this is exactly the train of thought you need when working with AI as a business model. However, as the field is relatively unsaturated and hype surrounding AI is still fresh for enterprises, right now is the prime time to start something new if generative AI interests you at all. With that being said, I'll be going over three of the most successful AI-adjacent businesses I've seen over this past year, in addition to some tips and resources to point you in the right direction. so.. WTF is an AI Automation Agency? The AI automation agency (or as some YouTubers have coined it, the AAA model) at its core involves creating custom AI solutions for businesses. I have over 1500 AI tools listed in my directory, however the feedback I've received from some enterprise users is that ready-made SaaS tools are too generic to meet their specific needs. Combine this with the fact virtually no smaller companies have the time or skills required to develop custom solutions right off the bat, and you have yourself real demand. I would say in practice, the AAA model is quite similar to Wordpress and even web dev agencies, with the major difference being all solutions you develop will incorporate key aspects of AI AND automation. Which brings me to my second point- JUST AI IS NOT ENOUGH. Rather than reducing the amount of time required to complete certain tasks, I've seen many AI agencies make the mistake of recommending and (trying to) sell solutions that more likely than not increase the workload of their clients. For example, if you were to make an internal tool that has AI answer questions based on their knowledge base, but this knowledge base has to be updated manually, this is creating unnecessary work. As such I think one of the key components of building successful AI solutions is incorporating the new (Generative AI/LLMs) with the old (programmtic automation- think Zapier, APIs, etc.). Finally, for this business model to be successful, ideally you should target a niche in which you have already worked and understand pain points and needs. Not only does this make it much easier to get calls booked with prospects, the solutions you build will have much greater value to your clients (meaning you get paid more). A mistake I've seen many AAA operators make (and I blame this on the "Get Rich Quick" YouTubers) is focusing too much on a specific productized service, rather than really understanding the needs of businesses. The former is much done via a SaaS model, but when going the agency route the only thing that makes sense is building custom solutions. This is why I always take a consultant-first approach. You can only build once you understand what they actually need and how certain solutions may impact their operations, workflows, and bottom-line. Basics of How to Get Started Pick a niche. As I mentioned previously, preferably one that you've worked in before. Niches I know of that are actively being bombarded with cold emails include real estate, e-commerce, auto-dealerships, lawyers, and medical offices. There is a reason for this, but I will tell you straight up this business model works well if you target any white-collar service business (internal tools approach) or high volume businesses (customer facing tools approach). Setup your toolbox. If you wanted to start a pressure washing business, you would need a pressure-washer. This is no different. For those without programming knowledge, I've seen two common ways AAA get setup to build- one is having a network of on-call web developers, whether its personal contacts or simply going to Upwork or any talent sourcing agency. The second is having an arsenal of no-code tools. I'll get to this more in a second, but this works beecause at its core, when we are dealing with the practical applications of AI, the code is quite simple, simply put. Start cold sales. Unless you have a network already, this is not a step you can skip. You've already picked a niche, so all you have to do is find the right message. Keep cold emails short, sweet, but enticing- and it will help a lot if you did step 1 correctly and intimately understand who your audience is. I'll be touching base later about how you can leverage AI yourself to help you with outreach and closing. The beauty of gen AI and the AAA model You don't need to be a seasoned web developer to make this business model work. The large majority of solutions that SME clients want is best done using an API for an LLM for the actual AI aspect. The value we create with the solutions we build comes with the conceptual framework and design that not only does what they need it to but integrates smoothly with their existing tech-stack and workflow. The actual implementation is quite straightforward once you understand the high level design and know which tools you are going to use. To give you a sense, even if you plan to build out these apps yourself (say in Python) the large majority of the nitty gritty technical work has already been done for you, especially if you leverage Python libraries and packages that offer high level abstraction for LLM-related functions. For instance, calling GPT can be as little as a single line of code. (And there are no-code tools where these functions are simply an icon on a GUI). Aside from understanding the capabilities and limitations of these tools and frameworks, the only thing that matters is being able to put them in a way that makes sense for what you want to build. Which is why outsourcing and no-code tools both work in our case. Okay... but how TF am I suppposed to actually build out these solutions? Now the fun part. I highly recommend getting familiar with Langchain and LlamaIndex. Both are Python libraires that help a lot with the high-level LLM abstraction I mentioned previously. The two most important aspects include being able to integrate internal data sources/knowledge bases with LLMs, and have LLMs perform autonomous actions. The two most common methods respectively are RAG and output parsing. RAG (retrieval augmented Generation) If you've ever seen a tool that seemingly "trains" GPT on your own data, and wonder how it all works- well I have an answer from you. At a high level, the user query is first being fed to what's called a vector database to run vector search. Vector search basically lets you do semantic search where you are searching data based on meaning. The vector databases then retrieves the most relevant sections of text as it relates to the user query, and this text gets APPENDED to your GPT prompt to provide extra context to the AI. Further, with prompt engineering, you can limit GPT to only generate an answer if it can be found within this extra context, greatly limiting the chance of hallucination (this is where AI makes random shit up). Aside from vector databases, we can also implement RAG with other data sources and retrieval methods, for example SQL databses (via parsing the outputs of LLM's- more on this later). Autonomous Agents via Output Parsing A common need of clients has been having AI actually perform tasks, rather than simply spitting out text. For example, with autonomous agents, we can have an e-commerce chatbot do the work of a basic customer service rep (i.e. look into orders, refunds, shipping). At a high level, what's going on is that the response of the LLM is being used programmtically to determine which API to call. Keeping on with the e-commerce example, if I wanted a chatbot to check shipping status, I could have a LLM response within my app (not shown to the user) with a prompt that outputs a random hash or string, and programmatically I can determine which API call to make based on this hash/string. And using the same fundamental concept as with RAG, I can append the the API response to a final prompt that would spit out the answer for the user. How No Code Tools Can Fit In (With some example solutions you can build) With that being said, you don't necessarily need to do all of the above by coding yourself, with Python libraries or otherwise. However, I will say that having that high level overview will help IMMENSELY when it comes to using no-code tools to do the actual work for you. Regardless, here are a few common solutions you might build for clients as well as some no-code tools you can use to build them out. Ex. Solution 1: AI Chatbots for SMEs (Small and Medium Enterprises) This involves creating chatbots that handle user queries, lead gen, and so forth with AI, and will use the principles of RAG at heart. After getting the required data from your client (i.e. product catalogues, previous support tickets, FAQ, internal documentation), you upload this into your knowledge base and write a prompt that makes sense for your use case. One no-code tool that does this well is MyAskAI. The beauty of it especially for building external chatbots is the ability to quickly ingest entire websites into your knowledge base via a sitemap, and bulk uploading files. Essentially, they've covered the entire grunt work required to do this manually. Finally, you can create a inline or chat widget on your client's website with a few lines of HTML, or altneratively integrate it with a Slack/Teams chatbot (if you are going for an internal Q&A chatbot approach). Other tools you could use include Botpress and Voiceflow, however these are less for RAG and more for building out complete chatbot flows that may or may not incorporate LLMs. Both apps are essentially GUIs that eliminate the pain and tears and trying to implement complex flows manually, and both natively incoporate AI intents and a knowledge base feature. Ex. Solution 2: Internal Apps Similar to the first example, except we go beyond making just chatbots but tools such as report generation and really any sort of internal tool or automations that may incorporate LLM's. For instance, you can have a tool that automatically generates replies to inbound emails based on your client's knowledge base. Or an automation that does the same thing but for replies to Instagram comments. Another example could be a tool that generates a description and screeenshot based on a URL (useful for directory sites, made one for my own :P). Getting into more advanced implementations of LLMs, we can have tools that can generate entire drafts of reports (think 80+ pages), based not only on data from a knowledge base but also the writing style, format, and author voice of previous reports. One good tool to create content generation panels for your clients would be MindStudio. You can train LLM's via prompt engineering in a structured way with your own data to essentially fine tune them for whatever text you need it to generate. Furthermore, it has a GUI where you can dictate the entire AI flow. You can also upload data sources via multiple formats, including PDF, CSV, and Docx. For automations that require interactions between multiple apps, I recommend the OG zapier/make.com if you want a no-code solution. For instance, for the automatic email reply generator, I can have a trigger such that when an email is received, a custom AI reply is generated by MyAskAI, and finally a draft is created in my email client. Or, for an automation where I can create a social media posts on multiple platforms based on a RSS feed (news feed), I can implement this directly in Zapier with their native GPT action (see screenshot) As for more complex LLM flows that may require multiple layers of LLMs, data sources, and APIs working together to generate a single response i.e. a long form 100 page report, I would recommend tools such as Stack AI or Flowise (open-source alternative) to build these solutions out. Essentially, you get most of the functions and features of Python packages such as Langchain and LlamaIndex in a GUI. See screenshot for an example of a flow How the hell are you supposed to find clients? With all that being said, none of this matters if you can't find anyone to sell to. You will have to do cold sales, one way or the other, especially if you are brand new to the game. And what better way to sell your AI services than with AI itself? If we want to integrate AI into the cold outreach process, first we must identify what it's good at doing, and that's obviously writing a bunch of text, in a short amount of time. Similar to the solutions that an AAA can build for its clients, we can take advantage of the same principles in our own sales processes. How to do outreach Once you've identified your niche and their pain points/opportunities for automation, you want to craft a compelling message in which you can send via cold email and cold calls to get prospects booked on demos/consultations. I won't get into too much detail in terms of exactly how to write emails or calling scripts, as there are millions of resources to help with this, but I will tell you a few key points you want to keep in mind when doing outreach for your AAA. First, you want to keep in mind that many businesses are still hesitant about AI and may not understand what it really is or how it can benefit their operations. However, we can take advantage of how mass media has been reporting on AI this past year- at the very least people are AWARE that sooner or later they may have to implement AI into their businesses to stay competitive. We want to frame our message in a way that introduces generative AI as a technology that can have a direct, tangible, and positive impact on their business. Although it may be hard to quantify, I like to include estimates of man-hours saved or costs saved at least in my final proposals to prospects. Times are TOUGH right now, and money is expensive, so you need to have a compelling reason for businesses to get on board. Once you've gotten your messaging down, you will want to create a list of prospects to contact. Tools you can use to find prospects include Apollo.io, reply.io, zoominfo (expensive af), and Linkedin Sales Navigator. What specific job titles, etc. to target will depend on your niche but for smaller companies this will tend to be the owner. For white collar niches, i.e. law, the professional that will be directly benefiting from the tool (i.e. partners) may be better to contact. And for larger organizations you may want to target business improvement and digital transformation leads/directors- these are the people directly in charge of projects like what you may be proposing. Okay- so you have your message, and your list, and now all it comes down to is getting the good word out. I won't be going into the details of how to send these out, a quick Google search will give you hundreds of resources for cold outreach methods. However, personalization is key and beyond simple dynamic variables you want to make sure you can either personalize your email campaigns directly with AI (SmartWriter.ai is an example of a tool that can do this), or at the very least have the ability to import email messages programmatically. Alternatively, ask ChatGPT to make you a Python Script that can take in a list of emails, scrape info based on their linkedin URL or website, and all pass this onto a GPT prompt that specifies your messaging to generate an email. From there, send away. How tf do I close? Once you've got some prospects booked in on your meetings, you will need to close deals with them to turn them into clients. Call #1: Consultation Tying back to when I mentioned you want to take a consultant-first appraoch, you will want to listen closely to their goals and needs and understand their pain points. This would be the first call, and typically I would provide a high level overview of different solutions we could build to tacke these. It really helps to have a presentation available, so you can graphically demonstrate key points and key technologies. I like to use Plus AI for this, it's basically a Google Slides add-on that can generate slide decks for you. I copy and paste my default company messaging, add some key points for the presentation, and it comes out with pretty decent slides. Call #2: Demo The second call would involve a demo of one of these solutions, and typically I'll quickly prototype it with boilerplate code I already have, otherwise I'll cook something up in a no-code tool. If you have a niche where one type of solution is commonly demanded, it helps to have a general demo set up to be able to handle a larger volume of calls, so you aren't burning yourself out. I'll also elaborate on how the final product would look like in comparison to the demo. Call #3 and Beyond: Once the initial consultation and demo is complete, you will want to alleviate any remaining concerns from your prospects and work with them to reach a final work proposal. It's crucial you lay out exactly what you will be building (in writing) and ensure the prospect understands this. Furthermore, be clear and transparent with timelines and communication methods for the project. In terms of pricing, you want to take this from a value-based approach. The same solution may be worth a lot more to client A than client B. Furthermore, you can create "add-ons" such as monthly maintenance/upgrade packages, training sessions for employeees, and so forth, separate from the initial setup fee you would charge. How you can incorporate AI into marketing your businesses Beyond cold sales, I highly recommend creating a funnel to capture warm leads. For instance, I do this currently with my AI tools directory, which links directly to my AI agency and has consistent branding throughout. Warm leads are much more likely to close (and honestly, much nicer to deal with). However, even without an AI-related website, at the very least you will want to create a presence on social media and the web in general. As with any agency, you will want basic a professional presence. A professional virtual address helps, in addition to a Google Business Profile (GBP) and TrustPilot. a GBP (especially for local SEO) and Trustpilot page also helps improve the looks of your search results immensely. For GBP, I recommend using ProfilePro, which is a chrome extension you can use to automate SEO work for your GBP. Aside from SEO optimzied business descriptions based on your business, it can handle Q/A answers, responses, updates, and service descriptions based on local keywords. Privacy and Legal Concerns of the AAA Model Aside from typical concerns for agencies relating to service contracts, there are a few issues (especially when using no-code tools) that will need to be addressed to run a successful AAA. Most of these surround privacy concerns when working with proprietary data. In your terms with your client, you will want to clearly define hosting providers and any third party tools you will be using to build their solution, and a DPA with these third parties listed as subprocessors if necessary. In addition, you will want to implement best practices like redacting private information from data being used for building solutions. In terms of addressing concerns directly from clients, it helps if you host your solutions on their own servers (not possible with AI tools), and address the fact only ChatGPT queries in the web app, not OpenAI API calls, will be used to train OpenAI's models (as reported by mainstream media). The key here is to be open and transparent with your clients about ALL the tools you are using, where there data will be going, and make sure to get this all in writing. have fun, and keep an open mind Before I finish this post, I just want to reiterate the fact that this is NOT an easy way to make money. Running an AI agency will require hours and hours of dedication and work, and constantly rearranging your schedule to meet prospect and client needs. However, if you are looking for a new business to run, and have a knack for understanding business operations and are genuinely interested in the pracitcal applications of generative AI, then I say go for it. The time is ticking before AAA becomes the new dropshipping or SMMA, and I've a firm believer that those who set foot first and establish themselves in this field will come out top. And remember, while 100 thousand people may read this post, only 2 may actually take initiative and start.

#reddit#automation#agency

reddit

0

1

pablonm•This week

I am starting a startup on AI research automation. Looking for feedback!

Hi everyone, I would like to share a product idea that I'm working on. I studied computer science and have worked for Silicon Valley startups for the last 6 years. I'm currently employed full-time at a startup that sells an AI-powered search engine, so I have gained valuable experience in the AI/information retrieval space. I turned 29 last week, and I think it's time for me to start my own business. I've always wanted to run my own tech company, and I feel like now is the right time to begin with an idea. Are you a researcher in any field? Do you often find yourself learning new, highly complex topics and don't know where to start? Google is a great tool for finding answers to specific questions, but what if you don't know what questions to ask? I am developing a "deep search" engine that, given a topic, produces a multi-page report aggregating information from several properly cited sources. It finds and explains different perspectives and ideas related to the topic of interest. You can use it to automate the research process, but it's much more than that because it can help you uncover hidden perspectives, important questions, and ideas that you might not otherwise find when just googling. I welcome any feedback and ideas! Do you think this product would deliver significant value to your life? Why or why not? Would you be willing to pay to use it? I will post updates about this product in this thread in case you want to follow its development and try the product when it's ready.

#reddit#starting#startup

reddit

0

1

CALLIRDAN90•This week

Only 2 months of cash in the Bank for my business but was able to save it with the help of AI.

Hi there! I’m excited to share something very personal with you. We needed to book at least 2 appointments per day in the next 60 days, or my business would fail. We were already trying two acquisition channels, LinkedIn and email. The problem with these channels was that the positive response rate was very low in both. So I decided to focus on LinkedIn and get the attention of the lead by sending videos directly to them via LinkedIn messages. (You can send videos to your connections on LinkedIn if you use your cell phone.) This wasn’t new, but I added a small twist to get the lead’s attention. All the covers of the videos had a picture of me holding a sign with the person’s name and an interesting phrase. This showed some okay results, but the rest of the video was not personalized. Only the picture on the cover was. I even developed a Chrome extension for this because I thought this would be the answer and that I would book tons of appointments.  But after more trial and outreach, my leads responded, telling me that because the video itself wasn’t personalized for them, they felt like I didn’t put enough effort in, so they would not book a call with me. So after investing time and effort into my “new bright idea” and getting developers to make the Chrome extension, I was back to square one with no results. A few weeks went by, and after researching online, I found an online course from a guy who promised to teach me how to book 30+ appointments per month, guaranteed (at the time, I was making 2 or 3 appointments per week, maximum). He promised that I would only pay if he actually booked appointments for me and even offered to give me money if his course didn’t work for me. I never paid attention to internet gurus, but the offer was actually not bad, so I looked into this guy’s website. I found out he had hundreds of reviews from people who had taken his course and were talking amazing things about it. The more I read, the more excited I got. I booked a call that day and talked to a salesperson. The call was very short, and he promised I would get at least 2 appointments per day, easily. He seemed a bit cocky and told me that I just needed to trust him and the 100+ reviews from people who had taken the course. He didn’t share details, a proposal, or anything. I asked the price, and he told me it was close to $10k. (Not kidding, this was the price.) Then he told me that I would make the money back in no time with the clients I would get following his course, and that if it didn’t work, he would give me the money back. But I needed to follow everything the course said for at least 6 months. I had never paid $10k for anything in my life; it was extremely expensive for me. Also, my salary from my business was not in dollars but in a currency that was worth much less than the dollar. I continued to research more and more, but no other course was close to the number of reviews and promises that this guy had. I got desperate and told myself that I would bet everything on this course. If it worked for so many others, surely it would work for me. I got a loan from the bank and paid for the course. You might read this and think it was the most stupid thing ever, but the reality is that after 2 months in the course (I did the course as fast as I could), I learned a lot. The course was not bad; it was very extensive—probably more than 200 hours or so—and they taught a lot of things. I don’t think it was worth $10k for me, but I can see how for other people it might be worth that. Now, to the question you’re all thinking: did it get me the 2 appointments I needed per day? The answer is no. Here’s the thing: most of the techniques they taught were innovative and disruptive, but the focus was always on personalization, and they didn’t teach any way to automate the personalization. (I think, at the time they made the course, the tools didn’t exist yet.) So they taught how to do everything manually, and it took a lot—a lot of time and effort. And most annoyingly: an incredible amount of time doing operational things. I did get 2 appointments on some days, but it wasn’t consistent, and I didn’t have the time to spend 14 hours a day doing everything manually or the money to hire someone to do this for me. (I needed to also spend time delivering our service to our current clients; otherwise, they would leave.) I told them this, and they were very reasonable. After some negotiation, they gave me part of the money back. (To be fair, there was a lot of value in the course, so asking for the full $10k back would have been excessive because, in the end, it really taught me a lot of things I didn’t know.) So in the end, I spent $10k and 200+ hours on an online course, spent time and effort developing a Chrome extension, and was still not able to hit the meetings I needed. Money in the business was running out, and I needed to do something fast, or I was doomed. After investing time and effort in tools, research, and spending $10k and over 200 hours on a course that didn’t deliver the consistent results I needed, I was at a crossroads. My businesses were running out of money, and I knew I needed to find a solution quickly, or everything I had worked for would collapse. It was during this time of desperation that I started exploring other options. One night, while scrolling through the internet, I stumbled upon a 2024 article about how AI was being used to revolutionize various industries. It wasn’t directly related to appointment booking, but it sparked an idea in my mind. What if I could use AI to automate the personalization process that I had learned in the course? It seemed like a long shot, but I had nothing to lose. I started researching AI tools and technologies—YouTube videos, podcasts, pretty much everything related to AI—desperate to find something that could help me scale my outreach without investing too much time, while still maintaining the personalization that was so important. After a lot of trial and error, I found a few tools that showed promise. All of these tools were extremely new. Some of them had just launched the versions I needed just weeks ago. I can say I researched and tested more than 50 AI startups, experimenting with them, testing different approaches, checking prices (the problem was that most of them were cheap but became very expensive when applying the volume I needed to get results), and gradually refining my process. It wasn’t an overnight success, but for the first time, I felt like I was onto something that could truly work. The idea of combining AI personalization with volume was something new, and it gave me hope that I could finally book the meetings I needed without burning out. One day, I sent a video of myself talking—completely AI-generated—to my family chat group and waited for their response. None of them noticed it wasn’t actually me. At that moment, I said to myself: “Okay, I am ready to test this in the real world and see if it works.” Like everything in life, focus is key. As I mentioned earlier, we were already trying outbound strategies on LinkedIn and email, but I decided to narrow my focus to LinkedIn and specifically to video outreach. My goal was to stand out from the crowd, where most people were using text or sending generic videos. I knew that if my videos were 100% personalized, it would make a strong impression on my leads. I focused on two key metrics during my tests: Time spent on manual personalized outreach vs. AI-generated personalized outreach. Positive reply rate for non-personalized manual outreach vs. AI-generated personalized outreach. I ran a test using a sample of 50 one-minute videos sent to 50 leads, and here are the results: Time Spent to Make the Videos: Manual Process: It took me up to 10 hours to create and send 50 personalized videos. This included looking good on camera, brushing my hair, choosing appropriate clothing, ensuring proper lighting, not messing up the script, using a camera holder, recharging the phone, pausing to drink water, avoiding external sounds, being in an appropriate room, downloading the videos, deleting the videos that were not good, and sending the final ones. On average, it took me at least 12.5 minutes per one-minute video. AI Process: With AI, it took me just 32 seconds to create the exact same one-minute personalized video—without saying a word or recording a second of footage. In total, I could make and send the same 50 personalized videos in just 27 minutes. Result: The AI process was 24 times faster. Completely crazy! Positive Reply Rate: Non-Personalized Script (Manual): Using a good script without personalization (no name, job title, city, company, etc.) resulted in a positive reply rate of 4-6% on LinkedIn, including follow-ups. Personalized Script (AI): Using the same script but adding personalized details like the lead's name, company, city, and job title resulted in a positive reply rate of 15-20%, including follow-ups. Result: AI personalization led to 3x (three times) more replies. The best part was the responses. Almost everyone who replied thanked me for taking the time to research them, congratulated me on my speech, and appreciated the personalization and eloquence of my message.  These metrics were a complete breakthrough for me. I researched online to see if anyone else had done something similar, but I couldn’t find anything close. After achieving these metrics, booking the two appointments I desperately needed became easy. In fact, in the last 10 weeks, I’ve been able to consistently book 3-4 appointments per day. This success allowed me to train someone in my company to handle the process, freeing me up to focus on other aspects of the business and ultimately saving it. With the AI appointment machine we built, I even have free time now—time that I’ve been using to develop a methodology and tech tools that I now teach to others. I named the methodology Clip2Lead as a reference to the first Chrome extension I developed that didn’t work but ended up being the first step toward everything that followed. I’ve condensed everything I learned and throughout my experiences into a simple and short FREE training where I cover the entire AI appointment booking process. This includes how to find leads, create scripts, set up follow-up sequences, generate AI videos, clone your voice, compare non-AI metrics with AI metrics, and even navigate AI safety controls. I also offer Chrome extensions that helped me automate the process even further, so you can spend your time closing deals or focusing on other acquisition channels, while your AI machine for booking appointments runs with minimal effort from you. If you’re interested please get in touch with me and thank you for taking the time to read my personal story.

#reddit#only#months

reddit

0

0

pknerd•This week

What kind of online "Boring" businesses that could generate minimum $1k/month

So there is a term that is being used a lot, "Boring Business" To be honest, I am not exactly sure what it means but it seems kind of niche online/offline businesses that have demands but yet are underserved. I watched a video on the "Niche Pursuit" channel on which Spencer discussed some truck websites that generate 3-4 grand per month. Having said that, 2025 is starting. I am a developer, know AI/Automation..would not mind working on such kinda apps/websites and automating them. PS: I am OK to partner with marketing/sales kind of people here. Let's grow together! PPS: Many ppl DMing me about my location. I am from Pakistan and currently working for a LA based company remotely in AI and automation

#reddit#kind#online

reddit

0

1

Old_Cloud_9186•This week

Thinking about commercializing my B2B tool for LinkedIn posts automation – Need feedback from other businesses please

Hey everyone, I’ve been running my own small company selling industrial equipment, and as a one-person operation, I built a tool that’s been a real lifesaver for me. It automates all my LinkedIn posts, and I’m wondering if this could be useful for others in the industry. I’m considering commercializing it, but before I go down that road, I’d love some feedback. Here’s how it works: The tool uses AI to study your brand identity, products, audience, and past LinkedIn posts, following your brand guidelines to replicate your company’s style. It builds a full-year content calendar with different types of posts, like case studies, industry news, etc. You get an email on the days you need to post, with three ready-to-go options generated by AI. All you need to do is copy and paste on LinkedIn. There’s also a form where you can create custom posts for special occasions, like company recognitions or events. It’s been super helpful for me, but I’m curious if other businesses would see value in something like this. Would you use a tool like this? Or do you think it’s overkill for most businesses? Any feedback would be appreciated! Thanks in advance!

#reddit#thinking#about

reddit

0

1

swagamoney•This week

My (23M) first $10k month installing internal GPT-4 for businesses

It all started in this very own subreddit just a month ago. I posted “How I made a secure GPT-4 for my company knowledge base” and left a cheeky Google Form in the comments. The post got 162 upvotes, 67 comments and, most importantly… ~30 form answers 😈 From there I got on 12 calls and even though I initially offered to do it for free… I closed 2 clients for $5k each. Data privacy was my main selling point: 1st company was a manufacturer with private instructions/manuals on how to operate certain systems. I trained GPT on them and let their employees talk with these 100-page PDFs. (When I say “train”, I refer to RAG, not fine-tune) 2nd company had customers sending them photos of sensitive documents for a customs clearing service. They had people manually extracting the info so we automated all of that. How did I ensure data privacy and security? I simply used MS Azure AI. They have all of the same stuff OpenAI has, but offer data privacy guarantees and network isolation. That’s both SOC 2 and GDPR compliant. Companies love it. Now I’m cold emailing my first 2 clients’ competitors for a quick rinse and repeat. P.S. I’m extremely curious of different use cases since I’m looking to niche down, so I’d be happy to talk to businesses with ideas of how to use this. You’d give me a use case idea and I’d give you advice on how to implement it. Edit: I’m getting TONS of DMs so please be comprehensive in your first message!

#reddit#(23m)#first

reddit

0

1

AI_Scout_Official•This week

I run an AI automation agency (AAA). My honest overview and review of this new business model

I started an AI tools directory in February, and then branched off that to start an AI automation agency (AAA) in June. So far I've come across a lot of unsustainable "ideas" to make money with AI, but at the same time a few diamonds in the rough that aren't fully tapped into yet- especially the AAA model. Thought I'd share this post to shine light into this new business model and share some ways you could potentially start your own agency, or at the very least know who you are dealing with and how to pick and choose when you (inevitably) get bombarded with cold emails from them down the line. Foreword Running an AAA does NOT involve using AI tools directly to generate and sell content directly. That ship has sailed, and unless you are happy with $5 from Fiverr every month or so, it is not a real business model. Cry me a river but generating generic art with AI and slapping it onto a T-shirt to sell on Etsy won't make you a dime. At the same time, the AAA model will NOT require you to have a deep theoretical knowledge of AI, or any academic degree, as we are more so dealing with the practical applications of generative AI and how we can implement these into different workflows and tech-stacks, rather than building AI models from the ground up. Regardless of all that, common sense and a willingness to learn will help (a shit ton), as with anything. Keep in mind - this WILL involve work and motivation as well. The mindset that AI somehow means everything can be done for you on autopilot is not the right way to approach things. The common theme of businesses I've seen who have successfully implemented AI into their operations is the willingess to work with AI in a way that augments their existing operations, rather than flat out replace a worker or team. And this is exactly the train of thought you need when working with AI as a business model. However, as the field is relatively unsaturated and hype surrounding AI is still fresh for enterprises, right now is the prime time to start something new if generative AI interests you at all. With that being said, I'll be going over three of the most successful AI-adjacent businesses I've seen over this past year, in addition to some tips and resources to point you in the right direction. so.. WTF is an AI Automation Agency? The AI automation agency (or as some YouTubers have coined it, the AAA model) at its core involves creating custom AI solutions for businesses. I have over 1500 AI tools listed in my directory, however the feedback I've received from some enterprise users is that ready-made SaaS tools are too generic to meet their specific needs. Combine this with the fact virtually no smaller companies have the time or skills required to develop custom solutions right off the bat, and you have yourself real demand. I would say in practice, the AAA model is quite similar to Wordpress and even web dev agencies, with the major difference being all solutions you develop will incorporate key aspects of AI AND automation. Which brings me to my second point- JUST AI IS NOT ENOUGH. Rather than reducing the amount of time required to complete certain tasks, I've seen many AI agencies make the mistake of recommending and (trying to) sell solutions that more likely than not increase the workload of their clients. For example, if you were to make an internal tool that has AI answer questions based on their knowledge base, but this knowledge base has to be updated manually, this is creating unnecessary work. As such I think one of the key components of building successful AI solutions is incorporating the new (Generative AI/LLMs) with the old (programmtic automation- think Zapier, APIs, etc.). Finally, for this business model to be successful, ideally you should target a niche in which you have already worked and understand pain points and needs. Not only does this make it much easier to get calls booked with prospects, the solutions you build will have much greater value to your clients (meaning you get paid more). A mistake I've seen many AAA operators make (and I blame this on the "Get Rich Quick" YouTubers) is focusing too much on a specific productized service, rather than really understanding the needs of businesses. The former is much done via a SaaS model, but when going the agency route the only thing that makes sense is building custom solutions. This is why I always take a consultant-first approach. You can only build once you understand what they actually need and how certain solutions may impact their operations, workflows, and bottom-line. Basics of How to Get Started Pick a niche. As I mentioned previously, preferably one that you've worked in before. Niches I know of that are actively being bombarded with cold emails include real estate, e-commerce, auto-dealerships, lawyers, and medical offices. There is a reason for this, but I will tell you straight up this business model works well if you target any white-collar service business (internal tools approach) or high volume businesses (customer facing tools approach). Setup your toolbox. If you wanted to start a pressure washing business, you would need a pressure-washer. This is no different. For those without programming knowledge, I've seen two common ways AAA get setup to build- one is having a network of on-call web developers, whether its personal contacts or simply going to Upwork or any talent sourcing agency. The second is having an arsenal of no-code tools. I'll get to this more in a second, but this works beecause at its core, when we are dealing with the practical applications of AI, the code is quite simple, simply put. Start cold sales. Unless you have a network already, this is not a step you can skip. You've already picked a niche, so all you have to do is find the right message. Keep cold emails short, sweet, but enticing- and it will help a lot if you did step 1 correctly and intimately understand who your audience is. I'll be touching base later about how you can leverage AI yourself to help you with outreach and closing. The beauty of gen AI and the AAA model You don't need to be a seasoned web developer to make this business model work. The large majority of solutions that SME clients want is best done using an API for an LLM for the actual AI aspect. The value we create with the solutions we build comes with the conceptual framework and design that not only does what they need it to but integrates smoothly with their existing tech-stack and workflow. The actual implementation is quite straightforward once you understand the high level design and know which tools you are going to use. To give you a sense, even if you plan to build out these apps yourself (say in Python) the large majority of the nitty gritty technical work has already been done for you, especially if you leverage Python libraries and packages that offer high level abstraction for LLM-related functions. For instance, calling GPT can be as little as a single line of code. (And there are no-code tools where these functions are simply an icon on a GUI). Aside from understanding the capabilities and limitations of these tools and frameworks, the only thing that matters is being able to put them in a way that makes sense for what you want to build. Which is why outsourcing and no-code tools both work in our case. Okay... but how TF am I suppposed to actually build out these solutions? Now the fun part. I highly recommend getting familiar with Langchain and LlamaIndex. Both are Python libraires that help a lot with the high-level LLM abstraction I mentioned previously. The two most important aspects include being able to integrate internal data sources/knowledge bases with LLMs, and have LLMs perform autonomous actions. The two most common methods respectively are RAG and output parsing. RAG (retrieval augmented Generation) If you've ever seen a tool that seemingly "trains" GPT on your own data, and wonder how it all works- well I have an answer from you. At a high level, the user query is first being fed to what's called a vector database to run vector search. Vector search basically lets you do semantic search where you are searching data based on meaning. The vector databases then retrieves the most relevant sections of text as it relates to the user query, and this text gets APPENDED to your GPT prompt to provide extra context to the AI. Further, with prompt engineering, you can limit GPT to only generate an answer if it can be found within this extra context, greatly limiting the chance of hallucination (this is where AI makes random shit up). Aside from vector databases, we can also implement RAG with other data sources and retrieval methods, for example SQL databses (via parsing the outputs of LLM's- more on this later). Autonomous Agents via Output Parsing A common need of clients has been having AI actually perform tasks, rather than simply spitting out text. For example, with autonomous agents, we can have an e-commerce chatbot do the work of a basic customer service rep (i.e. look into orders, refunds, shipping). At a high level, what's going on is that the response of the LLM is being used programmtically to determine which API to call. Keeping on with the e-commerce example, if I wanted a chatbot to check shipping status, I could have a LLM response within my app (not shown to the user) with a prompt that outputs a random hash or string, and programmatically I can determine which API call to make based on this hash/string. And using the same fundamental concept as with RAG, I can append the the API response to a final prompt that would spit out the answer for the user. How No Code Tools Can Fit In (With some example solutions you can build) With that being said, you don't necessarily need to do all of the above by coding yourself, with Python libraries or otherwise. However, I will say that having that high level overview will help IMMENSELY when it comes to using no-code tools to do the actual work for you. Regardless, here are a few common solutions you might build for clients as well as some no-code tools you can use to build them out. Ex. Solution 1: AI Chatbots for SMEs (Small and Medium Enterprises) This involves creating chatbots that handle user queries, lead gen, and so forth with AI, and will use the principles of RAG at heart. After getting the required data from your client (i.e. product catalogues, previous support tickets, FAQ, internal documentation), you upload this into your knowledge base and write a prompt that makes sense for your use case. One no-code tool that does this well is MyAskAI. The beauty of it especially for building external chatbots is the ability to quickly ingest entire websites into your knowledge base via a sitemap, and bulk uploading files. Essentially, they've covered the entire grunt work required to do this manually. Finally, you can create a inline or chat widget on your client's website with a few lines of HTML, or altneratively integrate it with a Slack/Teams chatbot (if you are going for an internal Q&A chatbot approach). Other tools you could use include Botpress and Voiceflow, however these are less for RAG and more for building out complete chatbot flows that may or may not incorporate LLMs. Both apps are essentially GUIs that eliminate the pain and tears and trying to implement complex flows manually, and both natively incoporate AI intents and a knowledge base feature. Ex. Solution 2: Internal Apps Similar to the first example, except we go beyond making just chatbots but tools such as report generation and really any sort of internal tool or automations that may incorporate LLM's. For instance, you can have a tool that automatically generates replies to inbound emails based on your client's knowledge base. Or an automation that does the same thing but for replies to Instagram comments. Another example could be a tool that generates a description and screeenshot based on a URL (useful for directory sites, made one for my own :P). Getting into more advanced implementations of LLMs, we can have tools that can generate entire drafts of reports (think 80+ pages), based not only on data from a knowledge base but also the writing style, format, and author voice of previous reports. One good tool to create content generation panels for your clients would be MindStudio. You can train LLM's via prompt engineering in a structured way with your own data to essentially fine tune them for whatever text you need it to generate. Furthermore, it has a GUI where you can dictate the entire AI flow. You can also upload data sources via multiple formats, including PDF, CSV, and Docx. For automations that require interactions between multiple apps, I recommend the OG zapier/make.com if you want a no-code solution. For instance, for the automatic email reply generator, I can have a trigger such that when an email is received, a custom AI reply is generated by MyAskAI, and finally a draft is created in my email client. Or, for an automation where I can create a social media posts on multiple platforms based on a RSS feed (news feed), I can implement this directly in Zapier with their native GPT action (see screenshot) As for more complex LLM flows that may require multiple layers of LLMs, data sources, and APIs working together to generate a single response i.e. a long form 100 page report, I would recommend tools such as Stack AI or Flowise (open-source alternative) to build these solutions out. Essentially, you get most of the functions and features of Python packages such as Langchain and LlamaIndex in a GUI. See screenshot for an example of a flow How the hell are you supposed to find clients? With all that being said, none of this matters if you can't find anyone to sell to. You will have to do cold sales, one way or the other, especially if you are brand new to the game. And what better way to sell your AI services than with AI itself? If we want to integrate AI into the cold outreach process, first we must identify what it's good at doing, and that's obviously writing a bunch of text, in a short amount of time. Similar to the solutions that an AAA can build for its clients, we can take advantage of the same principles in our own sales processes. How to do outreach Once you've identified your niche and their pain points/opportunities for automation, you want to craft a compelling message in which you can send via cold email and cold calls to get prospects booked on demos/consultations. I won't get into too much detail in terms of exactly how to write emails or calling scripts, as there are millions of resources to help with this, but I will tell you a few key points you want to keep in mind when doing outreach for your AAA. First, you want to keep in mind that many businesses are still hesitant about AI and may not understand what it really is or how it can benefit their operations. However, we can take advantage of how mass media has been reporting on AI this past year- at the very least people are AWARE that sooner or later they may have to implement AI into their businesses to stay competitive. We want to frame our message in a way that introduces generative AI as a technology that can have a direct, tangible, and positive impact on their business. Although it may be hard to quantify, I like to include estimates of man-hours saved or costs saved at least in my final proposals to prospects. Times are TOUGH right now, and money is expensive, so you need to have a compelling reason for businesses to get on board. Once you've gotten your messaging down, you will want to create a list of prospects to contact. Tools you can use to find prospects include Apollo.io, reply.io, zoominfo (expensive af), and Linkedin Sales Navigator. What specific job titles, etc. to target will depend on your niche but for smaller companies this will tend to be the owner. For white collar niches, i.e. law, the professional that will be directly benefiting from the tool (i.e. partners) may be better to contact. And for larger organizations you may want to target business improvement and digital transformation leads/directors- these are the people directly in charge of projects like what you may be proposing. Okay- so you have your message, and your list, and now all it comes down to is getting the good word out. I won't be going into the details of how to send these out, a quick Google search will give you hundreds of resources for cold outreach methods. However, personalization is key and beyond simple dynamic variables you want to make sure you can either personalize your email campaigns directly with AI (SmartWriter.ai is an example of a tool that can do this), or at the very least have the ability to import email messages programmatically. Alternatively, ask ChatGPT to make you a Python Script that can take in a list of emails, scrape info based on their linkedin URL or website, and all pass this onto a GPT prompt that specifies your messaging to generate an email. From there, send away. How tf do I close? Once you've got some prospects booked in on your meetings, you will need to close deals with them to turn them into clients. Call #1: Consultation Tying back to when I mentioned you want to take a consultant-first appraoch, you will want to listen closely to their goals and needs and understand their pain points. This would be the first call, and typically I would provide a high level overview of different solutions we could build to tacke these. It really helps to have a presentation available, so you can graphically demonstrate key points and key technologies. I like to use Plus AI for this, it's basically a Google Slides add-on that can generate slide decks for you. I copy and paste my default company messaging, add some key points for the presentation, and it comes out with pretty decent slides. Call #2: Demo The second call would involve a demo of one of these solutions, and typically I'll quickly prototype it with boilerplate code I already have, otherwise I'll cook something up in a no-code tool. If you have a niche where one type of solution is commonly demanded, it helps to have a general demo set up to be able to handle a larger volume of calls, so you aren't burning yourself out. I'll also elaborate on how the final product would look like in comparison to the demo. Call #3 and Beyond: Once the initial consultation and demo is complete, you will want to alleviate any remaining concerns from your prospects and work with them to reach a final work proposal. It's crucial you lay out exactly what you will be building (in writing) and ensure the prospect understands this. Furthermore, be clear and transparent with timelines and communication methods for the project. In terms of pricing, you want to take this from a value-based approach. The same solution may be worth a lot more to client A than client B. Furthermore, you can create "add-ons" such as monthly maintenance/upgrade packages, training sessions for employeees, and so forth, separate from the initial setup fee you would charge. How you can incorporate AI into marketing your businesses Beyond cold sales, I highly recommend creating a funnel to capture warm leads. For instance, I do this currently with my AI tools directory, which links directly to my AI agency and has consistent branding throughout. Warm leads are much more likely to close (and honestly, much nicer to deal with). However, even without an AI-related website, at the very least you will want to create a presence on social media and the web in general. As with any agency, you will want basic a professional presence. A professional virtual address helps, in addition to a Google Business Profile (GBP) and TrustPilot. a GBP (especially for local SEO) and Trustpilot page also helps improve the looks of your search results immensely. For GBP, I recommend using ProfilePro, which is a chrome extension you can use to automate SEO work for your GBP. Aside from SEO optimzied business descriptions based on your business, it can handle Q/A answers, responses, updates, and service descriptions based on local keywords. Privacy and Legal Concerns of the AAA Model Aside from typical concerns for agencies relating to service contracts, there are a few issues (especially when using no-code tools) that will need to be addressed to run a successful AAA. Most of these surround privacy concerns when working with proprietary data. In your terms with your client, you will want to clearly define hosting providers and any third party tools you will be using to build their solution, and a DPA with these third parties listed as subprocessors if necessary. In addition, you will want to implement best practices like redacting private information from data being used for building solutions. In terms of addressing concerns directly from clients, it helps if you host your solutions on their own servers (not possible with AI tools), and address the fact only ChatGPT queries in the web app, not OpenAI API calls, will be used to train OpenAI's models (as reported by mainstream media). The key here is to be open and transparent with your clients about ALL the tools you are using, where there data will be going, and make sure to get this all in writing. have fun, and keep an open mind Before I finish this post, I just want to reiterate the fact that this is NOT an easy way to make money. Running an AI agency will require hours and hours of dedication and work, and constantly rearranging your schedule to meet prospect and client needs. However, if you are looking for a new business to run, and have a knack for understanding business operations and are genuinely interested in the pracitcal applications of generative AI, then I say go for it. The time is ticking before AAA becomes the new dropshipping or SMMA, and I've a firm believer that those who set foot first and establish themselves in this field will come out top. And remember, while 100 thousand people may read this post, only 2 may actually take initiative and start.

#reddit#automation#agency

reddit

0

1

FrostyButterscotch77•This week

Is there a need for better tools to securely adopt AI in businesses? (e.g., access controls, data redaction, compliance dashboards)

Hey Reddit, I’ve been thinking a lot about the rise of AI tools like ChatGPT, DeepSeek, and others, and how businesses are struggling to balance the benefits of AI with the risks of sharing sensitive data. Many companies are concerned about employees accidentally leaking proprietary info, violating compliance regulations, or exposing customer data. Do you think there’s a need for tools that help businesses securely adopt AI? For example: Access controls: Restricting who can use AI tools and what data they can access. Data redaction: Automatically masking sensitive info before it’s processed by AI. Compliance dashboards: Tracking AI usage and ensuring adherence to regulations like GDPR, HIPAA, etc. I’m curious: Are you or your company already using tools like this? If so, what’s working (or not working)? What pain points do you face when trying to securely adopt AI? Would you pay for a solution that addresses these challenges? I’m exploring this idea and would love to hear your thoughts, experiences, or suggestions. Thanks in advance!

#reddit#there#need

reddit

0

0

shanumas•This week

Looking for a business co-founder for my AI startup in manufacturing.

I spent over a decade as a Senior Software Developer building manufacturing optimization products for global enterprises across the Americas and Europe. It’s a million-dollar industry, and I have strong connections with multinational clients. With AI advancements, there’s a huge opportunity to disrupt the market. My plan is to offer locally hosted AI-powered applications with an option for private cloud deployment. I already have 4–5 high-impact use cases, each of which can be built in a month. I’m looking for a business partner—ideally someone with deep expertise in manufacturing and strong connections in Europe, the USA, China, or India. I’ll handle the tech; you drive the business. Beyond optimization, I have additional solid use cases—some aligned with what YC-backed companies are doing. I found a YC company working on something similar, which I can share in DM.

#reddit#looking#business

reddit

0

1

CountryPitiful•This week

This founder was about to shut down his business and open a restaurant. He pivoted the business and grew it to $45m ARR in 12 months. What other businesses can scale like this?

I heard that Jasper scaled to $45m ARR in 12 months...with a team of 8. For context, they are one of the fastest-growing companies ever. Grew from $0 to $45m ARR in 12 months (then raised $125m at a $1.5b valuation). As a fellow founder, their story is really inspiring to me (curious about what others think): In December 2020, Dave Rogenmoser and his co-founders were on the brink of shutting down their business. They'd spent 3+ years building a conversion optimization software called Proof...and it was flatlining. A few weeks prior they had to make the painful decision to let go of half their team. Competition and churn had completely eroded growth. Things were painful. 8 years of work left them with a string of startups that never quite made it: 2 failed software businesses (couldn't make money*) A SMB marketing agency (maxed out at $25k/mo*) An online course company (hard to get big*) The Pivot: In January 2021, they had an idea to use Chat GPT-3, the generative AI model released 6 months earlier, to write high-converting Facebook ads. Within 30 days, they launched the business. With the skeleton crew remaining from the last startup, they scaled the business to $45m ARR and 70,000+ customers without hiring a single new person. Soon after, they raised $125m at a $1.5b valuation. Dave Rogenmoser, CEO at Jasper, had some great one-liners in a few podcasts I listened to on the business. Here are some of his learnings: Right Skill, Wrong Vehicle: He spent 8 years building marketing businesses which gave this team the knowledge and confidence to spend $1m/mo on sales and marketing to scale the business to $45m ARR in year 1. Launch Fast & Iterate Quickly: The team agreed that if the business didn't work in 30 days, they'd shut it down. Dave says, "If you have been working on a problem for more than 18 months and haven't found Product market fit (PMF), odds are you won't...Make the hard pivot."* Ride A Big Wave: Generative AI technology is a new technology that is changing the way we work. But it's not just text. It's images, voice, etc. Identify new customer segments (e.g., Municipalities, Banks, Lawyers, etc.), learn their problems, and apply this novel technology to solve them. What other businesses have you seen scale like this? I've never seen a SaaS business grow that fast. I meet interesting founders 2x per week and share the learnings here.

#reddit#founder#about

reddit

0

1

CountryPitiful•This week

This founder was about to shut down his startup and open a restaurant. He pivoted the business and grew it to $45m ARR in 12 months. What else have you seen grow that fast?

I heard that Jasper scaled to $45m ARR in 12 months...with a team of 8. For context, they are one of the fastest-growing companies ever. Grew from $0 to $45m ARR in 12 months (then raised $125m at a $1.5b valuation). As a fellow founder, their story is really inspiring to me (curious about what others think): In December 2020, Dave Rogenmoser and his co-founders were on the brink of shutting down their business. They'd spent 3+ years building a conversion optimization software called Proof...and it was flatlining. A few weeks prior they had to make the painful decision to let go of half their team. Competition and churn had completely eroded growth. Things were painful. 8 years of work left them with a string of startups that never quite made it: 2 failed software businesses (couldn't make money*) A SMB marketing agency (maxed out at $25k/mo*) An online course company (hard to get big*) The Pivot: In January 2021, they had an idea to use Chat GPT-3, the generative AI model released 6 months earlier, to write high-converting Facebook ads. Within 30 days, they launched the business. With the skeleton crew remaining from the last startup, they scaled the business to $45m ARR and 70,000+ customers without hiring a single new person. Soon after, they raised $125m at a $1.5b valuation. Dave Rogenmoser, CEO at Jasper, had some great one-liners in a few podcasts I listened to on the business. Here are some of his learnings: Right Skill, Wrong Vehicle: He spent 8 years building marketing businesses which gave this team the knowledge and confidence to spend $1m/mo on sales and marketing to scale the business to $45m ARR in year 1. Launch Fast & Iterate Quickly: The team agreed that if the business didn't work in 30 days, they'd shut it down. Dave says, "If you have been working on a problem for more than 18 months and haven't found Product market fit (PMF), odds are you won't...Make the hard pivot."* Ride A Big Wave: Generative AI technology is a new technology that is changing the way we work. But it's not just text. It's images, voice, etc. Identify new customer segments (e.g., Municipalities, Banks, Lawyers, etc.), learn their problems, and apply this novel technology to solve them. What other businesses have you seen scale like this? I've never seen a SaaS business grow that fast. I meet interesting founders 2x per week and share the learnings here.

#reddit#founder#about

reddit

0

1

Nevoy_92•This week

Building Business Development/Sales Pipeline

Hey all! Happy weekend wherever you may be! Wanting to get some advice and insight into a couple areas as mentioned in the title. Background is the following: My Partner and I started our company about in 2021. When we kicked off we were building a control and camera vision system for automating and optimizing indoor vertical farms. We got to early mvp but market was not as big and barrier to entry was high. So we pivoted early 2023 to utilize components of our technology in a wildfire detection and risk analysis platform. Happy to say we are once again at MVP but need to get PMF and pipeline going both with revenue generating clients and pilots/demos. Through this period we’ve kept the lights on by running a consulting service and digital agency. We’ve also pushed out a couple of AI tools to market. Effectively I need to build out a strong pipeline for each vertical and associated sales team. Right now spread too thin trying to conduct sales and business dev on each front. Challenges: Wildfire: Business to Gov relationships so need to build for that. Additionally early stage technology so imo relationships are critical. Additionally need to take advantage of grant funding. Target Markets: Canada, USA, Mediterranean, Northern Europe/Scandavian Countries. Consulting and Agency: Things feel dry… we have a recurring client list but we want to grow this channel exponentially, focusing on RFP’s and med to large company profiles rather then the current SMB. Our current activités are mediocre imo for outreach and connection. AI Tools: I believe these are great opportunities. TLDR 1)sales based assistant as well as 2)central AI aggregation with prompt repository. Business Dev Energy into this is basically focused on digital means. In the process of generating video content to push via ads and online social platforms. Challenge: low engagement right now users signing up but no commitments to purchase. Need to evaluate value offer and feedback on PMF. From the sales team side, effectively need to generate the sales so I can expand the team and grow accordingly. I’m a huge proponent of commission based compensation. Also open to a base salary. However anyone I onboard at this moment would have to be commission cause cash-flow. On that front, what are current commissions structures looking like for people? What’s engaging what’s worth taking a risk what is just a huge no? On the challenges for the product lines any feedback questions and even poking holes is appreciated! Thanks!

#reddit#building#business

reddit

0

0.667

alexanderolssen•This week

5 no-code tools to build your website fast and easy.

Hey, reddittors👋 Want to build a website but don't know how to code? 🥺 No problem! There are a number of no-code tools available that can help you create a professional-looking website without any coding knowledge. 👇 Carrd Carrd is a free website builder that allows you to create simple, one-page websites, profile pages, portfolios and forms with super-easy-to learn editor. It's a great option for people who want to create a website quickly and easily without having to learn how to code. Carrd has 16 website design elements, such as text, audio, video, images, buttons, tables, galleries, and code embeds that can be used to define the structure of your website. Pros: Easy to use, affordable (free/$19 per year plans), variety of templates, widgets (PayPal, Gumroad, Stripe, Typeform, etc), responsive out of the box, has some basic animations. Cons: Lack of design freedom, hard to build a scalable website, most of the templates looks design outdated, not suitable for blogs and online stores. Best for: Solo entrepreneurs, Artists, Photographers, Copywriters, SMB’s with no design/development background. Framer Primarily aimed at designers, Framer is a no-code tool that let’s you create highly-customized websites that vary from simple landing pages to multi-page company websites. It has all the necessary building blocks and features to create any website your company might need. It’s even has an AI websites builder built in! Pros: Complete design freedom, powerful animation engine, content management system (CMS), Easy to pick up for designers, plenty of learning resources, code embeds, SEO settings, affordable ($19/month), collaboration (you can invite team to work with you on the website simultaneously), library of prebuilt components, Figma-to-Framer plugin that lets you copy-paste designs into Framer with ease. Cons: Learning curve, not the best pick for bulky websites. Best for: Freelance designers & agencies, In-house design teams WordPress WordPress is a free and open-source content management system (CMS). It is the most popular website builder in the world, powering over 455 million websites. It has all features you might need to build a landing page, multi-page website, blogs, ecommerce stores, gated content websites, etc. Pros: Tons of learning materials, highly customizable, SEO-friendly, scalability, lots of plugins and themes, large community Cons: Security vulnerabilities, learning curve, website maintenance required, performance issues, dependency on plugins. Best for: Freelance designers & agencies, In-house design teams, solo entrepreneurs, SMB’s, bloggers. &#x200B; Wix Wix is a popular website builder that has gained immense popularity for its user-friendly interface and a wide range of features designed to cater to both beginners and experienced web creators. Offering an array of customizable templates, drag-and-drop functionality, and an impressive app market, Wix empowers users to bring their online visions to life without requiring extensive technical knowledge. Pros: Easy-to-use, robust learning resources, scalability, huge template library, e-commerce tools, feature-rich (app market, appointment booking, etc) Cons: Limited design flexibility, \\\\not so flexible, websites may be slow, bad customer support, limited SEO features Best for: Freelance designers & agencies, In-house design teams, solo entrepreneurs, SMB’s. &#x200B; Webflow Webflow is a no-code platform that lets you build any type of website visually, from marketing landing pages to multi-page corporate websites, gated content websites, blogs, portfolios, and ecommerce stores. It is a powerful and versatile tool that is suitable for a variety of users, including businesses that care about design and want to move quickly. Pros: Absolute design freedom, Robust learning resources, SEO-friendly, scalability, huge template library, large and supportive community, Integrations, Advanced SEO control, custom code, website export, powerful animation engine and CMS. Cons: learning curve, not for massive ecommerce stores, high pricing, Webflow support. Best for: Freelance designers & agencies, In-house design teams, solo entrepreneurs, SMB’s. &#x200B; Bonus tools: Hubspot landing pages — Marketing-oriented landing page builder. Instapage — Great for businesses that use paid advertising, as it offers A/B testing and heatmaps to help you optimize your landing pages for better results Unicorn Platform — SaaS-oriented landing page builder. \---------- Resume: If you have a budget and need a tool with strong design capabilities, scalability, and speed of build, then Webflow is a good choice. Framer is a great option for teams with a single designer, as it is easy for designers to learn and use. Or try Unicorn Platform, if you're running a SaaS business on your own and tight on a budget. No matter which tool you choose, you can create a well-designed website by using the extensive template library that each tool offers. These templates can be customized to fit your specific needs and branding.

#reddit#no-code#tools

reddit

0

1

Medical-Wait-6960•This week

How Our AI Tool Helped a Small Business Save 15% on Annual Expenses

I’m the founder of a startup that built an AI-powered tool to analyze and optimize business finances, with a special focus on small and medium-sized enterprises (SMEs). After months of development and testing, I’m pumped to share our solution with you and get your feedback. Here’s what we do, how it works, and the results we’ve seen. The Problem We Solve Managing a company’s finances, especially for an SME, is often a nightmare: forgotten subscriptions, poorly negotiated supplier contracts, invoices with errors… We’ve all been there. Our tool uses AI to automate expense analysis, spot issues, and suggest practical ways to cut costs—without you having to spend hours on it. How It Works (A Bit of Tech Talk) We built our tool on a multi-agent architecture using the CREWAI framework. Here are the main AI agents we’ve got running: Expense Analyst: Digs through your invoices and categorizes your spending. Compliance Auditor: Checks for errors, fraud, or compliance hiccups. Financial Reporter: Generates clear reports with actionable recommendations. Supplier Negotiator: Hunts down cheaper supplier options using the Serper API and offers negotiation strategies. To hook up your company’s data, we use NEEDLE, a RAG (Retrieval-Augmented Generation) system that lets our agents tap into your info in real time. Everything’s locked down in an SQLite database with end-to-end encryption. Real Results We tested the tool with 10 companies, and here’s what we found: Average cost reduction of 12% in three months. Fraud detection: For example, we flagged 5 shady invoices at one company, saving them €3,000. Supplier optimization: For an SME, we found an energy supplier 20% cheaper, saving them €8,000 a year. A real-world case: A consulting firm with 50 employees ran our tool on their SaaS subscriptions. Outcome? They ditched 3 unused subscriptions, renegotiated 2 contracts, and saved 15% on their annual expenses. Challenges We Tackled No sugarcoating here—it wasn’t a walk in the park. The biggest hurdle? Data security. We’re handling sensitive stuff, so we went all in: End-to-end encryption for everything we process. GDPR compliance with strict rules. Role-based access controls to limit who sees what. Another tough one was integrating with existing systems. We’ve already got connectors for QuickBooks, Xero, and SAP, and we’re working on more. Why It’s Different Sure, there are tools like Expensify or Ramp out there, but our multi-agent approach digs deeper. We deliver super-detailed analysis and precise recommendations. And our knack for finding cheaper suppliers in real time? That’s a game-changer for quick savings.I’m the founder of a startup that built an AI-powered tool to analyze and optimize business finances, with a special focus on small and medium-sized enterprises (SMEs). After months of development and testing, I’m pumped to share our solution with you and get your feedback. Here’s what we do, how it works, and the results we’ve seen. Ask me your technical questions, share your ideas or critiques we’re here to get better! Thanks you for reading this.

#reddit#tool#helped

reddit

0

1

AI_Scout_Official•This week

I run an AI automation agency (AAA). My honest overview and review of this new business model

I started an AI tools directory in February, and then branched off that to start an AI automation agency (AAA) in June. So far I've come across a lot of unsustainable "ideas" to make money with AI, but at the same time a few diamonds in the rough that aren't fully tapped into yet- especially the AAA model. Thought I'd share this post to shine light into this new business model and share some ways you could potentially start your own agency, or at the very least know who you are dealing with and how to pick and choose when you (inevitably) get bombarded with cold emails from them down the line. Foreword Running an AAA does NOT involve using AI tools directly to generate and sell content directly. That ship has sailed, and unless you are happy with $5 from Fiverr every month or so, it is not a real business model. Cry me a river but generating generic art with AI and slapping it onto a T-shirt to sell on Etsy won't make you a dime. At the same time, the AAA model will NOT require you to have a deep theoretical knowledge of AI, or any academic degree, as we are more so dealing with the practical applications of generative AI and how we can implement these into different workflows and tech-stacks, rather than building AI models from the ground up. Regardless of all that, common sense and a willingness to learn will help (a shit ton), as with anything. Keep in mind - this WILL involve work and motivation as well. The mindset that AI somehow means everything can be done for you on autopilot is not the right way to approach things. The common theme of businesses I've seen who have successfully implemented AI into their operations is the willingess to work with AI in a way that augments their existing operations, rather than flat out replace a worker or team. And this is exactly the train of thought you need when working with AI as a business model. However, as the field is relatively unsaturated and hype surrounding AI is still fresh for enterprises, right now is the prime time to start something new if generative AI interests you at all. With that being said, I'll be going over three of the most successful AI-adjacent businesses I've seen over this past year, in addition to some tips and resources to point you in the right direction. so.. WTF is an AI Automation Agency? The AI automation agency (or as some YouTubers have coined it, the AAA model) at its core involves creating custom AI solutions for businesses. I have over 1500 AI tools listed in my directory, however the feedback I've received from some enterprise users is that ready-made SaaS tools are too generic to meet their specific needs. Combine this with the fact virtually no smaller companies have the time or skills required to develop custom solutions right off the bat, and you have yourself real demand. I would say in practice, the AAA model is quite similar to Wordpress and even web dev agencies, with the major difference being all solutions you develop will incorporate key aspects of AI AND automation. Which brings me to my second point- JUST AI IS NOT ENOUGH. Rather than reducing the amount of time required to complete certain tasks, I've seen many AI agencies make the mistake of recommending and (trying to) sell solutions that more likely than not increase the workload of their clients. For example, if you were to make an internal tool that has AI answer questions based on their knowledge base, but this knowledge base has to be updated manually, this is creating unnecessary work. As such I think one of the key components of building successful AI solutions is incorporating the new (Generative AI/LLMs) with the old (programmtic automation- think Zapier, APIs, etc.). Finally, for this business model to be successful, ideally you should target a niche in which you have already worked and understand pain points and needs. Not only does this make it much easier to get calls booked with prospects, the solutions you build will have much greater value to your clients (meaning you get paid more). A mistake I've seen many AAA operators make (and I blame this on the "Get Rich Quick" YouTubers) is focusing too much on a specific productized service, rather than really understanding the needs of businesses. The former is much done via a SaaS model, but when going the agency route the only thing that makes sense is building custom solutions. This is why I always take a consultant-first approach. You can only build once you understand what they actually need and how certain solutions may impact their operations, workflows, and bottom-line. Basics of How to Get Started Pick a niche. As I mentioned previously, preferably one that you've worked in before. Niches I know of that are actively being bombarded with cold emails include real estate, e-commerce, auto-dealerships, lawyers, and medical offices. There is a reason for this, but I will tell you straight up this business model works well if you target any white-collar service business (internal tools approach) or high volume businesses (customer facing tools approach). Setup your toolbox. If you wanted to start a pressure washing business, you would need a pressure-washer. This is no different. For those without programming knowledge, I've seen two common ways AAA get setup to build- one is having a network of on-call web developers, whether its personal contacts or simply going to Upwork or any talent sourcing agency. The second is having an arsenal of no-code tools. I'll get to this more in a second, but this works beecause at its core, when we are dealing with the practical applications of AI, the code is quite simple, simply put. Start cold sales. Unless you have a network already, this is not a step you can skip. You've already picked a niche, so all you have to do is find the right message. Keep cold emails short, sweet, but enticing- and it will help a lot if you did step 1 correctly and intimately understand who your audience is. I'll be touching base later about how you can leverage AI yourself to help you with outreach and closing. The beauty of gen AI and the AAA model You don't need to be a seasoned web developer to make this business model work. The large majority of solutions that SME clients want is best done using an API for an LLM for the actual AI aspect. The value we create with the solutions we build comes with the conceptual framework and design that not only does what they need it to but integrates smoothly with their existing tech-stack and workflow. The actual implementation is quite straightforward once you understand the high level design and know which tools you are going to use. To give you a sense, even if you plan to build out these apps yourself (say in Python) the large majority of the nitty gritty technical work has already been done for you, especially if you leverage Python libraries and packages that offer high level abstraction for LLM-related functions. For instance, calling GPT can be as little as a single line of code. (And there are no-code tools where these functions are simply an icon on a GUI). Aside from understanding the capabilities and limitations of these tools and frameworks, the only thing that matters is being able to put them in a way that makes sense for what you want to build. Which is why outsourcing and no-code tools both work in our case. Okay... but how TF am I suppposed to actually build out these solutions? Now the fun part. I highly recommend getting familiar with Langchain and LlamaIndex. Both are Python libraires that help a lot with the high-level LLM abstraction I mentioned previously. The two most important aspects include being able to integrate internal data sources/knowledge bases with LLMs, and have LLMs perform autonomous actions. The two most common methods respectively are RAG and output parsing. RAG (retrieval augmented Generation) If you've ever seen a tool that seemingly "trains" GPT on your own data, and wonder how it all works- well I have an answer from you. At a high level, the user query is first being fed to what's called a vector database to run vector search. Vector search basically lets you do semantic search where you are searching data based on meaning. The vector databases then retrieves the most relevant sections of text as it relates to the user query, and this text gets APPENDED to your GPT prompt to provide extra context to the AI. Further, with prompt engineering, you can limit GPT to only generate an answer if it can be found within this extra context, greatly limiting the chance of hallucination (this is where AI makes random shit up). Aside from vector databases, we can also implement RAG with other data sources and retrieval methods, for example SQL databses (via parsing the outputs of LLM's- more on this later). Autonomous Agents via Output Parsing A common need of clients has been having AI actually perform tasks, rather than simply spitting out text. For example, with autonomous agents, we can have an e-commerce chatbot do the work of a basic customer service rep (i.e. look into orders, refunds, shipping). At a high level, what's going on is that the response of the LLM is being used programmtically to determine which API to call. Keeping on with the e-commerce example, if I wanted a chatbot to check shipping status, I could have a LLM response within my app (not shown to the user) with a prompt that outputs a random hash or string, and programmatically I can determine which API call to make based on this hash/string. And using the same fundamental concept as with RAG, I can append the the API response to a final prompt that would spit out the answer for the user. How No Code Tools Can Fit In (With some example solutions you can build) With that being said, you don't necessarily need to do all of the above by coding yourself, with Python libraries or otherwise. However, I will say that having that high level overview will help IMMENSELY when it comes to using no-code tools to do the actual work for you. Regardless, here are a few common solutions you might build for clients as well as some no-code tools you can use to build them out. Ex. Solution 1: AI Chatbots for SMEs (Small and Medium Enterprises) This involves creating chatbots that handle user queries, lead gen, and so forth with AI, and will use the principles of RAG at heart. After getting the required data from your client (i.e. product catalogues, previous support tickets, FAQ, internal documentation), you upload this into your knowledge base and write a prompt that makes sense for your use case. One no-code tool that does this well is MyAskAI. The beauty of it especially for building external chatbots is the ability to quickly ingest entire websites into your knowledge base via a sitemap, and bulk uploading files. Essentially, they've covered the entire grunt work required to do this manually. Finally, you can create a inline or chat widget on your client's website with a few lines of HTML, or altneratively integrate it with a Slack/Teams chatbot (if you are going for an internal Q&A chatbot approach). Other tools you could use include Botpress and Voiceflow, however these are less for RAG and more for building out complete chatbot flows that may or may not incorporate LLMs. Both apps are essentially GUIs that eliminate the pain and tears and trying to implement complex flows manually, and both natively incoporate AI intents and a knowledge base feature. Ex. Solution 2: Internal Apps Similar to the first example, except we go beyond making just chatbots but tools such as report generation and really any sort of internal tool or automations that may incorporate LLM's. For instance, you can have a tool that automatically generates replies to inbound emails based on your client's knowledge base. Or an automation that does the same thing but for replies to Instagram comments. Another example could be a tool that generates a description and screeenshot based on a URL (useful for directory sites, made one for my own :P). Getting into more advanced implementations of LLMs, we can have tools that can generate entire drafts of reports (think 80+ pages), based not only on data from a knowledge base but also the writing style, format, and author voice of previous reports. One good tool to create content generation panels for your clients would be MindStudio. You can train LLM's via prompt engineering in a structured way with your own data to essentially fine tune them for whatever text you need it to generate. Furthermore, it has a GUI where you can dictate the entire AI flow. You can also upload data sources via multiple formats, including PDF, CSV, and Docx. For automations that require interactions between multiple apps, I recommend the OG zapier/make.com if you want a no-code solution. For instance, for the automatic email reply generator, I can have a trigger such that when an email is received, a custom AI reply is generated by MyAskAI, and finally a draft is created in my email client. Or, for an automation where I can create a social media posts on multiple platforms based on a RSS feed (news feed), I can implement this directly in Zapier with their native GPT action (see screenshot) As for more complex LLM flows that may require multiple layers of LLMs, data sources, and APIs working together to generate a single response i.e. a long form 100 page report, I would recommend tools such as Stack AI or Flowise (open-source alternative) to build these solutions out. Essentially, you get most of the functions and features of Python packages such as Langchain and LlamaIndex in a GUI. See screenshot for an example of a flow How the hell are you supposed to find clients? With all that being said, none of this matters if you can't find anyone to sell to. You will have to do cold sales, one way or the other, especially if you are brand new to the game. And what better way to sell your AI services than with AI itself? If we want to integrate AI into the cold outreach process, first we must identify what it's good at doing, and that's obviously writing a bunch of text, in a short amount of time. Similar to the solutions that an AAA can build for its clients, we can take advantage of the same principles in our own sales processes. How to do outreach Once you've identified your niche and their pain points/opportunities for automation, you want to craft a compelling message in which you can send via cold email and cold calls to get prospects booked on demos/consultations. I won't get into too much detail in terms of exactly how to write emails or calling scripts, as there are millions of resources to help with this, but I will tell you a few key points you want to keep in mind when doing outreach for your AAA. First, you want to keep in mind that many businesses are still hesitant about AI and may not understand what it really is or how it can benefit their operations. However, we can take advantage of how mass media has been reporting on AI this past year- at the very least people are AWARE that sooner or later they may have to implement AI into their businesses to stay competitive. We want to frame our message in a way that introduces generative AI as a technology that can have a direct, tangible, and positive impact on their business. Although it may be hard to quantify, I like to include estimates of man-hours saved or costs saved at least in my final proposals to prospects. Times are TOUGH right now, and money is expensive, so you need to have a compelling reason for businesses to get on board. Once you've gotten your messaging down, you will want to create a list of prospects to contact. Tools you can use to find prospects include Apollo.io, reply.io, zoominfo (expensive af), and Linkedin Sales Navigator. What specific job titles, etc. to target will depend on your niche but for smaller companies this will tend to be the owner. For white collar niches, i.e. law, the professional that will be directly benefiting from the tool (i.e. partners) may be better to contact. And for larger organizations you may want to target business improvement and digital transformation leads/directors- these are the people directly in charge of projects like what you may be proposing. Okay- so you have your message, and your list, and now all it comes down to is getting the good word out. I won't be going into the details of how to send these out, a quick Google search will give you hundreds of resources for cold outreach methods. However, personalization is key and beyond simple dynamic variables you want to make sure you can either personalize your email campaigns directly with AI (SmartWriter.ai is an example of a tool that can do this), or at the very least have the ability to import email messages programmatically. Alternatively, ask ChatGPT to make you a Python Script that can take in a list of emails, scrape info based on their linkedin URL or website, and all pass this onto a GPT prompt that specifies your messaging to generate an email. From there, send away. How tf do I close? Once you've got some prospects booked in on your meetings, you will need to close deals with them to turn them into clients. Call #1: Consultation Tying back to when I mentioned you want to take a consultant-first appraoch, you will want to listen closely to their goals and needs and understand their pain points. This would be the first call, and typically I would provide a high level overview of different solutions we could build to tacke these. It really helps to have a presentation available, so you can graphically demonstrate key points and key technologies. I like to use Plus AI for this, it's basically a Google Slides add-on that can generate slide decks for you. I copy and paste my default company messaging, add some key points for the presentation, and it comes out with pretty decent slides. Call #2: Demo The second call would involve a demo of one of these solutions, and typically I'll quickly prototype it with boilerplate code I already have, otherwise I'll cook something up in a no-code tool. If you have a niche where one type of solution is commonly demanded, it helps to have a general demo set up to be able to handle a larger volume of calls, so you aren't burning yourself out. I'll also elaborate on how the final product would look like in comparison to the demo. Call #3 and Beyond: Once the initial consultation and demo is complete, you will want to alleviate any remaining concerns from your prospects and work with them to reach a final work proposal. It's crucial you lay out exactly what you will be building (in writing) and ensure the prospect understands this. Furthermore, be clear and transparent with timelines and communication methods for the project. In terms of pricing, you want to take this from a value-based approach. The same solution may be worth a lot more to client A than client B. Furthermore, you can create "add-ons" such as monthly maintenance/upgrade packages, training sessions for employeees, and so forth, separate from the initial setup fee you would charge. How you can incorporate AI into marketing your businesses Beyond cold sales, I highly recommend creating a funnel to capture warm leads. For instance, I do this currently with my AI tools directory, which links directly to my AI agency and has consistent branding throughout. Warm leads are much more likely to close (and honestly, much nicer to deal with). However, even without an AI-related website, at the very least you will want to create a presence on social media and the web in general. As with any agency, you will want basic a professional presence. A professional virtual address helps, in addition to a Google Business Profile (GBP) and TrustPilot. a GBP (especially for local SEO) and Trustpilot page also helps improve the looks of your search results immensely. For GBP, I recommend using ProfilePro, which is a chrome extension you can use to automate SEO work for your GBP. Aside from SEO optimzied business descriptions based on your business, it can handle Q/A answers, responses, updates, and service descriptions based on local keywords. Privacy and Legal Concerns of the AAA Model Aside from typical concerns for agencies relating to service contracts, there are a few issues (especially when using no-code tools) that will need to be addressed to run a successful AAA. Most of these surround privacy concerns when working with proprietary data. In your terms with your client, you will want to clearly define hosting providers and any third party tools you will be using to build their solution, and a DPA with these third parties listed as subprocessors if necessary. In addition, you will want to implement best practices like redacting private information from data being used for building solutions. In terms of addressing concerns directly from clients, it helps if you host your solutions on their own servers (not possible with AI tools), and address the fact only ChatGPT queries in the web app, not OpenAI API calls, will be used to train OpenAI's models (as reported by mainstream media). The key here is to be open and transparent with your clients about ALL the tools you are using, where there data will be going, and make sure to get this all in writing. have fun, and keep an open mind Before I finish this post, I just want to reiterate the fact that this is NOT an easy way to make money. Running an AI agency will require hours and hours of dedication and work, and constantly rearranging your schedule to meet prospect and client needs. However, if you are looking for a new business to run, and have a knack for understanding business operations and are genuinely interested in the pracitcal applications of generative AI, then I say go for it. The time is ticking before AAA becomes the new dropshipping or SMMA, and I've a firm believer that those who set foot first and establish themselves in this field will come out top. And remember, while 100 thousand people may read this post, only 2 may actually take initiative and start.

#reddit#automation#agency

reddit

0

-1

Neuralearthnet•This week

Giving away AI Startup Ideas - but no traction? What am I doing wrong?

Hi All, I think with AI, tech will be democratized. I am fortunate and working on a new AI company with my technical partners but many do not have tech skills and don't know where to start. So I'm working on giving away ideas that can be built easily using no-code or low-code. However, not sure if I’m presenting these ideas wrong or no one really wants to build it. I mean it's no-code, but doesn't mean no-work. Startups take a lot of time and energy, no matter what. So far I've shared the following ideas and wanted to get your thoughts on it. Is it my presentation that's bad or the ideas. LOL. Honest feedback appreciated. You can see the a sample of presentation here on Instagram. https://www.instagram.com/p/C69xWvgvPAT/ and here are the ideas I've shared thus far: AI Coin Maker AI ADHD Holo device (a-la Humane or Rabbit AI but with a focus on ADHD) OnlyAIFans - OnlyFans but only using AI models AI Election Predictor and Poll Maker AI Real-Time Gen Z Translator AI Color Analysis for Fashion Thoughts?

#reddit#giving#away

reddit

0

1

SnooPears4795•This week

Unbiased opinion - Ideas

Hi, I’m currently looking to set up along site my full time job. I’m working away so have spare time mid week evenings to get cracking! If anyone has any other ideas which would link up with my interests please let me know. Note: I set up an airconditioning company which didn’t go to plan as I was just not passionate enough to chase sales/grow the company. Details Capital: I could invest upto 1k a month would prefer less Location: would prefer remote but the below ideas are all possible from my hotel room. Strengths: work well under pressure, technical minded, problem solving Weaknesses: can be lazy if not passionate, organisation, confidence Interests: Music, guitars, tech, coding, beer, motorbikes Experience: 12 years in railway electrical roles, coding bootcamp Ideas Idea: Guitar Electronics (pedals) Pros: cheap to start Enjoy building Creative Design work Cool field Cons: Time consuming Not much profit Scalability Competition is cheap Idea: Project management app/document selection Pros: Experienced in field Relatively quick if excel based Could charge subscription Contacts in industry Expensive if app based Make once sell multiple Remote Small overheads Cons: Not as fun as others learn new language? Limited market Other competition already good (apps) Idea: YouTube - mysteries, interesting topics Pros: Free to startup Enjoy researching Build community leading to other online projects Can voice over/AI No need to have cam Improve confidence Cons: Returns will take a while Get better at video editing Overcome speaking No overheads (have equipment) Time/money slow at start Idea: Railway Electrical Book/Course Pros: Throughly experienced Small market Niche - good money if can get sales Have to learn course software Contacts in field Create once Cons: Not as passionate as other ideas Amount of interest (possibly get other fields electricians involved?) Expensive to make?

#reddit#unbiased#opinion

reddit

0

1

CerealEntre•This week

Legal Skim: "We make it easy for anyone to read legal contracts"

The Problem Nobody has the time to read contracts, so nobody reads them Lawyers cost to much money to simply "review" a contract for you The Solution An AI Software solution that reads your contract for you* and then highlights the important clauses to read, and shares helpful insights into what the "legal jargon" definitions are This would be a product built for "the everyman" Not for legal teams, but for your everyday, average Joe. I imagine the review highlights would be color-coded, with pastel and "happy feel" colors This would be for two reasons: To make it easy to read and immediately know what's important or unimportant To provide a comforting feeling to the stress of reading a contract that you don't understand I imagine the colors using the "Green, Yellow, Red" system Green colors mean mean there's no concern. If you skip this, no biggie Yellow colors mean you might want to take a closer look Red means if you skip this, you'll likely get screwed Slogan "We make it easy for anyone to read legal contracts" Competitor Analysis Ontra.com "The complete solution for negotiating and managing routine contracts." It looks like this is mostly for actual legal teams, not for consumers Delino.io "Delino’s automated contract review platform empowers you to manage the inherent risk in business contracts, so you can accelerate growth." This also looks like it's mostly actual legal teams, not for consumers LegalZoom.com This is a standard "Lawyer Review", not a software solution &#x200B; If you vote "This already exists", feel free to comment what company so I can add them to the competitor analysis 🙏 View Poll

#reddit#legal#skim:

reddit

0

1

dojagroup•This week

We just pivoted our entire business to AI and No-Code! AMA!

I'm new to Reddit but keen to understand how this platform works and how the community interacts. I'm an ex-Amazon consultant and I recently sold my logistics company after automating a lot of the processes with no-code and AI, to move into the digital services market to sell Amazon account management, we also raised a 6-figure funding round. It quickly became obvious that we were able to use our no-code learnings to automate the agency business model and we saved about 80% on our costs in comparison to the traditional business model functions. Our clients quickly wanted us to sell in our workflow solutions instead of advertising (lol), so we pivoted the business hard to sell in AI workflows and no-code, and its going extremely well. My social media strategy is quite literally to give away our learnings and value as we believe the market is growing so fast there is space for anyone who's interested in what we're doing. I'm pushing out a video a day that talks to how we are automating specific business functions in businesses that allow us to sell this into businesses. Is there an appitite for this content to be shared here? The content is mainly shortform but I'd be happy to do some longer form explainer videos for anyone that really wants to learn the detail. Let me know, also ask me anything and I'll be happy to knowledge share. Cheers,Dan

#reddit#just#pivoted

reddit

0

1

Due_Cryptographer461•This week

Interview with founder of ReadyPlayerMe (raised $70M+ from a16z)

Thanks to everyone who replied to my previous post with the questions you had for Rainer, I added some of them into this interview. I’m Nikita of Databas3 , and that’s my first interview in a series where I’m learning more about the journey of the best tech and web3 founders. Would appreciate your feedback and suggestions for the next guest! Nikita: Let’s begin with a brief introduction. Can you share a bit about yourself and how the business started? Rainer: I’m Rainer, the CTO of ReadyPlayerMe. Our journey began in 2013 with four co-founders. Over the years, our focus has shifted mainly around our product’s evolution, but our core idea always revolved around virtual actors or virtual people. Our initial venture was into hardware. We created the first full-body scanner in the Nordics, a significant step in photogrammetry. This led us to develop the Luna Scanner, a three-meter tall structure designed to capture facial features and likenesses. When Facebook acquired Oculus in 2014, we foresaw the potential of VR and virtual worlds, especially in social experiences. Nikita: Interesting. How did you move on from there? Rainer: Recognizing the limitations of hardware, we transitioned into software. Our early scanner designs had limitations in scalability. For example, our three-meter tall scanner wasn’t a feasible solution for scanning millions of people. So, we leveraged the datasets from our initial projects and designed a mobile version, making facial scanning as easy as using your phone. Around 2015, this was a new territory, as facial scanning wasn’t a mainstream application. Nikita: What were the early applications of these scanned models? Rainer: In the beginning, we focused on 3D printed figurines from full-body scans. However, as we shifted to facial scanning, we licensed our technology to gaming companies, collaborating with giants like Wargaming and Tencent. We even ventured into virtual fittings with H&M. Each collaboration was custom-tailored, blending our technology with their systems. This model made us cash flow positive. Nikita: So this was the beginning of your foray into the gaming industry? Rainer: Precisely. The demand from gaming companies was substantial. As we built custom solutions for these enterprises, we saw a bigger potential. While our cash flow was positive, we realized the challenge of scaling through exclusive enterprise deals. We envisioned our avatar creation tech reaching indie games and beyond. Nikita: And that led to the birth of ReadyPlayerMe? Rainer: Exactly. Once we understood our market direction, we quickly developed the first iteration of ReadyPlayerMe as a web-based experience, emphasizing easy integration for game developers. The initial version was a character builder, allowing users to personalize their avatars, which many adopted for their social media profiles. Our goal was to create avatars that users could connect with and use across various platforms. Instead of licensing our technology, we offered it for free to everyone. As ReadyPlayerMe gained traction, especially in VR applications, we secured funding to further our mission. Nikita: Your growth seems swift and organic. Were there any challenges? Rainer: Our focus on easy integration significantly fueled our adoption. Pairing that with personalized avatars resonated well with our audience. But like any venture, we’ve faced our share of challenges and have always aimed to evolve and better our offerings. The rapid growth in Web3 projects and virtual worlds made personalization and customization more important. With the NFT boom, you could add utility by allowing access to selected collections. This played into web-based games and metaverse applications. The shift towards Web3 and personalization provided a significant tailwind for us. Many used our characters as profile pictures on social media. Nikita: I’ve heard from other founders that a16z really values viral marketing. Was this one reason they wanted to invest in your project? How was the process with them? Rainer: When a16z reached out, it felt like a natural fit. We wanted investors who understood the gaming space. Our main market is Web3, but we’re exploring the top games market. Their expertise in gaming was invaluable. They’ve been very supportive throughout. We were fortunate to be on their radar. Nikita: So your early growth and organic traction played a role in attracting investors? Rainer: Definitely. Early product growth and the potential future trajectory were essential in our discussions. Nikita: As the CTO, you must have faced challenges. Can you speak about the tech side and its evolution? Rainer: The early version of our platform was built by in-house engineers. As we grew, we had to adapt to increasing complexities and ensure we had the right team to execute our vision. My role often shifted between product management and tech, depending on the need. Nikita: It sounds like the startup environment remains strong within your company. Rainer: Absolutely. We’re all committed, hands-on, and working towards building the best product. Nikita: You mentioned the team earlier. How many people are in your team now? Rainer: We have 70 people, with about half in product and engineering. Nikita: And did you hire the tech team? Rainer: We brought on a head of engineering at the beginning of this year. He’s been instrumental in scaling the engineering organization, from increasing the headcount to refining engineering processes. We’ve recently reorganized into domain-specific teams. As the team grows, regular reorganization ensures we focus on delivering specific customer value. Every stage requires attention to the team’s composition to ensure efficient delivery. Nikita: Any advice for founders just starting with their first startup? Rainer: Focus on customer value, no matter how niche it might seem initially. Begin with a specific problem and solution, then expand from there. You don’t need a massive project right away. Begin small, prove the concept, and scale from there. Nikita: You’ve mentioned your love for books and podcasts. Any recommendations? Rainer: For startups, “High Growth Handbook” and “Lean Startup” are must-reads. “Working Backwards” offers insights into Amazon’s customer-centric approach. For podcasts, I listen to “Rework,” “Lenny’s Podcast,” and “Huberman Lab.” Nikita: All of us have some side project ideas from time to time. How do you handle these when managing a big project? Rainer: Over the years, I’ve built various side projects. Some are small applications to solve immediate problems, like a menu bar app for AirPods which made it to No. 1 on Product Hunt, and was nominated for Golden Kitty Award. I sometimes delve into 3D and AI, merging them for technical demos. I keep a list of ideas and pick from them as the urge arises. Nikita: Any final thoughts or advice? Rainer: As you scale, do so with clarity. Avoid scaling just for external appeal. Always hire when there’s genuine need, not just for the sake of expansion. It helps in staying lean and focused.

#reddit#interview#founder

reddit

0

1

torrentialdownpour34•This week

Seeking Feedback on Business Idea: AI-Powered Business Partner Matching Platform

Hey everyone, I've been toying with an idea for a new business venture and I'd love to get some feedback and insights from this community. The Idea: I'm considering building a business platform that utilizes AI to match potential business partners. Whether you're a startup looking for a co-founder, a company seeking strategic partnerships, or an investor searching for promising ventures, this platform would help connect you with compatible partners based on your specific needs, goals, and preferences. How It Works: Users would create detailed profiles outlining their business objectives, industry expertise, skills, and what they're looking for in a partner. The AI algorithm would then analyze this data to identify compatible matches, taking into account factors like complementary skill sets, shared values, and mutual goals. The platform would provide users with a curated list of potential partners, along with insights and recommendations to facilitate meaningful connections. Key Features: Comprehensive Profiles: Users can create detailed profiles highlighting their background, experience, and what they bring to the table. AI Matching Algorithm: The platform's AI algorithm would use advanced data analysis techniques to generate accurate partner recommendations. Communication Tools: Built-in messaging and video conferencing tools would enable seamless communication between potential partners. Feedback and Ratings: Users can leave feedback and ratings for their matches, helping to build trust and credibility within the community. Resource Hub: Access to resources, articles, and guides on partnership development, negotiation strategies, and other relevant topics. Why It's Needed: Finding the right business partner can be a daunting task, often relying on personal networks or serendipitous encounters. By harnessing the power of AI, this platform aims to streamline the partner matching process, saving time and increasing the likelihood of finding compatible collaborators. Looking for Feedback: Before diving headfirst into this venture, I wanted to reach out to this community to gather some feedback: Does this idea resonate with you? Why or why not? Are there any existing platforms or services that offer similar functionalities? What features would be essential for you as a user? Any potential challenges or concerns you foresee with this concept? I'm eager to hear your thoughts and suggestions. Thanks in advance for your input!

#reddit#seeking#feedback

reddit

0

1

rasvi786•This week

Founder Pitch: AI Agent for Simplifying Public Cloud Management

Video to understand : https://youtu.be/9ocUjlUrU\w?si=S0ETDbKSdJqlVDyg Are You Ready to Redefine Cloud Management with AI? Imagine an intelligent AI agent that transforms the complexity of managing public cloud infrastructure into simple, natural language commands. No more navigating through endless configurations or deciphering technical documentation—our AI agent is here to revolutionize the way organizations interact with cloud platforms. About the Project We’re building an AI-powered agent designed to handle public cloud management tasks seamlessly. Whether you’re setting up your organization’s cloud foundation or deploying complex workloads, this AI agent makes it as easy as having a conversation. What Can the AI Agent Do? Cloud Foundation Setup: Example: “Please set up a cloud foundation blueprint for my organization on Google Cloud.”* The AI agent will ask key questions (e.g., organization ID) and guide you through authentication. Once authorized, it sets up the foundation using GCP APIs. Workload Deployment: Example: “Spin up a GKE cluster for me.”* The agent will ask for necessary details (e.g., number of nodes, VPC info), authenticate, and deploy the cluster in minutes. Security and Compliance Validation: Example: “Validate my organization’s cloud setup and check for security vulnerabilities.”* The agent audits your setup, identifies potential risks, and provides actionable insights. Current Progress We’ve developed a working prototype that integrates with major cloud providers like Google Cloud. The AI agent can already: Authenticate with cloud APIs Execute foundational tasks such as setting up organizations and spinning up clusters Perform initial security validations Who I’m Looking For I’m searching for a co-founder with enterprise sales experience and a strategic vision to grow our user base. You will be instrumental in helping us: Build relationships with companies willing to pilot our product Develop go-to-market strategies for enterprise adoption Identify opportunities for partnerships with cloud service providers Your Role As a co-founder, you’ll lead efforts to: Secure Pilot Programs: Identify and onboard enterprises for product trials to gather feedback and refine the solution. Drive Growth: Develop scalable strategies to grow our user base across industries. Market Positioning: Work with me to define our unique value proposition and establish thought leadership in the cloud management space. My Background I bring over a decade of experience in tech, with a strong focus on software engineering and infrastructure. My contributions so far include: Developing the core AI engine and cloud integrations Designing workflows that simplify complex cloud tasks Why Join This Project? Revolutionize Cloud Management: Be part of a project that will redefine how organizations interact with public clouds. Tackle Challenging Problems: Work at the cutting edge of AI and cloud computing. High Growth Potential: Join an industry projected to grow exponentially as enterprises embrace AI-driven automation. Build a Company from Scratch: Shape the product, team, and culture as we grow together. What’s Next? Our immediate priorities include: Expanding the AI agent’s capabilities to support multi-cloud setups. Conducting pilot programs with enterprise clients. Iterating on the product based on real-world feedback. What We Need to Succeed Expertise in enterprise sales and partnerships A deep understanding of enterprise challenges and cloud adoption trends A shared passion for leveraging AI to solve complex problems Let’s work together to build the future of cloud management. If you’re excited about this vision and bring the expertise we need, I’d love to connect and discuss how we can take this project to the next level.

#reddit#founder#pitch:

reddit

0

0

tomorrow_needs_you•This week

Subscription-Based Tool for Multi-Step Funnels Behind Landing Pages

Hey everyone, I recently developed a tool for a client who needed to implement multi-step funnels behind their Unbounce landing pages, but couldn't find an existing service that fit their needs. Essentially, they required a way to create click-through pages that gather various data points from leads, which Unbounce currently doesn't support. Here’s what the tool does: Routing Leads Through Funnels: It directs leads through sequential pages based on a configurable backend, optimizing the lead qualification process. Data Validation and Recording: The tool actively monitors and validates lead data across specified fields, ensuring accuracy and completeness. The setup is straightforward—simply embed a JavaScript script and add a few attributes and CSS classes to your funnel pages, all of which are designed in pure HTML. This approach empowers HTML designers to create or modify funnels without needing programming skills, opening the door for potential AI-assisted design capabilities in the future. I’m considering developing this tool further into a SaaS model if there’s enough interest from the community. Would this be something your company or clients could benefit from? Your feedback would be greatly appreciated! Thank you!

#reddit#subscription-based#tool

reddit

0

1

gutoarraes•This week

Just another AI business idea

Hi everyone, I have been tinkering with the idea of creating an AI chatbot for folks to add to their websites (I know, I know... extremely creative on my part.). I wanted to check for feedback from businesses who have hired this type of service in the past and see if you saw value in it. There are a few reasons I'm looking to build it: \* Worldwide client reach \* Low cost to start since I can code the product \* There is momentum given the AI hype \* In my regular job, AI was implemented at the home page and it solves around 40% of customer inquiries. On that last point, I work at a large tech company where I believe there is too much information to sif though before you can find your answer in their website. Most companies would be a lot smaller, so I am not sure if this would be a good opportunity for those cases too. I have coded a chatbot that can be added to people's websites, but I still need to improve the frontend and make the model trainable for each different use-case. I am not working with anyone else, and been able to do everything by myself so far, even though I'm a junior level developer. I appreciate any/all feedback you can give around this.

#reddit#just#another

reddit

0

1

Time_Inspector1831•This week

Starting a new consultancy focused on helping small companies become more digital with their recruitment practices.

I am based in the UK. Approaching 20 years' recruitment experience in agency and in house. I know what good looks like. Currently I am head of talent and have helped my company increase headcount by over 200% in 3 years in a very cost effective way. I am considering starting my own consultancy business focused on small companies who may have no in-house recruitment teams. The objective is to create the infrastructure for them to be able to grow and be self sufficient thus reducing agency spend and enabling them to become more digital. For example: Building online presence/careers page Implementing a new ATS Developing an EVP Introducing more data driven decision making Competitor mapping Standardising process Question banks Glassdoor elevation Streamlining ED&I Interview training Using AI practically GDPR The list goes on... Do you think there is an appetite for this sort of thing with companies less than 100? By digitilising the process, it will enhance compliance processes, save time and money.

#reddit#starting#consultancy

reddit

0

1

thewhitelynx•This week

Idea feedback: AI-native self-improvement & wellness

Hello redditors! Thesis: We're all trying to live our best lives and many of us try to leverage technology to become better faster and easier. I’m trying to build a company that builds an AI-native solution for self-improvement. My thesis is that AI is an incredibly powerful tool for solving problems, particularly in programming and generally life - but ChatGPT isn't really designed to be your long-term 'coach'. It's great for handling specific tasks, answering questions, doing research, etc. - but it's memory and UX isn't optimized around things like behavior change, mental health support, and long-term personal life planning I believe my core problems (which I think are shared by many) are: 1) Staying motivated - it's easy to lose motivation when progress isn't immediately apparent, there are setbacks, etc. 2) Self-doubt - it makes me question myself and waste time wondering if I'm the right person to be doing this, if the idea is too broad, etc. Some of this is good - but a lot of it just makes me less effective 3) Staying on Track - I start a thing, but then gradually pivot a million different directions. This may be a touch of ADHD. I find that I'll have a long-term goal (e.g. launching a successful business), but I'll tend to wonder a lot in the process of executing over weeks and months. Staying on track just feels suprisingly difficult. I do create TODO lists and have a Kanban board I’m considering a bunch of features and have built a version focused more specifically towards mental health which implements a few: \----- • Guided Journaling Guided journaling prompts to facilitate deeper reflection • Specialist AI Coaches Personalized, expert AI coaching for your specific area of focus and goals For startup, marketing, life, fashion, whatever you want. • Goal Tracking Define, track, and achieve your goals • Behavior Change & Habit Formation Leverage the science of behavior change to help you make lasting changes in your life • Mood tracking Track and improve your mood leveraging science-backed techniques • Areas for growth Identify and develop your strengths and manage your weaknesses • Insight reports Get personalized insights into your cognitive and behavioral patterns • Inspirational Quotes Stay motivated with curated daily quotes relevant to your journey • Gamification of Growth & Mood Turn your mental health journey into a game and earn rewards for your progress \---- Would love thoughts on the idea, and feedback - and if anyone is interested in being a design partner / early user, I'd love to chat in greater depth 1:1!

#reddit#idea#feedback:

reddit

0

1

Ambitious-Waltz6119•This week

Exploring Manufacturing Automation & IoT Services: Demand Check

Hey everyone! I run a tech consulting business and I'm looking to branch out into helping smaller manufacturers automate their processes and implement IoT/AI solutions. I just wrapped up a cool project with my buddy who owns a food manufacturing company - we managed to streamline a bunch of his micro processes and the results were pretty impressive! Now I'm curious - is this something other manufacturing businesses actually need? Would love to hear from folks who've either hired someone for this kind of work or provided these services themselves. Any insights on whether there's real demand out there? Thanks in advance for any thoughts or experiences you can share!

#reddit#exploring#manufacturing

reddit

0

0

g-rodz•This week

I wanna sell access to business ideas extracted from real life problems and discussions

How cool would it be if there was a hub for aspirant entrepreneurs to buy a shortcut for high demand business ideas, or sometimes high demand unsolved business problems? It’s stupid to ask AI to generate business idea, but it’s certainly possible to ask for an analysis over discussions. I built a webscraper that’s fetching over several forums looking for 100% public information, including Reddit, extracting business ideas from people discussing about real life situations, or simply problems. Many entrepreneurs find they niche business ideas by reading Reddit and interpreting what the post and comments mean. So instead of generating business opportunities using AI, I’m extracting them from conversations that people usually suggest to each other and could easily turn into a company or business, but people are busy and end up screwing up in their own solutions and never consider launching them.

#reddit#wanna#sell

reddit

0

1

luxendary•This week

Need help with the growth I couldn't handle

Calling all innovators, dreamers, and disruptors! &#x200B; We're pioneering a new frontier in the world of manufacturing with our vision: "Text to Product". I'm seeking individuals passionate about AI, manufacturing, efficiency and automation. While we can't promise immediate financial rewards, we're offering equity in a venture that's setting out to redefine the way things are made and sold. If the prospect of revolutionizing the future of humanity excites you, we'd love to hear from you. &#x200B; &#x200B; P.S. I realized that I can't always use "brute force" for solving problems, so seeking "the right connections" (seasoned entrepreneurs, advisors). Here's the TLDR version of my story: Started a company with ex-boss, bought him out, grinded for 2 years, found a way to 1000x the orders.* Went full speed for a month, got overwhelmed, barely kept up with half the demand (with that production process).* Focused on this one "platform", shipped hundreds of thousands of units in one holiday season.* Next quarter "the platform" returned about 85% of products as "overstock", demanded money back, made legal threats.* I told them that I will go to court and they stopped bothering me.* Then Covid + Nasty divorce which made me put a pause to regroup.* 2 years later, with 2x the production capacity and after relocating to a friendlier state (from NYC to MIA) I'm ready to relaunch (with a clear head, knowledge of fast growth and what to avoid).*

#reddit#need#help

reddit

0

1

SoffrontHQ•This week

Marketing Automation Trends To Look For in 2018

As the new year is upon us, marketing automation software and AI continue to soar in the CRM Industry. In 2018, keep an eye out for these constraints as they will revolutionize marketing, keeping customer engagement in the forefront. Customer experience: In 2018, customer experience will be instrumental in driving the marketing automation software market. The recent shift in the trends of markets has forced the companies to develop new ways of engaging the customer and giving them an enriched experience. As new strategies are deployed to the target customer, shorter content, full streaming videos or infographics will be preferred. Content marketing automation: After the content is finished, it is only left to communicate it to the right channels, at the right time. But in order to have an edge in the regularity of publications and efficiency, companies are opting for automation tools to communicate and promote content through various channels. The results are obvious, not only you gain efficiency but this method helps in reaching and retaining those group of individuals whose appointments happen on a daily basis thus putting your company in the expert bracket. Chatbots: Chatbots are perfect examples of online CRM applications impacting the business in 2018. These intelligent programs have the ability to comprehend, analyze and then formulate an adequate reply to customer queries in real time. Ever since Facebook messenger opened its API, the ease and simplicity of installing these on CMS have inspired a lot of companies to implement it. In the future, their challenge will be to innovate customer engagement providing a better user experience rather than mere customer service using customer data. Further expectations will shape up in the form of artificial empathy where they will be able to connect to the customer emotionally and listen to their wanting. This will automate customer expectations and enable humans to focus on their “real” customer holding strong added value. The future looks bright with thought-leaders pioneering digital transformation and paving the way to tremendous opportunities. If they can manage to anticipate the consequence of the current mutations, companies will evolve and marketing resources will experience growth like never before.

#reddit#marketing#automation

reddit

0

1

dojagroup•This week

We just pivoted our entire business to AI and No-Code! AMA!

I'm new to Reddit but keen to understand how this platform works and how the community interacts. I'm an ex-Amazon consultant and I recently sold my logistics company after automating a lot of the processes with no-code and AI, to move into the digital services market to sell Amazon account management, we also raised a 6-figure funding round. It quickly became obvious that we were able to use our no-code learnings to automate the agency business model and we saved about 80% on our costs in comparison to the traditional business model functions. Our clients quickly wanted us to sell in our workflow solutions instead of advertising (lol), so we pivoted the business hard to sell in AI workflows and no-code, and its going extremely well. My social media strategy is quite literally to give away our learnings and value as we believe the market is growing so fast there is space for anyone who's interested in what we're doing. I'm pushing out a video a day that talks to how we are automating specific business functions in businesses that allow us to sell this into businesses. Is there an appitite for this content to be shared here? The content is mainly shortform but I'd be happy to do some longer form explainer videos for anyone that really wants to learn the detail. Let me know, also ask me anything and I'll be happy to knowledge share. Cheers,Dan

#reddit#just#pivoted

reddit

0

1

rasvi786•This week

Founder Pitch: AI Agent for Simplifying Public Cloud Management

Video to understand : https://youtu.be/9ocUjlUrU\w?si=S0ETDbKSdJqlVDyg Are You Ready to Redefine Cloud Management with AI? Imagine an intelligent AI agent that transforms the complexity of managing public cloud infrastructure into simple, natural language commands. No more navigating through endless configurations or deciphering technical documentation—our AI agent is here to revolutionize the way organizations interact with cloud platforms. About the Project We’re building an AI-powered agent designed to handle public cloud management tasks seamlessly. Whether you’re setting up your organization’s cloud foundation or deploying complex workloads, this AI agent makes it as easy as having a conversation. What Can the AI Agent Do? Cloud Foundation Setup: Example: “Please set up a cloud foundation blueprint for my organization on Google Cloud.”* The AI agent will ask key questions (e.g., organization ID) and guide you through authentication. Once authorized, it sets up the foundation using GCP APIs. Workload Deployment: Example: “Spin up a GKE cluster for me.”* The agent will ask for necessary details (e.g., number of nodes, VPC info), authenticate, and deploy the cluster in minutes. Security and Compliance Validation: Example: “Validate my organization’s cloud setup and check for security vulnerabilities.”* The agent audits your setup, identifies potential risks, and provides actionable insights. Current Progress We’ve developed a working prototype that integrates with major cloud providers like Google Cloud. The AI agent can already: Authenticate with cloud APIs Execute foundational tasks such as setting up organizations and spinning up clusters Perform initial security validations Who I’m Looking For I’m searching for a co-founder with enterprise sales experience and a strategic vision to grow our user base. You will be instrumental in helping us: Build relationships with companies willing to pilot our product Develop go-to-market strategies for enterprise adoption Identify opportunities for partnerships with cloud service providers Your Role As a co-founder, you’ll lead efforts to: Secure Pilot Programs: Identify and onboard enterprises for product trials to gather feedback and refine the solution. Drive Growth: Develop scalable strategies to grow our user base across industries. Market Positioning: Work with me to define our unique value proposition and establish thought leadership in the cloud management space. My Background I bring over a decade of experience in tech, with a strong focus on software engineering and infrastructure. My contributions so far include: Developing the core AI engine and cloud integrations Designing workflows that simplify complex cloud tasks Why Join This Project? Revolutionize Cloud Management: Be part of a project that will redefine how organizations interact with public clouds. Tackle Challenging Problems: Work at the cutting edge of AI and cloud computing. High Growth Potential: Join an industry projected to grow exponentially as enterprises embrace AI-driven automation. Build a Company from Scratch: Shape the product, team, and culture as we grow together. What’s Next? Our immediate priorities include: Expanding the AI agent’s capabilities to support multi-cloud setups. Conducting pilot programs with enterprise clients. Iterating on the product based on real-world feedback. What We Need to Succeed Expertise in enterprise sales and partnerships A deep understanding of enterprise challenges and cloud adoption trends A shared passion for leveraging AI to solve complex problems Let’s work together to build the future of cloud management. If you’re excited about this vision and bring the expertise we need, I’d love to connect and discuss how we can take this project to the next level.

#reddit#founder#pitch:

reddit

0

1

GrowthGet•This week

WE JUST GOT $2,500 in angel investment for our AI Cold Calling Startup! Hooray! Looking for web dev + digital marketing agencies to partner with.

Hey y'all. The AI cold calling startup I've been working on for 3-4 months now just got a $2,500 angel investment, and we have 2 current customers, a credit card processing broker and a hospital equipment rental company based out of Texas. We have around $1,500 revenue so far, but we're having lots of trouble fulfilling the contracts because our tech just isn't "there" yet. I'm the Chief Tech Officer, and I'm also running some operations. The other main person in this is the CEO who has a strong sales background and came up with the idea. I've been working purely remotely, and it's great having some income because I'm stuck at home because I'm disabled, basically... We're using 11labs, openai, google speech to text, and a sh\*tty online dialer right now to run the first MVP which runs locally on our "botrunners" computers, and we're developing a web app with django python + javascript react. Our plan is, after we get the webapp working better, to hire more botrunners for $3 per hour from countries like Phillipines and India, and we're going to try to track all the actions the botrunners take to be able to train the AI to run it fully automated. The biggest problem we're facing right now with the tech is reducing latency, it started at 27 seconds to get a response and I've been able to get it down to 6 seconds, but people are still hanging up. We're trying several ways to mitigate this, including having pre-rendered speech playing something like "Okay" or "As an artificial representative, I'm still learning to be quicker on the pickup. We appreciate your patience." One of the industries we want to target is international web development and digital marketing companies, and we want to use the bot to cold-call businesses to pitch them our services. The goal is to replace $30 an hour cold-callers from the USA with $3 per hour total-cost automation. Apparently the CEO was given a $5 million valuation from the strength of the MVP from a VC. Our investment so far was at a $300k valuation tho. It's exciting. Trying to get Twilio working to be able to make calls programmatically instead of using our hacky workaround. Let me know if you have any questions, or feedback. Looking for digital marketing and web dev agencies to partner with to test the next stage of our business model. Thanks. I just wanted to share this awesome news!

#reddit#just#$2,500

reddit

0

1

FrenzyOfLife•This week

What do you think of SaaS 2.0: Service-as-a-Software?

A new term has recently emerged in the business world: Service-as-a-Software a.k.a. SaaS 2.0 In general, some authors of articles promoting this term assume that the new and rapidly growing possibilities offered by AI and automation mean that problems that were previously too individual or support-intensive can now be tackled. The focus is on (human) service on the customer side and the background processes in the company are fully AI-supported and automated. Unlike traditional SaaS, no software is primarily offered here as self-use. In other words: "Service as a Software" (SaaS 2.0) is a new type of business model that mixes software automation with real human support. Unlike traditional SaaS, which provides self-service tools for users to solve problems on their own, SaaS 2.0 focuses on delivering results by combining technology with human expertise. In this model, software handles repetitive tasks like data processing, scheduling, or matching, while humans step in to provide guidance, handle exceptions, or solve complex issues. This approach is often called Human-in-the-Loop because humans are actively involved in key parts of the process, ensuring a personalized and empathetic experience for the customer. SaaS 2.0 is especially useful in industries like healthcare, education, or elderly care placement, where trust and personalization are critical. For example, a traditional SaaS might offer a tool to search for care homes, while a SaaS 2.0 solution would also provide a care consultant to help families make the best choice. In this case no traditional marketplace is needed where the supply and demand side used to be scaled simultaneously. Instead, an AI can now search for the best match for a place in a retirement home and a human in the loop can be the external face for the customer and the retirement homes and thus act as an agent. By automating routine tasks and using humans for high-value touchpoints, SaaS 2.0 delivers better outcomes, builds stronger relationships with customers, and stands out from traditional software that relies only on automation. What do you think about the potential of this concept?

#reddit#think#saas

reddit

0

1

Ambitious-Waltz6119•This week

Exploring Manufacturing Automation & IoT Services: Demand Check

Hey everyone! I run a tech consulting business and I'm looking to branch out into helping smaller manufacturers automate their processes and implement IoT/AI solutions. I just wrapped up a cool project with my buddy who owns a food manufacturing company - we managed to streamline a bunch of his micro processes and the results were pretty impressive! Now I'm curious - is this something other manufacturing businesses actually need? Would love to hear from folks who've either hired someone for this kind of work or provided these services themselves. Any insights on whether there's real demand out there? Thanks in advance for any thoughts or experiences you can share!

#reddit#exploring#manufacturing

reddit

0

1

GrowthGet•This week

WE JUST GOT $2,500 in angel investment for our AI Cold Calling Startup! Hooray! Looking for web dev + digital marketing agencies to partner with.

Hey y'all. The AI cold calling startup I've been working on for 3-4 months now just got a $2,500 angel investment, and we have 2 current customers, a credit card processing broker and a hospital equipment rental company based out of Texas. We have around $1,500 revenue so far, but we're having lots of trouble fulfilling the contracts because our tech just isn't "there" yet. I'm the Chief Tech Officer, and I'm also running some operations. The other main person in this is the CEO who has a strong sales background and came up with the idea. I've been working purely remotely, and it's great having some income because I'm stuck at home because I'm disabled, basically... We're using 11labs, openai, google speech to text, and a sh\*tty online dialer right now to run the first MVP which runs locally on our "botrunners" computers, and we're developing a web app with django python + javascript react. Our plan is, after we get the webapp working better, to hire more botrunners for $3 per hour from countries like Phillipines and India, and we're going to try to track all the actions the botrunners take to be able to train the AI to run it fully automated. The biggest problem we're facing right now with the tech is reducing latency, it started at 27 seconds to get a response and I've been able to get it down to 6 seconds, but people are still hanging up. We're trying several ways to mitigate this, including having pre-rendered speech playing something like "Okay" or "As an artificial representative, I'm still learning to be quicker on the pickup. We appreciate your patience." One of the industries we want to target is international web development and digital marketing companies, and we want to use the bot to cold-call businesses to pitch them our services. The goal is to replace $30 an hour cold-callers from the USA with $3 per hour total-cost automation. Apparently the CEO was given a $5 million valuation from the strength of the MVP from a VC. Our investment so far was at a $300k valuation tho. It's exciting. Trying to get Twilio working to be able to make calls programmatically instead of using our hacky workaround. Let me know if you have any questions, or feedback. Looking for digital marketing and web dev agencies to partner with to test the next stage of our business model. Thanks. I just wanted to share this awesome news!

#reddit#just#$2,500

reddit

0

1

AI_Business_Brief•This week

The Weekly Brief for anyone looking to incorporate AI into their business.

Good morning and happy Sunday. Today is Sunday and you know what that means. The weekly brief. Covering all of last week’s most important AI business related stories. Here are some of the biggest stories: Claude the newest generative AI. Amazon to change up its search. AI leaders Testify. Meta Open sources its LLM. Voice Actors Struggle Growing AI innovations has led to a struggle for many voice actors. As AI powered voice technology is progressing everyday jobs are becoming more and more scarce. With many publishers already leaning towards replacing many of their voice actors for faster, cheaper, and more efficient AI voices. Meet Claude Anthropic, an AI company founded by ex-OpenAI employee released their generative AI called Claude. Some key aspects of their model is the ability to give more correct and less harmful answers, and perform similar tasks that many other generative AI’s can do. A keynote is that Google has invested 300milloion into the company, which is a direct competitor to their AI Bard. Interesting to see how that will play out. Amazon Changes to Change up Search A new job description at Amazon may have hinted towards their future plans for AI. The description under software developer read “reimagining Amazon Search with an interactive conversational experience”. This may hint towards a generative AI search experience in Amazon for customers. ChatGPT User Get More Access Premium ChatGPT users got access to Web browsing and plugins. This is a crucial step for OpenAI as they plan to pivot to a more assist type AI. While at the same time continuing to research and develop their AI models. This move puts a lot of pressure on Google to hopefully step up their game. AI Leaders Testify This Wednesday AI leaders (Sam Altman, Christina Montgomery and Gary Marcus) all testified before congress about AI regulation. They were asked many questions about AI regulation but came up with two solutions. FDA-Like Approval Processing: AI developing companies are open to safety checks, audits, licensing and risk review. Precision Approach: Develop risk rules, provide explanations and provide guidelines for risks, encourage transparency around AI companies, finally assess impact of AI technologies. Meta Open Sourcing Thursday Meta open sourced this coding for their LLM. As the company wants to see the use of its LLM to help drive innovation, inspire smaller companies, and overall develop better AI technologies. Comes as an interesting move as competitors try and keep their AI’s an insider secret.

#reddit#weekly#brief

reddit

0

1

OstrichGrand8119•This week

AI Interns for Small Businesses: Who Will Lead the Market?

I've been working on making my own AI tools (https://openai.com/blog/introducing-gpts), kind of like building a team but without the big costs. It's like having a bunch of helpful interns, but they're all computer programs. This got me thinking a lot about small businesses like ours. Building My Own AI Team on a Budget Making these AI tools felt like creating my own team. It's really cheap compared to hiring real people, and these AI interns can do lots of different jobs. This is a big deal for folks like us who don't have lots of money to spend. Spotting What's Missing for Small Businesses While playing around with this AI stuff, I noticed there are things missing that small businesses really need. There's a big chance here to make something that fills these gaps, a tool made just for small businesses. The Big Question: Competing with Big Companies But here's the tricky part. Big companies like OpenAI are making their own AI stuff, like the GPT Store and GPT Enterprise. This makes me wonder if it's a good idea to make a new product that's kind of the same but more focused on what small businesses need. The Big Choice: Special Tools vs. Big Company Tools We're at a crossroads about what's better: Special Tools: Making something that's just right for small businesses could be really useful and fit our needs better. Big Company Tools: But, big companies have more stuff to offer and are already well-known. I Want to Hear From You If you run a small business or like tech stuff, what do you think? Would you like a special AI tool made for small businesses, or would you rather use the big ones from famous companies? How do you think the future looks for AI help in small businesses with all these changes? https://preview.redd.it/9pks3r65rg7c1.jpg?width=1460&format=pjpg&auto=webp&s=d767d2352f5e57e3303974f0b951a0176a0745c3

#reddit#interns#small

reddit

0

1

armaan-dev•This week

Looking for a Business Partner for an AI Stock recommendation SaaS

Hey everyone, I’m a 15-year-old full-stack developer, currently building StockWise, a startup focused on AI-driven stock market insights and analytics. I can handle all engineering, backend, frontend, and AI-related work—but I need a business partner who can take care of the marketing, sales, and user acquisition side of things. So this SaaS is currently in development. Also this I believe this can be both b2c and b2b. Like for b2c - it's the website included, with the recommendations, for individual users, for b2b - we can provide API's. Here is the classic workflow : \-> You can give your preferences, such as your monthly investment capital, if you're expecting short term or long term, and also if there are any specific areas you are more interested like AI, hydrogen fuel related, ev, compaines. \-> Then with this data, we recommend you stocks to buy, analyzing your preferences, looking at market, researching, looking into company's stock history, background, product \-> You will also have a chatbot like interface you can talk to about anything, and it will be personalized \-> Also you can add your portfolio here, and you can get insights based on the market data \-> Also there can be a weekly newsletter, too, if you subscribe to it. I'm much more of a builder, likes to build stuff, is good at it, but not good at the business side of things, that's why I'm really looking for a business partner. If you’re interested in joining as a co-founder or business partner, drop a comment or DM me!, Thanks a lot, Armaan

#reddit#looking#business

reddit

0

1

FrenzyOfLife•This week

What do you think of SaaS 2.0: Service-as-a-Software?

A new term has recently emerged in the business world: Service-as-a-Software a.k.a. SaaS 2.0 In general, some authors of articles promoting this term assume that the new and rapidly growing possibilities offered by AI and automation mean that problems that were previously too individual or support-intensive can now be tackled. The focus is on (human) service on the customer side and the background processes in the company are fully AI-supported and automated. Unlike traditional SaaS, no software is primarily offered here as self-use. In other words: "Service as a Software" (SaaS 2.0) is a new type of business model that mixes software automation with real human support. Unlike traditional SaaS, which provides self-service tools for users to solve problems on their own, SaaS 2.0 focuses on delivering results by combining technology with human expertise. In this model, software handles repetitive tasks like data processing, scheduling, or matching, while humans step in to provide guidance, handle exceptions, or solve complex issues. This approach is often called Human-in-the-Loop because humans are actively involved in key parts of the process, ensuring a personalized and empathetic experience for the customer. SaaS 2.0 is especially useful in industries like healthcare, education, or elderly care placement, where trust and personalization are critical. For example, a traditional SaaS might offer a tool to search for care homes, while a SaaS 2.0 solution would also provide a care consultant to help families make the best choice. In this case no traditional marketplace is needed where the supply and demand side used to be scaled simultaneously. Instead, an AI can now search for the best match for a place in a retirement home and a human in the loop can be the external face for the customer and the retirement homes and thus act as an agent. By automating routine tasks and using humans for high-value touchpoints, SaaS 2.0 delivers better outcomes, builds stronger relationships with customers, and stands out from traditional software that relies only on automation. What do you think about the potential of this concept?

#reddit#think#saas

reddit

0

1

nocturnal_1_1995•This week

Not sure if this is the right sub for it, but could you guys please roast my CV?

A brief about myself, I am an MSc from a top European University where I focused on NLP mostly hence most of my projects are just in NLP. I do have an experience of 3 years as a SE, did a 6 month stint as a consultant that I did not like, and finally got hired by a company I was doing my university project under to built their first products. The last 2 employments were part-time as I was also completing my masters at the same time. I am looking to apply in India mostly now. What do you think I can do differently, I just feel like something is missing here. Would be very thankful to anyone who can give me some constructive criticism on what to change here. Thanks again!

#reddit#sure#right

reddit

0

1

MohammadBais•This week

TiCs -where innovation meets intelligence

Be Part of India’s AI Revolution – Join the TiCs Movement! We are TiCs (Tuba International Cooperative Society)—India’s first global AI powerhouse. We’re not just building a company; we’re launching a movement that will redefine AI-driven healthcare, fitness, and well-being. Through our brands WellNest (AI-powered health ecosystem) and Zenova (next-gen smart wearables), we are pioneering a future where technology truly understands and enhances human health. Why Are We Calling You? We’re assembling a community of passionate minds—AI enthusiasts, developers, designers, innovators, and problem-solvers—who want to be part of something bigger. This is NOT an internship. This is NOT a job. This is a mission to build the future of health-tech. What’s in It for You? ✅ Work on groundbreaking AI & LLM projects that solve real-world healthcare problems ✅ Hands-on experience in AI, ML, IoT, and smart wearables ✅ Mentorship & learning opportunities from top AI leaders ✅ Exclusive perks like health, wellness, and gym packages ✅ Recognition & growth opportunities—top contributors will be given leadership roles as we scale ✅ Certificates & endorsements to showcase your contributions ✅ Opportunity to be part of a global AI-led revolution in healthcare & fitness ✅ Network with like-minded innovators, entrepreneurs, and industry pioneers ✅ Early access to WellNest & Zenova products and AI-driven health plans ✅ Possibility of paid roles & equity-based opportunities for the most dedicated members Who Should Join? Students & fresh graduates eager to apply their skills AI & tech enthusiasts passionate about real-world innovation Developers, designers, and creators who want to build something impactful Anyone who believes in the power of AI for good and wants to contribute This is More Than Just a Tech Project We’re building an AI-powered health revolution. If you want to be part of something that changes lives, breaks barriers, and creates real impact, this is your chance. Movements aren’t built by employees—they are led by believers. If you believe in the power of AI to transform health, join us and let’s build the future together!

#reddit#tics#-where

reddit

0

1

No-Definition-2886•This week

I single-handedly built the world’s best AI investing platform. Here’s NexusTrade’s 2024 year in review

I copy-pasted the content of this article to save you a click! I’ve been developing an AI investing platform for 4 years, and I’m blown away by all of the new features I’ve gotten done! Here’s my project’s 2024 year in review —- When someone asks me what is the best way to learn how to trade and invest, I have an unbiased answer – NexusTrade.io. I started NexusTrade to empower everybody, including beginners and non-technical investors, to learn how to make smarter investing decisions. NexusTrade is the best way for a new investor to learn algorithmic trading and financial research, and I’m not the only person to think so. Just this year alone, user growth has skyrocketed from 1,703 users to 14,319 users. This is driven by new features, better research tools, and the launch of algorithmic trading. Here’s NexusTrade’s 2024 year in review, a semi-complete list of the features I’ve launched. Summarizing this year in review TL;DR: I implemented a variety of new features to enhance NexusTrade’s algorithmic trading and financial research capabilities. This includes: Cryptocurrency support Enhanced financial research, like the AI-Powered Stock Screener Unique watchlists and daily market summaries Live-trading with Alpaca. Next year, I plan to implement features to make NexusTrade more tailored for each user’s experience, and launch several unique features including copy trading and fully automated algorithmic trading. Feature-by-feature: What have I done so far in 2024? Algorithmic Cryptocurrency Trading Picture: Algorithmic Cryptocurrency Trading I kicked off the year by adding cryptocurrency support to NexusTrade. Users can now research, design, and implement automated strategies for popular cryptocurrencies, such as Bitcoin, Dogecoin, and Ethereum. AI-Powered Stock Screener and research capabilities Picture: AI-Powered Stock Screener In tandem with cryptocurrency support, I made a huge update to Aurora, the AI Assistant in NexusTrade, by implementing a natural language stock screener. This screener makes it easy to find fundamentally strong stocks. Throughout the year, I’ve made several enhancements to it. Over time, I’ve made the screener faster, more accurate, and expanded its capabilities. Using fundamental indicators within trading strategies Picture: Using fundamental indicators Doing financial research for companies isn’t enough; we also need a way to integrate this type of research into trading strategies. Thus, I’ve expanded the NexusTrade indicators, and made it possible to create strategies using metrics like revenue, net income, free cash flow, and P/E ratio. Stock watchlists with tailored, automated daily emails Picture: Stock watchlists In addition, I didn’t want the research you may have done for a stock (or list of stocks) to be forgotten. Thus, I created the most useful watchlist page of any investing platform. This watchlist makes it easy to keep track of your favorite stocks, track them over time, and even receive curated, daily emails about them. Enhanced user profile page, Google sign-ins, and two-factor authentication Picture: Enhanced user profile Keeping in theme with adding new pages to NexusTrade, many pages, such as the profile page, got a huge revamp. The new profile page is cleaner, easier to use, and allows you to secure your account more effectively, for example, by using two-factor authentication. GPT-Reports: an AI-generated analysis of every stock in the market Picture: GPT-Reports I created GPT-Stock Reports, an AI-Generated analysis of every stock in the market. This report was generated by taking each company’s earnings data and asking GPT to analyze the stock and give it a rating. Manual and semi-automated algorithmic trading with Alpaca Picture: Manual and semi-automated trading Finally, I’ve fully launched the Alpaca integration, and enabled users to execute real trades directly in the NexusTrade app! This integration has transformed NexusTrade from a financial research app into a real, algorithmic trading platform for retail investors. Concluding Thoughts When I say that NexusTrade is the best platform for traders and investors to make more money in the stock market, you may naively think that I’m biased. I created the app, and the rose-tinted glasses is bound to make every red flag look like a regular flag, right? Wrong. NexusTrade is objectively a completely new way for investors to approach financial markets. The fact that the app is so expansive is nothing short of miraculous.

#reddit#single-handedly#built

github

0.563

0.24210481455988786

NirDiamant•Mar 28, 2025

GenAI_Agents

🌟 Support This Project: Your sponsorship fuels innovation in GenAI agent development. Become a sponsor to help maintain and expand this valuable resource! GenAI Agents: Comprehensive Repository for Development and Implementation 🚀 Welcome to one of the most extensive and dynamic collections of Generative AI (GenAI) agent tutorials and implementations available today. This repository serves as a comprehensive resource for learning, building, and sharing GenAI agents, ranging from simple conversational bots to complex, multi-agent systems. 📫 Stay Updated! 🚀Cutting-edgeUpdates 💡ExpertInsights 🎯Top 0.1%Content Join over 15,000 of AI enthusiasts getting unique cutting-edge insights and free tutorials! Plus, subscribers get exclusive early access and special 33% discounts to my book and the upcoming RAG Techniques course! Introduction Generative AI agents are at the forefront of artificial intelligence, revolutionizing the way we interact with and leverage AI technologies. This repository is designed to guide you through the development journey, from basic agent implementations to advanced, cutting-edge systems. 📚 Learn to Build Your First AI Agent Your First AI Agent: Simpler Than You Think This detailed blog post complements the repository by providing a complete A-Z walkthrough with in-depth explanations of core concepts, step-by-step implementation, and the theory behind AI agents. It's designed to be incredibly simple to follow while covering everything you need to know to build your first working agent from scratch. 💡 Plus: Subscribe to the newsletter for exclusive early access to tutorials and special discounts on upcoming courses and books! Our goal is to provide a valuable resource for everyone - from beginners taking their first steps in AI to seasoned practitioners pushing the boundaries of what's possible. By offering a range of examples from foundational to complex, we aim to facilitate learning, experimentation, and innovation in the rapidly evolving field of GenAI agents. Furthermore, this repository serves as a platform for showcasing innovative agent creations. Whether you've developed a novel agent architecture or found an innovative application for existing techniques, we encourage you to share your work with the community. Related Projects 📚 Dive into my comprehensive guide on RAG techniques to learn about integrating external knowledge into AI systems, enhancing their capabilities with up-to-date and relevant information retrieval. 🖋️ Explore my Prompt Engineering Techniques guide for an extensive collection of prompting strategies, from fundamental concepts to advanced methods, improving your ability to communicate effectively with AI language models. A Community-Driven Knowledge Hub This repository grows stronger with your contributions! Join our vibrant Discord community — the central hub for shaping and advancing this project together 🤝 GenAI Agents Discord Community Whether you're a novice eager to learn or an expert ready to share your knowledge, your insights can shape the future of GenAI agents. Join us to propose ideas, get feedback, and collaborate on innovative implementations. For contribution guidelines, please refer to our CONTRIBUTING.md file. Let's advance GenAI agent technology together! 🔗 For discussions on GenAI, agents, or to explore knowledge-sharing opportunities, feel free to connect on LinkedIn. Key Features 🎓 Learn to build GenAI agents from beginner to advanced levels 🧠 Explore a wide range of agent architectures and applications 📚 Step-by-step tutorials and comprehensive documentation 🛠️ Practical, ready-to-use agent implementations 🌟 Regular updates with the latest advancements in GenAI 🤝 Share your own agent creations with the community GenAI Agent Implementations Explore our extensive list of GenAI agent implementations, sorted by categories: 🌱 Beginner-Friendly Agents Simple Conversational Agent LangChain PydanticAI Overview 🔎 A context-aware conversational AI maintains information across interactions, enabling more natural dialogues. Implementation 🛠️ Integrates a language model, prompt template, and history manager to generate contextual responses and track conversation sessions. Simple Question Answering Agent Overview 🔎 Answering (QA) agent using LangChain and OpenAI's language model understands user queries and provides relevant, concise answers. Implementation 🛠️ Combines OpenAI's GPT model, a prompt template, and an LLMChain to process user questions and generate AI-driven responses in a streamlined manner. Simple Data Analysis Agent LangChain PydanticAI Overview 🔎 An AI-powered data analysis agent interprets and answers questions about datasets using natural language, combining language models with data manipulation tools for intuitive data exploration. Implementation 🛠️ Integrates a language model, data manipulation framework, and agent framework to process natural language queries and perform data analysis on a synthetic dataset, enabling accessible insights for non-technical users. 🔧 Framework Tutorial: LangGraph Introduction to LangGraph: Building Modular AI Workflows Overview 🔎 This tutorial introduces LangGraph, a powerful framework for creating modular, graph-based AI workflows. Learn how to leverage LangGraph to build more complex and flexible AI agents that can handle multi-step processes efficiently. Implementation 🛠️ Step-by-step guide on using LangGraph to create a StateGraph workflow. The tutorial covers key concepts such as state management, node creation, and graph compilation. It demonstrates these principles by constructing a simple text analysis pipeline, serving as a foundation for more advanced agent architectures. Additional Resources 📚 Blog Post 🎓 Educational and Research Agents ATLAS: Academic Task and Learning Agent System Overview 🔎 ATLAS demonstrates how to build an intelligent multi-agent system that transforms academic support through AI-powered assistance. The system leverages LangGraph's workflow framework to coordinate multiple specialized agents that provide personalized academic planning, note-taking, and advisory support. Implementation 🛠️ Implements a state-managed multi-agent architecture using four specialized agents (Coordinator, Planner, Notewriter, and Advisor) working in concert through LangGraph's workflow framework. The system features sophisticated workflows for profile analysis and academic support, with continuous adaptation based on student performance and feedback. Additional Resources 📚 YouTube Explanation Blog Post Scientific Paper Agent - Literature Review Overview 🔎 An intelligent research assistant that helps users navigate, understand, and analyze scientific literature through an orchestrated workflow. The system combines academic APIs with sophisticated paper processing techniques to automate literature review tasks, enabling researchers to efficiently extract insights from academic papers while maintaining research rigor and quality control. Implementation 🛠️ Leverages LangGraph to create a five-node workflow system including decision making, planning, tool execution, and quality validation nodes. The system integrates the CORE API for paper access, PDFplumber for document processing, and advanced language models for analysis. Key features include a retry mechanism for robust paper downloads, structured data handling through Pydantic models, and quality-focused improvement cycles with human-in-the-loop validation options. Additional Resources 📚 YouTube Explanation Blog Post Chiron - A Feynman-Enhanced Learning Agent Overview 🔎 An adaptive learning agent that guides users through educational content using a structured checkpoint system and Feynman-style teaching. The system processes learning materials (either user-provided or web-retrieved), verifies understanding through interactive checkpoints, and provides simplified explanations when needed, creating a personalized learning experience that mimics one-on-one tutoring. Implementation 🛠️ Uses LangGraph to orchestrate a learning workflow that includes checkpoint definition, context building, understanding verification, and Feynman teaching nodes. The system integrates web search for dynamic content retrieval, employs semantic chunking for context processing, and manages embeddings for relevant information retrieval. Key features include a 70% understanding threshold for progression, interactive human-in-the-loop validation, and structured output through Pydantic models for consistent data handling. Additional Resources 📚 YouTube Explanation 💼 Business and Professional Agents Customer Support Agent (LangGraph) Overview 🔎 An intelligent customer support agent using LangGraph categorizes queries, analyzes sentiment, and provides appropriate responses or escalates issues. Implementation 🛠️ Utilizes LangGraph to create a workflow combining state management, query categorization, sentiment analysis, and response generation. Essay Grading Agent (LangGraph) Overview 🔎 An automated essay grading system using LangGraph and an LLM model evaluates essays based on relevance, grammar, structure, and depth of analysis. Implementation 🛠️ Utilizes a state graph to define the grading workflow, incorporating separate grading functions for each criterion. Travel Planning Agent (LangGraph) Overview 🔎 A Travel Planner using LangGraph demonstrates how to build a stateful, multi-step conversational AI application that collects user input and generates personalized travel itineraries. Implementation 🛠️ Utilizes StateGraph to define the application flow, incorporates custom PlannerState for process management. GenAI Career Assistant Agent Overview 🔎 The GenAI Career Assistant demonstrates how to create a multi-agent system that provides personalized guidance for careers in Generative AI. Using LangGraph and Gemini LLM, the system delivers customized learning paths, resume assistance, interview preparation, and job search support. Implementation 🛠️ Leverages a multi-agent architecture using LangGraph to coordinate specialized agents (Learning, Resume, Interview, Job Search) through TypedDict-based state management. The system employs sophisticated query categorization and routing while integrating with external tools like DuckDuckGo for job searches and dynamic content generation. Additional Resources 📚 YouTube Explanation Project Manager Assistant Agent Overview 🔎 An AI agent designed to assist in project management tasks by automating the process of creating actionable tasks from project descriptions, identifying dependencies, scheduling work, and assigning tasks to team members based on expertise. The system includes risk assessment and self-reflection capabilities to optimize project plans through multiple iterations, aiming to minimize overall project risk. Implementation 🛠️ Leverages LangGraph to orchestrate a workflow of specialized nodes including task generation, dependency mapping, scheduling, allocation, and risk assessment. Each node uses GPT-4o-mini for structured outputs following Pydantic models. The system implements a feedback loop for self-improvement, where risk scores trigger reflection cycles that generate insights to optimize the project plan. Visualization tools display Gantt charts of the generated schedules across iterations. Additional Resources 📚 YouTube Explanation Contract Analysis Assistant (ClauseAI) Overview 🔎 ClauseAI demonstrates how to build an AI-powered contract analysis system using a multi-agent approach. The system employs specialized AI agents for different aspects of contract review, from clause analysis to compliance checking, and leverages LangGraph for workflow orchestration and Pinecone for efficient clause retrieval and comparison. Implementation 🛠️ Implements a sophisticated state-based workflow using LangGraph to coordinate multiple AI agents through contract analysis stages. The system features Pydantic models for data validation, vector storage with Pinecone for clause comparison, and LLM-based analysis for generating comprehensive contract reports. The implementation includes parallel processing capabilities and customizable report generation based on user requirements. Additional Resources 📚 YouTube Explanation E2E Testing Agent Overview 🔎 The E2E Testing Agent demonstrates how to build an AI-powered system that converts natural language test instructions into executable end-to-end web tests. Using LangGraph for workflow orchestration and Playwright for browser automation, the system enables users to specify test cases in plain English while handling the complexity of test generation and execution. Implementation 🛠️ Implements a structured workflow using LangGraph to coordinate test generation, validation, and execution. The system features TypedDict state management, integration with Playwright for browser automation, and LLM-based code generation for converting natural language instructions into executable test scripts. The implementation includes DOM state analysis, error handling, and comprehensive test reporting. Additional Resources 📚 YouTube Explanation 🎨 Creative and Content Generation Agents GIF Animation Generator Agent (LangGraph) Overview 🔎 A GIF animation generator that integrates LangGraph for workflow management, GPT-4 for text generation, and DALL-E for image creation, producing custom animations from user prompts. Implementation 🛠️ Utilizes LangGraph to orchestrate a workflow that generates character descriptions, plots, and image prompts using GPT-4, creates images with DALL-E 3, and assembles them into GIFs using PIL. Employs asynchronous programming for efficient parallel processing. TTS Poem Generator Agent (LangGraph) Overview 🔎 An advanced text-to-speech (TTS) agent using LangGraph and OpenAI's APIs classifies input text, processes it based on content type, and generates corresponding speech output. Implementation 🛠️ Utilizes LangGraph to orchestrate a workflow that classifies input text using GPT models, applies content-specific processing, and converts the processed text to speech using OpenAI's TTS API. The system adapts its output based on the identified content type (general, poem, news, or joke). Music Compositor Agent (LangGraph) Overview 🔎 An AI Music Compositor using LangGraph and OpenAI's language models generates custom musical compositions based on user input. The system processes the input through specialized components, each contributing to the final musical piece, which is then converted to a playable MIDI file. Implementation 🛠️ LangGraph orchestrates a workflow that transforms user input into a musical composition, using ChatOpenAI (GPT-4) to generate melody, harmony, and rhythm, which are then style-adapted. The final AI-generated composition is converted to a MIDI file using music21 and can be played back using pygame. Content Intelligence: Multi-Platform Content Generation Agent Overview 🔎 Content Intelligence demonstrates how to build an advanced content generation system that transforms input text into platform-optimized content across multiple social media channels. The system employs LangGraph for workflow orchestration to analyze content, conduct research, and generate tailored content while maintaining brand consistency across different platforms. Implementation 🛠️ Implements a sophisticated workflow using LangGraph to coordinate multiple specialized nodes (Summary, Research, Platform-Specific) through the content generation process. The system features TypedDict and Pydantic models for state management, integration with Tavily Search for research enhancement, and platform-specific content generation using GPT-4. The implementation includes parallel processing for multiple platforms and customizable content templates. Additional Resources 📚 YouTube Explanation Business Meme Generator Using LangGraph and Memegen.link Overview 🔎 The Business Meme Generator demonstrates how to create an AI-powered system that generates contextually relevant memes based on company website analysis. Using LangGraph for workflow orchestration, the system combines Groq's Llama model for text analysis and the Memegen.link API to automatically produce brand-aligned memes for digital marketing. Implementation 🛠️ Implements a state-managed workflow using LangGraph to coordinate website content analysis, meme concept generation, and image creation. The system features Pydantic models for data validation, asynchronous processing with aiohttp, and integration with external APIs (Groq, Memegen.link) to create a complete meme generation pipeline with customizable templates. Additional Resources 📚 YouTube Explanation Murder Mystery Game with LLM Agents Overview 🔎 A text-based detective game that utilizes autonomous LLM agents as interactive characters in a procedurally generated murder mystery. Drawing inspiration from the UNBOUNDED paper, the system creates unique scenarios each time, with players taking on the role of Sherlock Holmes to solve the case through character interviews and deductive reasoning. Implementation 🛠️ Leverages two LangGraph workflows - a main game loop for story/character generation and game progression, and a conversation sub-graph for character interactions. The system uses a combination of LLM-powered narrative generation, character AI, and structured game mechanics to create an immersive investigative experience with replayable storylines. Additional Resources 📚 YouTube Explanation 📊 Analysis and Information Processing Agents Memory-Enhanced Conversational Agent Overview 🔎 A memory-enhanced conversational AI agent incorporates short-term and long-term memory systems to maintain context within conversations and across multiple sessions, improving interaction quality and personalization. Implementation 🛠️ Integrates a language model with separate short-term and long-term memory stores, utilizes a prompt template incorporating both memory types, and employs a memory manager for storage and retrieval. The system includes an interaction loop that updates and utilizes memories for each response. Multi-Agent Collaboration System Overview 🔎 A multi-agent collaboration system combining historical research with data analysis, leveraging large language models to simulate specialized agents working together to answer complex historical questions. Implementation 🛠️ Utilizes a base Agent class to create specialized HistoryResearchAgent and DataAnalysisAgent, orchestrated by a HistoryDataCollaborationSystem. The system follows a five-step process: historical context provision, data needs identification, historical data provision, data analysis, and final synthesis. Self-Improving Agent Overview 🔎 A Self-Improving Agent using LangChain engages in conversations, learns from interactions, and continuously improves its performance over time through reflection and adaptation. Implementation 🛠️ Integrates a language model with chat history management, response generation, and a reflection mechanism. The system employs a learning system that incorporates insights from reflection to enhance future performance, creating a continuous improvement loop. Task-Oriented Agent Overview 🔎 A language model application using LangChain that summarizes text and translates the summary to Spanish, combining custom functions, structured tools, and an agent for efficient text processing. Implementation 🛠️ Utilizes custom functions for summarization and translation, wrapped as structured tools. Employs a prompt template to guide the agent, which orchestrates the use of tools. An agent executor manages the process, taking input text and producing both an English summary and its Spanish translation. Internet Search and Summarize Agent Overview 🔎 An intelligent web research assistant that combines web search capabilities with AI-powered summarization, automating the process of gathering information from the internet and distilling it into concise, relevant summaries. Implementation 🛠️ Integrates a web search module using DuckDuckGo's API, a result parser, and a text summarization engine leveraging OpenAI's language models. The system performs site-specific or general searches, extracts relevant content, generates concise summaries, and compiles attributed results for efficient information retrieval and synthesis. Multi agent research team - Autogen Overview 🔎 This technique explores a multi-agent system for collaborative research using the AutoGen library. It employs agents to solve tasks collaboratively, focusing on efficient execution and quality assurance. The system enhances research by distributing tasks among specialized agents. Implementation 🛠️ Agents are configured with specific roles using the GPT-4 model, including admin, developer, planner, executor, and quality assurance. Interaction management ensures orderly communication with defined transitions. Task execution involves collaborative planning, coding, execution, and quality checking, demonstrating a scalable framework for various domains. Additional Resources 📚 comprehensive solution with UI Blogpost Sales Call Analyzer Overview 🔎 An intelligent system that automates the analysis of sales call recordings by combining audio transcription with advanced natural language processing. The analyzer transcribes audio using OpenAI's Whisper, processes the text using NLP techniques, and generates comprehensive reports including sentiment analysis, key phrases, pain points, and actionable recommendations to improve sales performance. Implementation 🛠️ Utilizes multiple components in a structured workflow: OpenAI Whisper for audio transcription, CrewAI for task automation and agent management, and LangChain for orchestrating the analysis pipeline. The system processes audio through a series of steps from transcription to detailed analysis, leveraging custom agents and tasks to generate structured JSON reports containing insights about customer sentiment, sales opportunities, and recommended improvements. Additional Resources 📚 YouTube Explanation Weather Emergency & Response System Overview 🔎 A comprehensive system demonstrating two agent graph implementations for weather emergency response: a real-time graph processing live weather data, and a hybrid graph combining real and simulated data for testing high-severity scenarios. The system handles complete workflow from data gathering through emergency plan generation, with automated notifications and human verification steps. Implementation 🛠️ Utilizes LangGraph for orchestrating complex workflows with state management, integrating OpenWeatherMap API for real-time data, and Gemini for analysis and response generation. The system incorporates email notifications, social media monitoring simulation, and severity-based routing with configurable human verification for low/medium severity events. Additional Resources 📚 YouTube Explanation Self-Healing Codebase System Overview 🔎 An intelligent system that automatically detects, diagnoses, and fixes runtime code errors using LangGraph workflow orchestration and ChromaDB vector storage. The system maintains a memory of encountered bugs and their fixes through vector embeddings, enabling pattern recognition for similar errors across the codebase. Implementation 🛠️ Utilizes a state-based graph workflow that processes function definitions and runtime arguments through specialized nodes for error detection, code analysis, and fix generation. Incorporates ChromaDB for vector-based storage of bug patterns and fixes, with automated search and retrieval capabilities for similar error patterns, while maintaining code execution safety through structured validation steps. Additional Resources 📚 YouTube Explanation DataScribe: AI-Powered Schema Explorer Overview 🔎 An intelligent agent system that enables intuitive exploration and querying of relational databases through natural language interactions. The system utilizes a fleet of specialized agents, coordinated by a stateful Supervisor, to handle schema discovery, query planning, and data analysis tasks while maintaining contextual understanding through vector-based relationship graphs. Implementation 🛠️ Leverages LangGraph for orchestrating a multi-agent workflow including discovery, inference, and planning agents, with NetworkX for relationship graph visualization and management. The system incorporates dynamic state management through TypedDict classes, maintains database context between sessions using a db_graph attribute, and includes safety measures to prevent unauthorized database modifications. Memory-Enhanced Email Agent (LangGraph & LangMem) Overview 🔎 An intelligent email assistant that combines three types of memory (semantic, episodic, and procedural) to create a system that improves over time. The agent can triage incoming emails, draft contextually appropriate responses using stored knowledge, and enhance its performance based on user feedback. Implementation 🛠️ Leverages LangGraph for workflow orchestration and LangMem for sophisticated memory management across multiple memory types. The system implements a triage workflow with memory-enhanced decision making, specialized tools for email composition and calendar management, and a self-improvement mechanism that updates its own prompts based on feedback and past performance. Additional Resources 📚 Blog Post 📰 News and Information Agents News TL;DR using LangGraph Overview 🔎 A news summarization system that generates concise TL;DR summaries of current events based on user queries. The system leverages large language models for decision making and summarization while integrating with news APIs to access up-to-date content, allowing users to quickly catch up on topics of interest through generated bullet-point summaries. Implementation 🛠️ Utilizes LangGraph to orchestrate a workflow combining multiple components: GPT-4o-mini for generating search terms and article summaries, NewsAPI for retrieving article metadata, BeautifulSoup for web scraping article content, and Asyncio for concurrent processing. The system follows a structured pipeline from query processing through article selection and summarization, managing the flow between components to produce relevant TL;DRs of current news articles. Additional Resources 📚 YouTube Explanation Blog Post AInsight: AI/ML Weekly News Reporter Overview 🔎 AInsight demonstrates how to build an intelligent news aggregation and summarization system using a multi-agent architecture. The system employs three specialized agents (NewsSearcher, Summarizer, Publisher) to automatically collect, process and summarize AI/ML news for general audiences through LangGraph-based workflow orchestration. Implementation 🛠️ Implements a state-managed multi-agent system using LangGraph to coordinate the news collection (Tavily API), technical content summarization (GPT-4), and report generation processes. The system features modular architecture with TypedDict-based state management, external API integration, and markdown report generation with customizable templates. Additional Resources 📚 YouTube Explanation Journalism-Focused AI Assistant Overview 🔎 A specialized AI assistant that helps journalists tackle modern journalistic challenges like misinformation, bias, and information overload. The system integrates fact-checking, tone analysis, summarization, and grammar review tools to enhance the accuracy and efficiency of journalistic work while maintaining ethical reporting standards. Implementation 🛠️ Leverages LangGraph to orchestrate a workflow of specialized components including language models for analysis and generation, web search integration via DuckDuckGo's API, document parsing tools like PyMuPDFLoader and WebBaseLoader, text splitting with RecursiveCharacterTextSplitter, and structured JSON outputs. Each component works together through a unified workflow to analyze content, verify facts, detect bias, extract quotes, and generate comprehensive reports. Blog Writer (Open AI Swarm) Overview 🔎 A multi-agent system for collaborative blog post creation using OpenAI's Swarm package. It leverages specialized agents to perform research, planning, writing, and editing tasks efficiently. Implementation 🛠️ Utilizes OpenAI's Swarm Package to manage agent interactions. Includes an admin, researcher, planner, writer, and editor, each with specific roles. The system follows a structured workflow: topic setting, outlining, research, drafting, and editing. This approach enhances content creation through task distribution, specialization, and collaborative problem-solving. Additional Resources 📚 Swarm Repo Podcast Internet Search and Generate Agent 🎙️ Overview 🔎 A two step agent that first searches the internet for a given topic and then generates a podcast on the topic found. The search step uses a search agent and search function to find the most relevant information. The second step uses a podcast generation agent and generation function to create a podcast on the topic found. Implementation 🛠️ Utilizes LangGraph to orchestrate a two-step workflow. The first step involves a search agent and function to gather information from the internet. The second step uses a podcast generation agent and function to create a podcast based on the gathered information. 🛍️ Shopping and Product Analysis Agents ShopGenie - Redefining Online Shopping Customer Experience Overview 🔎 An AI-powered shopping assistant that helps customers make informed purchasing decisions even without domain expertise. The system analyzes product information from multiple sources, compares specifications and reviews, identifies the best option based on user needs, and delivers recommendations through email with supporting video reviews, creating a comprehensive shopping experience. Implementation 🛠️ Uses LangGraph to orchestrate a workflow combining Tavily for web search, Llama-3.1-70B for structured data analysis and product comparison, and YouTube API for review video retrieval. The system processes search results through multiple nodes including schema mapping, product comparison, review identification, and email generation. Key features include structured Pydantic models for consistent data handling, retry mechanisms for robust API interactions, and email delivery through SMTP for sharing recommendations. Additional Resources 📚 YouTube Explanation Car Buyer AI Agent Overview 🔎 The Smart Product Buyer AI Agent demonstrates how to build an intelligent system that assists users in making informed purchasing decisions. Using LangGraph and LLM-based intelligence, the system processes user requirements, scrapes product listings from websites like AutoTrader, and provides detailed analysis and recommendations for car purchases. Implementation 🛠️ Implements a state-based workflow using LangGraph to coordinate user interaction, web scraping, and decision support. The system features TypedDict state management, async web scraping with Playwright, and integrates with external APIs for comprehensive product analysis. The implementation includes a Gradio interface for real-time chat interaction and modular scraper architecture for easy extension to additional product categories. Additional Resources 📚 YouTube Explanation 🎯 Task Management and Productivity Agents Taskifier - Intelligent Task Allocation & Management Overview 🔎 An intelligent task management system that analyzes user work styles and creates personalized task breakdown strategies, born from the observation that procrastination often stems from task ambiguity among students and early-career professionals. The system evaluates historical work patterns, gathers relevant task information through web search, and generates customized step-by-step approaches to optimize productivity and reduce workflow paralysis. Implementation 🛠️ Leverages LangGraph for orchestrating a multi-step workflow including work style analysis, information gathering via Tavily API, and customized plan generation. The system maintains state through the process, integrating historical work pattern data with fresh task research to output detailed, personalized task execution plans aligned with the user's natural working style. Additional Resources 📚 YouTube Explanation Grocery Management Agents System Overview 🔎 A multi-agent system built with CrewAI that automates grocery management tasks including receipt interpretation, expiration date tracking, inventory management, and recipe recommendations. The system uses specialized agents to extract data from receipts, estimate product shelf life, track consumption, and suggest recipes to minimize food waste. Implementation 🛠️ Implements four specialized agents using CrewAI - a Receipt Interpreter that extracts item details from receipts, an Expiration Date Estimator that determines shelf life using online sources, a Grocery Tracker that maintains inventory based on consumption, and a Recipe Recommender that suggests meals using available ingredients. Each agent has specific tools and tasks orchestrated through a crew workflow. Additional Resources 📚 YouTube Explanation 🔍 Quality Assurance and Testing Agents LangGraph-Based Systems Inspector Overview 🔎 A comprehensive testing and validation tool for LangGraph-based applications that automatically analyzes system architecture, generates test cases, and identifies potential vulnerabilities through multi-agent inspection. The inspector employs specialized AI testers to evaluate different aspects of the system, from basic functionality to security concerns and edge cases. Implementation 🛠️ Integrates LangGraph for workflow orchestration, multiple LLM-powered testing agents, and a structured evaluation pipeline that includes static analysis, test case generation, and results verification. The system uses Pydantic for data validation, NetworkX for graph representation, and implements a modular architecture that allows for parallel test execution and comprehensive result analysis. Additional Resources 📚 YouTube Explanation Blog Post EU Green Deal FAQ Bot Overview 🔎 The EU Green Deal FAQ Bot demonstrates how to build a RAG-based AI agent that helps businesses understand EU green deal policies. The system processes complex regulatory documents into manageable chunks and provides instant, accurate answers to common questions about environmental compliance, emissions reporting, and waste management requirements. Implementation 🛠️ Implements a sophisticated RAG pipeline using FAISS vectorstore for document storage, semantic chunking for preprocessing, and multiple specialized agents (Retriever, Summarizer, Evaluator) for query processing. The system features query rephrasing for improved accuracy, cross-reference with gold Q&A datasets for answer validation, and comprehensive evaluation metrics to ensure response quality and relevance. Additional Resources 📚 YouTube Explanation Systematic Review Automation System + Paper Draft Creation Overview 🔎 A comprehensive system for automating academic systematic reviews using a directed graph architecture and LangChain components. The system generates complete, publication-ready systematic review papers, automatically processing everything from literature search through final draft generation with multiple revision cycles. Implementation 🛠️ Utilizes a state-based graph workflow that handles paper search and selection (up to 3 papers), PDF processing, and generates a complete academic paper with all standard sections (abstract, introduction, methods, results, conclusions, references). The system incorporates multiple revision cycles with automated critique and improvement phases, all orchestrated through LangGraph state management. Additional Resources 📚 YouTube Explanation 🌟 Special Advanced Technique 🌟 Sophisticated Controllable Agent for Complex RAG Tasks 🤖 Overview 🔎 An advanced RAG solution designed to tackle complex questions that simple semantic similarity-based retrieval cannot solve. This approach uses a sophisticated deterministic graph as the "brain" 🧠 of a highly controllable autonomous agent, capable of answering non-trivial questions from your own data. Implementation 🛠️ • Implement a multi-step process involving question anonymization, high-level planning, task breakdown, adaptive information retrieval and question answering, continuous re-planning, and rigorous answer verification to ensure grounded and accurate responses. Getting Started To begin exploring and building GenAI agents: Clone this repository: Navigate to the technique you're interested in: Follow the detailed implementation guide in each technique's notebook. Contributing We welcome contributions from the community! If you have a new technique or improvement to suggest: Fork the repository Create your feature branch: git checkout -b feature/AmazingFeature Commit your changes: git commit -m 'Add some AmazingFeature' Push to the branch: git push origin feature/AmazingFeature Open a pull request Contributors License This project is licensed under a custom non-commercial license - see the LICENSE file for details. ⭐️ If you find this repository helpful, please consider giving it a star! Keywords: GenAI, Generative AI, Agents, NLP, AI, Machine Learning, Natural Language Processing, LLM, Conversational AI, Task-Oriented AI

#github#genai_agents

github

0.447

0.1014145151561518

superiorlu•Mar 28, 2025

AITreasureBox

AI TreasureBox English | 中文 Collect practical AI repos, tools, websites, papers and tutorials on AI. Translated from ChatGPT, picture from Midjourney. Catalog Repos Tools Websites Report&Paper Tutorials Repos updated repos and stars every 2 hours and re-ranking automatically. | No. | Repos | Description | | ----:|:-----------------------------------------|:------------------------------------------------------------------------------------------------------| | 1|🔥codecrafters-io/build-your-own-x !2025-03-28364681428|Master programming by recreating your favorite technologies from scratch.| | 2|sindresorhus/awesome !2025-03-28353614145|😎 Awesome lists about all kinds of interesting topics| | 3|public-apis/public-apis !2025-03-28334299125|A collective list of free APIs| | 4|kamranahmedse/developer-roadmap !2025-03-2831269540|Interactive roadmaps, guides and other educational content to help developers grow in their careers.| | 5|vinta/awesome-python !2025-03-28238581114|A curated list of awesome Python frameworks, libraries, software and resources| | 6|practical-tutorials/project-based-learning !2025-03-28222661124|Curated list of project-based tutorials| | 7|tensorflow/tensorflow !2025-03-281888714|An Open Source Machine Learning Framework for Everyone| | 8|Significant-Gravitas/AutoGPT !2025-03-2817391338|An experimental open-source attempt to make GPT-4 fully autonomous.| | 9|jackfrued/Python-100-Days !2025-03-2816305141|Python - 100天从新手到大师| | 10|AUTOMATIC1111/stable-diffusion-webui !2025-03-2815011553|Stable Diffusion web UI| | 11|huggingface/transformers !2025-03-2814207850|🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.| | 12|ollama/ollama !2025-03-28135166151|Get up and running with Llama 2, Mistral, Gemma, and other large language models.| | 13|f/awesome-chatgpt-prompts !2025-03-2812212738 |This repo includes ChatGPT prompt curation to use ChatGPT better.| | 14|justjavac/free-programming-books-zhCN !2025-03-2811316119|📚 免费的计算机编程类中文书籍，欢迎投稿| | 15|krahets/hello-algo !2025-03-2811107930|《Hello 算法》：动画图解、一键运行的数据结构与算法教程。支持 Python, Java, C++, C, C#, JS, Go, Swift, Rust, Ruby, Kotlin, TS, Dart 代码。简体版和繁体版同步更新，English version ongoing| | 16|yt-dlp/yt-dlp !2025-03-28105801114|A feature-rich command-line audio/video downloader| | 17|langchain-ai/langchain !2025-03-2810449479|⚡ Building applications with LLMs through composability ⚡| | 18|goldbergyoni/nodebestpractices !2025-03-281021629|✅ The Node.js best practices list (July 2024)| | 19|puppeteer/puppeteer !2025-03-289018212|JavaScript API for Chrome and Firefox| | 20|pytorch/pytorch !2025-03-288833938|Tensors and Dynamic neural networks in Python with strong GPU acceleration| | 21|neovim/neovim !2025-03-288781482|Vim-fork focused on extensibility and usability| | 22|🔥🔥langgenius/dify !2025-03-2887342639 |One API for plugins and datasets, one interface for prompt engineering and visual operation, all for creating powerful AI applications.| | 23|mtdvio/every-programmer-should-know !2025-03-28867069|A collection of (mostly) technical things every software developer should know about| | 24|open-webui/open-webui !2025-03-2886025159|User-friendly WebUI for LLMs (Formerly Ollama WebUI)| | 25|ChatGPTNextWeb/NextChat !2025-03-288231521|✨ Light and Fast AI Assistant. Support: Web | | 26|supabase/supabase !2025-03-287990956|The open source Firebase alternative.| | 27|openai/whisper !2025-03-287905542|Robust Speech Recognition via Large-Scale Weak Supervision| | 28|home-assistant/core !2025-03-287773219|🏡 Open source home automation that puts local control and privacy first.| | 29|tensorflow/models !2025-03-28774694|Models and examples built with TensorFlow| | 30| ggerganov/llama.cpp !2025-03-287731836 | Port of Facebook's LLaMA model in C/C++ | | 31|3b1b/manim !2025-03-287641918|Animation engine for explanatory math videos| | 32|microsoft/generative-ai-for-beginners !2025-03-287623860|12 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/| | 33|nomic-ai/gpt4all !2025-03-28729285 |gpt4all: an ecosystem of open-source chatbots trained on a massive collection of clean assistant data including code, stories and dialogue| | 34|comfyanonymous/ComfyUI !2025-03-2872635111|The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.| | 35|bregman-arie/devops-exercises !2025-03-2872225209|Linux, Jenkins, AWS, SRE, Prometheus, Docker, Python, Ansible, Git, Kubernetes, Terraform, OpenStack, SQL, NoSQL, Azure, GCP, DNS, Elastic, Network, Virtualization. DevOps Interview Questions| | 36|elastic/elasticsearch !2025-03-28721419|Free and Open, Distributed, RESTful Search Engine| | 37|🔥n8n-io/n8n !2025-03-2872093495|Free and source-available fair-code licensed workflow automation tool. Easily automate tasks across different services.| | 38|fighting41love/funNLP !2025-03-287200422|The Most Powerful NLP-Weapon Arsenal| | 39|hoppscotch/hoppscotch !2025-03-287060134|Open source API development ecosystem - https://hoppscotch.io (open-source alternative to Postman, Insomnia)| | 40|abi/screenshot-to-code !2025-03-286932817|Drop in a screenshot and convert it to clean HTML/Tailwind/JS code| | 41|binary-husky/gptacademic !2025-03-28680374|Academic Optimization of GPT| | 42|d2l-ai/d2l-zh !2025-03-286774142|Targeting Chinese readers, functional and open for discussion. The Chinese and English versions are used for teaching in over 400 universities across more than 60 countries| | 43|josephmisiti/awesome-machine-learning !2025-03-286739215|A curated list of awesome Machine Learning frameworks, libraries and software.| | 44|grafana/grafana !2025-03-286725414|The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.| | 45|python/cpython !2025-03-286602218|The Python programming language| | 46|apache/superset !2025-03-286519020|Apache Superset is a Data Visualization and Data Exploration Platform| | 47|xtekky/gpt4free !2025-03-28639391 |decentralizing the Ai Industry, free gpt-4/3.5 scripts through several reverse engineered API's ( poe.com, phind.com, chat.openai.com etc...)| | 48|sherlock-project/sherlock !2025-03-286332536|Hunt down social media accounts by username across social networks| | 49|twitter/the-algorithm !2025-03-28630586 |Source code for Twitter's Recommendation Algorithm| | 50|keras-team/keras !2025-03-28627835|Deep Learning for humans| | 51|openai/openai-cookbook !2025-03-28625136 |Examples and guides for using the OpenAI API| | 52|immich-app/immich !2025-03-286238670|High performance self-hosted photo and video management solution.| | 53|AppFlowy-IO/AppFlowy !2025-03-286173528|Bring projects, wikis, and teams together with AI. AppFlowy is an AI collaborative workspace where you achieve more without losing control of your data. The best open source alternative to Notion.| | 54|scikit-learn/scikit-learn !2025-03-286158212|scikit-learn: machine learning in Python| | 55|binhnguyennus/awesome-scalability !2025-03-286117021|The Patterns of Scalable, Reliable, and Performant Large-Scale Systems| | 56|labmlai/annotateddeeplearningpaperimplementations !2025-03-285951726|🧑‍🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠| | 57|OpenInterpreter/open-interpreter !2025-03-285894710|A natural language interface for computers| | 58|lobehub/lobe-chat !2025-03-285832054|🤖 Lobe Chat - an open-source, extensible (Function Calling), high-performance chatbot framework. It supports one-click free deployment of your private ChatGPT/LLM web application.| | 59|meta-llama/llama !2025-03-28579536|Inference code for Llama models| | 60|nuxt/nuxt !2025-03-28566437|The Intuitive Vue Framework.| | 61|imartinez/privateGPT !2025-03-28555192|Interact with your documents using the power of GPT, 100% privately, no data leaks| | 62|Stirling-Tools/Stirling-PDF !2025-03-285500846|#1 Locally hosted web application that allows you to perform various operations on PDF files| | 63|PlexPt/awesome-chatgpt-prompts-zh !2025-03-285459720|ChatGPT Chinese Training Guide. Guidelines for various scenarios. Learn how to make it listen to you| | 64|dair-ai/Prompt-Engineering-Guide !2025-03-285451025 |🐙 Guides, papers, lecture, notebooks and resources for prompt engineering| | 65|ageitgey/facerecognition !2025-03-28544382|The world's simplest facial recognition api for Python and the command line| | 66|CorentinJ/Real-Time-Voice-Cloning !2025-03-285384814|Clone a voice in 5 seconds to generate arbitrary speech in real-time| | 67|geekan/MetaGPT !2025-03-285375376|The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo | | 68|gpt-engineer-org/gpt-engineer !2025-03-285367419|Specify what you want it to build, the AI asks for clarification, and then builds it.| | 69|lencx/ChatGPT !2025-03-2853653-3|🔮 ChatGPT Desktop Application (Mac, Windows and Linux)| | 70|deepfakes/faceswap !2025-03-28535672|Deepfakes Software For All| | 71|langflow-ai/langflow !2025-03-285319584|Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.| | 72|commaai/openpilot !2025-03-28529759|openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 275+ supported cars.| | 73|clash-verge-rev/clash-verge-rev !2025-03-2852848124|Continuation of Clash Verge - A Clash Meta GUI based on Tauri (Windows, MacOS, Linux)| | 74|All-Hands-AI/OpenHands !2025-03-285150675|🙌 OpenHands: Code Less, Make More| | 75|xai-org/grok-1 !2025-03-28502504|Grok open release| | 76|meilisearch/meilisearch !2025-03-284999122|A lightning-fast search API that fits effortlessly into your apps, websites, and workflow| | 77|🔥browser-use/browser-use !2025-03-2849910294|Make websites accessible for AI agents| | 78|jgthms/bulma !2025-03-28496783|Modern CSS framework based on Flexbox| | 79|facebookresearch/segment-anything !2025-03-284947116|The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.| |!green-up-arrow.svg 80|hacksider/Deep-Live-Cam !2025-03-2848612146|real time face swap and one-click video deepfake with only a single image (uncensored)| |!red-down-arrow 81|mlabonne/llm-course !2025-03-284860934|Course with a roadmap and notebooks to get into Large Language Models (LLMs).| | 82|PaddlePaddle/PaddleOCR !2025-03-284785530|Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)| | 83|alist-org/alist !2025-03-284732618|🗂️A file list/WebDAV program that supports multiple storages, powered by Gin and Solidjs. / 一个支持多存储的文件列表/WebDAV程序，使用 Gin 和 Solidjs。| | 84|infiniflow/ragflow !2025-03-2847027129|RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.| | 85|Avik-Jain/100-Days-Of-ML-Code !2025-03-284679312|100 Days of ML Coding| | 86|v2ray/v2ray-core !2025-03-28458706|A platform for building proxies to bypass network restrictions.| | 87|hiyouga/LLaMA-Factory !2025-03-284555881|Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)| | 88|Asabeneh/30-Days-Of-Python !2025-03-284544930|30 days of Python programming challenge is a step-by-step guide to learn the Python programming language in 30 days. This challenge may take more than100 days, follow your own pace. These videos may help too: https://www.youtube.com/channel/UC7PNRuno1rzYPb1xLa4yktw| | 89|type-challenges/type-challenges !2025-03-284488511|Collection of TypeScript type challenges with online judge| | 90|lllyasviel/Fooocus !2025-03-284402716|Focus on prompting and generating| | 91|RVC-Boss/GPT-SoVITS !2025-03-284327738|1 min voice data can also be used to train a good TTS model! (few shot voice cloning)| | 92|rasbt/LLMs-from-scratch !2025-03-284320667|Implementing a ChatGPT-like LLM from scratch, step by step| | 93|oobabooga/text-generation-webui !2025-03-284302012 |A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, OPT, and GALACTICA.| | 94|vllm-project/vllm !2025-03-2842982102|A high-throughput and memory-efficient inference and serving engine for LLMs| | 95|dani-garcia/vaultwarden !2025-03-284297121|Unofficial Bitwarden compatible server written in Rust, formerly known as bitwarden_rs| | 96|microsoft/autogen !2025-03-284233049|Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ| | 97|jeecgboot/JeecgBoot !2025-03-284205920|🔥「企业级低代码平台」前后端分离架构SpringBoot 2.x/3.x，SpringCloud，Ant Design&Vue3，Mybatis，Shiro，JWT。强大的代码生成器让前后端代码一键生成，无需写任何代码! 引领新的开发模式OnlineCoding->代码生成->手工MERGE，帮助Java项目解决70%重复工作，让开发更关注业务，既能快速提高效率，帮助公司节省成本，同时又不失灵活性。| | 98|Mintplex-Labs/anything-llm !2025-03-284186955|A full-stack application that turns any documents into an intelligent chatbot with a sleek UI and easier way to manage your workspaces.| | 99|THUDM/ChatGLM-6B !2025-03-28410192 |ChatGLM-6B: An Open Bilingual Dialogue Language Model| | 100|hpcaitech/ColossalAI !2025-03-28406902|Making large AI models cheaper, faster and more accessible| | 101|Stability-AI/stablediffusion !2025-03-28406337|High-Resolution Image Synthesis with Latent Diffusion Models| | 102|mingrammer/diagrams !2025-03-28405063|🎨 Diagram as Code for prototyping cloud system architectures| | 103|Kong/kong !2025-03-28404616|🦍 The Cloud-Native API Gateway and AI Gateway.| | 104|getsentry/sentry !2025-03-284040913|Developer-first error tracking and performance monitoring| | 105| karpathy/nanoGPT !2025-03-284034613 |The simplest, fastest repository for training/finetuning medium-sized GPTs| | 106|fastlane/fastlane !2025-03-2840014-1|🚀 The easiest way to automate building and releasing your iOS and Android apps| | 107|psf/black !2025-03-28399765|The uncompromising Python code formatter| | 108|OpenBB-finance/OpenBBTerminal !2025-03-283972074 |Investment Research for Everyone, Anywhere.| | 109|2dust/v2rayNG !2025-03-283943415|A V2Ray client for Android, support Xray core and v2fly core| | 110|apache/airflow !2025-03-283937314|Apache Airflow - A platform to programmatically author, schedule, and monitor workflows| | 111|KRTirtho/spotube !2025-03-283902746|🎧 Open source Spotify client that doesn't require Premium nor uses Electron! Available for both desktop & mobile!| | 112|coqui-ai/TTS !2025-03-283889719 |🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production| | 113|ggerganov/whisper.cpp !2025-03-283882116|Port of OpenAI's Whisper model in C/C++| | 114|ultralytics/ultralytics !2025-03-283866951|NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite| | 115|typst/typst !2025-03-283863914|A new markup-based typesetting system that is powerful and easy to learn.| | 116|streamlit/streamlit !2025-03-283845828|Streamlit — A faster way to build and share data apps.| | 117|LC044/WeChatMsg !2025-03-283836931|提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手| | 118|lm-sys/FastChat !2025-03-283822112 |An open platform for training, serving, and evaluating large languages. Release repo for Vicuna and FastChat-T5.| | 119|NaiboWang/EasySpider !2025-03-283819013|A visual no-code/code-free web crawler/spider易采集：一个可视化浏览器自动化测试/数据采集/爬虫软件，可以无代码图形化的设计和执行爬虫任务。别名：ServiceWrapper面向Web应用的智能化服务封装系统。| | 120|microsoft/DeepSpeed !2025-03-283765816 |A deep learning optimization library that makes distributed training and inference easy, efficient, and effective| | 121|QuivrHQ/quivr !2025-03-28376067|Your GenAI Second Brain 🧠 A personal productivity assistant (RAG) ⚡️🤖 Chat with your docs (PDF, CSV, ...) & apps using Langchain, GPT 3.5 / 4 turbo, Private, Anthropic, VertexAI, Ollama, LLMs, that you can share with users ! Local & Private alternative to OpenAI GPTs & ChatGPT powered by retrieval-augmented generation.| | 122|freqtrade/freqtrade !2025-03-283757817 |Free, open source crypto trading bot| | 123|suno-ai/bark !2025-03-28373178 |🔊 Text-Prompted Generative Audio Model| | 124|🔥cline/cline !2025-03-2837307282|Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, and more with your permission every step of the way.| | 125|LAION-AI/Open-Assistant !2025-03-28372712 |OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.| | 126|penpot/penpot !2025-03-283716217|Penpot: The open-source design tool for design and code collaboration| | 127|gradio-app/gradio !2025-03-283713320|Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!| | 128|FlowiseAI/Flowise !2025-03-283667135 |Drag & drop UI to build your customized LLM flow using LangchainJS| | 129|SimplifyJobs/Summer2025-Internships !2025-03-28366506|Collection of Summer 2025 tech internships!| | 130|TencentARC/GFPGAN !2025-03-28365027 |GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.| | 131|ray-project/ray !2025-03-283626819|Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.| | 132|babysor/MockingBird !2025-03-28360498|🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time| | 133|unslothai/unsloth !2025-03-283603691|5X faster 50% less memory LLM finetuning| | 134|zhayujie/chatgpt-on-wechat !2025-03-283600124 |Wechat robot based on ChatGPT, which uses OpenAI api and itchat library| | 135|upscayl/upscayl !2025-03-283599824|🆙 Upscayl - Free and Open Source AI Image Upscaler for Linux, MacOS and Windows built with Linux-First philosophy.| | 136|freeCodeCamp/devdocs !2025-03-28359738|API Documentation Browser| | 137|XingangPan/DragGAN !2025-03-28359043 |Code for DragGAN (SIGGRAPH 2023)| | 138|2noise/ChatTTS !2025-03-283543922|ChatTTS is a generative speech model for daily dialogue.| | 139|google-research/google-research !2025-03-28352207 |Google Research| | 140|karanpratapsingh/system-design !2025-03-28351003|Learn how to design systems at scale and prepare for system design interviews| | 141|lapce/lapce !2025-03-28350855|Lightning-fast and Powerful Code Editor written in Rust| | 142| microsoft/TaskMatrix !2025-03-2834500-3 | Talking, Drawing and Editing with Visual Foundation Models| | 143|chatchat-space/Langchain-Chatchat !2025-03-283442020|Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM) QA app with langchain| | 144|unclecode/crawl4ai !2025-03-283434163|🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & Scrapper| | 145|Bin-Huang/chatbox !2025-03-283374733 |A desktop app for GPT-4 / GPT-3.5 (OpenAI API) that supports Windows, Mac & Linux| | 146|milvus-io/milvus !2025-03-283366525 |A cloud-native vector database, storage for next generation AI applications| | 147|mendableai/firecrawl !2025-03-2833297128|🔥 Turn entire websites into LLM-ready markdown| | 148|pola-rs/polars !2025-03-283269320|Fast multi-threaded, hybrid-out-of-core query engine focussing on DataFrame front-ends| | 149|Pythagora-io/gpt-pilot !2025-03-28325321|PoC for a scalable dev tool that writes entire apps from scratch while the developer oversees the implementation| | 150|hashicorp/vault !2025-03-28320797|A tool for secrets management, encryption as a service, and privileged access management| | 151|shardeum/shardeum !2025-03-28319580|Shardeum is an EVM based autoscaling blockchain| | 152|Chanzhaoyu/chatgpt-web !2025-03-28319242 |A demonstration website built with Express and Vue3 called ChatGPT| | 153|lllyasviel/ControlNet !2025-03-283186413 |Let us control diffusion models!| | 154|google/jax !2025-03-28317727|Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more| | 155|facebookresearch/detectron2 !2025-03-28315987|Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.| | 156|myshell-ai/OpenVoice !2025-03-28315233|Instant voice cloning by MyShell| | 157|TheAlgorithms/C-Plus-Plus !2025-03-283151411|Collection of various algorithms in mathematics, machine learning, computer science and physics implemented in C++ for educational purposes.| | 158|hiroi-sora/Umi-OCR !2025-03-283138129|OCR图片转文字识别软件，完全离线。截屏/批量导入图片，支持多国语言、合并段落、竖排文字。可排除水印区域，提取干净的文本。基于 PaddleOCR 。| | 159|mudler/LocalAI !2025-03-283127815|🤖 The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.| | 160|facebookresearch/fairseq !2025-03-28312124 |Facebook AI Research Sequence-to-Sequence Toolkit written in Python.| | 161|alibaba/nacos !2025-03-28310559|an easy-to-use dynamic service discovery, configuration and service management platform for building cloud native applications.| | 162|yunjey/pytorch-tutorial !2025-03-28310326|PyTorch Tutorial for Deep Learning Researchers| | 163|v2fly/v2ray-core !2025-03-28307448|A platform for building proxies to bypass network restrictions.| | 164|mckaywrigley/chatbot-ui !2025-03-283067714|The open-source AI chat interface for everyone.| | 165|TabbyML/tabby !2025-03-28305949 |Self-hosted AI coding assistant| | 166|deepseek-ai/awesome-deepseek-integration !2025-03-283053193|| | 167|danielmiessler/fabric !2025-03-283028914|fabric is an open-source framework for augmenting humans using AI.| | 168|xinntao/Real-ESRGAN !2025-03-283026623 |Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.| | 169|paul-gauthier/aider !2025-03-283014642|aider is GPT powered coding in your terminal| | 170|tatsu-lab/stanfordalpaca !2025-03-28299022 |Code and documentation to train Stanford's Alpaca models, and generate the data.| | 171|DataTalksClub/data-engineering-zoomcamp !2025-03-282971817|Free Data Engineering course!| | 172|HeyPuter/puter !2025-03-282967014|🌐 The Internet OS! Free, Open-Source, and Self-Hostable.| | 173|mli/paper-reading !2025-03-282962314|Classic Deep Learning and In-Depth Reading of New Papers Paragraph by Paragraph| | 174|linexjlin/GPTs !2025-03-28295568|leaked prompts of GPTs| | 175|s0md3v/roop !2025-03-28295286 |one-click deepfake (face swap)| | 176|JushBJJ/Mr.-Ranedeer-AI-Tutor !2025-03-2829465-1 |A GPT-4 AI Tutor Prompt for customizable personalized learning experiences.| | 177|opendatalab/MinerU !2025-03-282927074|A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。| | 178|mouredev/Hello-Python !2025-03-282920720|Curso para aprender el lenguaje de programación Python desde cero y para principiantes. 75 clases, 37 horas en vídeo, código, proyectos y grupo de chat. Fundamentos, frontend, backend, testing, IA...| | 179|Lightning-AI/pytorch-lightning !2025-03-28292039|Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.| | 180|crewAIInc/crewAI !2025-03-282919344|Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.| | 181|facebook/folly !2025-03-282916612|An open-source C++ library developed and used at Facebook.| | 182|google-ai-edge/mediapipe !2025-03-28291519|Cross-platform, customizable ML solutions for live and streaming media.| | 183| getcursor/cursor !2025-03-282892025 | An editor made for programming with AI| | 184|chatanywhere/GPTAPIfree !2025-03-282856424|Free ChatGPT API Key, Free ChatGPT API, supports GPT-4 API (free), ChatGPT offers a free domestic forwarding API that allows direct connections without the need for a proxy. It can be used in conjunction with software/plugins like ChatBox, significantly reducing interface usage costs. Enjoy unlimited and unrestricted chatting within China| | 185|meta-llama/llama3 !2025-03-28285552|The official Meta Llama 3 GitHub site| | 186|tinygrad/tinygrad !2025-03-282845811|You like pytorch? You like micrograd? You love tinygrad! ❤️| | 187|google-research/tuningplaybook !2025-03-282841514|A playbook for systematically maximizing the performance of deep learning models.| | 188|huggingface/diffusers !2025-03-282830222|🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.| | 189|tokio-rs/tokio !2025-03-28282408|A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...| | 190|RVC-Project/Retrieval-based-Voice-Conversion-WebUI !2025-03-282823817|Voice data !2025-03-282822612|Jan is an open source alternative to ChatGPT that runs 100% offline on your computer| | 192|openai/CLIP !2025-03-282814720|CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image| | 193|🔥khoj-ai/khoj !2025-03-2828112313|Your AI second brain. A copilot to get answers to your questions, whether they be from your own notes or from the internet. Use powerful, online (e.g gpt4) or private, local (e.g mistral) LLMs. Self-host locally or use our web app. Access from Obsidian, Emacs, Desktop app, Web or Whatsapp.| | 194| acheong08/ChatGPT !2025-03-2828054-2 | Reverse engineered ChatGPT API | | 195|iperov/DeepFaceLive !2025-03-28279345 |Real-time face swap for PC streaming or video calls| | 196|eugeneyan/applied-ml !2025-03-28278471|📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.| | 197|XTLS/Xray-core !2025-03-282778213|Xray, Penetrates Everything. Also the best v2ray-core, with XTLS support. Fully compatible configuration.| | 198|feder-cr/JobsApplierAIAgent !2025-03-282776410|AutoJobsApplierAI_Agent aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in an automated and personalized way.| | 199|mindsdb/mindsdb !2025-03-282750631|The platform for customizing AI from enterprise data| | 200|DataExpert-io/data-engineer-handbook !2025-03-282721611|This is a repo with links to everything you'd ever want to learn about data engineering| | 201|exo-explore/exo !2025-03-282721633|Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚| | 202|taichi-dev/taichi !2025-03-2826926-1|Productive, portable, and performant GPU programming in Python.| | 203|mem0ai/mem0 !2025-03-282689134|The memory layer for Personalized AI| | 204|svc-develop-team/so-vits-svc !2025-03-28268096 |SoftVC VITS Singing Voice Conversion| | 205|OpenBMB/ChatDev !2025-03-28265624|Create Customized Software using Natural Language Idea (through Multi-Agent Collaboration)| | 206|roboflow/supervision !2025-03-282632010|We write your reusable computer vision tools. 💜| | 207|drawdb-io/drawdb !2025-03-282626913|Free, simple, and intuitive online database design tool and SQL generator.| | 208|karpathy/llm.c !2025-03-28261633|LLM training in simple, raw C/CUDA| | 209|airbnb/lottie-ios !2025-03-28261431|An iOS library to natively render After Effects vector animations| | 210|openai/openai-python !2025-03-282607713|The OpenAI Python library provides convenient access to the OpenAI API from applications written in the Python language.| | 211|academic/awesome-datascience !2025-03-28259876|📝 An awesome Data Science repository to learn and apply for real world problems.| | 212|harry0703/MoneyPrinterTurbo !2025-03-282576618|Generate short videos with one click using a large model| | 213|gabime/spdlog !2025-03-282571511|Fast C++ logging library.| | 214|ocrmypdf/OCRmyPDF !2025-03-2825674217|OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched| | 215|Vision-CAIR/MiniGPT-4 !2025-03-28256170 |Enhancing Vision-language Understanding with Advanced Large Language Models| | 216|Stability-AI/generative-models !2025-03-28255936|Generative Models by Stability AI| | 217|DS4SD/docling !2025-03-282555662|Get your docs ready for gen AI| | 218|PostHog/posthog !2025-03-282533227|🦔 PostHog provides open-source product analytics, session recording, feature flagging and A/B testing that you can self-host.| | 219|nrwl/nx !2025-03-282509612|Smart Monorepos · Fast CI| | 220|continuedev/continue !2025-03-282500737|⏩ the open-source copilot chat for software development—bring the power of ChatGPT to VS Code| | 221|opentofu/opentofu !2025-03-28247968|OpenTofu lets you declaratively manage your cloud infrastructure.| | 222|invoke-ai/InvokeAI !2025-03-28247293|InvokeAI is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, supports terminal use through a CLI, and serves as the foundation for multiple commercial products.| | 223|deepinsight/insightface !2025-03-282471615 |State-of-the-art 2D and 3D Face Analysis Project| | 224|apache/flink !2025-03-28246865|Apache Flink| | 225|ComposioHQ/composio !2025-03-28246436|Composio equips agents with well-crafted tools empowering them to tackle complex tasks| | 226|Genesis-Embodied-AI/Genesis !2025-03-282458314|A generative world for general-purpose robotics & embodied AI learning.| | 227|stretchr/testify !2025-03-28243184|A toolkit with common assertions and mocks that plays nicely with the standard library| | 228| yetone/openai-translator !2025-03-28242921 | Browser extension and cross-platform desktop application for translation based on ChatGPT API | | 229|frappe/erpnext !2025-03-282425211|Free and Open Source Enterprise Resource Planning (ERP)| | 230|songquanpeng/one-api !2025-03-282410034|OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistribution system, using a single API for all LLMs, and features an English UI.| | 231| microsoft/JARVIS !2025-03-28240604 | a system to connect LLMs with ML community | | 232|google/flatbuffers !2025-03-28239965|FlatBuffers: Memory Efficient Serialization Library| | 233|microsoft/graphrag !2025-03-282398928|A modular graph-based Retrieval-Augmented Generation (RAG) system| | 234|rancher/rancher !2025-03-28239675|Complete container management platform| | 235|bazelbuild/bazel !2025-03-282384618|a fast, scalable, multi-language and extensible build system| | 236|modularml/mojo !2025-03-28238236 |The Mojo Programming Language| | 237|danny-avila/LibreChat !2025-03-282378753|Enhanced ChatGPT Clone: Features OpenAI, GPT-4 Vision, Bing, Anthropic, OpenRouter, Google Gemini, AI model switching, message search, langchain, DALL-E-3, ChatGPT Plugins, OpenAI Functions, Secure Multi-User System, Presets, completely open-source for self-hosting. More features in development| |!green-up-arrow.svg 238|🔥🔥🔥Shubhamsaboo/awesome-llm-apps !2025-03-28237391211|Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.| |!red-down-arrow 239|microsoft/semantic-kernel !2025-03-282373611|Integrate cutting-edge LLM technology quickly and easily into your apps| |!red-down-arrow 240|TheAlgorithms/Rust !2025-03-28236995|All Algorithms implemented in Rust| | 241|stanford-oval/storm !2025-03-28236326|An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.| | 242|openai/gpt-2 !2025-03-28232483|Code for the paper "Language Models are Unsupervised Multitask Learners"| | 243|labring/FastGPT !2025-03-282319445|A platform that uses the OpenAI API to quickly build an AI knowledge base, supporting many-to-many relationships.| | 244|pathwaycom/llm-app !2025-03-2822928-10|Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.| | 245|warpdotdev/Warp !2025-03-282286825|Warp is a modern, Rust-based terminal with AI built in so you and your team can build great software, faster.| | 246|🔥agno-agi/agno !2025-03-2822833298|Agno is a lightweight library for building Multimodal Agents. It exposes LLMs as a unified API and gives them superpowers like memory, knowledge, tools and reasoning.| | 247|qdrant/qdrant !2025-03-282275214 |Qdrant - Vector Database for the next generation of AI applications. Also available in the cloud https://cloud.qdrant.io/| | 248|ashishpatel26/500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code !2025-03-282271815|500 AI Machine learning Deep learning Computer vision NLP Projects with code| | 249|stanfordnlp/dspy !2025-03-282268321|Stanford DSPy: The framework for programming—not prompting—foundation models| | 250|PaddlePaddle/Paddle !2025-03-28226246|PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）| | 251|zulip/zulip !2025-03-28225464|Zulip server and web application. Open-source team chat that helps teams stay productive and focused.| | 252|Hannibal046/Awesome-LLM !2025-03-282240721|Awesome-LLM: a curated list of Large Language Model| | 253|facefusion/facefusion !2025-03-282218812|Next generation face swapper and enhancer| | 254|Mozilla-Ocho/llamafile !2025-03-28220624|Distribute and run LLMs with a single file.| | 255|yuliskov/SmartTube !2025-03-282201614|SmartTube - an advanced player for set-top boxes and tvs running Android OS| | 256|haotian-liu/LLaVA !2025-03-282201316 |Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.| | 257|ashishps1/awesome-system-design-resources !2025-03-282189367|This repository contains System Design resources which are useful while preparing for interviews and learning Distributed Systems| | 258|Cinnamon/kotaemon !2025-03-28218248|An open-source RAG-based tool for chatting with your documents.| | 259|CodePhiliaX/Chat2DB !2025-03-282179757|🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.| | 260|blakeblackshear/frigate !2025-03-282177113|NVR with realtime local object detection for IP cameras| | 261|facebookresearch/audiocraft !2025-03-28217111|Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.| | 262|karpathy/minGPT !2025-03-28216567|A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training| | 263|grpc/grpc-go !2025-03-282159510|The Go language implementation of gRPC. HTTP/2 based RPC| | 264|HumanSignal/label-studio !2025-03-282137618|Label Studio is a multi-type data labeling and annotation tool with standardized output format| | 265|yoheinakajima/babyagi !2025-03-28212764 |uses OpenAI and Pinecone APIs to create, prioritize, and execute tasks, This is a pared-down version of the original Task-Driven Autonomous Agent| | 266|deepseek-ai/DeepSeek-Coder !2025-03-282118210|DeepSeek Coder: Let the Code Write Itself| | 267|BuilderIO/gpt-crawler !2025-03-282118010|Crawl a site to generate knowledge files to create your own custom GPT from a URL| | 268| openai/chatgpt-retrieval-plugin !2025-03-2821152-1 | Plugins are chat extensions designed specifically for language models like ChatGPT, enabling them to access up-to-date information, run computations, or interact with third-party services in response to a user's request.| | 269|microsoft/OmniParser !2025-03-282113123|A simple screen parsing tool towards pure vision based GUI agent| | 270|black-forest-labs/flux !2025-03-282107219|Official inference repo for FLUX.1 models| | 271|ItzCrazyKns/Perplexica !2025-03-282099154|Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI| | 272|microsoft/unilm !2025-03-28209876|Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities| | 273|Sanster/lama-cleaner !2025-03-282077614|Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.| | 274|assafelovic/gpt-researcher !2025-03-282057222|GPT based autonomous agent that does online comprehensive research on any given topic| | 275|PromtEngineer/localGPT !2025-03-28204230 |Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.| | 276|elastic/kibana !2025-03-28203482|Your window into the Elastic Stack| | 277|fishaudio/fish-speech !2025-03-282033222|Brand new TTS solution| | 278|mlc-ai/mlc-llm !2025-03-282028110 |Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.| | 279|deepset-ai/haystack !2025-03-282005320|🔍 Haystack is an open source NLP framework to interact with your data using Transformer models and LLMs (GPT-4, ChatGPT and alike). Haystack offers production-ready tools to quickly build complex question answering, semantic search, text generation applications, and more.| | 280|tree-sitter/tree-sitter !2025-03-28200487|An incremental parsing system for programming tools| | 281|Anjok07/ultimatevocalremovergui !2025-03-281999811|GUI for a Vocal Remover that uses Deep Neural Networks.| | 282|guidance-ai/guidance !2025-03-28199622|A guidance language for controlling large language models.| | 283|ml-explore/mlx !2025-03-28199619|MLX: An array framework for Apple silicon| | 284|mlflow/mlflow !2025-03-281995314|Open source platform for the machine learning lifecycle| | 285|ml-tooling/best-of-ml-python !2025-03-28198631|🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.| | 286|BerriAI/litellm !2025-03-281981862|Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)| | 287|LazyVim/LazyVim !2025-03-281981320|Neovim config for the lazy| | 288|wez/wezterm !2025-03-281976018|A GPU-accelerated cross-platform terminal emulator and multiplexer written by @wez and implemented in Rust| | 289|valkey-io/valkey !2025-03-281970416|A flexible distributed key-value datastore that supports both caching and beyond caching workloads.| | 290|LiLittleCat/awesome-free-chatgpt !2025-03-28196185|🆓免费的 ChatGPT 镜像网站列表，持续更新。List of free ChatGPT mirror sites, continuously updated.| | 291|Byaidu/PDFMathTranslate !2025-03-281947645|PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker| | 292|openai/swarm !2025-03-281947111|Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.| | 293|HqWu-HITCS/Awesome-Chinese-LLM !2025-03-281921423|Organizing smaller, cost-effective, privately deployable open-source Chinese language models, including related datasets and tutorials| | 294|stitionai/devika !2025-03-28190903|Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective. Devika aims to be a competitive open-source alternative to Devin by Cognition AI.| | 295|OpenBMB/MiniCPM-o !2025-03-28190887|MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone| | 296|samber/lo !2025-03-281904815|💥 A Lodash-style Go library based on Go 1.18+ Generics (map, filter, contains, find...)| | 297|chroma-core/chroma !2025-03-281895221 |the AI-native open-source embedding database| | 298|DarkFlippers/unleashed-firmware !2025-03-28189278|Flipper Zero Unleashed Firmware| | 299|brave/brave-browser !2025-03-281892710|Brave browser for Android, iOS, Linux, macOS, Windows.| | 300| tloen/alpaca-lora !2025-03-28188641 | Instruct-tune LLaMA on consumer hardware| | 301|VinciGit00/Scrapegraph-ai !2025-03-281884618|Python scraper based on AI| | 302|gitroomhq/postiz-app !2025-03-281879110|📨 Schedule social posts, measure them, exchange with other members and get a lot of help from AI 🚀| | 303|PrefectHQ/prefect !2025-03-281878715|Prefect is a workflow orchestration tool empowering developers to build, observe, and react to data pipelines| | 304|ymcui/Chinese-LLaMA-Alpaca !2025-03-28187723 |Chinese LLaMA & Alpaca LLMs| | 305|kenjihiranabe/The-Art-of-Linear-Algebra !2025-03-28187335|Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"| | 306|joonspk-research/generativeagents !2025-03-28187288|Generative Agents: Interactive Simulacra of Human Behavior| | 307|renovatebot/renovate !2025-03-28186820|Universal dependency update tool that fits into your workflows.| | 308|gventuri/pandas-ai !2025-03-28186109 |Pandas AI is a Python library that integrates generative artificial intelligence capabilities into Pandas, making dataframes conversational| | 309|thingsboard/thingsboard !2025-03-28185184|Open-source IoT Platform - Device management, data collection, processing and visualization.| | 310|ente-io/ente !2025-03-28184722|Fully open source, End to End Encrypted alternative to Google Photos and Apple Photos| | 311|serengil/deepface !2025-03-281840113|A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python| | 312|Raphire/Win11Debloat !2025-03-281840132|A simple, easy to use PowerShell script to remove pre-installed apps from windows, disable telemetry, remove Bing from windows search as well as perform various other changes to declutter and improve your windows experience. This script works for both windows 10 and windows 11.| | 313|Avaiga/taipy !2025-03-28179235|Turns Data and AI algorithms into production-ready web applications in no time.| | 314|microsoft/qlib !2025-03-281784231|Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.| | 315|CopilotKit/CopilotKit !2025-03-281778571|Build in-app AI chatbots 🤖, and AI-powered Textareas ✨, into react web apps.| | 316|QwenLM/Qwen-7B !2025-03-281766017|The official repo of Qwen-7B (通义千问-7B) chat & pretrained large language model proposed by Alibaba Cloud.| | 317|w-okada/voice-changer !2025-03-28176078 |リアルタイムボイスチェンジャー Realtime Voice Changer| | 318|rlabbe/Kalman-and-Bayesian-Filters-in-Python !2025-03-281756011|Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.| | 319|Mikubill/sd-webui-controlnet !2025-03-28174794 |WebUI extension for ControlNet| | 320|jingyaogong/minimind !2025-03-2817380116|「大模型」3小时完全从0训练26M的小参数GPT，个人显卡即可推理训练！| | 321|apify/crawlee !2025-03-28172696|Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.| | 322|apple/ml-stable-diffusion !2025-03-28172395|Stable Diffusion with Core ML on Apple Silicon| | 323| transitive-bullshit/chatgpt-api !2025-03-28172095 | Node.js client for the official ChatGPT API. | | 324|teableio/teable !2025-03-281719222|✨ The Next Gen Airtable Alternative: No-Code Postgres| | 325| xx025/carrot !2025-03-28170900 | Free ChatGPT Site List | | 326|microsoft/LightGBM !2025-03-28170723|A fast, distributed, high-performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.| | 327|VikParuchuri/surya !2025-03-28169827|Accurate line-level text detection and recognition (OCR) in any language| | 328|deepseek-ai/Janus !2025-03-281692825|Janus-Series: Unified Multimodal Understanding and Generation Models| | 329|ardalis/CleanArchitecture !2025-03-28168823|Clean Architecture Solution Template: A starting point for Clean Architecture with ASP.NET Core| | 330|neondatabase/neon !2025-03-28166466|Neon: Serverless Postgres. We separated storage and compute to offer autoscaling, code-like database branching, and scale to zero.| | 331|kestra-io/kestra !2025-03-281661313|⚡ Workflow Automation Platform. Orchestrate & Schedule code in any language, run anywhere, 500+ plugins. Alternative to Zapier, Rundeck, Camunda, Airflow...| | 332|Dao-AILab/flash-attention !2025-03-281659720|Fast and memory-efficient exact attention| | 333|RPCS3/rpcs3 !2025-03-281655712|PS3 emulator/debugger| | 334|meta-llama/llama-recipes !2025-03-28165486|Scripts for fine-tuning Llama2 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization & question answering. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment.Demo apps to showcase Llama2 for WhatsApp & Messenger| | 335|emilwallner/Screenshot-to-code !2025-03-28165180|A neural network that transforms a design mock-up into a static website.| | 336|datawhalechina/llm-cookbook !2025-03-281650922|面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版| | 337|e2b-dev/awesome-ai-agents !2025-03-281643923|A list of AI autonomous agents| | 338|QwenLM/Qwen2.5 !2025-03-281641114|Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.| | 339|dair-ai/ML-YouTube-Courses !2025-03-28164114|📺 Discover the latest machine learning / AI courses on YouTube.| | 340|pybind/pybind11 !2025-03-28163620|Seamless operability between C++11 and Python| | 341|graphdeco-inria/gaussian-splatting !2025-03-281627116|Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"| | 342|meta-llama/codellama !2025-03-28162531|Inference code for CodeLlama models| | 343|TransformerOptimus/SuperAGI !2025-03-28161292 | SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.| | 344|microsoft/onnxruntime !2025-03-28161169|ONNX Runtime: cross-platform, high-performance ML inferencing and training accelerator| | 345|IDEA-Research/Grounded-Segment-Anything !2025-03-281601411 |Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP - Automatically Detect, Segment and Generate Anything with Image and Text Inputs| | 346|ddbourgin/numpy-ml !2025-03-28160054|Machine learning, in numpy| | 347|eosphoros-ai/DB-GPT !2025-03-281585225|Revolutionizing Database Interactions with Private LLM Technology| | 348|Stability-AI/StableLM !2025-03-28158310 |Stability AI Language Models| | 349|openai/evals !2025-03-28157935 |Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.| | 350|THUDM/ChatGLM2-6B !2025-03-28157500|ChatGLM2-6B: An Open Bilingual Chat LLM | | 351|sunner/ChatALL !2025-03-28156761 |Concurrently chat with ChatGPT, Bing Chat, Bard, Alpaca, Vincuna, Claude, ChatGLM, MOSS, iFlytek Spark, ERNIE and more, discover the best answers| | 352|abseil/abseil-cpp !2025-03-28156656|Abseil Common Libraries (C++)| | 353|NVIDIA/open-gpu-kernel-modules !2025-03-28156531|NVIDIA Linux open GPU kernel module source| | 354|letta-ai/letta !2025-03-281563718|Letta (formerly MemGPT) is a framework for creating LLM services with memory.| | 355|typescript-eslint/typescript-eslint !2025-03-28156211|✨ Monorepo for all the tooling which enables ESLint to support TypeScript| | 356|umijs/umi !2025-03-28156211|A framework in react community ✨| | 357|AI4Finance-Foundation/FinGPT !2025-03-281561215|Data-Centric FinGPT. Open-source for open finance! Revolutionize 🔥 We'll soon release the trained model.| | 358|amplication/amplication !2025-03-28156022|🔥🔥🔥 The Only Production-Ready AI-Powered Backend Code Generation| | 359|KindXiaoming/pykan !2025-03-28155477|Kolmogorov Arnold Networks| | 360|arc53/DocsGPT !2025-03-28154900|GPT-powered chat for documentation, chat with your documents| | 361|influxdata/telegraf !2025-03-28154502|Agent for collecting, processing, aggregating, and writing metrics, logs, and other arbitrary data.| | 362|microsoft/Bringing-Old-Photos-Back-to-Life !2025-03-28154084|Bringing Old Photo Back to Life (CVPR 2020 oral)| | 363|GaiZhenbiao/ChuanhuChatGPT !2025-03-2815394-2|GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.| | 364|Zeyi-Lin/HivisionIDPhotos !2025-03-281529710|⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。| | 365| mayooear/gpt4-pdf-chatbot-langchain !2025-03-281529518 | GPT4 & LangChain Chatbot for large PDF docs | | 366|1Panel-dev/MaxKB !2025-03-2815277148|? Based on LLM large language model knowledge base Q&A system. Ready to use out of the box, supports quick integration into third-party business systems. Officially produced by 1Panel| | 367|ai16z/eliza !2025-03-281526811|Conversational Agent for Twitter and Discord| | 368|apache/arrow !2025-03-28151684|Apache Arrow is a multi-language toolbox for accelerated data interchange and in-memory processing| | 369|princeton-nlp/SWE-agent !2025-03-281516119|SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models| | 370|mlc-ai/web-llm !2025-03-281509311 |Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.| | 371|guillaumekln/faster-whisper !2025-03-281507117 |Faster Whisper transcription with CTranslate2| | 372|overleaf/overleaf !2025-03-28150316|A web-based collaborative LaTeX editor| | 373|triton-lang/triton !2025-03-28150169|Development repository for the Triton language and compiler| | 374|soxoj/maigret !2025-03-281500410|🕵️‍♂️ Collect a dossier on a person by username from thousands of sites| | 375|alibaba/lowcode-engine !2025-03-28149841|An enterprise-class low-code technology stack with scale-out design / 一套面向扩展设计的企业级低代码技术体系| | 376|espressif/esp-idf !2025-03-28148545|Espressif IoT Development Framework. Official development framework for Espressif SoCs.| | 377|pgvector/pgvector !2025-03-281484913|Open-source vector similarity search for Postgres| | 378|datawhalechina/leedl-tutorial !2025-03-28148246|《李宏毅深度学习教程》（李宏毅老师推荐👍），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases| | 379|xcanwin/KeepChatGPT !2025-03-28147972 |Using ChatGPT is more efficient and smoother, perfectly solving ChatGPT network errors. No longer do you need to frequently refresh the webpage, saving over 10 unnecessary steps| | 380|m-bain/whisperX !2025-03-281471313|WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)| | 381|HumanAIGC/AnimateAnyone !2025-03-2814706-1|Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation| |!green-up-arrow.svg 382|naklecha/llama3-from-scratch !2025-03-281469024|llama3 implementation one matrix multiplication at a time| |!red-down-arrow 383| fauxpilot/fauxpilot !2025-03-28146871 | An open-source GitHub Copilot server | | 384|LlamaFamily/Llama-Chinese !2025-03-28145111|Llama Chinese Community, the best Chinese Llama large model, fully open source and commercially available| | 385|BradyFU/Awesome-Multimodal-Large-Language-Models !2025-03-281450121|Latest Papers and Datasets on Multimodal Large Language Models| | 386|vanna-ai/vanna !2025-03-281449819|🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.| | 387|bleedline/aimoneyhunter !2025-03-28144845|AI Side Hustle Money Mega Collection: Teaching You How to Utilize AI for Various Side Projects to Earn Extra Income.| | 388|stefan-jansen/machine-learning-for-trading !2025-03-28144629|Code for Machine Learning for Algorithmic Trading, 2nd edition.| | 389|state-spaces/mamba !2025-03-28144139|Mamba: Linear-Time Sequence Modeling with Selective State Spaces| | 390|vercel/ai-chatbot !2025-03-281434614|A full-featured, hackable Next.js AI chatbot built by Vercel| | 391|steven-tey/novel !2025-03-281428410|Notion-style WYSIWYG editor with AI-powered autocompletions| | 392|unifyai/ivy !2025-03-281409348|Unified AI| | 393|chidiwilliams/buzz !2025-03-281402411 |Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.| | 394|lukas-blecher/LaTeX-OCR !2025-03-28139769|pix2tex: Using a ViT to convert images of equations into LaTeX code.| | 395|openai/tiktoken !2025-03-28139599|tiktoken is a fast BPE tokeniser for use with OpenAI's models.| | 396|nocobase/nocobase !2025-03-281391522|NocoBase is a scalability-first, open-source no-code/low-code platform for building business applications and enterprise solutions.| | 397|neonbjb/tortoise-tts !2025-03-28139010 |A multi-voice TTS system trained with an emphasis on quality| | 398|yamadashy/repomix !2025-03-281382036|📦 Repomix (formerly Repopack) is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools like Claude, ChatGPT, and Gemini.| | 399|adobe/react-spectrum !2025-03-28136766|A collection of libraries and tools that help you build adaptive, accessible, and robust user experiences.| | 400|THUDM/ChatGLM3 !2025-03-28136684|ChatGLM3 series: Open Bilingual Chat LLMs | | 401|NVIDIA/NeMo !2025-03-28134837|A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)| | 402|BlinkDL/RWKV-LM !2025-03-28134346 |RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it combines the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.| | 403| fuergaosi233/wechat-chatgpt !2025-03-28133330 | Use ChatGPT On Wechat via wechaty | | 404|udecode/plate !2025-03-28133325|A rich-text editor powered by AI| | 405|xenova/transformers.js !2025-03-281331219|State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!| | 406|stas00/ml-engineering !2025-03-281325615|Machine Learning Engineering Guides and Tools| | 407| wong2/chatgpt-google-extension !2025-03-2813241-1 | A browser extension that enhances search engines with ChatGPT, this repos will not be updated from 2023-02-20| | 408|mrdbourke/pytorch-deep-learning !2025-03-281317520|Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.| | 409|Koenkk/zigbee2mqtt !2025-03-28131544|Zigbee 🐝 to MQTT bridge 🌉, get rid of your proprietary Zigbee bridges 🔨| | 410|vercel-labs/ai !2025-03-281298528|Build AI-powered applications with React, Svelte, and Vue| | 411|netease-youdao/QAnything !2025-03-28129318|Question and Answer based on Anything.| | 412|huggingface/trl !2025-03-281289622|Train transformer language models with reinforcement learning.| | 413|microsoft/BitNet !2025-03-28128503|Official inference framework for 1-bit LLMs| | 414|mediar-ai/screenpipe !2025-03-281283915|24/7 local AI screen & mic recording. Build AI apps that have the full context. Works with Ollama. Alternative to Rewind.ai. Open. Secure. You own your data. Rust.| | 415|Skyvern-AI/skyvern !2025-03-281277612|Automate browser-based workflows with LLMs and Computer Vision| | 416|pytube/pytube !2025-03-28126591|A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.| | 417|official-stockfish/Stockfish !2025-03-28126574|UCI chess engine| | 418|sgl-project/sglang !2025-03-281260143|SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with LLMs faster and more controllable.| | 419|plasma-umass/scalene !2025-03-28125535|Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals| | 420|danswer-ai/danswer !2025-03-28125503|Ask Questions in natural language and get Answers backed by private sources. Connects to tools like Slack, GitHub, Confluence, etc.| | 421|OpenTalker/SadTalker !2025-03-28125226|[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation| | 422|facebookresearch/AnimatedDrawings !2025-03-28123693 |Code to accompany "A Method for Animating Children's Drawings of the Human Figure"| | 423|activepieces/activepieces !2025-03-28123609|Your friendliest open source all-in-one automation tool ✨ Workflow automation tool 100+ integration / Enterprise automation tool / Zapier Alternative| | 424|ggerganov/ggml !2025-03-28121992 |Tensor library for machine learning| | 425|bytebase/bytebase !2025-03-28121694|World's most advanced database DevOps and CI/CD for Developer, DBA and Platform Engineering teams. The GitLab/GitHub for database DevOps.| | 426| willwulfken/MidJourney-Styles-and-Keywords-Reference !2025-03-28120971 | A reference containing Styles and Keywords that you can use with MidJourney AI| | 427|Huanshere/VideoLingo !2025-03-281207013|Netflix-level subtitle cutting, translation, alignment, and even dubbing - one-click fully automated AI video subtitle team | | 428|OpenLMLab/MOSS !2025-03-28120330 |An open-source tool-augmented conversational language model from Fudan University| | 429|llmware-ai/llmware !2025-03-281200727|Providing enterprise-grade LLM-based development framework, tools, and fine-tuned models.| | 430|PKU-YuanGroup/Open-Sora-Plan !2025-03-28119362|This project aim to reproduce Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.| | 431|ShishirPatil/gorilla !2025-03-28119332 |Gorilla: An API store for LLMs| | 432|NVIDIA/Megatron-LM !2025-03-281192716|Ongoing research training transformer models at scale| | 433|illacloud/illa-builder !2025-03-28119192|Create AI-Driven Apps like Assembling Blocks| | 434|marimo-team/marimo !2025-03-281191521|A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.| | 435|smol-ai/developer !2025-03-28119111 | With 100k context windows on the way, it's now feasible for every dev to have their own smol developer| | 436|Lightning-AI/litgpt !2025-03-28118878|Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.| | 437|openai/shap-e !2025-03-28118474 |Generate 3D objects conditioned on text or images| | 438|eugeneyan/open-llms !2025-03-28118451 |A list of open LLMs available for commercial use.| | 439|andrewyng/aisuite !2025-03-28118124|Simple, unified interface to multiple Generative AI providers| | 440|hajimehoshi/ebiten !2025-03-28117816|Ebitengine - A dead simple 2D game engine for Go| | 441|kgrzybek/modular-monolith-with-ddd !2025-03-28117493|Full Modular Monolith application with Domain-Driven Design approach.| | 442|h2oai/h2ogpt !2025-03-2811736-1 |Come join the movement to make the world's best open source GPT led by H2O.ai - 100% private chat and document search, no data leaks, Apache 2.0| | 443|owainlewis/awesome-artificial-intelligence !2025-03-28117332|A curated list of Artificial Intelligence (AI) courses, books, video lectures and papers.| | 444|DataTalksClub/mlops-zoomcamp !2025-03-28116643|Free MLOps course from DataTalks.Club| | 445|Rudrabha/Wav2Lip !2025-03-281163410|This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.| | 446|aishwaryanr/awesome-generative-ai-guide !2025-03-281152810|A one stop repository for generative AI research updates, interview resources, notebooks and much more!| | 447|karpathy/micrograd !2025-03-28115146|A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API| | 448|InstantID/InstantID !2025-03-28115111|InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥| | 449|facebookresearch/seamlesscommunication !2025-03-28114434|Foundational Models for State-of-the-Art Speech and Text Translation| | 450|anthropics/anthropic-cookbook !2025-03-281140112|A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.| | 451|mastra-ai/mastra !2025-03-281139240|the TypeScript AI agent framework| | 452|NVIDIA/TensorRT !2025-03-28113864|NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.| | 453|plandex-ai/plandex !2025-03-28113645|An AI coding engine for complex tasks| | 454|RUCAIBox/LLMSurvey !2025-03-28112735 |A collection of papers and resources related to Large Language Models.| | 455|kubeshark/kubeshark !2025-03-28112711|The API traffic analyzer for Kubernetes providing real-time K8s protocol-level visibility, capturing and monitoring all traffic and payloads going in, out and across containers, pods, nodes and clusters. Inspired by Wireshark, purposely built for Kubernetes| | 456|electric-sql/pglite !2025-03-28112617|Lightweight Postgres packaged as WASM into a TypeScript library for the browser, Node.js, Bun and Deno from https://electric-sql.com| | 457|lightaime/camel !2025-03-281124441 |🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society| | 458|huggingface/lerobot !2025-03-281120184|🤗 LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch| | 459|normal-computing/outlines !2025-03-28111657|Generative Model Programming| | 460|libretro/RetroArch !2025-03-28110701|Cross-platform, sophisticated frontend for the libretro API. Licensed GPLv3.| | 461|THUDM/CogVideo !2025-03-28110599|Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)| | 462|bentoml/OpenLLM !2025-03-28110495|An open platform for operating large language models (LLMs) in production. Fine-tune, serve, deploy, and monitor any LLMs with ease.| | 463|vosen/ZLUDA !2025-03-28110429|CUDA on AMD GPUs| | 464|dair-ai/ML-Papers-of-the-Week !2025-03-28110304 |🔥Highlighting the top ML papers every week.| | 465|WordPress/gutenberg !2025-03-28110212|The Block Editor project for WordPress and beyond. Plugin is available from the official repository.| | 466|microsoft/data-formulator !2025-03-281099827|🪄 Create rich visualizations with AI| | 467|LibreTranslate/LibreTranslate !2025-03-28109887|Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.| | 468|block/goose !2025-03-281097737|an open-source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM| | 469|getumbrel/llama-gpt !2025-03-28109553|A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device.| | 470|HigherOrderCO/HVM !2025-03-28109182|A massively parallel, optimal functional runtime in Rust| | 471|databrickslabs/dolly !2025-03-2810812-3 | A large language model trained on the Databricks Machine Learning Platform| | 472|srush/GPU-Puzzles !2025-03-28108014|Solve puzzles. Learn CUDA.| | 473|Z3Prover/z3 !2025-03-28107952|The Z3 Theorem Prover| | 474|UFund-Me/Qbot !2025-03-281079313 |Qbot is an AI-oriented quantitative investment platform, which aims to realize the potential, empower AI technologies in quantitative investment| | 475|langchain-ai/langgraph !2025-03-281077336|| | 476|lz4/lz4 !2025-03-28107647|Extremely Fast Compression algorithm| | 477|magic-research/magic-animate !2025-03-28107160|MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model| | 478|PaperMC/Paper !2025-03-281071410|The most widely used, high performance Minecraft server that aims to fix gameplay and mechanics inconsistencies| | 479|getomni-ai/zerox !2025-03-281071015|Zero shot pdf OCR with gpt-4o-mini| |!green-up-arrow.svg 480|🔥NirDiamant/GenAIAgents !2025-03-2810693318|This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.| |!red-down-arrow 481|Unstructured-IO/unstructured !2025-03-28106889|Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.| | 482|apache/thrift !2025-03-28106610|Apache Thrift| | 483| TheR1D/shellgpt !2025-03-28106097 | A command-line productivity tool powered by ChatGPT, will help you accomplish your tasks faster and more efficiently | | 484|TheRamU/Fay !2025-03-281060312 |Fay is a complete open source project that includes Fay controller and numeral models, which can be used in different applications such as virtual hosts, live promotion, numeral human interaction and so on| | 485|zyronon/douyin !2025-03-28105566|Vue3 + Pinia + Vite5 仿抖音，Vue 在移动端的最佳实践 . Imitate TikTok ，Vue Best practices on Mobile| | 486|THU-MIG/yolov10 !2025-03-28105485|YOLOv10: Real-Time End-to-End Object Detection| | 487|idootop/mi-gpt !2025-03-281052522|? Transform XiaoAi speaker into a personal voice assistant with ChatGPT and DouBao integration.| | 488|SakanaAI/AI-Scientist !2025-03-281051310|The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬| | 489|szimek/sharedrop !2025-03-28105101|Easy P2P file transfer powered by WebRTC - inspired by Apple AirDrop| | 490|salesforce/LAVIS !2025-03-28103942 |LAVIS - A One-stop Library for Language-Vision Intelligence| | 491|aws/amazon-sagemaker-examples !2025-03-28103654|Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.| | 492|artidoro/qlora !2025-03-28103402 |QLoRA: Efficient Finetuning of Quantized LLMs| | 493|lllyasviel/stable-diffusion-webui-forge !2025-03-281029314| a platform on top of Stable Diffusion WebUI (based on Gradio) to make development easier, optimize resource management, and speed up inference| | 494|NielsRogge/Transformers-Tutorials !2025-03-28102487|This repository contains demos I made with the Transformers library by HuggingFace.| | 495|kedro-org/kedro !2025-03-28102371|Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.| | 496| chathub-dev/chathub !2025-03-28102301 | All-in-one chatbot client | | 497|microsoft/promptflow !2025-03-28101612|Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.| | 498|mistralai/mistral-src !2025-03-28101372|Reference implementation of Mistral AI 7B v0.1 model.| | 499|burn-rs/burn !2025-03-28101183|Burn - A Flexible and Comprehensive Deep Learning Framework in Rust| | 500|AIGC-Audio/AudioGPT !2025-03-28101150 |AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head| | 501|facebookresearch/dinov2 !2025-03-281011210 |PyTorch code and models for the DINOv2 self-supervised learning method.| | 502|RockChinQ/LangBot !2025-03-281008455|😎丰富生态、🧩支持扩展、🦄多模态 - 大模型原生即时通信机器人平台 🤖 | | 503|78/xiaozhi-esp32 !2025-03-281008180|Build your own AI friend| | 504|cumulo-autumn/StreamDiffusion !2025-03-28100761|StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation| | 505|DataTalksClub/machine-learning-zoomcamp !2025-03-28100664|The code from the Machine Learning Bookcamp book and a free course based on the book| | 506|nerfstudio-project/nerfstudio !2025-03-28100343|A collaboration friendly studio for NeRFs| | 507|cupy/cupy !2025-03-28100344|NumPy & SciPy for GPU| | 508|NVIDIA/TensorRT-LLM !2025-03-281000823|TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.| | 509|wasp-lang/open-saas !2025-03-2899665|A free, open-source SaaS app starter for React & Node.js with superpowers. Production-ready. Community-driven.| | 510|huggingface/text-generation-inference !2025-03-2899383|Large Language Model Text Generation Inference| | 511|jxnl/instructor !2025-03-2899224|structured outputs for llms| | 512|GoogleCloudPlatform/generative-ai !2025-03-2899086|Sample code and notebooks for Generative AI on Google Cloud| | 513|manticoresoftware/manticoresearch !2025-03-2898799|Easy to use open source fast database for search | | 514|langfuse/langfuse !2025-03-28985134|🪢 Open source LLM engineering platform. Observability, metrics, evals, prompt management, testing, prompt playground, datasets, LLM evaluations -- 🍊YC W23 🤖 integrate via Typescript, Python / Decorators, OpenAI, Langchain, LlamaIndex, Litellm, Instructor, Mistral, Perplexity, Claude, Gemini, Vertex| | 515|keephq/keep !2025-03-2897949|The open-source alert management and AIOps platform| | 516|sashabaranov/go-openai !2025-03-2897843|OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API wrapper for Go| | 517|autowarefoundation/autoware !2025-03-2897766|Autoware - the world's leading open-source software project for autonomous driving| | 518|anthropics/courses !2025-03-2897269|Anthropic's educational courses| | 519|popcorn-official/popcorn-desktop !2025-03-2896853|Popcorn Time is a multi-platform, free software BitTorrent client that includes an integrated media player ( Windows / Mac / Linux ) A Butter-Project Fork| | 520|getmaxun/maxun !2025-03-28968515|🔥 Open-source no-code web data extraction platform. Turn websites to APIs and spreadsheets with no-code robots in minutes! [In Beta]| | 521|wandb/wandb !2025-03-2896763|🔥 A tool for visualizing and tracking your machine learning experiments. This repo contains the CLI and Python API.| | 522|karpathy/minbpe !2025-03-2895353|Minimal, clean, code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.| | 523|bigscience-workshop/petals !2025-03-2895142|🌸 Run large language models at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading| | 524|OthersideAI/self-operating-computer !2025-03-2894931|A framework to enable multimodal models to operate a computer.| | 525|mshumer/gpt-prompt-engineer !2025-03-2894911|| | 526| BloopAI/bloop !2025-03-2894710 | A fast code search engine written in Rust| | 527|BlinkDL/ChatRWKV !2025-03-289467-1 |ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.| | 528|timlrx/tailwind-nextjs-starter-blog !2025-03-2894677|This is a Next.js, Tailwind CSS blogging starter template. Comes out of the box configured with the latest technologies to make technical writing a breeze. Easily configurable and customizable. Perfect as a replacement to existing Jekyll and Hugo individual blogs.| | 529|google/benchmark !2025-03-2893634|A microbenchmark support library| | 530|facebookresearch/nougat !2025-03-2893603|Implementation of Nougat Neural Optical Understanding for Academic Documents| | 531|modelscope/facechain !2025-03-2893536|FaceChain is a deep-learning toolchain for generating your Digital-Twin.| | 532|DrewThomasson/ebook2audiobook !2025-03-2893388|Convert ebooks to audiobooks with chapters and metadata using dynamic AI models and voice cloning. Supports 1,107+ languages!| | 533|RayTracing/raytracing.github.io !2025-03-2893035|Main Web Site (Online Books)| | 534|QwenLM/Qwen2.5-VL !2025-03-28930249|Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.| | 535|WongKinYiu/yolov9 !2025-03-2892201|Implementation of paper - YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information| | 536|alibaba-damo-academy/FunASR !2025-03-28920222|A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models.| | 537|Visualize-ML/Book4Power-of-Matrix !2025-03-2891931|Book4 'Power of Matrix' | | 538|dice2o/BingGPT !2025-03-289185-1 |Desktop application of new Bing's AI-powered chat (Windows, macOS and Linux)| | 539|browserbase/stagehand !2025-03-28917621|An AI web browsing framework focused on simplicity and extensibility.| | 540|FlagOpen/FlagEmbedding !2025-03-28914111|Dense Retrieval and Retrieval-augmented LLMs| | 541|Const-me/Whisper !2025-03-2890979|High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model| | 542|lucidrains/denoising-diffusion-pytorch !2025-03-2890942|Implementation of Denoising Diffusion Probabilistic Model in Pytorch| | 543|Chainlit/chainlit !2025-03-28904422|Build Conversational AI in minutes ⚡️| | 544|togethercomputer/OpenChatKit !2025-03-2890160 |OpenChatKit provides a powerful, open-source base to create both specialized and general purpose chatbots for various applications| | 545|Stability-AI/StableStudio !2025-03-2889631 |Community interface for generative AI| | 546|voicepaw/so-vits-svc-fork !2025-03-2889482 |so-vits-svc fork with realtime support, improved interface and more features.| | 547|pymc-devs/pymc !2025-03-2889413|Bayesian Modeling and Probabilistic Programming in Python| | 548|espnet/espnet !2025-03-2889302|End-to-End Speech Processing Toolkit| | 549|kedacore/keda !2025-03-2888991|KEDA is a Kubernetes-based Event Driven Autoscaling component. It provides event driven scale for any container running in Kubernetes| | 550|open-mmlab/Amphion !2025-03-28886911|Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.| | 551|gorse-io/gorse !2025-03-2888451|Gorse open source recommender system engine| | 552|adams549659584/go-proxy-bingai !2025-03-288768-1 |A Microsoft New Bing demo site built with Vue3 and Go, providing a consistent UI experience, supporting ChatGPT prompts, and accessible within China| | 553|open-mmlab/mmsegmentation !2025-03-2887513|OpenMMLab Semantic Segmentation Toolbox and Benchmark.| | 554|bytedance/monolith !2025-03-2887223|ByteDance's Recommendation System| | 555|LouisShark/chatgptsystemprompt !2025-03-2887216|store all agent's system prompt| | 556|brexhq/prompt-engineering !2025-03-2887080 |Tips and tricks for working with Large Language Models like OpenAI's GPT-4.| | 557|erincatto/box2d !2025-03-2886841|Box2D is a 2D physics engine for games| | 558|🔥microsoft/ai-agents-for-beginners !2025-03-288669323|10 Lessons to Get Started Building AI Agents| | 559|nashsu/FreeAskInternet !2025-03-2886102|FreeAskInternet is a completely free, private and locally running search aggregator & answer generate using LLM, without GPU needed. The user can ask a question and the system will make a multi engine search and combine the search result to the ChatGPT3.5 LLM and generate the answer based on search results.| | 560|goldmansachs/gs-quant !2025-03-2885981|Python toolkit for quantitative finance| | 561|srbhr/Resume-Matcher !2025-03-2885800|Open Source Free ATS Tool to compare Resumes with Job Descriptions and create a score to rank them.| | 562|facebookresearch/ImageBind !2025-03-2885681 |ImageBind One Embedding Space to Bind Them All| | 563|ashawkey/stable-dreamfusion !2025-03-2885481 |A pytorch implementation of text-to-3D dreamfusion, powered by stable diffusion.| | 564|meetecho/janus-gateway !2025-03-2885232|Janus WebRTC Server| | 565|google/magika !2025-03-2885003|Detect file content types with deep learning| | 566|huggingface/chat-ui !2025-03-2884871 |Open source codebase powering the HuggingChat app| | 567|EleutherAI/lm-evaluation-harness !2025-03-28843012|A framework for few-shot evaluation of autoregressive language models.| | 568|jina-ai/reader !2025-03-2884089|Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/| | 569|microsoft/TypeChat !2025-03-288406-1|TypeChat is a library that makes it easy to build natural language interfaces using types.| | 570|thuml/Time-Series-Library !2025-03-28839715|A Library for Advanced Deep Time Series Models.| | 571|OptimalScale/LMFlow !2025-03-2883882|An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Model for All.| | 572|baptisteArno/typebot.io !2025-03-2883845|💬 Typebot is a powerful chatbot builder that you can self-host.| | 573|jzhang38/TinyLlama !2025-03-2883504|The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.| | 574|fishaudio/Bert-VITS2 !2025-03-2883472|vits2 backbone with multilingual-bert| | 575|OpenBMB/XAgent !2025-03-2882683|An Autonomous LLM Agent for Complex Task Solving| | 576|Acly/krita-ai-diffusion !2025-03-2882387|Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.| | 577|jasonppy/VoiceCraft !2025-03-2882151|Zero-Shot Speech Editing and Text-to-Speech in the Wild| | 578|SJTU-IPADS/PowerInfer !2025-03-2881693|High-speed Large Language Model Serving on PCs with Consumer-grade GPUs| | 579|modelscope/DiffSynth-Studio !2025-03-28814713|Enjoy the magic of Diffusion models!| | 580|o3de/o3de !2025-03-2881443|Open 3D Engine (O3DE) is an Apache 2.0-licensed multi-platform 3D engine that enables developers and content creators to build AAA games, cinema-quality 3D worlds, and high-fidelity simulations without any fees or commercial obligations.| | 581|zmh-program/chatnio !2025-03-2881325|🚀 Next Generation AI One-Stop Internationalization Solution. 🚀 下一代 AI 一站式 B/C 端解决方案，支持 OpenAI，Midjourney，Claude，讯飞星火，Stable Diffusion，DALL·E，ChatGLM，通义千问，腾讯混元，360 智脑，百川 AI，火山方舟，新必应，Gemini，Moonshot 等模型，支持对话分享，自定义预设，云端同步，模型市场，支持弹性计费和订阅计划模式，支持图片解析，支持联网搜索，支持模型缓存，丰富美观的后台管理与仪表盘数据统计。| | 582|leptonai/searchwithlepton !2025-03-2880632|Building a quick conversation-based search demo with Lepton AI.| | 583|sebastianstarke/AI4Animation !2025-03-2880620|Bringing Characters to Life with Computer Brains in Unity| | 584|wangrongding/wechat-bot !2025-03-2880528|🤖一个基于 WeChaty 结合 DeepSeek / ChatGPT / Kimi / 讯飞等Ai服务实现的微信机器人 ，可以用来帮助你自动回复微信消息，或者管理微信群/好友，检测僵尸粉等...| | 585|openvinotoolkit/openvino !2025-03-2880528|OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference| | 586|steven2358/awesome-generative-ai !2025-03-28802610|A curated list of modern Generative Artificial Intelligence projects and services| | 587|adam-maj/tiny-gpu !2025-03-2880234|A minimal GPU design in Verilog to learn how GPUs work from the ground up| | 588| anse-app/chatgpt-demo !2025-03-2880180 | A demo repo based on OpenAI API (gpt-3.5-turbo) | | 589| acheong08/EdgeGPT !2025-03-288015-1 |Reverse engineered API of Microsoft's Bing Chat | | 590|ai-collection/ai-collection !2025-03-2879994 |The Generative AI Landscape - A Collection of Awesome Generative AI Applications| | 591|GreyDGL/PentestGPT !2025-03-2879953 |A GPT-empowered penetration testing tool| | 592|delta-io/delta !2025-03-2879112|An open-source storage framework that enables building a Lakehouse architecture with compute engines including Spark, PrestoDB, Flink, Trino, and Hive and APIs| | 593|dataelement/bisheng !2025-03-2879085|Bisheng is an open LLM devops platform for next generation AI applications.| | 594|e2b-dev/e2b !2025-03-2878447 |Vercel for AI agents. We help developers to build, deploy, and monitor AI agents. Focusing on specialized AI agents that build software for you - your personal software developers.| | 595|01-ai/Yi !2025-03-2878311|A series of large language models trained from scratch by developers @01-ai| | 596|Plachtaa/VALL-E-X !2025-03-287830-1|An open source implementation of Microsoft's VALL-E X zero-shot TTS model. The demo is available at https://plachtaa.github.io| | 597|abhishekkrthakur/approachingalmost !2025-03-2878204|Approaching (Almost) Any Machine Learning Problem| | 598|pydantic/pydantic-ai !2025-03-28781041|Agent Framework / shim to use Pydantic with LLMs| | 599|rany2/edge-tts !2025-03-2877901|Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key| | 600|CASIA-IVA-Lab/FastSAM !2025-03-2877881|Fast Segment Anything| | 601|netease-youdao/EmotiVoice !2025-03-2877817|EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine| | 602|lllyasviel/IC-Light !2025-03-2877804|More relighting!| | 603|kroma-network/tachyon !2025-03-287774-1|Modular ZK(Zero Knowledge) backend accelerated by GPU| | 604|deep-floyd/IF !2025-03-2877731 |A novel state-of-the-art open-source text-to-image model with a high degree of photorealism and language understanding| | 605|oumi-ai/oumi !2025-03-2877705|Everything you need to build state-of-the-art foundation models, end-to-end.| | 606|reorproject/reor !2025-03-2877681|AI note-taking app that runs models locally.| | 607|lightpanda-io/browser !2025-03-28775813|Lightpanda: the headless browser designed for AI and automation| | 608|xiangsx/gpt4free-ts !2025-03-287755-1|Providing a free OpenAI GPT-4 API ! This is a replication project for the typescript version of xtekky/gpt4free| | 609|IDEA-Research/GroundingDINO !2025-03-28773311|Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"| | 610|bunkerity/bunkerweb !2025-03-2877326|🛡️ Make your web services secure by default !| | 611|vikhyat/moondream !2025-03-2877057|tiny vision language model| | 612|firmai/financial-machine-learning !2025-03-287703-1|A curated list of practical financial machine learning tools and applications.| | 613|n8n-io/self-hosted-ai-starter-kit !2025-03-28765121|The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.| | 614|intel-analytics/ipex-llm !2025-03-2876507|Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max). A PyTorch LLM library that seamlessly integrates with llama.cpp, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, ModelScope, etc.| | 615|jrouwe/JoltPhysics !2025-03-28764510|A multi core friendly rigid body physics and collision detection library. Written in C++. Suitable for games and VR applications. Used by Horizon Forbidden West.| | 616|THUDM/CodeGeeX2 !2025-03-2876270|CodeGeeX2: A More Powerful Multilingual Code Generation Model| | 617|meta-llama/llama-stack !2025-03-2875866|Composable building blocks to build Llama Apps| | 618|sweepai/sweep !2025-03-287530-1|Sweep is an AI junior developer| | 619|lllyasviel/Omost !2025-03-2875301|Your image is almost there!| | 620|ahmedbahaaeldin/From-0-to-Research-Scientist-resources-guide !2025-03-2875050|Detailed and tailored guide for undergraduate students or anybody want to dig deep into the field of AI with solid foundation.| | 621|dair-ai/ML-Papers-Explained !2025-03-2875050|Explanation to key concepts in ML| | 622|zaidmukaddam/scira !2025-03-28750110|Scira (Formerly MiniPerplx) is a minimalistic AI-powered search engine that helps you find information on the internet. Powered by Vercel AI SDK! Search with models like Grok 2.0.| | 623|Portkey-AI/gateway !2025-03-28749416|A Blazing Fast AI Gateway. Route to 100+ LLMs with 1 fast & friendly API.| | 624|web-infra-dev/midscene !2025-03-28748729|An AI-powered automation SDK can control the page, perform assertions, and extract data in JSON format using natural language.| | 625|zilliztech/GPTCache !2025-03-2874801 |GPTCache is a library for creating semantic cache to store responses from LLM queries.| | 626|niedev/RTranslator !2025-03-2874742|RTranslator is the world's first open source real-time translation app.| |!green-up-arrow.svg 627|roboflow/notebooks !2025-03-2874666|Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM.| |!red-down-arrow 628|openlm-research/openllama !2025-03-2874652|OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset| | 629|LiheYoung/Depth-Anything !2025-03-2874155|Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data| | 630|enso-org/enso !2025-03-2874040|Hybrid visual and textual functional programming.| | 631|bigcode-project/starcoder !2025-03-287401-1 |Home of StarCoder: fine-tuning & inference!| | 632|git-ecosystem/git-credential-manager !2025-03-2873975|Secure, cross-platform Git credential storage with authentication to GitHub, Azure Repos, and other popular Git hosting services.| | 633|OpenGVLab/InternVL !2025-03-2873634|[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源模型| | 634|WooooDyy/LLM-Agent-Paper-List !2025-03-2873551|The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.| | 635|lencx/Noi !2025-03-2873157|🦄 AI + Tools + Plugins + Community| | 636|udlbook/udlbook !2025-03-2873075|Understanding Deep Learning - Simon J.D. Prince| | 637|OpenBMB/MiniCPM !2025-03-2872841|MiniCPM-2B: An end-side LLM outperforms Llama2-13B.| | 638|jaywalnut310/vits !2025-03-2872815 |VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech| | 639|xorbitsai/inference !2025-03-28727528|Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.| | 640|PWhiddy/PokemonRedExperiments !2025-03-2872492|Playing Pokemon Red with Reinforcement Learning| | 641|Canner/WrenAI !2025-03-28723213|🤖 Open-source AI Agent that empowers data-driven teams to chat with their data to generate Text-to-SQL, charts, spreadsheets, reports, and BI. 📈📊📋🧑‍💻| | 642|miurla/morphic !2025-03-2872258|An AI-powered answer engine with a generative UI| | 643|ml-explore/mlx-examples !2025-03-2872168|Examples in the MLX framework| | 644|PKU-YuanGroup/ChatLaw !2025-03-2872010|Chinese Legal Large Model| | 645|NVIDIA/cutlass !2025-03-2871883|CUDA Templates for Linear Algebra Subroutines| | 646|FoundationVision/VAR !2025-03-28717444|[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction"| | 647|ymcui/Chinese-LLaMA-Alpaca-2 !2025-03-2871561|Chinese LLaMA-2 & Alpaca-2 LLMs| | 648|nadermx/backgroundremover !2025-03-2871514 |Background Remover lets you Remove Background from images and video using AI with a simple command line interface that is free and open source.| | 649|onuratakan/gpt-computer-assistant !2025-03-28714514|gpt-4o for windows, macos and ubuntu| | 650|graviraja/MLOps-Basics !2025-03-2871326|| | 651|Future-House/paper-qa !2025-03-287118-1|High accuracy RAG for answering questions from scientific documents with citations| | 652|open-mmlab/mmagic !2025-03-2871102 |OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox| | 653|bhaskatripathi/pdfGPT !2025-03-2870941 |PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The only open source solution to turn your pdf files in a chatbot!| | 654|ollama/ollama-python !2025-03-28709117|Ollama Python library| | 655|facebookresearch/DiT !2025-03-2870376|Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"| | 656|geekyutao/Inpaint-Anything !2025-03-2870262 |Inpaint anything using Segment Anything and inpainting models.| | 657|AbdullahAlfaraj/Auto-Photoshop-StableDiffusion-Plugin !2025-03-2870160 |A user-friendly plug-in that makes it easy to generate stable diffusion images inside Photoshop using Automatic1111-sd-webui as a backend.| | 658|apple/corenet !2025-03-2869990|CoreNet: A library for training deep neural networks| | 659|openstatusHQ/openstatus !2025-03-2869926|🏓 The open-source synthetic monitoring platform 🏓| | 660|weaviate/Verba !2025-03-2869772|Retrieval Augmented Generation (RAG) chatbot powered by Weaviate| | 661|meshery/meshery !2025-03-2869630|Meshery, the cloud native manager| | 662|OpenTalker/video-retalking !2025-03-2869530|[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild| | 663|digitalinnovationone/dio-lab-open-source !2025-03-28689013|Repositório do lab "Contribuindo em um Projeto Open Source no GitHub" da Digital Innovation One.| | 664|jianchang512/ChatTTS-ui !2025-03-2868842|一个简单的本地网页界面，直接使用ChatTTS将文字合成为语音，同时支持对外提供API接口。| | 665|patchy631/ai-engineering-hub !2025-03-28686434|In-depth tutorials on LLMs, RAGs and real-world AI agent applications.| | 666|gunnarmorling/1brc !2025-03-2868512|1️⃣🐝🏎️ The One Billion Row Challenge -- A fun exploration of how quickly 1B rows from a text file can be aggregated with Java| | 667|Azure-Samples/azure-search-openai-demo !2025-03-2868482 |A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.| | 668|mit-han-lab/streaming-llm !2025-03-2868382|Efficient Streaming Language Models with Attention Sinks| | 669|InternLM/InternLM !2025-03-2868352|InternLM has open-sourced a 7 billion parameter base model, a chat model tailored for practical scenarios and the training system.| | 670|dependency-check/DependencyCheck !2025-03-2868191|OWASP dependency-check is a software composition analysis utility that detects publicly disclosed vulnerabilities in application dependencies.| | 671|Soulter/AstrBot !2025-03-28678643|✨易上手的多平台 LLM 聊天机器人及开发框架✨。支持 QQ、QQ频道、Telegram、微信平台(Gewechat, 企业微信)、内置 Web Chat，OpenAI GPT、DeepSeek、Ollama、Llama、GLM、Gemini、OneAPI、LLMTuner，支持 LLM Agent 插件开发，可视化面板。一键部署。支持 Dify 工作流、代码执行器、Whisper 语音转文字。| | 672|react-native-webview/react-native-webview !2025-03-2867792|React Native Cross-Platform WebView| | 673|modelscope/agentscope !2025-03-28676916|Start building LLM-empowered multi-agent applications in an easier way.| | 674|mylxsw/aidea !2025-03-2867381|AIdea is a versatile app that supports GPT and domestic large language models，also supports "Stable Diffusion" text-to-image generation, image-to-image generation, SDXL 1.0, super-resolution, and image colorization| | 675|langchain-ai/ollama-deep-researcher !2025-03-28668635|Fully local web research and report writing assistant| | 676|threestudio-project/threestudio !2025-03-2866653|A unified framework for 3D content generation.| | 677|gaomingqi/Track-Anything !2025-03-2866631 |A flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.| | 678|spdustin/ChatGPT-AutoExpert !2025-03-2866570|🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding).| | 679|HariSekhon/DevOps-Bash-tools !2025-03-2866463|1000+ DevOps Bash Scripts - AWS, GCP, Kubernetes, Docker, CI/CD, APIs, SQL, PostgreSQL, MySQL, Hive, Impala, Kafka, Hadoop, Jenkins, GitHub, GitLab, BitBucket, Azure DevOps, TeamCity, Spotify, MP3, LDAP, Code/Build Linting, pkg mgmt for Linux, Mac, Python, Perl, Ruby, NodeJS, Golang, Advanced dotfiles: .bashrc, .vimrc, .gitconfig, .screenrc, tmux..| | 680|modelscope/swift !2025-03-28661530|ms-swift: Use PEFT or Full-parameter to finetune 200+ LLMs or 15+ MLLMs| | 681|langchain-ai/opengpts !2025-03-2866080|This is an open source effort to create a similar experience to OpenAI's GPTs and Assistants API| | 682| yihong0618/xiaogpt !2025-03-2865131 | Play ChatGPT with xiaomi ai speaker | | 683| civitai/civitai !2025-03-2865111 | Build a platform where people can share their stable diffusion models | | 684|KoljaB/RealtimeSTT !2025-03-28649513|A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.| | 685|qunash/chatgpt-advanced !2025-03-2864910 | A browser extension that augments your ChatGPT prompts with web results.| | 686|Licoy/ChatGPT-Midjourney !2025-03-2864850|🎨 Own your own ChatGPT+Midjourney web service with one click| | 687|friuns2/BlackFriday-GPTs-Prompts !2025-03-2864744|List of free GPTs that doesn't require plus subscription| | 688|PixarAnimationStudios/OpenUSD !2025-03-2864700|Universal Scene Description| | 689|linyiLYi/street-fighter-ai !2025-03-2864630 |This is an AI agent for Street Fighter II Champion Edition.| | 690|run-llama/rags !2025-03-2864380|Build ChatGPT over your data, all with natural language| | 691|frdel/agent-zero !2025-03-2864154|Agent Zero AI framework| | 692|microsoft/DeepSpeedExamples !2025-03-2863911 |Example models using DeepSpeed| | 693|k8sgpt-ai/k8sgpt !2025-03-2863882|Giving Kubernetes Superpowers to everyone| | 694|open-metadata/OpenMetadata !2025-03-2863514|OpenMetadata is a unified platform for discovery, observability, and governance powered by a central metadata repository, in-depth lineage, and seamless team collaboration.| | 695|google/gemma.cpp !2025-03-2863163|lightweight, standalone C++ inference engine for Google's Gemma models.| | 696|RayVentura/ShortGPT !2025-03-286314-1|🚀🎬 ShortGPT - An experimental AI framework for automated short/video content creation. Enables creators to rapidly produce, manage, and deliver content using AI and automation.| | 697|openai/consistencymodels !2025-03-2862940 |Official repo for consistency models.| | 698|yangjianxin1/Firefly !2025-03-2862924|Firefly: Chinese conversational large language model (full-scale fine-tuning + QLoRA), supporting fine-tuning of Llma2, Llama, Baichuan, InternLM, Ziya, Bloom, and other large models| | 699|enricoros/big-AGI !2025-03-2862665|Generative AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. It features AI personas, AGI functions, multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.| | 700|aptos-labs/aptos-core !2025-03-2862633|Aptos is a layer 1 blockchain built to support the widespread use of blockchain through better technology and user experience.| | 701|wenda-LLM/wenda !2025-03-286262-1 |Wenda: An LLM invocation platform. Its objective is to achieve efficient content generation tailored to specific environments while considering the limited computing resources of individuals and small businesses, as well as knowledge security and privacy concerns| | 702|Project-MONAI/MONAI !2025-03-2862603|AI Toolkit for Healthcare Imaging| | 703|HVision-NKU/StoryDiffusion !2025-03-2862470|Create Magic Story!| | 704|deepseek-ai/DeepSeek-LLM !2025-03-2862463|DeepSeek LLM: Let there be answers| | 705|Tohrusky/Final2x !2025-03-2862393|2^x Image Super-Resolution| | 706|OpenSPG/KAG !2025-03-28619611|KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge bases. It can effectively overcome the shortcomings of the traditional RAG vector similarity calculation model.| | 707|Moonvy/OpenPromptStudio !2025-03-2861861 |AIGC Hint Word Visualization Editor| | 708|levihsu/OOTDiffusion !2025-03-2861761|Official implementation of OOTDiffusion| | 709|tmc/langchaingo !2025-03-2861729|LangChain for Go, the easiest way to write LLM-based programs in Go| | 710|vladmandic/automatic !2025-03-2861374|SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models| | 711|clovaai/donut !2025-03-2861231 |Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022| | 712|Shaunwei/RealChar !2025-03-286121-1|🎙️🤖Create, Customize and Talk to your AI Character/Companion in Realtime(All in One Codebase!). Have a natural seamless conversation with AI everywhere(mobile, web and terminal) using LLM OpenAI GPT3.5/4, Anthropic Claude2, Chroma Vector DB, Whisper Speech2Text, ElevenLabs Text2Speech🎙️🤖| | 713|microsoft/TinyTroupe !2025-03-2861142|LLM-powered multiagent persona simulation for imagination enhancement and business insights.| | 714| rustformers/llm !2025-03-2861010 | Run inference for Large Language Models on CPU, with Rust| | 715|firebase/firebase-ios-sdk !2025-03-2860950|Firebase SDK for Apple App Development| | 716|vespa-engine/vespa !2025-03-2860824|The open big data serving engine. https://vespa.ai| | 717|n4ze3m/page-assist !2025-03-28607610|Use your locally running AI models to assist you in your web browsing| | 718|Dooy/chatgpt-web-midjourney-proxy !2025-03-2860646|chatgpt web, midjourney, gpts,tts, whisper 一套ui全搞定| | 719|ethereum-optimism/optimism !2025-03-2860213|Optimism is Ethereum, scaled.| | 720|sczhou/ProPainter !2025-03-2859971|[ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting| | 721|MineDojo/Voyager !2025-03-2859951 |An Open-Ended Embodied Agent with Large Language Models| | 722|lavague-ai/LaVague !2025-03-2859800|Automate automation with Large Action Model framework| | 723|SevaSk/ecoute !2025-03-2859770 |Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.| | 724|google/mesop !2025-03-2859661|| | 725|pengxiao-song/LaWGPT !2025-03-2859542 |Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge| | 726|fr0gger/Awesome-GPT-Agents !2025-03-2859434|A curated list of GPT agents for cybersecurity| | 727|google-deepmind/graphcast !2025-03-2859412|| | 728|comet-ml/opik !2025-03-28594126|Open-source end-to-end LLM Development Platform| | 729|SciPhi-AI/R2R !2025-03-28594033|A framework for rapid development and deployment of production-ready RAG systems| | 730|SkalskiP/courses !2025-03-2859272 |This repository is a curated collection of links to various courses and resources about Artificial Intelligence (AI)| | 731|QuivrHQ/MegaParse !2025-03-2859122|File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.| | 732|pytorch-labs/gpt-fast !2025-03-2858971|Simple and efficient pytorch-native transformer text generation in !2025-03-2858886|Curated list of chatgpt prompts from the top-rated GPTs in the GPTs Store. Prompt Engineering, prompt attack & prompt protect. Advanced Prompt Engineering papers.| | 734|nilsherzig/LLocalSearch !2025-03-2858852|LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.| | 735|kuafuai/DevOpsGPT !2025-03-285874-2|Multi agent system for AI-driven software development. Convert natural language requirements into working software. Supports any development language and extends the existing base code.| | 736|myshell-ai/MeloTTS !2025-03-2858486|High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.| | 737|OpenGVLab/LLaMA-Adapter !2025-03-2858421 |Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters| | 738|volcengine/verl !2025-03-28582563|veRL: Volcano Engine Reinforcement Learning for LLM| | 739|a16z-infra/companion-app !2025-03-2858171|AI companions with memory: a lightweight stack to create and host your own AI companions| | 740|HumanAIGC/OutfitAnyone !2025-03-285816-1|Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person| | 741|josStorer/RWKV-Runner !2025-03-2857472|A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.| | 742|648540858/wvp-GB28181-pro !2025-03-2857414|WEB VIDEO PLATFORM是一个基于GB28181-2016标准实现的网络视频平台，支持NAT穿透，支持海康、大华、宇视等品牌的IPC、NVR、DVR接入。支持国标级联，支持rtsp/rtmp等视频流转发到国标平台，支持rtsp/rtmp等推流转发到国标平台。| | 743|ToonCrafter/ToonCrafter !2025-03-2857345|a research paper for generative cartoon interpolation| | 744|PawanOsman/ChatGPT !2025-03-2857191|OpenAI API Free Reverse Proxy| | 745|apache/hudi !2025-03-2857091|Upserts, Deletes And Incremental Processing on Big Data.| | 746| nsarrazin/serge !2025-03-2857081 | A web interface for chatting with Alpaca through llama.cpp. Fully dockerized, with an easy to use API| | 747|homanp/superagent !2025-03-2857021|🥷 Superagent - Build, deploy, and manage LLM-powered agents| | 748|ramonvc/freegpt-webui !2025-03-2856910|GPT 3.5/4 with a Chat Web UI. No API key is required.| | 749|baichuan-inc/baichuan-7B !2025-03-2856901|A large-scale 7B pretraining language model developed by BaiChuan-Inc.| | 750|Azure/azure-sdk-for-net !2025-03-2856792|This repository is for active development of the Azure SDK for .NET. For consumers of the SDK we recommend visiting our public developer docs at https://learn.microsoft.com/dotnet/azure/ or our versioned developer docs at https://azure.github.io/azure-sdk-for-net.| | 751|mnotgod96/AppAgent !2025-03-2856643|AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.| | 752|microsoft/TaskWeaver !2025-03-2856243|A code-first agent framework for seamlessly planning and executing data analytics tasks.| | 753| yetone/bob-plugin-openai-translator !2025-03-285600-1 | A Bob Plugin base ChatGPT API | | 754|PrefectHQ/marvin !2025-03-2855840 |A batteries-included library for building AI-powered software| | 755|microsoft/promptbase !2025-03-2855832|All things prompt engineering| | 756|fullstackhero/dotnet-starter-kit !2025-03-2855560|Production Grade Cloud-Ready .NET 8 Starter Kit (Web API + Blazor Client) with Multitenancy Support, and Clean/Modular Architecture that saves roughly 200+ Development Hours! All Batteries Included.| | 757|deepseek-ai/DeepSeek-Coder-V2 !2025-03-2855435|DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence| | 758|aiwaves-cn/agents !2025-03-2855391|An Open-source Framework for Autonomous Language Agents| | 759|microsoft/Mastering-GitHub-Copilot-for-Paired-Programming !2025-03-2855158|A 6 Lesson course teaching everything you need to know about harnessing GitHub Copilot and an AI Paired Programing resource.| | 760|allenai/OLMo !2025-03-2854506|Modeling, training, eval, and inference code for OLMo| | 761|apify/crawlee-python !2025-03-2854493|Crawlee—A web scraping and browser automation library for Python to build reliable crawlers. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with BeautifulSoup, Playwright, and raw HTTP. Both headful and headless mode. With proxy rotation.| | 762|k2-fsa/sherpa-onnx !2025-03-28541520|Speech-to-text, text-to-speech, and speaker recongition using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 servers, websocket server/client, C/C++, Python, Kotlin, C#, Go, NodeJS, Java, Swift| | 763|TEN-framework/TEN-Agent !2025-03-28541411|TEN Agent is a realtime conversational AI agent powered by TEN. It seamlessly integrates the OpenAI Realtime API, RTC capabilities, and advanced features like weather updates, web search, computer vision, and Retrieval-Augmented Generation (RAG).| | 764|google/gemmapytorch !2025-03-2854010|The official PyTorch implementation of Google's Gemma models| | 765|snakers4/silero-vad !2025-03-2853858|Silero VAD: pre-trained enterprise-grade Voice Activity Detector| | 766|livekit/agents !2025-03-2853836|Build real-time multimodal AI applications 🤖🎙️📹| | 767|pipecat-ai/pipecat !2025-03-28537811|Open Source framework for voice and multimodal conversational AI| | 768|EricLBuehler/mistral.rs !2025-03-28536324|Blazingly fast LLM inference.| | 769|asg017/sqlite-vec !2025-03-28535810|Work-in-progress vector search SQLite extension that runs anywhere.| | 770|albertan017/LLM4Decompile !2025-03-2853563|Reverse Engineering: Decompiling Binary Code with Large Language Models| | 771|Permify/permify !2025-03-2853235|An open-source authorization as a service inspired by Google Zanzibar, designed to build and manage fine-grained and scalable authorization systems for any application.| | 772|imoneoi/openchat !2025-03-2853171|OpenChat: Advancing Open-source Language Models with Imperfect Data| | 773|mosaicml/composer !2025-03-2853140|Train neural networks up to 7x faster| | 774|dsdanielpark/Bard-API !2025-03-285277-1 |The python package that returns a response of Google Bard through API.| | 775|lxfater/inpaint-web !2025-03-2852552|A free and open-source inpainting & image-upscaling tool powered by webgpu and wasm on the browser。| | 776|leanprover/lean4 !2025-03-2852441|Lean 4 programming language and theorem prover| | 777|AILab-CVC/YOLO-World !2025-03-2852415|Real-Time Open-Vocabulary Object Detection| | 778|openchatai/OpenChat !2025-03-2852260 |Run and create custom ChatGPT-like bots with OpenChat, embed and share these bots anywhere, the open-source chatbot console.| | 779|mufeedvh/code2prompt !2025-03-28519414|A CLI tool to convert your codebase into a single LLM prompt with source tree, prompt templating, and token counting.| | 780|biobootloader/wolverine !2025-03-2851700 |Automatically repair python scripts through GPT-4 to give them regenerative abilities.| | 781|huggingface/parler-tts !2025-03-2851671|Inference and training library for high-quality TTS models.| | 782|Akegarasu/lora-scripts !2025-03-2851308 |LoRA training scripts use kohya-ss's trainer, for diffusion model.| | 783|openchatai/OpenCopilot !2025-03-285128-3|🤖 🔥 Let your users chat with your product features and execute things by text - open source Shopify sidekick| | 784|e2b-dev/fragments !2025-03-2851228|Open-source Next.js template for building apps that are fully generated by AI. By E2B.| | 785|microsoft/SynapseML !2025-03-2851132|Simple and Distributed Machine Learning| | 786|aigc-apps/sd-webui-EasyPhoto !2025-03-285108-1|📷 EasyPhoto | | 787|ChaoningZhang/MobileSAM !2025-03-2850944|This is the official code for Faster Segment Anything (MobileSAM) project that makes SAM lightweight| | 788|huggingface/alignment-handbook !2025-03-2850932|Robust recipes for to align language models with human and AI preferences| | 789|alpkeskin/mosint !2025-03-2850920|An automated e-mail OSINT tool| | 790|TaskingAI/TaskingAI !2025-03-2850891|The open source platform for AI-native application development.| | 791|lipku/metahuman-stream !2025-03-28507615|Real time interactive streaming digital human| | 792|OpenInterpreter/01 !2025-03-2850530|The open-source language model computer| | 793|open-compass/opencompass !2025-03-28505111|OpenCompass is an LLM evaluation platform, supporting a wide range of models (InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.| | 794|xxlong0/Wonder3D !2025-03-2850491|A cross-domain diffusion model for 3D reconstruction from a single image| | 795|pytorch/torchtune !2025-03-2850342|A Native-PyTorch Library for LLM Fine-tuning| | 796|SuperDuperDB/superduperdb !2025-03-2850192|🔮 SuperDuperDB: Bring AI to your database: Integrate, train and manage any AI models and APIs directly with your database and your data.| | 797|WhiskeySockets/Baileys !2025-03-2850057|Lightweight full-featured typescript/javascript WhatsApp Web API| | 798| mpociot/chatgpt-vscode !2025-03-2849890 | A VSCode extension that allows you to use ChatGPT | | 799|OpenGVLab/DragGAN !2025-03-2849880|Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）| | 800|microsoft/LLMLingua !2025-03-2849824|To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.| | 801|Zipstack/unstract !2025-03-2849745|No-code LLM Platform to launch APIs and ETL Pipelines to structure unstructured documents| | 802|OpenBMB/ToolBench !2025-03-2849621|An open platform for training, serving, and evaluating large language model for tool learning.| | 803|Fanghua-Yu/SUPIR !2025-03-2849593|SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild| | 804|GaiaNet-AI/gaianet-node !2025-03-2849360|Install and run your own AI agent service| | 805|qodo-ai/qodo-cover !2025-03-284922-1|Qodo-Cover: An AI-Powered Tool for Automated Test Generation and Code Coverage Enhancement! 💻🤖🧪🐞| | 806|Zejun-Yang/AniPortrait !2025-03-2849042|AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation| | 807|lvwzhen/law-cn-ai !2025-03-2848901 |⚖️ AI Legal Assistant| | 808|developersdigest/llm-answer-engine !2025-03-2848740|Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Mixtral, Langchain, OpenAI, Brave & Serper| | 809|Plachtaa/VITS-fast-fine-tuning !2025-03-2848640|This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion| | 810|espeak-ng/espeak-ng !2025-03-2848601|eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.| | 811|ant-research/CoDeF !2025-03-2848581|[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing| | 812|deepseek-ai/DeepSeek-V2 !2025-03-2848512|| | 813|XRPLF/rippled !2025-03-2848210|Decentralized cryptocurrency blockchain daemon implementing the XRP Ledger protocol in C++| | 814|AutoMQ/automq !2025-03-28478721|AutoMQ is a cloud-first alternative to Kafka by decoupling durability to S3 and EBS. 10x cost-effective. Autoscale in seconds. Single-digit ms latency.| | 815|AILab-CVC/VideoCrafter !2025-03-2847800|VideoCrafter1: Open Diffusion Models for High-Quality Video Generation| | 816|nautechsystems/nautilustrader !2025-03-2847702|A high-performance algorithmic trading platform and event-driven backtester| | 817|kyegomez/swarms !2025-03-2847563|The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework Join our Community: https://discord.com/servers/agora-999382051935506503| | 818|Deci-AI/super-gradients !2025-03-2847310 |Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.| | 819|QwenLM/Qwen2.5-Coder !2025-03-2847236|Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.| | 820|SCIR-HI/Huatuo-Llama-Med-Chinese !2025-03-2847191 |Repo for HuaTuo (华驼), Llama-7B tuned with Chinese medical knowledge| | 821|togethercomputer/RedPajama-Data !2025-03-2846841 |code for preparing large datasets for training large language models| | 822|mishushakov/llm-scraper !2025-03-2846704|Turn any webpage into structured data using LLMs| | 823|1rgs/jsonformer !2025-03-2846663 |A Bulletproof Way to Generate Structured JSON from Language Models| | 824|anti-work/shortest !2025-03-2846565|QA via natural language AI tests| | 825|dnhkng/GlaDOS !2025-03-2846510|This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.| | 826|Nukem9/dlssg-to-fsr3 !2025-03-2846380|Adds AMD FSR3 Frame Generation to games by replacing Nvidia DLSS-G Frame Generation (nvngx_dlssg).| | 827|BuilderIO/ai-shell !2025-03-2846373 |A CLI that converts natural language to shell commands.| | 828|facebookincubator/AITemplate !2025-03-2846220 |AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.| | 829|terraform-aws-modules/terraform-aws-eks !2025-03-2846030|Terraform module to create AWS Elastic Kubernetes (EKS) resources 🇺🇦| | 830|timescale/pgai !2025-03-2845915|A suite of tools to develop RAG, semantic search, and other AI applications more easily with PostgreSQL| | 831|awslabs/multi-agent-orchestrator !2025-03-2845788|Flexible and powerful framework for managing multiple AI agents and handling complex conversations| | 832|sanchit-gandhi/whisper-jax !2025-03-2845771 |Optimised JAX code for OpenAI's Whisper Model, largely built on the Hugging Face Transformers Whisper implementation| | 833|NVIDIA/NeMo-Guardrails !2025-03-2845755|NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.| | 834|PathOfBuildingCommunity/PathOfBuilding !2025-03-2845480|Offline build planner for Path of Exile.| | 835|UX-Decoder/Segment-Everything-Everywhere-All-At-Once !2025-03-2845412 |Official implementation of the paper "Segment Everything Everywhere All at Once"| | 836|build-trust/ockam !2025-03-2845171|Orchestrate end-to-end encryption, cryptographic identities, mutual authentication, and authorization policies between distributed applications – at massive scale.| | 837|google-research/timesfm !2025-03-2845135|TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.| | 838|luosiallen/latent-consistency-model !2025-03-2844842|Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference| | 839|NVlabs/neuralangelo !2025-03-2844740|Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)| | 840|kyegomez/tree-of-thoughts !2025-03-2844720 |Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%| | 841|sjvasquez/handwriting-synthesis !2025-03-2844720 |Handwriting Synthesis with RNNs ✏️| | 842| madawei2699/myGPTReader !2025-03-2844420 | A slack bot that can read any webpage, ebook or document and summarize it with chatGPT | | 843|OpenBMB/AgentVerse !2025-03-2844413|🤖 AgentVerse 🪐 provides a flexible framework that simplifies the process of building custom multi-agent environments for large language models (LLMs).| | 844|argmaxinc/WhisperKit !2025-03-2844395|Swift native speech recognition on-device for iOS and macOS applications.| | 845|landing-ai/vision-agent !2025-03-2844346|Vision agent| | 846|InternLM/xtuner !2025-03-2844273|An efficient, flexible and full-featured toolkit for fine-tuning large models (InternLM, Llama, Baichuan, Qwen, ChatGLM)| | 847|google-deepmind/alphageometry !2025-03-284421-1|Solving Olympiad Geometry without Human Demonstrations| | 848|ostris/ai-toolkit !2025-03-2844093|Various AI scripts. Mostly Stable Diffusion stuff.| | 849|LLM-Red-Team/kimi-free-api !2025-03-2844004|🚀 KIMI AI 长文本大模型白嫖服务，支持高速流式输出、联网搜索、长文档解读、图像解析、多轮对话，零配置部署，多路token支持，自动清理会话痕迹。| | 850|argilla-io/argilla !2025-03-2843991|Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.| | 851|spring-projects/spring-ai !2025-03-28438419|An Application Framework for AI Engineering| | 852|alibaba-damo-academy/FunClip !2025-03-2843555|Open-source, accurate and easy-to-use video clipping tool, LLM based AI clipping intergrated | | 853|yisol/IDM-VTON !2025-03-2843541|IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild| | 854|fchollet/ARC-AGI !2025-03-2843368|The Abstraction and Reasoning Corpus| | 855|MahmoudAshraf97/whisper-diarization !2025-03-2843064|Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper| | 856|Speykious/cve-rs !2025-03-2843047|Blazingly 🔥 fast 🚀 memory vulnerabilities, written in 100% safe Rust. 🦀| | 857|Blealtan/efficient-kan !2025-03-2842770|An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).| | 858|smol-ai/GodMode !2025-03-284249-1|AI Chat Browser: Fast, Full webapp access to ChatGPT / Claude / Bard / Bing / Llama2! I use this 20 times a day.| | 859|openai/plugins-quickstart !2025-03-284235-4 |Get a ChatGPT plugin up and running in under 5 minutes!| | 860|Doriandarko/maestro !2025-03-2842260|A framework for Claude Opus to intelligently orchestrate subagents.| | 861|philz1337x/clarity-upscaler !2025-03-2842204|Clarity-Upscaler: Reimagined image upscaling for everyone| | 862|facebookresearch/co-tracker !2025-03-2842142|CoTracker is a model for tracking any point (pixel) on a video.| | 863|xlang-ai/OpenAgents !2025-03-2842031|OpenAgents: An Open Platform for Language Agents in the Wild| | 864|alibaba/higress !2025-03-28419514|🤖 AI Gateway | | 865|ray-project/llm-numbers !2025-03-2841920 |Numbers every LLM developer should know| | 866|fudan-generative-vision/champ !2025-03-2841820|Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance| | 867|NVIDIA/garak !2025-03-2841795|the LLM vulnerability scanner| | 868|leetcode-mafia/cheetah !2025-03-2841740 |Whisper & GPT-based app for passing remote SWE interviews| | 869|ragapp/ragapp !2025-03-2841710|The easiest way to use Agentic RAG in any enterprise| | 870|collabora/WhisperSpeech !2025-03-2841692|An Open Source text-to-speech system built by inverting Whisper.| | 871|Facico/Chinese-Vicuna !2025-03-2841520 |Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model| | 872|openai/grok !2025-03-2841381|| | 873|CrazyBoyM/llama3-Chinese-chat !2025-03-2841361|Llama3 Chinese Repository with modified versions, and training and deployment resources| | 874|luban-agi/Awesome-AIGC-Tutorials !2025-03-2841301|Curated tutorials and resources for Large Language Models, AI Painting, and more.| | 875|damo-vilab/AnyDoor !2025-03-2841192|Official implementations for paper: Anydoor: zero-shot object-level image customization| | 876|raspberrypi/pico-sdk !2025-03-2841072|| | 877|mshumer/gpt-llm-trainer !2025-03-284097-1|| | 878|metavoiceio/metavoice-src !2025-03-284076-1|AI for human-level speech intelligence| | 879|intelowlproject/IntelOwl !2025-03-2840763|IntelOwl: manage your Threat Intelligence at scale| | 880|a16z-infra/ai-getting-started !2025-03-2840682|A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs| | 881|MarkFzp/mobile-aloha !2025-03-2840641|Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation| | 882| keijiro/AICommand !2025-03-2840380 | ChatGPT integration with Unity Editor | | 883|Tencent/HunyuanDiT !2025-03-2840214|Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding| | 884|hengyoush/kyanos !2025-03-2840061|Visualize the time packets spend in the kernel, watch & analyze in command line.| | 885|agiresearch/AIOS !2025-03-2840045|AIOS: LLM Agent Operating System| | 886|truefoundry/cognita !2025-03-2839773|RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry| | 887|X-PLUG/MobileAgent !2025-03-2839557|Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception| | 888|jackMort/ChatGPT.nvim !2025-03-2839231|ChatGPT Neovim Plugin: Effortless Natural Language Generation with OpenAI's ChatGPT API| | 889|microsoft/RD-Agent !2025-03-28388422|Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are committed to automate these high-value generic R&D processes through our open source R&D automation tool RD-Agent, which let AI drive data-driven AI.| | 890|Significant-Gravitas/Auto-GPT-Plugins !2025-03-283882-1 |Plugins for Auto-GPT| | 891|apple/ml-mgie !2025-03-2838770|| | 892|OpenDriveLab/UniAD !2025-03-2838727|[CVPR 2023 Best Paper] Planning-oriented Autonomous Driving| | 893|llSourcell/DoctorGPT !2025-03-2838640|DoctorGPT is an LLM that can pass the US Medical Licensing Exam. It works offline, it's cross-platform, & your health data stays private.| | 894|FlagAI-Open/FlagAI !2025-03-2838601|FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.| | 895|krishnaik06/Roadmap-To-Learn-Generative-AI-In-2024 !2025-03-2838513|Roadmap To Learn Generative AI In 2024| | 896|SysCV/sam-hq !2025-03-2838491|Segment Anything in High Quality| | 897|google/security-research !2025-03-2838420|This project hosts security advisories and their accompanying proof-of-concepts related to research conducted at Google which impact non-Google owned code.| | 898|shroominic/codeinterpreter-api !2025-03-2838330|Open source implementation of the ChatGPT Code Interpreter 👾| | 899|Yonom/assistant-ui !2025-03-2838308|React Components for AI Chat 💬 🚀| | 900|nucleuscloud/neosync !2025-03-2838262|Open source data anonymization and synthetic data orchestration for developers. Create high fidelity synthetic data and sync it across your environments.| | 901|ravenscroftj/turbopilot !2025-03-2838230 |Turbopilot is an open source large-language-model based code completion engine that runs locally on CPU| | 902|NVlabs/Sana !2025-03-28380810|SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer| | 903|huggingface/distil-whisper !2025-03-2838061|Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.| | 904|Codium-ai/AlphaCodium !2025-03-2837971|code generation tool that surpasses most human competitors in CodeContests| | 905|fixie-ai/ultravox !2025-03-2837710|A fast multimodal LLM for real-time voice| | 906|unit-mesh/auto-dev !2025-03-28375715|🧙‍AutoDev: The AI-powered coding wizard with multilingual support 🌐, auto code generation 🏗️, and a helpful bug-slaying assistant 🐞! Customizable prompts 🎨 and a magic Auto Dev/Testing/Document/Agent feature 🧪 included! 🚀| | 907|Marker-Inc-Korea/AutoRAG !2025-03-2837432|AutoML tool for RAG| | 908|deepseek-ai/DeepSeek-VL !2025-03-283734-1|DeepSeek-VL: Towards Real-World Vision-Language Understanding| | 909|hiyouga/ChatGLM-Efficient-Tuning !2025-03-283692-1|Fine-tuning ChatGLM-6B with PEFT | | 910| Yue-Yang/ChatGPT-Siri !2025-03-2836921 | Shortcuts for Siri using ChatGPT API gpt-3.5-turbo model | | 911|0hq/WebGPT !2025-03-2836901 |Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~2000 lines of vanilla Javascript.| | 912|cvg/LightGlue !2025-03-2836903|LightGlue: Local Feature Matching at Light Speed (ICCV 2023)| | 913|deanxv/coze-discord-proxy !2025-03-2836791|代理Discord-Bot对话Coze-Bot，实现API形式请求GPT4对话模型/微调模型| | 914|MervinPraison/PraisonAI !2025-03-2836764|PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration.| | 915|Ironclad/rivet !2025-03-2836345 |The open-source visual AI programming environment and TypeScript library| | 916|BasedHardware/OpenGlass !2025-03-2835851|Turn any glasses into AI-powered smart glasses| | 917|ricklamers/gpt-code-ui !2025-03-2835840 |An open source implementation of OpenAI's ChatGPT Code interpreter| | 918|whoiskatrin/chart-gpt !2025-03-2835830 |AI tool to build charts based on text input| | 919|github/CopilotForXcode !2025-03-2835788|Xcode extension for GitHub Copilot| | 920|hemansnation/God-Level-Data-Science-ML-Full-Stack !2025-03-2835570 |A collection of scientific methods, processes, algorithms, and systems to build stories & models. This roadmap contains 16 Chapters, whether you are a fresher in the field or an experienced professional who wants to transition into Data Science & AI| | 921|pytorch/torchchat !2025-03-2835461|Run PyTorch LLMs locally on servers, desktop and mobile| | 922| Kent0n-Li/ChatDoctor !2025-03-2835451 | A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain Knowledge | | 923|xtekky/chatgpt-clone !2025-03-283519-1 |ChatGPT interface with better UI| | 924|jupyterlab/jupyter-ai !2025-03-2835120|A generative AI extension for JupyterLab| | 925|pytorch/torchtitan !2025-03-2835064|A native PyTorch Library for large model training| | 926|minimaxir/simpleaichat !2025-03-2835031|Python package for easily interfacing with chat apps, with robust features and minimal code complexity.| | 927|srush/Tensor-Puzzles !2025-03-2834930|Solve puzzles. Improve your pytorch.| | 928|Helicone/helicone !2025-03-2834918|🧊 Open source LLM-Observability Platform for Developers. One-line integration for monitoring, metrics, evals, agent tracing, prompt management, playground, etc. Supports OpenAI SDK, Vercel AI SDK, Anthropic SDK, LiteLLM, LLamaIndex, LangChain, and more. 🍓 YC W23| | 929|run-llama/llama-hub !2025-03-2834740|A library of data loaders for LLMs made by the community -- to be used with LlamaIndex and/or LangChain| | 930|NExT-GPT/NExT-GPT !2025-03-2834700|Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model| | 931|souzatharsis/podcastfy !2025-03-2834661|An Open Source Python alternative to NotebookLM's podcast feature: Transforming Multimodal Content into Captivating Multilingual Audio Conversations with GenAI| | 932|Dataherald/dataherald !2025-03-2834450|Interact with your SQL database, Natural Language to SQL using LLMs| | 933|iryna-kondr/scikit-llm !2025-03-2834350 |Seamlessly integrate powerful language models like ChatGPT into scikit-learn for enhanced text analysis tasks.| | 934|Netflix/maestro !2025-03-2834230|Maestro: Netflix’s Workflow Orchestrator| | 935|CanadaHonk/porffor !2025-03-2833560|A from-scratch experimental AOT JS engine, written in JS| | 936|hustvl/Vim !2025-03-2833323|Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model| | 937|pashpashpash/vault-ai !2025-03-2833250 |OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, etc) using a simple React frontend.| | 938|tencentmusic/supersonic !2025-03-28330611|SuperSonic is the next-generation BI platform that integrates Chat BI (powered by LLM) and Headless BI (powered by semantic layer) paradigms.| | 939|billmei/every-chatgpt-gui !2025-03-2832981|Every front-end GUI client for ChatGPT| | 940|microsoft/torchgeo !2025-03-2832772|TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data| | 941|LLMBook-zh/LLMBook-zh.github.io !2025-03-28326110|《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣| | 942|dvlab-research/MiniGemini !2025-03-2832601|Official implementation for Mini-Gemini| | 943|rashadphz/farfalle !2025-03-2832460|🔍 AI search engine - self-host with local or cloud LLMs| | 944|Luodian/Otter !2025-03-2832450|🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.| | 945|AprilNEA/ChatGPT-Admin-Web !2025-03-2832370 | ChatGPT WebUI with user management and admin dashboard system| | 946|MarkFzp/act-plus-plus !2025-03-2832365|Imitation Learning algorithms with Co-traing for Mobile ALOHA: ACT, Diffusion Policy, VINN| | 947|ethen8181/machine-learning !2025-03-2832310|🌎 machine learning tutorials (mainly in Python3)| | 948|opengeos/segment-geospatial !2025-03-2832312 |A Python package for segmenting geospatial data with the Segment Anything Model (SAM)| | 949|iusztinpaul/hands-on-llms !2025-03-283225-2|🦖 𝗟𝗲𝗮𝗿𝗻 about 𝗟𝗟𝗠𝘀, 𝗟𝗟𝗠𝗢𝗽𝘀, and 𝘃𝗲𝗰𝘁𝗼𝗿 𝗗𝗕𝘀 for free by designing, training, and deploying a real-time financial advisor LLM system ~ 𝘴𝘰𝘶𝘳𝘤𝘦 𝘤𝘰𝘥𝘦 + 𝘷𝘪𝘥𝘦𝘰 & 𝘳𝘦𝘢𝘥𝘪𝘯𝘨 𝘮𝘢𝘵𝘦𝘳𝘪𝘢𝘭𝘴| | 950|ToTheBeginning/PuLID !2025-03-2832221|Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment| | 951|neo4j-labs/llm-graph-builder !2025-03-2832164|Neo4j graph construction from unstructured data using LLMs| | 952|OpenGVLab/InternGPT !2025-03-2832150 |InternGPT (iGPT) is an open source demo platform where you can easily showcase your AI models. Now it supports DragGAN, ChatGPT, ImageBind, multimodal chat like GPT-4, SAM, interactive image editing, etc. Try it at igpt.opengvlab.com (支持DragGAN、ChatGPT、ImageBind、SAM的在线Demo系统)| | 953|PKU-YuanGroup/Video-LLaVA !2025-03-2832060 |Video-LLaVA: Learning United Visual Representation by Alignment Before Projection| | 954|DataTalksClub/llm-zoomcamp !2025-03-2832030|LLM Zoomcamp - a free online course about building an AI bot that can answer questions about your knowledge base| | 955|gptscript-ai/gptscript !2025-03-2832010|Natural Language Programming| |!green-up-arrow.svg 956|isaac-sim/IsaacLab !2025-03-28320113|Unified framework for robot learning built on NVIDIA Isaac Sim| |!red-down-arrow 957|ai-boost/Awesome-GPTs !2025-03-2832003|Curated list of awesome GPTs 👍.| | 958|huggingface/safetensors !2025-03-2831901|Simple, safe way to store and distribute tensors| | 959|linyiLYi/bilibot !2025-03-2831771|A local chatbot fine-tuned by bilibili user comments.| | 960| project-baize/baize-chatbot !2025-03-283168-1 | Let ChatGPT teach your own chatbot in hours with a single GPU! | | 961|Azure-Samples/cognitive-services-speech-sdk !2025-03-2831280|Sample code for the Microsoft Cognitive Services Speech SDK| | 962|microsoft/Phi-3CookBook !2025-03-2831231|This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) available, outperforming models of the same size and next size up across a variety of language, reasoning, coding, and math benchmarks.| | 963|neuralmagic/deepsparse !2025-03-2831180|Sparsity-aware deep learning inference runtime for CPUs| | 964|sugarforever/chat-ollama !2025-03-2831000|ChatOllama is an open source chatbot based on LLMs. It supports a wide range of language models, and knowledge base management.| | 965|amazon-science/chronos-forecasting !2025-03-2830974|Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting| | 966|damo-vilab/i2vgen-xl !2025-03-2830902|Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models| | 967|google-deepmind/gemma !2025-03-2830733|Open weights LLM from Google DeepMind.| | 968|iree-org/iree !2025-03-2830733|A retargetable MLIR-based machine learning compiler and runtime toolkit.| | 969|NVlabs/VILA !2025-03-2830724|VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)| | 970|microsoft/torchscale !2025-03-2830661|Foundation Architecture for (M)LLMs| | 971|openai/openai-realtime-console !2025-03-2830656|React app for inspecting, building and debugging with the Realtime API| | 972|daveshap/OpenAIAgentSwarm !2025-03-2830610|HAAS = Hierarchical Autonomous Agent Swarm - "Resistance is futile!"| | 973|microsoft/PromptWizard !2025-03-2830555|Task-Aware Agent-driven Prompt Optimization Framework| | 974|CVI-SZU/Linly !2025-03-2830490 |Chinese-LLaMA basic model; ChatFlow Chinese conversation model; NLP pre-training/command fine-tuning dataset| | 975|cohere-ai/cohere-toolkit !2025-03-2830130|Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.| | 976|adamcohenhillel/ADeus !2025-03-2830131|An open source AI wearable device that captures what you say and hear in the real world and then transcribes and stores it on your own server. You can then chat with Adeus using the app, and it will have all the right context about what you want to talk about - a truly personalized, personal AI.| | 977|Lightning-AI/LitServe !2025-03-2830132|Lightning-fast serving engine for AI models. Flexible. Easy. Enterprise-scale.| | 978|potpie-ai/potpie !2025-03-2829973|Prompt-To-Agent : Create custom engineering agents for your codebase| | 979|ant-design/x !2025-03-28299529|Craft AI-driven interfaces effortlessly 🤖| | 980|meta-llama/PurpleLlama !2025-03-2829832|Set of tools to assess and improve LLM security.| | 981|williamyang1991/RerenderAVideo !2025-03-2829800|[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation| | 982|baichuan-inc/Baichuan-13B !2025-03-2829790|A 13B large language model developed by Baichuan Intelligent Technology| | 983|Stability-AI/stable-audio-tools !2025-03-2829761|Generative models for conditional audio generation| | 984|li-plus/chatglm.cpp !2025-03-2829720|C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & more LLMs| | 985|NVIDIA/GenerativeAIExamples !2025-03-2829546|Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.| | 986|Josh-XT/AGiXT !2025-03-2829521 |AGiXT is a dynamic AI Automation Platform that seamlessly orchestrates instruction management and complex task execution across diverse AI providers. Combining adaptive memory, smart features, and a versatile plugin system, AGiXT delivers efficient and comprehensive AI solutions.| | 987|MrForExample/ComfyUI-3D-Pack !2025-03-2829515|An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)| | 988|olimorris/codecompanion.nvim !2025-03-28295111|✨ AI-powered coding, seamlessly in Neovim. Supports Anthropic, Copilot, Gemini, Ollama, OpenAI and xAI LLMs| | 989|salesforce/CodeT5 !2025-03-282940-1 |Home of CodeT5: Open Code LLMs for Code Understanding and Generation| | 990|facebookresearch/ijepa !2025-03-2829391|Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive architecture."| | 991|eureka-research/Eureka !2025-03-2829351|Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models"| | 992|NVIDIA/trt-llm-rag-windows !2025-03-282934-1|A developer reference project for creating Retrieval Augmented Generation (RAG) chatbots on Windows using TensorRT-LLM| | 993|gmpetrov/databerry !2025-03-282930-1|The no-code platform for building custom LLM Agents| | 994|AI4Finance-Foundation/FinRobot !2025-03-28291946|FinRobot: An Open-Source AI Agent Platform for Financial Applications using LLMs 🚀 🚀 🚀| | 995|nus-apr/auto-code-rover !2025-03-2829013|A project structure aware autonomous software engineer aiming for autonomous program improvement| | 996|deepseek-ai/DreamCraft3D !2025-03-2828921|[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior| | 997|mlabonne/llm-datasets !2025-03-2828848|High-quality datasets, tools, and concepts for LLM fine-tuning.| | 998|facebookresearch/jepa !2025-03-2828712|PyTorch code and models for V-JEPA self-supervised learning from video.| | 999|facebookresearch/habitat-sim !2025-03-2828604|A flexible, high-performance 3D simulator for Embodied AI research.| | 1000|xenova/whisper-web !2025-03-2828581|ML-powered speech recognition directly in your browser| | 1001|cvlab-columbia/zero123 !2025-03-2828530|Zero-1-to-3: Zero-shot One Image to 3D Object: https://zero123.cs.columbia.edu/| | 1002|yuruotong1/autoMate !2025-03-28285121|Like Manus, Computer Use Agent(CUA) and Omniparser, we are computer-using agents.AI-driven local automation assistant that uses natural language to make computers work by themselves| | 1003|muellerberndt/mini-agi !2025-03-282845-1 |A minimal generic autonomous agent based on GPT3.5/4. Can analyze stock prices, perform network security tests, create art, and order pizza.| | 1004|allenai/open-instruct !2025-03-2828432|| | 1005|CodingChallengesFYI/SharedSolutions !2025-03-2828360|Publicly shared solutions to Coding Challenges| | 1006|hegelai/prompttools !2025-03-2828220|Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chroma, Weaviate).| | 1007|mazzzystar/Queryable !2025-03-2828222|Run CLIP on iPhone to Search Photos.| | 1008|Doubiiu/DynamiCrafter !2025-03-2828173|DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors| | 1009|SamurAIGPT/privateGPT !2025-03-282805-1 |An app to interact privately with your documents using the power of GPT, 100% privately, no data leaks| | 1010|facebookresearch/Pearl !2025-03-2827951|A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.| | 1011|intuitem/ciso-assistant-community !2025-03-2827954|CISO Assistant is a one-stop-shop for GRC, covering Risk, AppSec and Audit Management and supporting +70 frameworks worldwide with auto-mapping: NIST CSF, ISO 27001, SOC2, CIS, PCI DSS, NIS2, CMMC, PSPF, GDPR, HIPAA, Essential Eight, NYDFS-500, DORA, NIST AI RMF, 800-53, 800-171, CyFun, CJIS, AirCyber, NCSC, ECC, SCF and so much more| | 1012|facebookresearch/audio2photoreal !2025-03-2827840|Code and dataset for photorealistic Codec Avatars driven from audio| | 1013|Azure/azure-rest-api-specs !2025-03-2827770|The source for REST API specifications for Microsoft Azure.| | 1014|SCUTlihaoyu/open-chat-video-editor !2025-03-2827690 |Open source short video automatic generation tool| | 1015|Alpha-VLLM/LLaMA2-Accessory !2025-03-2827642|An Open-source Toolkit for LLM Development| | 1016|johnma2006/mamba-minimal !2025-03-2827601|Simple, minimal implementation of the Mamba SSM in one file of PyTorch.| | 1017|nerfstudio-project/gsplat !2025-03-2827576|CUDA accelerated rasterization of gaussian splatting| | 1018|Physical-Intelligence/openpi !2025-03-28274617|| | 1019|leptonai/leptonai !2025-03-2827246|A Pythonic framework to simplify AI service building| |!green-up-arrow.svg 1020|joanrod/star-vector !2025-03-28271149|StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.| |!red-down-arrow 1021|jqnatividad/qsv !2025-03-2827092|CSVs sliced, diced & analyzed.| | 1022|FranxYao/chain-of-thought-hub !2025-03-2826991|Benchmarking large language models' complex reasoning ability with chain-of-thought prompting| | 1023|princeton-nlp/SWE-bench !2025-03-2826965|[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?| | 1024|elastic/otel-profiling-agent !2025-03-2826930|The production-scale datacenter profiler| | 1025|src-d/hercules !2025-03-2826900|Gaining advanced insights from Git repository history.| | 1026|lanqian528/chat2api !2025-03-2826695|A service that can convert ChatGPT on the web to OpenAI API format.| | 1027|ishan0102/vimGPT !2025-03-2826681|Browse the web with GPT-4V and Vimium| | 1028|TMElyralab/MuseV !2025-03-2826650|MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising| | 1029|georgia-tech-db/eva !2025-03-2826600 |AI-Relational Database System | | 1030|kubernetes-sigs/controller-runtime !2025-03-2826590|Repo for the controller-runtime subproject of kubebuilder (sig-apimachinery)| | 1031|gptlink/gptlink !2025-03-2826550 |Build your own free commercial ChatGPT environment in 10 minutes. The setup is simple and includes features such as user management, orders, tasks, and payments| | 1032|pytorch/executorch !2025-03-2826534|On-device AI across mobile, embedded and edge for PyTorch| | 1033|NVIDIA/nv-ingest !2025-03-2826290|NVIDIA Ingest is an early access set of microservices for parsing hundreds of thousands of complex, messy unstructured PDFs and other enterprise documents into metadata and text to embed into retrieval systems.| | 1034|SuperTux/supertux !2025-03-2826081|SuperTux source code| | 1035|abi/secret-llama !2025-03-2826050|Fully private LLM chatbot that runs entirely with a browser with no server needed. Supports Mistral and LLama 3.| | 1036|liou666/polyglot !2025-03-2825841 |Desktop AI Language Practice Application| | 1037|janhq/nitro !2025-03-2825821|A fast, lightweight, embeddable inference engine to supercharge your apps with local AI. OpenAI-compatible API| | 1038|deepseek-ai/DeepSeek-Math !2025-03-2825825|DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models| | 1039|anthropics/prompt-eng-interactive-tutorial !2025-03-2825781|Anthropic's Interactive Prompt Engineering Tutorial| | 1040|microsoft/promptbench !2025-03-2825741|A unified evaluation framework for large language models| | 1041|baaivision/Painter !2025-03-2825580 |Painter & SegGPT Series: Vision Foundation Models from BAAI| | 1042|OpenPipe/OpenPipe !2025-03-2825581|Turn expensive prompts into cheap fine-tuned models| | 1043|TracecatHQ/tracecat !2025-03-2825531|😼 The AI-native, open source alternative to Tines / Splunk SOAR.| | 1044|JoshuaC215/agent-service-toolkit !2025-03-2825528|Full toolkit for running an AI agent service built with LangGraph, FastAPI and Streamlit| | 1045|databricks/dbrx !2025-03-2825460|Code examples and resources for DBRX, a large language model developed by Databricks| | 1046|lamini-ai/lamini !2025-03-2825271 |Official repo for Lamini's data generator for generating instructions to train instruction-following LLMs| | 1047|mshumer/gpt-author !2025-03-282510-1|| | 1048|TMElyralab/MusePose !2025-03-2824971|MusePose: a Pose-Driven Image-to-Video Framework for Virtual Human Generation| | 1049|Kludex/fastapi-tips !2025-03-2824974|FastAPI Tips by The FastAPI Expert!| | 1050|openai/simple-evals !2025-03-2824813|| | 1051|iterative/datachain !2025-03-2824732|AI-data warehouse to enrich, transform and analyze data from cloud storages| | 1052|girafe-ai/ml-course !2025-03-2824703|Open Machine Learning course| | 1053|kevmo314/magic-copy !2025-03-2824620 |Magic Copy is a Chrome extension that uses Meta's Segment Anything Model to extract a foreground object from an image and copy it to the clipboard.| | 1054|Eladlev/AutoPrompt !2025-03-2824432|A framework for prompt tuning using Intent-based Prompt Calibration| | 1055|OpenBMB/CPM-Bee !2025-03-282434-1 |A bilingual large-scale model with trillions of parameters| | 1056|IDEA-Research/T-Rex !2025-03-2824310|T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy| | 1057|microsoft/genaiscript !2025-03-2824202|Automatable GenAI Scripting| | 1058|paulpierre/RasaGPT !2025-03-2824090 |💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram| | 1059|ashishpatel26/LLM-Finetuning !2025-03-2823911|LLM Finetuning with peft| | 1060|SoraWebui/SoraWebui !2025-03-2823570|SoraWebui is an open-source Sora web client, enabling users to easily create videos from text with OpenAI's Sora model.| | 1061|6drf21e/ChatTTScolab !2025-03-2823491|🚀 一键部署（含离线整合包）！基于 ChatTTS ，支持音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。| | 1062|Azure/PyRIT !2025-03-2823343|The Python Risk Identification Tool for generative AI (PyRIT) is an open access automation framework to empower security professionals and machine learning engineers to proactively find risks in their generative AI systems.| | 1063|tencent-ailab/V-Express !2025-03-2823201|V-Express aims to generate a talking head video under the control of a reference image, an audio, and a sequence of V-Kps images.| | 1064|THUDM/CogVLM2 !2025-03-2823170|GPT4V-level open-source multi-modal model based on Llama3-8B| | 1065|dvmazur/mixtral-offloading !2025-03-2823001|Run Mixtral-8x7B models in Colab or consumer desktops| | 1066|semanser/codel !2025-03-2822950|✨ Fully autonomous AI Agent that can perform complicated tasks and projects using terminal, browser, and editor.| | 1067|mshumer/gpt-investor !2025-03-2822590|| | 1068|aixcoder-plugin/aiXcoder-7B !2025-03-2822550|official repository of aiXcoder-7B Code Large Language Model| | 1069|Azure-Samples/graphrag-accelerator !2025-03-2822503|One-click deploy of a Knowledge Graph powered RAG (GraphRAG) in Azure| | 1070|emcf/engshell !2025-03-2821830 |An English-language shell for any OS, powered by LLMs| | 1071|hncboy/chatgpt-web-java !2025-03-2821771|ChatGPT project developed in Java, based on Spring Boot 3 and JDK 17, supports both AccessToken and ApiKey modes| | 1072|openai/consistencydecoder !2025-03-2821692|Consistency Distilled Diff VAE| | 1073|Alpha-VLLM/Lumina-T2X !2025-03-2821681|Lumina-T2X is a unified framework for Text to Any Modality Generation| | 1074|bghira/SimpleTuner !2025-03-2821612|A general fine-tuning kit geared toward Stable Diffusion 2.1, Stable Diffusion 3, DeepFloyd, and SDXL.| | 1075|JiauZhang/DragGAN !2025-03-2821530 |Implementation of DragGAN: Interactive Point-based Manipulation on the Generative Image Manifold| | 1076|cgpotts/cs224u !2025-03-2821390|Code for Stanford CS224u| | 1077|PKU-YuanGroup/MoE-LLaVA !2025-03-2821300|Mixture-of-Experts for Large Vision-Language Models| | 1078|darrenburns/elia !2025-03-2820831|A snappy, keyboard-centric terminal user interface for interacting with large language models. Chat with ChatGPT, Claude, Llama 3, Phi 3, Mistral, Gemma and more.| | 1079|ageerle/ruoyi-ai !2025-03-28207898|RuoYi AI 是一个全栈式 AI 开发平台，旨在帮助开发者快速构建和部署个性化的 AI 应用。| | 1080|NVIDIA/gpu-operator !2025-03-2820510|NVIDIA GPU Operator creates/configures/manages GPUs atop Kubernetes| | 1081|BAAI-Agents/Cradle !2025-03-2820481|The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.| | 1082|microsoft/aici !2025-03-2820080|AICI: Prompts as (Wasm) Programs| | 1083|PRIS-CV/DemoFusion !2025-03-2820040|Let us democratise high-resolution generation! (arXiv 2023)| | 1084|apple/axlearn !2025-03-2820012|An Extensible Deep Learning Library| | 1085|naver/mast3r !2025-03-2819685|Grounding Image Matching in 3D with MASt3R| | 1086|liltom-eth/llama2-webui !2025-03-281958-1|Run Llama 2 locally with gradio UI on GPU or CPU from anywhere (Linux/Windows/Mac). Supporting Llama-2-7B/13B/70B with 8-bit, 4-bit. Supporting GPU inference (6 GB VRAM) and CPU inference.| | 1087|GaParmar/img2img-turbo !2025-03-2819582|One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more| | 1088|Niek/chatgpt-web !2025-03-2819560|ChatGPT web interface using the OpenAI API| | 1089|huggingface/cookbook !2025-03-2819421|Open-source AI cookbook| | 1090|pytorch/ao !2025-03-2819241|PyTorch native quantization and sparsity for training and inference| | 1091|emcie-co/parlant !2025-03-2819053|The behavior guidance framework for customer-facing LLM agents| | 1092|ymcui/Chinese-LLaMA-Alpaca-3 !2025-03-2818980|中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3| | 1093|Nutlope/notesGPT !2025-03-2818811|Record voice notes & transcribe, summarize, and get tasks| | 1094|InstantStyle/InstantStyle !2025-03-2818791|InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥| | 1095|idaholab/moose !2025-03-2818771|Multiphysics Object Oriented Simulation Environment| | 1096|The-OpenROAD-Project/OpenROAD !2025-03-2818351|OpenROAD's unified application implementing an RTL-to-GDS Flow. Documentation at https://openroad.readthedocs.io/en/latest/| | 1097|alibaba/spring-ai-alibaba !2025-03-281831121|Agentic AI Framework for Java Developers| | 1098|ytongbai/LVM !2025-03-2817990|Sequential Modeling Enables Scalable Learning for Large Vision Models| | 1099|microsoft/sample-app-aoai-chatGPT !2025-03-2817981|[PREVIEW] Sample code for a simple web chat experience targeting chatGPT through AOAI.| | 1100|AI-Citizen/SolidGPT !2025-03-2817830|Chat everything with your code repository, ask repository level code questions, and discuss your requirements. AI Scan and learning your code repository, provide you code repository level answer🧱 🧱| | 1101|YangLing0818/RPG-DiffusionMaster !2025-03-2817784|Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG)| | 1102|kyegomez/BitNet !2025-03-2817710|Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch| | 1103|eloialonso/diamond !2025-03-2817671|DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model.| | 1104|flowdriveai/flowpilot !2025-03-2817250|flow-pilot is an openpilot based driver assistance system that runs on linux, windows and android powered machines.| | 1105|xlang-ai/OSWorld !2025-03-2817200|OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments| | 1106|linyiLYi/snake-ai !2025-03-2817031|An AI agent that beats the classic game "Snake".| | 1107|baaivision/Emu !2025-03-2816991|Emu Series: Generative Multimodal Models from BAAI| | 1108|kevmo314/scuda !2025-03-2816870|SCUDA is a GPU over IP bridge allowing GPUs on remote machines to be attached to CPU-only machines.| | 1109|SharifiZarchi/IntroductiontoMachineLearning !2025-03-2816701|دوره‌ی مقدمه‌ای بر یادگیری ماشین، برای دانشجویان| | 1110|google/maxtext !2025-03-2816670|A simple, performant and scalable Jax LLM!| | 1111|ml-explore/mlx-swift-examples !2025-03-2816471|Examples using MLX Swift| | 1112|unitreerobotics/unitreerlgym !2025-03-2816256|| | 1113|collabora/WhisperFusion !2025-03-2815901|WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.| | 1114|lichao-sun/Mora !2025-03-2815520|Mora: More like Sora for Generalist Video Generation| | 1115|GoogleCloudPlatform/localllm !2025-03-2815370|Run LLMs locally on Cloud Workstations| | 1116|TencentARC/BrushNet !2025-03-2815330|The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"| | 1117|ai-christianson/RA.Aid !2025-03-2815288|Develop software autonomously.| | 1118|stephansturges/WALDO !2025-03-2815170|Whereabouts Ascertainment for Low-lying Detectable Objects. The SOTA in FOSS AI for drones!| | 1119|skills/copilot-codespaces-vscode !2025-03-2815112|Develop with AI-powered code suggestions using GitHub Copilot and VS Code| | 1120|andrewnguonly/Lumos !2025-03-2814920|A RAG LLM co-pilot for browsing the web, powered by local LLMs| | 1121|TeamNewPipe/NewPipeExtractor !2025-03-2814811|NewPipe's core library for extracting data from streaming sites| | 1122|mhamilton723/FeatUp !2025-03-2814770|Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024| | 1123|AnswerDotAI/fsdpqlora !2025-03-2814671|Training LLMs with QLoRA + FSDP| | 1124|jgravelle/AutoGroq !2025-03-2814330|| | 1125|OpenGenerativeAI/llm-colosseum !2025-03-2814130|Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM| | 1126|microsoft/vscode-ai-toolkit !2025-03-2814000|| | 1127|McGill-NLP/webllama !2025-03-2813930|Llama-3 agents that can browse the web by following instructions and talking to you| | 1128|lucidrains/self-rewarding-lm-pytorch !2025-03-2813760|Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI| | 1129|ishaan1013/sandbox !2025-03-2813650|A cloud-based code editing environment with an AI copilot and real-time collaboration.| | 1130|goatcorp/Dalamud !2025-03-2813275|FFXIV plugin framework and API| | 1131|Lightning-AI/lightning-thunder !2025-03-2813151|Make PyTorch models Lightning fast! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors at once.| | 1132|PKU-YuanGroup/MagicTime !2025-03-2813052|MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators| | 1133|SakanaAI/evolutionary-model-merge !2025-03-2813000|Official repository of Evolutionary Optimization of Model Merging Recipes| | 1134|a-real-ai/pywinassistant !2025-03-2812950|The first open source Large Action Model generalist Artificial Narrow Intelligence that controls completely human user interfaces by only using natural language. PyWinAssistant utilizes Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models.| | 1135|TraceMachina/nativelink !2025-03-2812630|NativeLink is an open source high-performance build cache and remote execution server, compatible with Bazel, Buck2, Reclient, and other RBE-compatible build systems. It offers drastically faster builds, reduced test flakiness, and significant infrastructure cost savings.| | 1136|MLSysOps/MLE-agent !2025-03-2812500|🤖 MLE-Agent: Your intelligent companion for seamless AI engineering and research. 🔍 Integrate with arxiv and paper with code to provide better code/research plans 🧰 OpenAI, Ollama, etc supported. 🎆 Code RAG| | 1137|wpilibsuite/allwpilib !2025-03-2811610|Official Repository of WPILibJ and WPILibC| | 1138|elfvingralf/macOSpilot-ai-assistant !2025-03-2811470|Voice + Vision powered AI assistant that answers questions about any application, in context and in audio.| | 1139|langchain-ai/langchain-extract !2025-03-2811210|🦜⛏️ Did you say you like data?| | 1140|FoundationVision/GLEE !2025-03-2811120|【CVPR2024】GLEE: General Object Foundation Model for Images and Videos at Scale| | 1141|Profluent-AI/OpenCRISPR !2025-03-2810990|AI-generated gene editing systems| | 1142|zju3dv/EasyVolcap !2025-03-2810821|[SIGGRAPH Asia 2023 (Technical Communications)] EasyVolcap: Accelerating Neural Volumetric Video Research| | 1143|PaddlePaddle/PaddleHelix !2025-03-2810560|Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集| | 1144|myshell-ai/JetMoE !2025-03-289800|Reaching LLaMA2 Performance with 0.1M Dollars| | 1145|likejazz/llama3.np !2025-03-289770|llama3.np is pure NumPy implementation for Llama 3 model.| | 1146|mustafaaljadery/gemma-2B-10M !2025-03-289500|Gemma 2B with 10M context length using Infini-attention.| | 1147|HITsz-TMG/FilmAgent !2025-03-289382|Resources of our paper "FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces". New versions in the making!| | 1148|aws-samples/amazon-bedrock-samples !2025-03-289362|This repository contains examples for customers to get started using the Amazon Bedrock Service. This contains examples for all available foundational models| | 1149|Akkudoktor-EOS/EOS !2025-03-2893154|This repository features an Energy Optimization System (EOS) that optimizes energy distribution, usage for batteries, heat pumps& household devices. It includes predictive models for electricity prices (planned), load forecasting& dynamic optimization to maximize energy efficiency & minimize costs. Founder Dr. Andreas Schmitz (YouTube @akkudoktor)| Tip: | symbol| rule | | :----| :---- | |🔥 | 256 1k| |!green-up-arrow.svg !red-down-arrow | ranking up / down| |⭐ | on trending page today| [Back to Top] Tools | No. | Tool | Description | | ----:|:----------------------------------------------- |:------------------------------------------------------------------------------------------- | | 1 | ChatGPT | A sibling model to InstructGPT, which is trained to follow instructions in a prompt and provide a detailed response | | 2 | DALL·E 2 | Create original, realistic images and art from a text description | | 3 | Murf AI | AI enabled, real people's voices| | 4 | Midjourney | An independent research lab that produces an artificial intelligence program under the same name that creates images from textual descriptions, used in Discord | 5 | Make-A-Video | Make-A-Video is a state-of-the-art AI system that generates videos from text | | 6 | Creative Reality™ Studio by D-ID| Use generative AI to create future-facing videos| | 7 | chat.D-ID| The First App Enabling Face-to-Face Conversations with ChatGPT| | 8 | Notion AI| Access the limitless power of AI, right inside Notion. Work faster. Write better. Think bigger. | | 9 | Runway| Text to Video with Gen-2 | | 10 | Resemble AI| Resemble’s AI voice generator lets you create human–like voice overs in seconds | | 11 | Cursor| Write, edit, and chat about your code with a powerful AI | | 12 | Hugging Face| Build, train and deploy state of the art models powered by the reference open source in machine learning | | 13 | Claude | A next-generation AI assistant for your tasks, no matter the scale | | 14 | Poe| Poe lets you ask questions, get instant answers, and have back-and-forth conversations with AI. Gives access to GPT-4, gpt-3.5-turbo, Claude from Anthropic, and a variety of other bots| [Back to Top] Websites | No. | WebSite |Description | | ----:|:------------------------------------------ |:---------------------------------------------------------------------------------------- | | 1 | OpenAI | An artificial intelligence research lab | | 2 | Bard | Base Google's LaMDA chatbots and pull from internet | | 3 | ERNIE Bot | Baidu’s new generation knowledge-enhanced large language model is a new member of the Wenxin large model family | | 4 | DALL·E 2 | An AI system that can create realistic images and art from a description in natural language | | 5 | Whisper | A general-purpose speech recognition model | | 6| CivitAI| A platform that makes it easy for people to share and discover resources for creating AI art| | 7|D-ID| D-ID’s Generative AI enables users to transform any picture or video into extraordinary experiences| | 8| Nvidia eDiff-I| Text-to-Image Diffusion Models with Ensemble of Expert Denoisers | | 9| Stability AI| The world's leading open source generative AI company which opened source Stable Diffusion | | 10| Meta AI| Whether it be research, product or infrastructure development, we’re driven to innovate responsibly with AI to benefit the world | | 11| ANTHROPIC| AI research and products that put safety at the frontier | [Back to Top] Reports&Papers | No. | Report&Paper | Description | |:---- |:-------------------------------------------------------------------------------------------------------------- |:---------------------------------------------------- | | 1 | GPT-4 Technical Report | GPT-4 Technical Report | | 2 | mli/paper-reading | Deep learning classics and new papers are read carefully paragraph by paragraph. | | 3 | labmlai/annotateddeeplearningpaperimplementations| A collection of simple PyTorch implementations of neural networks and related algorithms, which are documented with explanations | | 4 | Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models | Talking, Drawing and Editing with Visual Foundation Models | | 5 | OpenAI Research | The latest research report and papers from OpenAI | | 6 | Make-A-Video: Text-to-Video Generation without Text-Video Data|Meta's Text-to-Video Generation| | 7 | eDiff-I: Text-to-Image Diffusion Models with Ensemble of Expert Denoisers| Nvidia eDiff-I - New generation of generative AI content creation tool | | 8 | Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo | 2023 GPT4All Technical Report | | 9 | Segment Anything| Meta Segment Anything | | 10 | LLaMA: Open and Efficient Foundation Language Models| LLaMA: a collection of foundation language models ranging from 7B to 65B parameters| | 11 | papers-we-love/papers-we-love |Papers from the computer science community to read and discuss| | 12 | CVPR 2023 papers |The most exciting and influential CVPR 2023 papers| [Back to Top] Tutorials | No. | Tutorial | Description| |:---- |:---------------------------------------------------------------- | --- | | 1 | Coursera - Machine Learning | The Machine Learning Specialization Course taught by Dr. Andrew Ng| | 2 | microsoft/ML-For-Beginners | 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all| | 3 | ChatGPT Prompt Engineering for Developers | This short course taught by Isa Fulford (OpenAI) and Andrew Ng (DeepLearning.AI) will teach how to use a large language model (LLM) to quickly build new and powerful applications | | 4 | Dive into Deep Learning |Targeting Chinese readers, functional and open for discussion. The Chinese and English versions are used for teaching in over 400 universities across more than 60 countries | | 5 | AI Expert Roadmap | Roadmap to becoming an Artificial Intelligence Expert in 2022 | | 6 | Computer Science courses |List of Computer Science courses with video lectures| | 7 | Machine Learning with Python | Machine Learning with Python Certification on freeCodeCamp| | 8 | Building Systems with the ChatGPT API | This short course taught by Isa Fulford (OpenAI) and Andrew Ng (DeepLearning.AI), you will learn how to automate complex workflows using chain calls to a large language model| | 9 | LangChain for LLM Application Development | This short course taught by Harrison Chase (Co-Founder and CEO at LangChain) and Andrew Ng. you will gain essential skills in expanding the use cases and capabilities of language models in application development using the LangChain framework| | 10 | How Diffusion Models Work | This short course taught by Sharon Zhou (CEO, Co-founder, Lamini). you will gain a deep familiarity with the diffusion process and the models which carry it out. More than simply pulling in a pre-built model or using an API, this course will teach you to build a diffusion model from scratch| | 11 | Free Programming Books For AI |📚 Freely available programming books for AI | | 12 | microsoft/AI-For-Beginners |12 Weeks, 24 Lessons, AI for All!| | 13 | hemansnation/God-Level-Data-Science-ML-Full-Stack |A collection of scientific methods, processes, algorithms, and systems to build stories & models. This roadmap contains 16 Chapters, whether you are a fresher in the field or an experienced professional who wants to transition into Data Science & AI| | 14 | datawhalechina/prompt-engineering-for-developers |Chinese version of Andrew Ng's Big Model Series Courses, including "Prompt Engineering", "Building System", and "LangChain"| | 15 | ossu/computer-science |🎓 Path to a free self-taught education in Computer Science!| | 16 | microsoft/Data-Science-For-Beginners | 10 Weeks, 20 Lessons, Data Science for All! | |17 |jwasham/coding-interview-university !2023-09-29268215336 |A complete computer science study plan to become a software engineer.| [Back to Top] Thanks If this project has been helpful to you in any way, please give it a ⭐️ by clicking on the star.

#github#aitreasurebox

github

0.64

1

krishnakumarsekar•Mar 27, 2025

awesome-quantum-machine-learning

Awesome Quantum Machine Learning A curated list of awesome quantum machine learning algorithms,study materials,libraries and software (by language). Table of Contents INTRODUCTION Why Quantum Machine Learning? BASICS What is Quantum Mechanics? What is Quantum Computing? What is Topological Quantum Computing? Quantum Computing vs Classical Computing QUANTUM COMPUTING Atom Structure Photon wave Electron Fluctuation or spin States SuperPosition SuperPosition specific for machine learning(Quantum Walks) Classical Bit Quantum Bit or Qubit or Qbit Basic Gates in Quantum Computing Quantum Diode Quantum Transistor Quantum Processor Quantum Registery QRAM Quantum Entanglement QUANTUM COMPUTING MACHINE LEARNING BRIDGE Complex Numbers Tensors Tensors Network Oracle Hadamard transform Hilbert Space eigenvalues and eigenvectors Schr¨odinger Operators Quantum lambda calculus Quantum Amplitute Phase Qubits Encode and Decode convert classical bit to qubit Quantum Dirac and Kets Quantum Complexity Arbitrary State Generation QUANTUM ALGORITHMS Quantum Fourier Transform Variational-Quantum-Eigensolver Grovers Algorithm Shor's algorithm Hamiltonian Oracle Model Bernstein-Vazirani Algorithm Simon’s Algorithm Deutsch-Jozsa Algorithm Gradient Descent Phase Estimation Haar Tansform Quantum Ridgelet Transform Quantum NP Problem QUANTUM MACHINE LEARNING ALGORITHMS Quantum K-Nearest Neighbour Quantum K-Means Quantum Fuzzy C-Means Quantum Support Vector Machine Quantum Genetic Algorithm Quantum Hidden Morkov Models Quantum state classification with Bayesian methods Quantum Ant Colony Optimization Quantum Cellular Automata Quantum Classification using Principle Component Analysis Quantum Inspired Evolutionary Algorithm Quantum Approximate Optimization Algorithm Quantum Elephant Herding Optimization Quantum-behaved Particle Swarm Optimization Quantum Annealing Expectation-Maximization QAUNTUM NEURAL NETWORK Quantum perceptrons Qurons Quantum Auto Encoder Quantum Annealing Photonic Implementation of Quantum Neural Network Quantum Feed Forward Neural Network Quantum Boltzman Neural Network Quantum Neural Net Weight Storage Quantum Upside Down Neural Net Quantum Hamiltonian Neural Net QANN QPN SAL Quantum Hamiltonian Learning Compressed Quantum Hamiltonian Learning QAUNTUM STATISTICAL DATA ANALYSIS Quantum Probability Theory Kolmogorovian Theory Quantum Measurement Problem Intuitionistic Logic Heyting Algebra Quantum Filtering Paradoxes Quantum Stochastic Process Double Negation Quantum Stochastic Calculus Hamiltonian Calculus Quantum Ito's Formula Quantum Stochastic Differential Equations(QSDE) Quantum Stochastic Integration Itō Integral Quasiprobability Distributions Quantum Wiener Processes Quantum Statistical Ensemble Quantum Density Operator or Density Matrix Gibbs Canonical Ensemble Quantum Mean Quantum Variance Envariance Polynomial Optimization Quadratic Unconstrained Binary Optimization Quantum Gradient Descent Quantum Based Newton's Method for Constrained Optimization Quantum Based Newton's Method for UnConstrained Optimization Quantum Ensemble Quantum Topology Quantum Topological Data Analysis Quantum Bayesian Hypothesis Quantum Statistical Decision Theory Quantum Minimax Theorem Quantum Hunt-Stein Theorem Quantum Locally Asymptotic Normality Quantum Ising Model Quantum Metropolis Sampling Quantum Monte Carlo Approximation Quantum Bootstrapping Quantum Bootstrap Aggregation Quantum Decision Tree Classifier Quantum Outlier Detection Cholesky-Decomposition for Quantum Chemistry Quantum Statistical Inference Asymptotic Quantum Statistical Inference Quantum Gaussian Mixture Modal Quantum t-design Quantum Central Limit Theorem Quantum Hypothesis Testing Quantum Chi-squared and Goodness of Fit Testing Quantum Estimation Theory Quantum Way of Linear Regression Asymptotic Properties of Quantum Outlier Detection in Quantum Concepts QAUNTUM ARTIFICIAL INTELLIGENCE Heuristic Quantum Mechanics Consistent Quantum Reasoning Quantum Reinforcement Learning QAUNTUM COMPUTER VISION QUANTUM PROGRAMMING LANGUAGES , TOOLs and SOFTWARES ALL QUANTUM ALGORITHMS SOURCE CODES , GITHUBS QUANTUM HOT TOPICS Quantum Cognition Quantum Camera Quantum Mathematics Quantum Information Processing Quantum Image Processing Quantum Cryptography Quantum Elastic Search Quantum DNA Computing Adiabetic Quantum Computing Topological Big Data Anlytics using Quantum Hamiltonian Time Based Quantum Computing Deep Quantum Learning Quantum Tunneling Quantum Entanglment Quantum Eigen Spectrum Quantum Dots Quantum elctro dynamics Quantum teleportation Quantum Supremacy Quantum Zeno Effect Quantum Cohomology Quantum Chromodynamics Quantum Darwinism Quantum Coherence Quantum Decoherence Topological Quantum Computing Topological Quantum Field Theory Quantum Knots Topological Entanglment Boson Sampling Quantum Convolutional Code Stabilizer Code Quantum Chaos Quantum Game Theory Quantum Channel Tensor Space Theory Quantum Leap Quantum Mechanics for Time Travel Quantum Secured Block Chain Quantum Internet Quantum Optical Network Quantum Interference Quantum Optical Network Quantum Operating System Electron Fractionalization Flip-Flop Quantum Computer Quantum Information with Gaussian States Quantum Anomaly Detection Distributed Secure Quantum Machine Learning Decentralized Quantum Machine Learning Artificial Agents for Quantum Designs Light Based Quantum Chips for AI Training QUANTUM STATE PREPARATION ALGORITHM FOR MACHINE LEARNING Pure Quantum State Product State Matrix Product State Greenberger–Horne–Zeilinger State W state AKLT model Majumdar–Ghosh Model Multistate Landau–Zener Models Projected entangled-pair States Infinite Projected entangled-pair States Corner Transfer Matrix Method Tensor-entanglement Renormalization Tree Tensor Network for Supervised Learning QUANTUM MACHINE LEARNING VS DEEP LEARNING QUANTUM MEETUPS QUANTUM GOOGLE GROUPS QUANTUM BASED COMPANIES QUANTUM LINKEDLIN QUANTUM BASED DEGREES CONSOLIDATED QUANTUM ML BOOKS CONSOLIDATED QUANTUM ML VIDEOS CONSOLIDATED QUANTUM ML Reserach Papers CONSOLIDATED QUANTUM ML Reserach Scientist RECENT QUANTUM UPDATES FORUM ,PAGES AND NEWSLETTER INTRODUCTION Why Quantum Machine Learning? Machine Learning(ML) is just a term in recent days but the work effort start from 18th century. What is Machine Learning ? , In Simple word the answer is making the computer or application to learn themselves . So its totally related with computing fields like computer science and IT ? ,The answer is not true . ML is a common platform which is mingled in all the aspects of the life from agriculture to mechanics . Computing is a key component to use ML easily and effectively . To be more clear ,Who is the mother of ML ?, As no option Mathematics is the mother of ML . The world tremendous invention complex numbers given birth to this field . Applying mathematics to the real life problem always gives a solution . From Neural Network to the complex DNA is running under some specific mathematical formulas and theorems. As computing technology growing faster and faster mathematics entered into this field and makes the solution via computing to the real world . In the computing technology timeline once a certain achievements reached peoples interested to use advanced mathematical ideas such as complex numbers ,eigen etc and its the kick start for the ML field such as Artificial Neural Network ,DNA Computing etc. Now the main question, why this field is getting boomed now a days ? , From the business perspective , 8-10 Years before during the kick start time for ML ,the big barrier is to merge mathematics into computing field . people knows well in computing has no idea on mathematics and research mathematician has no idea on what is computing . The education as well as the Job Opportunities is like that in that time . Even if a person tried to study both then the business value for making a product be not good. Then the top product companies like Google ,IBM ,Microsoft decided to form a team with mathematician ,a physician and a computer science person to come up with various ideas in this field . Success of this team made some wonderful products and they started by providing cloud services using this product . Now we are in this stage. So what's next ? , As mathematics reached the level of time travel concepts but the computing is still running under classical mechanics . the companies understood, the computing field must have a change from classical to quantum, and they started working on the big Quantum computing field, and the market named this field as Quantum Information Science .The kick start is from Google and IBM with the Quantum Computing processor (D-Wave) for making Quantum Neural Network .The field of Quantum Computer Science and Quantum Information Science will do a big change in AI in the next 10 years. Waiting to see that........... .(google, ibm). References D-Wave - Owner of a quantum processor Google - Quantum AI Lab IBM - Quantum Computer Lab Quora - Question Regarding future of quantum AI NASA - NASA Quantum Works Youtube - Google Video of a Quantum Processor external-link - MIT Review microsoft new product - Newly Launched Microsoft Quantum Language and Development Kit microsoft - Microsoft Quantum Related Works Google2 - Google Quantum Machine Learning Blog BBC - About Google Quantum Supremacy,IBM Quantum Computer and Microsoft Q Google Quantum Supremacy - Latest 2019 Google Quantum Supremacy Achievement IBM Quantum Supremacy - IBM Talk on Quantum Supremacy as a Primer VICE on the fight - IBM Message on Google Quantum Supremacy IBM Zurich Quantum Safe Cryptography - An interesting startup to replace all our Certificate Authority Via Cloud and IBM Q BASICS What is Quantum Mechanics? In a single line study of an electron moved out of the atom then its classical mechanic ,vibrates inside the atom its quantum mechanics WIKIPEDIA - Basic History and outline LIVESCIENCE. - A survey YOUTUBE - Simple Animation Video Explanining Great. What is Quantum Computing? A way of parallel execution of multiple processess in a same time using qubit ,It reduces the computation time and size of the processor probably in neuro size WIKIPEDIA - Basic History and outline WEBOPEDIA. - A survey YOUTUBE - Simple Animation Video Explanining Great. Quantum Computing vs Classical Computing LINK - Basic outline Quantum Computing Atom Structure one line : Electron Orbiting around the nucleous in an eliptical format YOUTUBE - A nice animation video about the basic atom structure Photon Wave one line : Light nornmally called as wave transmitted as photons as similar as atoms in solid particles YOUTUBE - A nice animation video about the basic photon 1 YOUTUBE - A nice animation video about the basic photon 2 Electron Fluctuation or spin one line : When a laser light collide with solid particles the electrons of the atom will get spin between the orbitary layers of the atom ) YOUTUBE - A nice animation video about the basic Electron Spin 1 YOUTUBE - A nice animation video about the basic Electron Spin 2 YOUTUBE - A nice animation video about the basic Electron Spin 3 States one line : Put a point on the spinning electron ,if the point is in the top then state 1 and its in bottom state 0 YOUTUBE - A nice animation video about the Quantum States SuperPosition two line : During the spin of the electron the point may be in the middle of upper and lower position, So an effective decision needs to take on the point location either 0 or 1 . Better option to analyse it along with other electrons using probability and is called superposition YOUTUBE - A nice animation video about the Quantum Superposition SuperPosition specific for machine learning(Quantum Walks) one line : As due to computational complexity ,quantum computing only consider superposition between limited electrons ,In case to merge more than one set quantum walk be the idea YOUTUBE - A nice video about the Quantum Walks Classical Bits one line : If electron moved from one one atom to other ,from ground state to excited state a bit value 1 is used else bit value 0 used Qubit one line : The superposition value of states of a set of electrons is Qubit YOUTUBE - A nice video about the Quantum Bits 1 YOUTUBE - A nice video about the Bits and Qubits 2 Basic Gates in Quantum Computing one line : As like NOT, OR and AND , Basic Gates like NOT, Hadamard gate , SWAP, Phase shift etc can be made with quantum gates YOUTUBE - A nice video about the Quantum Gates Quantum Diode one line : Quantum Diodes using a different idea from normal diode, A bunch of laser photons trigger the electron to spin and the quantum magnetic flux will capture the information YOUTUBE - A nice video about the Quantum Diode Quantum Transistors one line : A transistor default have Source ,drain and gate ,Here source is photon wave ,drain is flux and gate is classical to quantum bits QUORA -Discussion about the Quantum Transistor YOUTUBE - Well Explained Quantum Processor one line : A nano integration circuit performing the quantum gates operation sorrounded by cooling units to reduce the tremendous amount of heat YOUTUBE - Well Explained Quantum Registery QRAM one line : Comapring the normal ram ,its ultrafast and very small in size ,the address location can be access using qubits superposition value ,for a very large memory set coherent superposition(address of address) be used PDF - very Well Explained QUANTUM COMPUTING MACHINE LEARNING BRIDGE Complex Numbers one line : Normally Waves Interference is in n dimensional structure , to find a polynomial equation n order curves ,better option is complex number YOUTUBE - Wonderful Series very super Explained Tensors one line : Vectors have a direction in 2D vector space ,If on a n dimensional vector space ,vectors direction can be specify with the tensor ,The best solution to find the superposition of a n vector electrons spin space is representing vectors as tensors and doing tensor calculus YOUTUBE - Wonderful super Explained tensors basics YOUTUBE - Quantum tensors basics Tensors Network one line : As like connecting multiple vectors ,multple tensors form a network ,solving such a network reduce the complexity of processing qubits YOUTUBE - Tensors Network Some ideas specifically for quantum algorithms QUANTUM MACHINE LEARNING ALGORITHMS Quantum K-Nearest Neighbour info : Here the centroid(euclidean distance) can be detected using the swap gates test between two states of the qubit , As KNN is regerssive loss can be tally using the average PDF1 from Microsoft - Theory Explanation PDF2 - A Good Material to understand the basics Matlab - Yet to come soon Python - Yet to come soon Quantum K-Means info : Two Approaches possible ,1. FFT and iFFT to make an oracle and calculate the means of superposition 2. Adiobtic Hamiltonian generation and solve the hamiltonian to determine the cluster PDF1 - Applying Quantum Kmeans on Images in a nice way PDF2 - Theory PDF3 - Explaining well the K-means clustering using hamiltonian Matlab - Yet to come soon Python - Yet to come soon Quantum Fuzzy C-Means info : As similar to kmeans fcm also using the oracle dialect ,but instead of means,here oracle optimization followed by a rotation gate is giving a good result PDF1 - Theory Matlab - Yet to come soon Python - Yet to come soon Quantum Support Vector Machine info : A little different from above as here kernel preparation is via classical and the whole training be in oracles and oracle will do the classification, As SVM is linear ,An optimal Error(Optimum of the Least Squares Dual Formulation) Based regression is needed to improve the performance PDF1 - Nice Explanation but little hard to understand :) PDF2 - Nice Application of QSVM Matlab - Yet to come soon Python - Yet to come soon Quantum Genetic Algorithm info : One of the best algorithm suited for Quantum Field ,Here the chromosomes act as qubit vectors ,the crossover part carrying by an evaluation and the mutation part carrying by the rotation of gates ![Flow Chart]() PDF1 - Very Beautiful Article , well explained and superp PDF2 - A big theory :) PDF3 - Super Comparison Matlab - Simulation Python1 - Simulation Python2 - Yet to come Quantum Hidden Morkov Models info : As HMM is already state based ,Here the quantum states acts as normal for the markov chain and the shift between states is using quantum operation based on probability distribution ![Flow Chart]() PDF1 - Nice idea and explanation PDF2 - Nice but a different concept little Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come Quantum state classification with Bayesian methods info : Quantum Bayesian Network having the same states concept using quantum states,But here the states classification to make the training data as reusable is based on the density of the states(Interference) ![Bayesian Network Sample1]() ![Bayesian Network Sample2]() ![Bayesian Network Sample3]() PDF1 - Good Theory PDF2 - Good Explanation Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come Quantum Ant Colony Optimization info : A good algorithm to process multi dimensional equations, ACO is best suited for Sales man issue , QACO is best suited for Sales man in three or more dimension, Here the quantum rotation circuit is doing the peromene update and qubits based colony communicating all around the colony in complex space ![Ant Colony Optimization 1]() PDF1 - Good Concept PDF2 - Good Application Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come Quantum Cellular Automata info : One of the very complex algorithm with various types specifically used for polynomial equations and to design the optimistic gates for a problem, Here the lattice is formed using the quatum states and time calculation is based on the change of the state between two qubits ,Best suited for nano electronics ![Quantum Cellular Automata]() Wikipedia - Basic PDF1 - Just to get the keywords PDF2 - Nice Explanation and an easily understandable application Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come QAUNTUM NEURAL NETWORK one line : Its really one of the hardest topic , To understand easily ,Normal Neural Network is doing parallel procss ,QNN is doing parallel of parallel processess ,In theory combination of various activation functions is possible in QNN ,In Normal NN more than one activation function reduce the performance and increase the complexity Quantum perceptrons info : Perceptron(layer) is the basic unit in Neural Network ,The quantum version of perceptron must satisfy both linear and non linear problems , Quantum Concepts is combination of linear(calculus of superposition) and nonlinear(State approximation using probability) ,To make a perceptron in quantum world ,Transformation(activation function) of non linearity to certain limit is needed ,which is carrying by phase estimation algorithm ![Quantum Perceptron 3]() PDF1 - Good Theory PDF2 - Good Explanation Matlab - Yet to come Python1 - Yet to come Python2 - Yet to come QAUNTUM STATISTICAL DATA ANALYSIS one line : An under research concept ,It can be seen in multiple ways, one best way if you want to apply n derivative for a problem in current classical theory its difficult to compute as its serialization problem instead if you do parallelization of differentiation you must estimate via probability the value in all flows ,Quantum Probability Helps to achieve this ,as the loss calculation is very less . the other way comparatively booming is Quantum Bayesianism, its a solution to solve most of the uncertainity problem in statistics to combine time and space in highly advanced physical research QUANTUM PROGRAMMING LANGUAGES , TOOLs and SOFTWARES All info : All Programming languages ,softwares and tools in alphabetical order Software - Nice content of all Python library - A python library Matlab based python library - Matlab Python Library Quantum Tensor Network Github - Tensor Network Bayesforge - A Beautiful Amazon Web Service Enabled Framework for Quantum Alogorithms and Data Analytics Rigetti - A best tools repository to use quantum computer in real time Rigetti Forest - An API to connect Quantum Computer quil/pyQuil - A quantum instruction language to use forest framework Grove - Grove is a repository to showcase quantum Fourier transform, phase estimation, the quantum approximate optimization algorithm, and others developed using Forest QISKit - A IBM Kit to access quantum computer and mainly for quantum circuits IBM Bluemix Simulator - A Bluemix Simulator for Quantum Circuits Microsoft Quantum Development Kit - Microsoft Visual Studio Enbaled Kit for Quantum Circuit Creation Microsoft "Q#" - Microsoft Q Sharp a new Programming Language for Quantum Circuit Creation qiskit api python - An API to connect IBM Quantum Computer ,With the generated token its easy to connect ,but very limited utils ,Lot of new utils will come soon Cyclops Tensor Framework - A framework to do tensor network simulations Python ToolKit for chemistry and physics Quantum Algorithm simulations - A New Started Project for simulating molecule and solids Bayesian Based Quatum Projects Repository - A nice repository and the kickstarter of bayesforge Google Fermion Products - A newly launched product specifivally for chemistry simulation Tree Tensor Networks - Interesting Tensor Network in Incubator Deep Tensor Neural Network - Some useful information about Tensor Neural Network in Incubator Generative Tensorial Networks - A startup to apply machine learning via tensor network for drug discovery Google Bristlecone - A new Quantum Processor from Google , Aimed for Future Hardwares with full fledged AI support XANADU - A Light based Quantum Hardware(chips supports) and Software Company Started in Preparation Stage. Soon will be in market fathom computing - A new concept to train the ai in a processor using light and quantum based concepts. soon products will be launch Alibaba Quantum Computing Cloud Service - Cloud Service to access 11 Bit Quantum Computing Processor Atomistic Machine Learning Project - Seems something Interesting with Deep Tensor Network for Quantum Chemistry Applications circQ and Google Works - Google Top Efforts on Tools IBM Safe Cryptography on Cloud - IBM Started and Developing a Quantm Safe Cryptography to replace all our Certificate Authority via Cloud Google Tensor Network Open Source - Google Started the Most Scientist Preferred Way To Use a Quantum Computer Circuit. Tensor Flow Which Makes Easy to Design the Network and Will Leave the Work Effect Of Gates, Processor Preparation and also going to tell the beauty of Maths Google Tensor Network Github - Github Project of Google Tensor Network Quantum Tensorflow - Yet to come soon Quantum Spark - Yet to come soon Quatum Map Reduce - Yet to come soon Quantum Database - Yet to come soon Quantum Server - Yet to come soon Quantum Data Analytics - Yet to come soon QUANTUM HOT TOPICS Deep Quantum Learning why and what is deep learning? In one line , If you know deep learning you can get a good job :) ,Even a different platform undergraduated and graduated person done a master specialization in deep learning can work in this big sector :), Practically speaking machine learning (vector mathematics) , deep learning (vector space(Graphics) mathematics) and big data are the terms created by big companies to make a trend in the market ,but in science and research there is no word such that , Now a days if you ask a junior person working in this big companies ,what is deep learning ,you will get some reply as "doing linear regression with stochastic gradient for a unsupervised data using Convolutional Neural Network :)" ,They knows the words clearly and knows how to do programming using that on a bunch of "relative data" , If you ask them about the FCM , SVM and HMM etc algorithms ,they will simply say these are olden days algorithms , deep learning replaced all :), But actually they dont know from the birth to the till level and the effectiveness of algorithms and mathematics ,How many mathematical theorems in vector, spaces , tensors etc solved to find this "hiding the complexity technology", They did not played with real non relative data like medical images, astro images , geology images etc , finding a relation and features is really complex and looping over n number of images to do pattern matching is a giant work , Now a days the items mentioned as deep learning (= multiple hidden artifical neural network) is not suitable for that why quantum deep learning or deep quantum learning? In the mid of Artificial Neural Network Research people realised at the maximum extreme only certain mathematical operations possible to do with ANN and the aim of this ANN is to achieve parallel execution of many mathematical operations , In artificial Intelligence ,the world intelligence stands for mathematics ,how effective if a probem can be solvable is based on the mathematics logic applying on the problem , more the logic will give more performance(more intelligent), This goal open the gate for quantum artificial neural network, On applying the ideas behind the deep learning to quantum mechanics environment, its possible to apply complex mathematical equations to n number of non relational data to find more features and can improve the performance Quantum Machine Learning vs Deep Learning Its fun to discuss about this , In recent days most of the employees from Product Based Companies Like google,microsoft etc using the word deep learning ,What actually Deep Learning ? and is it a new inventions ? how to learn this ? Is it replacing machine learning ? these question come to the mind of junior research scholars and mid level employees The one answer to all questions is deep learning = parallel "for" loops ,No more than that ,Its an effective way of executing multiple tasks repeatly and to reduce the computation cost, But it introduce a big cap between mathematics and computerscience , How ? All classical algorithms based on serial processing ,Its depends on the feedback of the first loop ,On applying a serial classical algorithm in multiple clusters wont give a good result ,but some light weight parallel classical algorithms(Deep learning) doing the job in multiple clusters and its not suitable for complex problems, What is the solution for then? As in the title Quantum Machine Learning ,The advantage behind is deep learning is doing the batch processing simply on the data ,but quantum machine learning designed to do batch processing as per the algorithm The product companies realised this one and they started migrating to quantum machine learning and executing the classical algorithms on quantum concept gives better result than deep learning algorithms on classical computer and the target to merge both to give very wonderful result References Quora - Good Discussion Quora - The Bridge Discussion Pdf - Nice Discussion Google - Google Research Discussion Microsoft - Microsoft plan to merge both IBM - IBM plan to merge both IBM Project - IBM Project idea MIT and Google - Solutions for all questions QUANTUM MEETUPS Meetup 1 - Quantum Physics Meetup 2 - Quantum Computing London Meetup 3 - Quantum Computing New York Meetup 4 - Quantum Computing Canada Meetup 5 - Quantum Artificial Intelligence Texas Meetup 6 - Genarl Quantum Mechanics , Mathematics New York Meetup 7 - Quantum Computing Mountain View California Meetup 8 - Statistical Analysis New York Meetup 9 - Quantum Mechanics London UK Meetup 10 - Quantum Physics Sydney Australia Meetup 11 - Quantum Physics Berkeley CA Meetup 12 - Quantum Computing London UK Meetup 13 - Quantum Mechanics Carmichael CA Meetup 14 - Maths and Science Group Portland Meetup 15 - Quantum Physics Santa Monica, CA Meetup 16 - Quantum Mechanics London Meetup 17 - Quantum Computing London Meetup 18 - Quantum Meta Physics ,Kansas City , Missouri ,US Meetup 19 - Quantum Mechanics and Physics ,Boston ,Massachusetts ,US Meetup 20 - Quantum Physics and Mechanics ,San Francisco ,California Meetup 21 - Quantum Mechanics ,Langhorne, Pennsylvania Meetup 22 - Quantum Mechanics ,Portland QUANTUM BASED DEGREES Plenty of courses around the world and many Universities Launching it day by day ,Instead of covering only Quantum ML , Covering all Quantum Related topics gives more idea in the order below Available Courses Quantum Mechanics for Science and Engineers Online Standford university - Nice Preparatory Course edx - Quantum Mechanics for Everyone NPTEL 1 - Nice Series of Courses to understand basics and backbone of quantum mechanics NPTEL 2 NPTEL 3 NPTEL 4 NPTEL 5 Class Based Course UK Bristol Australia Australian National University Europe Maxs Planks University Quantum Physics Online MIT - Super Explanation and well basics NPTEL - Nice Series of Courses to understand basics and backbone of quantum Physics Class Based Course Europe University of Copenhagen Quantum Chemistry Online NPTEL 1 - Nice Series of Courses to understand basics and backbone of quantum Chemistry NPTEL 2 - Class Based Course Europe UGent Belgium Quantum Computing Online MIT - Super Explanation and well basics edx - Nice Explanation NPTEL - Nice Series of Courses to understand basics and backbone of quantum Computing Class Based Course Canada uwaterloo Singapore National University Singapore USA Berkley China Baidu Quantum Technology Class Based Course Canada uwaterloo Singapore National University Singapore Europe Munich Russia Skoltech Quantum Information Science External Links quantwiki Online MIT - Super Explanation and well basics edx - Nice Explanation NPTEL - Nice Series of Courses to understand basics and backbone of quantum information and computing Class Based Course USA MIT Standford University Joint Center for Quantum Information and Computer Science - University of Maryland Canada Perimeter Institute Singapore National University Singapore Europe ULB Belgium IQOQI Quantum Electronics Online MIT - Wonderful Course NPTEL - Nice Series of Courses to understand basics and backbone of quantum Electronics Class Based Course USA Texas Europe Zurich ICFO Asia Tata Institute Quantum Field Theory Online Standford university - Nice Preparatory Course edx - Some QFT Concepts available Class Based Course UK Imperial Europe Vrije Quantum Computer Science Class Based Course USA Oxford Joint Center for Quantum Information and Computer Science - University of Maryland Quantum Artificial Intelligence and Machine Learning External Links Quora 1 Quora 1 Artificial Agents Research for Quantum Designs Quantum Mathematics Class Based Course USA University of Notre CONSOLIDATED Quantum Research Papers scirate - Plenty of Quantum Research Papers Available Peter Wittek - Famous Researcher for the Quantum Machine Leanrning , Published a book in this topic [Murphy Yuezhen Niu] (https://scholar.google.com/citations?user=0wJPxfkAAAAJ&hl=en) - A good researcher published some nice articles Recent Quantum Updates forum ,pages and newsletter Quantum-Tech - A Beautiful Newsletter Page Publishing Amazing Links facebook Quantum Machine Learning - Running By me . Not that much good :). You can get some ideas Linkedlin Quantum Machine Learning - A nice page running by experts. Can get plenty of ideas FOSDEM 2019 Quantum Talks - A one day talk in fosdem 2019 with more than 10 research topics,tools and ideas FOSDEM 2020 Quantum Talks - Live talk in fosdem 2020 with plenty new research topics,tools and ideas License Dedicated Opensources ![Dedicated Opensources]() Source code of plenty of Algortihms in Image Processing , Data Mining ,etc in Matlab, Python ,Java and VC++ Scripts Good Explanations of Plenty of algorithms with flow chart etc Comparison Matrix of plenty of algorithms Is Quantum Machine Learning Will Reveal the Secret Maths behind Astrology? Awesome Machine Learning and Deep Learning Mathematics is online Published Basic Presentation of the series Quantum Machine Learning Contribution If you think this page might helpful. Please help for World Education Charity or kids who wants to learn

#github#awesome-quantum-machine-learning

youtube

0.321

0.44

GeeksforGeeks•Mar 27, 2025

With Vibe Coding Say Goodbye to Boring Coding!

Coding doesn’t have to be boring anymore! With the rise of AI-powered tools and innovative development approaches, the way we write code is changing drastically. Are you ready to embrace this new era of vibe coding? 🚀 💡 Want to level up your coding and problem-solving skills? Join the Three 90 Challenge by GeeksforGeeks—ending on 31st March! ✅ Complete 90% of your course in 90 days ✅ Get 90% of your fee refunded! Yes, you read that right! 🌟 Over ₹5 CRORE in refunds already processed—yours could be next! 👉 Start the challenge now: https://gfgcdn.com/tu/U4a/ 📌 Stay Connected for More Coding Challenges & Learning Resources: 📱 Download the GeeksforGeeks App: https://play.google.com/store/apps/details?id=free.programming.programming 💬 Twitter: https://twitter.com/geeksforgeeks 🧑‍💼 LinkedIn: https://www.linkedin.com/company/geeksforgeeks 📷 Instagram: https://www.instagram.com/geeksforgeeks/ 💌 Telegram: https://t.me/geeksforgeeks_official 📌 Pinterest: https://in.pinterest.com/geeksforgeeks/ 🎮 Discord: https://discord.gg/geeksforgeeks 🔍 Tags: AI Coding, AI-Powered Development, Vibe Coding, Future of Programming, Software Development Trends, Coding with AI, AI-Assisted Programming, Tech Innovations, Machine Learning in Coding, AI Coding Assistants, Software Engineering Revolution, AI for Developers, ChatGPT Coding, AI Coding Tools, gfg, gfg courses, gfg classes, it jobs, it job market, ai trends, ai news, ai vs software developers 🔥 Hashtags: #AICoding #FutureOfProgramming #VibeCoding #SoftwareDevelopment #TechTrends #CodingWithAI #AIRevolution #AIInTech #MachineLearning #CodingFuture #GeeksforGeeks #CodeSmarter #AIforDevelopers

#AICoding#FutureOfProgramming#VibeCoding

github

0.545

0.10175553624190911

obsei•Mar 27, 2025

obsei

Note: Obsei is still in alpha stage hence carefully use it in Production. Also, as it is constantly undergoing development hence master branch may contain many breaking changes. Please use released version. Obsei (pronounced "Ob see" | /əb-'sē/) is an open-source, low-code, AI powered automation tool. Obsei consists of - Observer: Collect unstructured data from various sources like tweets from Twitter, Subreddit comments on Reddit, page post's comments from Facebook, App Stores reviews, Google reviews, Amazon reviews, News, Website, etc. Analyzer: Analyze unstructured data collected with various AI tasks like classification, sentiment analysis, translation, PII, etc. Informer: Send analyzed data to various destinations like ticketing platforms, data storage, dataframe, etc so that the user can take further actions and perform analysis on the data. All the Observers can store their state in databases (Sqlite, Postgres, MySQL, etc.), making Obsei suitable for scheduled jobs or serverless applications. !Obsei diagram Future direction - Text, Image, Audio, Documents and Video oriented workflows Collect data from every possible private and public channels Add every possible workflow to an AI downstream application to automate manual cognitive workflows Use cases Obsei use cases are following, but not limited to - Social listening: Listening about social media posts, comments, customer feedback, etc. Alerting/Notification: To get auto-alerts for events such as customer complaints, qualified sales leads, etc. Automatic customer issue creation based on customer complaints on Social Media, Email, etc. Automatic assignment of proper tags to tickets based content of customer complaint for example login issue, sign up issue, delivery issue, etc. Extraction of deeper insight from feedbacks on various platforms Market research Creation of dataset for various AI tasks Many more based on creativity 💡 Installation Prerequisite Install the following (if not present already) - Install Python 3.7+ Install PIP Install Obsei You can install Obsei either via PIP or Conda based on your preference. To install latest released version - Install from master branch (if you want to try the latest features) - Note: all option will install all the dependencies which might not be needed for your workflow, alternatively following options are available to install minimal dependencies as per need - pip install obsei[source]: To install dependencies related to all observers pip install obsei[sink]: To install dependencies related to all informers pip install obsei[analyzer]: To install dependencies related to all analyzers, it will install pytorch as well pip install obsei[twitter-api]: To install dependencies related to Twitter observer pip install obsei[google-play-scraper]: To install dependencies related to Play Store review scrapper observer pip install obsei[google-play-api]: To install dependencies related to Google official play store review API based observer pip install obsei[app-store-scraper]: To install dependencies related to Apple App Store review scrapper observer pip install obsei[reddit-scraper]: To install dependencies related to Reddit post and comment scrapper observer pip install obsei[reddit-api]: To install dependencies related to Reddit official api based observer pip install obsei[pandas]: To install dependencies related to TSV/CSV/Pandas based observer and informer pip install obsei[google-news-scraper]: To install dependencies related to Google news scrapper observer pip install obsei[facebook-api]: To install dependencies related to Facebook official page post and comments api based observer pip install obsei[atlassian-api]: To install dependencies related to Jira official api based informer pip install obsei[elasticsearch]: To install dependencies related to elasticsearch informer pip install obsei[slack-api]:To install dependencies related to Slack official api based informer You can also mix multiple dependencies together in single installation command. For example to install dependencies Twitter observer, all analyzer, and Slack informer use following command - How to use Expand the following steps and create a workflow - Step 1: Configure Source/Observer Twitter Youtube Scrapper Facebook Email Google Maps Reviews Scrapper AppStore Reviews Scrapper Play Store Reviews Scrapper Reddit Reddit Scrapper Note: Reddit heavily rate limit scrappers, hence use it to fetch small data during long period Google News Web Crawler Pandas DataFrame Step 2: Configure Analyzer Note: To run transformers in an offline mode, check transformers offline mode. Some analyzer support GPU and to utilize pass device parameter. List of possible values of device parameter (default value auto): auto: GPU (cuda:0) will be used if available otherwise CPU will be used cpu: CPU will be used cuda:{id} - GPU will be used with provided CUDA device id Text Classification Text classification: Classify text into user provided categories. Sentiment Analyzer Sentiment Analyzer: Detect the sentiment of the text. Text classification can also perform sentiment analysis but if you don't want to use heavy-duty NLP model then use less resource hungry dictionary based Vader Sentiment detector. NER Analyzer NER (Named-Entity Recognition) Analyzer: Extract information and classify named entities mentioned in text into pre-defined categories such as person names, organizations, locations, medical codes, time expressions, quantities, monetary values, percentages, etc Translator PII Anonymizer Dummy Analyzer Dummy Analyzer: Does nothing. Its simply used for transforming the input (TextPayload) to output (TextPayload) and adding the user supplied dummy data. Step 3: Configure Sink/Informer Slack Zendesk Jira ElasticSearch Http Pandas DataFrame Logger This is useful for testing and dry running the pipeline. Step 4: Join and create workflow source will fetch data from the selected source, then feed it to the analyzer for processing, whose output we feed into a sink to get notified at that sink. Step 5: Execute workflow Copy the code snippets from Steps 1 to 4 into a python file, for example example.py and execute the following command - Demo We have a minimal streamlit based UI that you can use to test Obsei. !Screenshot Watch UI demo video Check demo at (Note: Sometimes the Streamlit demo might not work due to rate limiting, use the docker image (locally) in such cases.) To test locally, just run To run Obsei workflow easily using GitHub Actions (no sign ups and cloud hosting required), refer to this repo. Companies/Projects using Obsei Here are some companies/projects (alphabetical order) using Obsei. To add your company/project to the list, please raise a PR or contact us via email. Oraika: Contextually understand customer feedback 1Page: Giving a better context in meetings and calls Spacepulse: The operating system for spaces Superblog: A blazing fast alternative to WordPress and Medium Zolve: Creating a financial world beyond borders Utilize: No-code app builder for businesses with a deskless workforce Articles Sr. No. Title Author 1 AI based Comparative Customer Feedback Analysis Using Obsei Reena Bapna 2 LinkedIn App - User Feedback Analysis Himanshu Sharma Tutorials Sr. No. Workflow Colab Binder 1 Observe app reviews from Google play store, Analyze them by performing text classification and then Inform them on console via logger PlayStore Reviews → Classification → Logger 2 Observe app reviews from Google play store, PreProcess text via various text cleaning functions, Analyze them by performing text classification, Inform them to Pandas DataFrame and store resultant CSV to Google Drive PlayStore Reviews → PreProcessing → Classification → Pandas DataFrame → CSV in Google Drive 3 Observe app reviews from Apple app store, PreProcess text via various text cleaning function, Analyze them by performing text classification, Inform them to Pandas DataFrame and store resultant CSV to Google Drive AppStore Reviews → PreProcessing → Classification → Pandas DataFrame → CSV in Google Drive 4 Observe news article from Google news, PreProcess text via various text cleaning function, Analyze them via performing text classification while splitting text in small chunks and later computing final inference using given formula Google News → Text Cleaner → Text Splitter → Classification → Inference Aggregator 💡Tips: Handle large text classification via Obsei Documentation For detailed installation instructions, usages and examples, refer to our documentation. Support and Release Matrix Linux Mac Windows Remark Tests ✅ ✅ ✅ Low Coverage as difficult to test 3rd party libs PIP ✅ ✅ ✅ Fully Supported Conda ❌ ❌ ❌ Not Supported Discussion forum Discussion about Obsei can be done at community forum Changelogs Refer releases for changelogs Security Issue For any security issue please contact us via email Stargazers over time Maintainers This project is being maintained by Oraika Technologies. Lalit Pagaria and Girish Patel are maintainers of this project. License Copyright holder: Oraika Technologies Overall Apache 2.0 and you can read License file. Multiple other secondary permissive or weak copyleft licenses (LGPL, MIT, BSD etc.) for third-party components refer Attribution. To make project more commercial friendly, we void third party components which have strong copyleft licenses (GPL, AGPL etc.) into the project. Attribution This could not have been possible without these open source softwares. Contribution First off, thank you for even considering contributing to this package, every contribution big or small is greatly appreciated. Please refer our Contribution Guideline and Code of Conduct. Thanks so much to all our contributors

#github#obsei

github

0.449

0.07795191529604462

sjinnovation•Mar 27, 2025

CollabAI

CollabAI About Welcome to Collabai.software, where we've taken the world of AI to new heights. We've been working tirelessly to bring you the most advanced, user-friendly platform that seamlessly integrates with the powerful OpenAI API, Gemini, and Claude. Imagine running your own ChatGPT on your server, with the ability to manage access for your entire team. Picture creating custom AI assistants that cater to your unique needs, and organizing your employees into groups for streamlined collaboration. With Collabai.software, this is not just a dream, but a reality. Collabai.software Features: Self-Hosting on Your Cloud: Gain full control by hosting the platform on your private cloud. Ensure data privacy by using your API codes, allowing for secure data handling. Enhanced Team Management: Manage teams with private accounts and customizable access levels (Departments). Prompt Templates: Utilize generic templates to streamline team usage. Departmental Access & Assistant Assignment: Assign AI assistants to specific departments for shared team access. Customizable AI Assistants: Create personalized AI assistants for users or organizations. Tagging Feature in Chats: Organize and retrieve chat data efficiently with custom tags. Chat Storage and Retrieval: Save all chats and replies for future analysis, with an option to restore accidentally deleted chats from Trash. Optimized Performance: Experience our high-speed, efficient platform. Our clients have been using it for over a year, with some spending $1500-$2000 per month on the API. File Upload & GPT-4 Vision Integration: Enhance interactions by uploading files for analysis and sending pictures for AI description. OpenAI API, Gemini, and Claude Integration: Seamlessly integrate with the powerful OpenAI API, Gemini, and Claude for a comprehensive suite of AI capabilities. API-Based Function Calls: Execute custom functions and automate tasks directly through the API. Usage Monitoring: Track your daily and monthly API usage costs to optimize spending. Day and Night Mode: Switch between light and dark themes to enhance visual comfort. Additional Features: Private Accounts: Ensure the security and privacy of your team members' data. Customizable Access Levels: Tailor access permissions to meet the specific needs of your organization. Shared Team Access: Foster collaboration by assigning AI assistants to specific departments or teams. AI-Powered File Analysis: Gain insights and automate tasks by uploading files for AI analysis. AI-Generated Image Descriptions: Enhance communication and understanding by sending pictures for AI-powered descriptions. !image !image !image Folder Structure Client The client folder contains the React-based frontend code for the application. This includes JSX, CSS, and JavaScript files, as well as any additional assets such as images or fonts. Below is a brief overview of the main subdirectories within the client folder: src: This directory contains the React components, styles, and scripts for the frontend application. public: Static assets, such as images or favicon.ico, go here. This folder is served as-is and not processed by the build system. Server The server folder contains all the backend-related code for the application, following a Model-View-Controller (MVC) pattern. Here is a breakdown of the main subdirectories within the server folder: controllers: This directory holds the controller files responsible for handling requests, processing data, and interacting with models. models: Data models and database-related code are organized in this folder. config: Configuration files for the backend, such as database configuration or any other service configuration should be stored here, can be stored in this directory. Getting Started Follow the steps below to get the project up and running. Prerequisites Node.js (Version: >=20.x) MongoDB NPM Development Setup Clone the Repository bash cd client Install Dependencies bash cd ../server Install Backend Dependencies bash npm start To initialize the application data and create a superadmin user, you can use either cURL or Postman: Using cURL If you prefer command-line tools, you can use curl to make a POST request to the /init-setup endpoint. Open your terminal and run the following command: curl -X POST http://localhost:8011/api/init -H "Content-Type: application/json" -d '{ "fname": "Super", "lname": "Admin", "email": "superadmin@example.com", "password": "yourSecurePassword", "employeeCount": 100, "companyName": "INIT_COMPANY" }' Initializing Setup with Postman Open Postman: Launch the Postman application. Create a New Request: Click on the '+' or 'New' button to create a new request. Set HTTP Method to POST: Ensure that the HTTP method is set to POST. Enter URL: Enter the URL http://localhost:8011/api/init. Set Headers: Go to the 'Headers' tab. Set Content-Type to application/json. Set Request Body: Switch to the 'Body' tab. Select the 'raw' radio button. Enter the JSON data for your superadmin user: Send Request: Click the 'Send' button to make the request. This will send a POST request to http://localhost:8011/api/init with the provided JSON payload, creating a superadmin user with the specified details. Site Setup: Login with the superadmin credentials and set up your site by adding configs from your settings page, for ex. API keys, etc. Reference CollaborativeAI Reference Guide Contributing If you would like to contribute to the project, we welcome your contributions! Please follow the guidelines outlined in the CONTRIBUTING.md file. Feel free to raise issues, suggest new features, or send pull requests to help improve the project. Your involvement is greatly appreciated! Thank you for contributing to our project! License MIT

#github#collabai

youtube

0.344

0.57

Matthew Berman•Mar 21, 2025

AI News: Vibe Jam, The BEST Small LLM, Claude Search, OpenAI Audio Models, and more!

AI News is back! Let me know down below if you want me to start making weekly news videos again! Join My Newsletter for Regular AI Updates 👇🏼 https://forwardfuture.ai My Links 🔗 👉🏻 Subscribe: https://www.youtube.com/@matthew_berman 👉🏻 Twitter: https://twitter.com/matthewberman 👉🏻 Discord: https://discord.gg/xxysSXBxFW 👉🏻 Patreon: https://patreon.com/MatthewBerman 👉🏻 Instagram: https://www.instagram.com/matthewberman_ai 👉🏻 Threads: https://www.threads.net/@matthewberman_ai 👉🏻 LinkedIn: https://www.linkedin.com/company/forward-future-ai Media/Sponsorship Inquiries ✅ https://bit.ly/44TC45V Timestamps: 0:00 - Vibe Coding Jam 1:20 - Mistral Model 2:20 - Claude Search 2:57 - OpenAI Audio 4:39 - Windsurf Wave 5 5:28 - KREA AI Video Training 5:52 - Notebook LM Mindmaps 6:13 - Hunyuan 3D Modeling AI 6:45 - Stability AI Stable Virtual Camera 7:22 - Gemini Canvas 7:41 - LG EXAONE Links: https://x.com/levelsio/status/1901660771505021314 https://x.com/bgdnandrew/status/1903093702827933879 https://x.com/fergarram/status/1902779314224996624 https://x.com/LBacaj/status/1903114707336048851 https://x.com/realitybndr/status/1903054190944960824 https://x.com/dev_clap/status/1902912215860060494 https://x.com/iamarkdev/status/1902131862421836120 https://x.com/gabebusto/status/1902727892284379324 https://x.com/scobelverse/status/1903069102777962554/photo/1 https://mistral.ai/news/mistral-small-3-1 https://x.com/MistralAI/status/1901668499832918151 https://x.com/AnthropicAI/status/1902765011727999046 https://x.com/OpenAIDevs/status/1902773659497885936 https://www.openai.fm/ https://openai.com/index/introducing-our-next-generation-audio-models/ https://x.com/TXhunyuan/status/1901831819655606598 https://stability.ai/news/introducing-stable-virtual-camera-multi-view-video-generation-with-3d-camera-control https://x.com/LGAIResearch/status/1901803002052436323

youtube

0.379

0.77

Greg Isenberg•Mar 21, 2025

He makes $750 a day 'Vibe Coding' Apps (using Replit, ChatGPT, Upwork)

Billy Howell shares his strategy for making money by building and selling custom web applications using AI tools like Replit. He demonstrates the process by finding projects on Upwork, creating a product requirements document with ChatGPT, and using Replit to automatically generate a functional web application. Billy explains that this approach is less risky than building SaaS products because it validates demand before significant development work. Timestamps: 00:00 - Intro 02:19 - Searching for App Ideas on Upwork 11:04 - Using ChatGPT for PRD Creation 12:22 - Why choose Replit for Development 15:15 - Building Prototype with Replit 19:53 - Areas of Concern when building with AI coders 23:30 - Earning Potential on Upwork 27:55 - The process for selling these Apps 32:03 - Comparing Different Business Models 35:40 - Huge opportunity: Unbundling SaaS 37:44 - Testing App 39:39 - How to standout on Upwork 40:35 - Integrating v0 UI to Replit Key Points • Billy Howell explains his method of "vibe coding" - using AI tools like Replit to quickly build and sell custom web applications • The process involves finding clients on Upwork who need solutions, creating a prototype, and selling it before building the complete app • Billy demonstrates how to use Repl.it with AI assistance to rapidly build a case management system for a nonprofit • The approach focuses on creating simple CRUD (Create, Read, Update, Delete) applications rather than complex systems 1) The "Sell First, Build Later" Framework Billy's #1 rule: Find someone to BUY your app BEFORE you build it. Most developers get this backward - they build something cool then struggle to find users. The secret? Don't market. SELL. How? Look for people ALREADY trying to pay for solutions 2) Upwork Gold Mining Strategy Billy's exact process: • Search Upwork for jobs mentioning expensive SaaS tools (Airtable, HubSpot, etc) • Look for simple CRUD apps (data entry, visualization) • Build a quick prototype in Repl.it • Send a Loom video demo to potential clients His first sale? $750 replacing an Airtable solution! 3) The Vibe Coding Tech Stack Billy's weapons of choice: • Replit for rapid prototyping (zero setup friction!) • ChatGPT to format requirements into PRDs • V0 for beautiful UI mockups • ShadCN components for clean interfaces The magic combo: Feed requirements to Replit + "build me this app" = working prototype in MINUTES. 4) What to Avoid When Vibe Coding Not all projects are created equal! Watch out for: • Payment processing (risky) • DocuSign integrations (complex) • Calendar functionality (AI struggles with time zones) • Anything changing data in other apps Start with simple CRUD apps that store and display information. 5) The Real Money-Making Model Billy's approach isn't just about one-off projects: • Initial build: $750-2,500 • Charge for hosting • Recurring revenue from feature requests • Get referrals to similar businesses One recent client is now reselling his solution to other companies in the same industry! 6) Why This Beats Building a SaaS Building a traditional SaaS = "nightmare money pit" according to Billy. With vibe coding consulting: • De-risk by getting paid upfront • Learn across multiple projects • No marketing costs • Discover validated problems • Build a portfolio of solutions Six figures on Upwork is VERY doable. 7) The 60-Second Sales Pitch Billy's exact closing technique: • Find job posting • Make mockup in V0 or Replit • Record 1-minute Loom: "I'm Billy, I make apps. I know you wanted Airtable, but I made this custom for you." • Personalize with company name • Send and repeat Simple. Effective. PROFITABLE. The future of coding isn't about knowing every framework—it's about SOLVING PROBLEMS quickly. Anyone can do this with the right tools and approach. Notable Quotes: "The number one thing is how to sell an app that you've built... And the secret is not to market. It's just to sell it." - Billy Howell "We start, we need to find someone to buy the app before we build it. That's where most people get this wrong, is they build something and then try to sell it or try to get users." - Billy Howell LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ BoringAds — ads agency that will build you profitable ad campaigns http://boringads.com/ BoringMarketing — SEO agency and tools to get your organic customers http://boringmarketing.com/ Startup Empire — a membership for builders who want to build cash-flowing businesses https://www.startupempire.co FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND BILLY ON SOCIAL X/Twitter: https://x.com/billyjhowell Youtube: https://www.youtube.com/@billyjhowell

#1

youtube

0.419

0.88

Stefan Mischook•Mar 20, 2025

What is Vibe Coding, should you Learn It?

Vibe coding is coding with Ai as the Ai creates the boilerplate code for you. But does that mean you don't need to understand coding/development? #vibecoding #aidevelopment 🔥 STEF'S DEVELOPER BOOTCAMP AND MENTORING PROGRAM https://unclestef.com/ 📽️ Get your questions answered, sponsor a video: https://unclestef.com/blog/2025/03/04/sponsored-video-request/ 🎤 Listen to my Uncle Stef podcasts: https://unclestef.com/blog/2024/07/26/uncle-stef-podcast-all-episodes/ 🔥 JOIN STEF'S 'CODER'S CAREER PATHS' NEWSLETTER: https://newsletters.stefanmischook.com/coderscareerpaths_signup 🔥 FREE: LIZARD WIZARD KOMODO - TRANSFORMATIONAL MIND TRAINING: https://newsletters.stefanmischook.com/komodo Channel Discord Server: https://discord.gg/rn8za8aq2v WEB HOST PAYS FOR YOUR WEB DESIGN TRAINING IN 2023: https://www.killersites.com/blog/2020/web-hosting-company-pays-for-your-web-design-training/ POPULAR & EASY CODING COURSES: Full stack web developer course: https://school.studioweb.com/store/course/completewebdeveloper Python 3 Foundations & Certification: https://school.studioweb.com/store/course/python3foundations&certificationpackage Complete Freelancer: https://school.studioweb.com/store/course/complete_freelancer Complete Entrepreneur: https://school.studioweb.com/store/course/completewebentrepreneur 🦎 Lizard Wizard Course: https://school.studioweb.com/store/course/lizard_wizard 📚 BOOKS TO READ: My Beginners HTML5, CSS3: https://amzn.to/2wKsVTh … Complements Studioweb courses on HTML5, CSS3 and JavaScript. Refactoring: Improving the Design of Existing Code (2nd Edition) https://amzn.to/3o5cTbw HeadFirst Design Patterns: https://amzn.to/2LQ0Gdh Java Refactoring: Improving the Design of Existing Code (1st Edition) https://amzn.to/3a9nSsZ The Naked Ape: https://amzn.to/3fhS1Lj ✉️ STAY IN CONTACT: Stef's social links: Instagram: https://www.instagram.com/stefanmischook/?hl=en Twitter: https://twitter.com/killersites Stef's business channel: https://www.youtube.com/channel/UCZdr0ql_B240VBVINAX7Acg 👉 GOOGLE REVIEW: https://g.page/studioWebedu/review?mt Leave a Google review about Stef. MY MOUSE & KEYBOARD: Logitech Keyboard I use: https://amzn.to/38jYDqE Logitech mouse I use: https://amzn.to/2IeVvBj SUPPLEMENTS THAT WORK AMAZING FOR ME: Protein Essentials Beef Gelatine Powder: https://amzn.to/2Pf52vL ... Healed my very bad knee. If you have joint problems, this *could do miracles for you. Webber Naturals 88862 Glucosamine Chondroitin https://amzn.to/3ss9WEa MY CAMERA GEAR: Godox VL150 lights: https://amzn.to/3lhsYZP Sigma 18-35 lens: https://amzn.to/33sRh0T Canon EOS C70 Cinema Camera Thanks! Stef #mentoring #codecourses #unclestef #codingcoach

#vibecoding#aidevelopment#mentoring

youtube

0.386

0.81

Matthew Berman•Mar 5, 2025

Vibe Coding Tutorial and Best Practices (Cursor / Windsurf)

Got a lot of questions asking about my stack and what I do when vibe coding. So I made a full video on it! 👉 Learn more on https://mammouth.ai/ Join My Newsletter for Regular AI Updates 👇🏼 https://forwardfuture.ai My Links 🔗 👉🏻 Subscribe: https://www.youtube.com/@matthew_berman 👉🏻 Twitter: https://twitter.com/matthewberman 👉🏻 Discord: https://discord.gg/xxysSXBxFW 👉🏻 Patreon: https://patreon.com/MatthewBerman 👉🏻 Instagram: https://www.instagram.com/matthewberman_ai 👉🏻 Threads: https://www.threads.net/@matthewberman_ai 👉🏻 LinkedIn: https://www.linkedin.com/company/forward-future-ai Media/Sponsorship Inquiries ✅ https://bit.ly/44TC45V

youtube

0.384

0.8

Matthew Berman•Mar 4, 2025

Vibe Coding a FULL Game 🎮 (AI Coding)

Is vibe coding really a vibe? let's make a game and find out! Check out Langtrace's GitHub here: https://bit.ly/4efuYxL 20% discount for Langtrace here: https://langtrace.ai/matthewberman Join Langtrace’s upcoming webinar to take your LLM apps from development to deployment: https://streamyard.com/watch/BsQGbHBJSuWV Join My Newsletter for Regular AI Updates 👇🏼 https://forwardfuture.ai My Links 🔗 👉🏻 Subscribe: https://www.youtube.com/@matthew_berman 👉🏻 Twitter: https://twitter.com/matthewberman 👉🏻 Discord: https://discord.gg/xxysSXBxFW 👉🏻 Patreon: https://patreon.com/MatthewBerman 👉🏻 Instagram: https://www.instagram.com/matthewberman_ai 👉🏻 Threads: https://www.threads.net/@matthewberman_ai 👉🏻 LinkedIn: https://www.linkedin.com/company/forward-future-ai Media/Sponsorship Inquiries ✅ https://bit.ly/44TC45V

youtube

0.382

0.56

Stefan Mischook•Feb 28, 2025

Vibe Coding and Coder Cry Babies

Vibe coding is a new thing in the Ai and development world, and it is gaining a lot of attention. The new age of development is upon us! 🔥 STEF'S DEVELOPER BOOTCAMP AND MENTORING PROGRAM https://unclestef.com/ 🎤 Listen to my Uncle Stef podcasts: https://unclestef.com/blog/2024/07/26/uncle-stef-podcast-all-episodes/ 🔥 JOIN STEF'S 'CODER'S CAREER PATHS' NEWSLETTER: https://newsletters.stefanmischook.com/coderscareerpaths_signup 🔥 FREE: LIZARD WIZARD KOMODO - TRANSFORMATIONAL MIND TRAINING: https://newsletters.stefanmischook.com/komodo Channel Discord Server: https://discord.gg/rn8za8aq2v WEB HOST PAYS FOR YOUR WEB DESIGN TRAINING IN 2023: https://www.killersites.com/blog/2020/web-hosting-company-pays-for-your-web-design-training/ POPULAR & EASY CODING COURSES: Full stack web developer course: https://school.studioweb.com/store/course/completewebdeveloper Python 3 Foundations & Certification: https://school.studioweb.com/store/course/python3foundations&certificationpackage Complete Freelancer: https://school.studioweb.com/store/course/complete_freelancer Complete Entrepreneur: https://school.studioweb.com/store/course/completewebentrepreneur 🦎 Lizard Wizard Course: https://school.studioweb.com/store/course/lizard_wizard 📚 BOOKS TO READ: My Beginners HTML5, CSS3: https://amzn.to/2wKsVTh … Complements Studioweb courses on HTML5, CSS3 and JavaScript. Refactoring: Improving the Design of Existing Code (2nd Edition) https://amzn.to/3o5cTbw HeadFirst Design Patterns: https://amzn.to/2LQ0Gdh Java Refactoring: Improving the Design of Existing Code (1st Edition) https://amzn.to/3a9nSsZ The Naked Ape: https://amzn.to/3fhS1Lj ✉️ STAY IN CONTACT: Stef's social links: Instagram: https://www.instagram.com/stefanmischook/?hl=en Twitter: https://twitter.com/killersites Stef's business channel: https://www.youtube.com/channel/UCZdr0ql_B240VBVINAX7Acg 👉 GOOGLE REVIEW: https://g.page/studioWebedu/review?mt Leave a Google review about Stef. MY MOUSE & KEYBOARD: Logitech Keyboard I use: https://amzn.to/38jYDqE Logitech mouse I use: https://amzn.to/2IeVvBj SUPPLEMENTS THAT WORK AMAZING FOR ME: Protein Essentials Beef Gelatine Powder: https://amzn.to/2Pf52vL ... Healed my very bad knee. If you have joint problems, this *could do miracles for you. Webber Naturals 88862 Glucosamine Chondroitin https://amzn.to/3ss9WEa MY CAMERA GEAR: Godox VL150 lights: https://amzn.to/3lhsYZP Sigma 18-35 lens: https://amzn.to/33sRh0T Canon EOS C70 Cinema Camera Thanks! Stef #mentoring #codecourses #unclestef #codingcoach

#mentoring#codecourses#unclestef

youtube

0.406

0.81

Matthew Berman•Feb 23, 2025

What is "Vibe Coding"? Here's how I do it...

Check out Langtrace's GitHub here: https://bit.ly/4efuYxL 20% discount for Langtrace here: https://langtrace.ai/matthewberman Join Langtrace’s upcoming webinar to take your LLM apps from development to deployment: https://streamyard.com/watch/BsQGbHBJSuWV Join My Newsletter for Regular AI Updates 👇🏼 https://forwardfuture.ai My Links 🔗 👉🏻 Subscribe: https://www.youtube.com/@matthew_berman 👉🏻 Twitter: https://twitter.com/matthewberman 👉🏻 Discord: https://discord.gg/xxysSXBxFW 👉🏻 Patreon: https://patreon.com/MatthewBerman 👉🏻 Instagram: https://www.instagram.com/matthewberman_ai 👉🏻 Threads: https://www.threads.net/@matthewberman_ai 👉🏻 LinkedIn: https://www.linkedin.com/company/forward-future-ai Media/Sponsorship Inquiries ✅ https://bit.ly/44TC45V

youtube

0.367

0.59

Matthew Berman•Feb 13, 2025

What is Vibe Coding? ☮️ 😎

Join My Newsletter for Regular AI Updates 👇🏼 https://forwardfuture.ai My Links 🔗 👉🏻 Subscribe: https://www.youtube.com/@matthew_berman 👉🏻 Twitter: https://twitter.com/matthewberman 👉🏻 Discord: https://discord.gg/xxysSXBxFW 👉🏻 Patreon: https://patreon.com/MatthewBerman 👉🏻 Instagram: https://www.instagram.com/matthewberman_ai 👉🏻 Threads: https://www.threads.net/@matthewberman_ai 👉🏻 LinkedIn: https://www.linkedin.com/company/forward-future-ai Media/Sponsorship Inquiries ✅ https://bit.ly/44TC45V

github

0.414

0.013305067808012168

dmcglone•Feb 4, 2025

airbnb

Notes on Airbnb business in New York and elsewhere ================================================== Disclaimer The script scrapes the Airbnb web site to collect data about the shape of the company's business. No guarantees are made about the quality of data obtained using this script, statistically or about an individual page. So please check your results. Changelog 2014-12-02 Tom Slee More robustness fixes. 2014-09-23 Tom Slee Bug fixes that solve problems where over-eager exception handling caused the script to exit too early. 2014-08-26 Tom Slee Version 2.1 is updated to be able to collect data from Airbnb's updated web site. Not all cities have the new format, but the script should handle both versions. It will not, however, handle cities without neighborhoods. 2014-05-26 Tom Slee Version 2 (May 2014) is much more thorough and efficient about searching Airbnb's web site for a given city and has more options. I have moved it to python 3 for better handling of unicode multi-lingual data. It is also ported to SAP SQL Anywhere to allow more flexible reporting and better concurrency than SQLite can provide. A free developer edition is available from the SAP web site. You may need to configure the python driver following the instructions given in http://dcx.sybase.com/index.html#sa160/en/dbprogramming/pg-python.html. airbnb.py is the python script to collect data. plot.py just produces some charts. airbnb.db is the data. The basic data is in the table room. A complete search of a given city's listings is a "survey" and the surveys are tracked in table survey. Using the script To create the database: python airbnb.py -dbi. This command does two things: initializes a database file (dbnb.db in the current directory) runs the reload.sql script against the database to create the tables, views, and stored procedures that make up the database. No data is added. On Windows, the reload.sql script does not always run. If that fails, try this to create the database tables: dbisql -c "uid=dba;pwd=sql;dbf=dbnb.db;eng=db" From Interactive SQL, click File > Open and choose reload.sql from the current directory. Hit F5 to execute the script and create the tables. Test that you can connect to the database file: run python airbnb.py --dbping and confirm that there are no errors. If there are errors, check the database file setting near the top of the script and change its location. To run a survey: add a city (search area) to the database, by running ./airbnb.py -asa "city-name". It scans the Airbnb web site and adds the neighborhoods for the city. add a survey to the database by running ./airbnb.py -asv "city-name". The command lists the survey_id value that was created. collect the roomids for the survey by running ./airbnb.py -s surveyid. The survey_id can be seen by running ./airbnb -ls. This search loops over neighborhoods, property types, and pages of listings in the Airbnb search pages. fill in the details of the rooms by running ./airbnb -f. If any step fails: If the -s step or the -f step fails (say because the internet connection was lost), you can just run it again, and it will pick up from where it left off without losing data. Continue until the script completes.

#github#airbnb

github

0.203

0

Softtechhub1•Feb 1, 2025

Mastering-AI-for-Entrepreneurs-9-Free-Courses

Mastering-AI-for-Entrepreneurs-9-Free-Courses Introduction: The Entrepreneur's AI RevolutionArtificial Intelligence (AI) is changing the way we do business. It's not just for tech giants anymore. Small businesses and startups are using AI to work smarter, not harder. As an entrepreneur, you need to understand AI to stay ahead.Why AI is a must-have skill for entrepreneursAI is everywhere. It's in the apps we use, the products we buy, and the services we rely on. Businesses that use AI are seeing big improvements:They're making better decisions with data-driven insightsThey're automating routine tasks, freeing up time for creativityThey're personalizing customer experiences, boosting satisfaction and salesIf you're not using AI, you're falling behind. But here's the good news: you don't need to be a tech wizard to harness the power of AI.Breaking the barriers to AI learningThink AI is too complex? Think again. You don't need a computer science degree to understand and use AI in your business. Many AI tools are designed for non-technical users. They're intuitive and user-friendly.The best part? You can learn about AI for free. There are tons of high-quality courses available at no cost. These courses are designed for busy entrepreneurs like you. They cut through the jargon and focus on practical applications.What to expect from this articleWe've handpicked nine free courses that will turn you into an AI-savvy entrepreneur. Each course is unique, offering different perspectives and skills. We'll cover:What makes each course specialWhat you'll learnHow it applies to your businessWho it's best suited forReady to dive in? Let's explore these game-changing courses that will boost your AI knowledge and give your business an edge.1. Google AI Essentials: A Beginner's Guide to Practical AIWhy This Course Is EssentialGoogle AI Essentials is perfect if you're just starting out. It's designed for people who don't have a tech background. The course focuses on how AI can help you in your day-to-day work, not on complex theories.What You'll LearnThis course is all about making AI work for you. You'll discover how to:Use AI to boost your productivity. Generate ideas, create content, and manage tasks more efficiently.Streamline your workflows. Learn how AI can help with everyday tasks like drafting emails and organizing your schedule.Use AI responsibly. Understand the potential biases in AI and how to use it ethically.Key TakeawaysYou'll earn a certificate from Google. This looks great on your resume or LinkedIn profile.You'll learn how to work alongside AI tools to get better results in your business.You'll gain practical skills you can use right away to improve your work.Get StartedEnroll in Google AI Essentials2. Introduction to Generative AI: A Quick Start for EntrepreneursWhy This Course Works for Busy EntrepreneursThis course is short and sweet. In just 30 minutes, you'll get a solid grasp of generative AI. It's perfect if you're short on time but want to understand the basics.What You'll LearnThe fundamentals of generative AI: what it is, how it works, and its limitsHow generative AI differs from other types of AIReal-world applications of generative AI in businessHow It Helps Your BusinessAfter this course, you'll be able to:Make smarter decisions about using AI tools in your businessSpot opportunities where generative AI could solve problems or create valueUnderstand the potential and limitations of this technologyGet StartedEnroll in Introduction to Generative AI3. Generative AI with Large Language Models: Advanced Skills for EntrepreneursWhy This Course Stands OutThis course digs deeper into the technical side of AI. It's ideal if you have some coding experience and want to understand how AI models work under the hood.What You'll LearnYou'll gain key skills for working with Large Language Models (LLMs):How to gather and prepare data for AI modelsChoosing the right model for your needsEvaluating model performance and improving resultsYou'll also learn about:The architecture behind transformer models (the tech powering many AI tools)Techniques for fine-tuning models to your specific business needsWho Should Take This CourseThis course is best for entrepreneurs who:Have basic Python programming skillsUnderstand the fundamentals of machine learningWant to go beyond using AI tools to actually building and customizing themGet StartedEnroll in Generative AI with Large Language Models4. AI for Everyone by Andrew Ng: Simplifying AI for Business LeadersWhy It's Perfect for BeginnersAndrew Ng is a leading figure in AI education. He's known for making complex topics easy to understand. This course is designed for non-technical learners. You don't need any coding or math skills to benefit from it.What You'll LearnHow AI works at a high levelHow to spot problems in your business that AI can solveWays to assess how AI might impact your business processes and strategiesWhy Entrepreneurs Love This CourseIt explains AI concepts in plain English, without technical jargonYou can complete it in just 8 hours, fitting it into your busy scheduleIt focuses on the business value of AI, not just the technologyGet StartedStart with AI for Everyone on Coursera5. Generative AI: Introduction and ApplicationsWhy This Course Is Ideal for EntrepreneursThis course offers a broad view of generative AI applications. You'll learn about AI in text, image, audio, and more. It's packed with hands-on experience using popular AI tools.What You'll LearnThe basics and history of generative AI technologiesHow different industries are using AI, from marketing to creative projectsPractical skills through labs using tools like ChatGPT, DALL-E, and Stable DiffusionHow It Stands OutYou'll hear from real AI practitioners about their experiencesThe course teaches you how to use generative AI to innovate and improve efficiency in your businessGet StartedEnroll in Generative AI: Introduction and Applications6. Generative AI for Everyone by Andrew Ng: Unlocking ProductivityWhy This Course Is a Must-HaveThis course focuses on using generative AI tools for everyday business tasks. It's all about boosting your productivity and efficiency.What You'll LearnHands-on exercises to integrate AI tools into your daily workReal examples of how businesses are using generative AI to save time and moneyTechniques for prompt engineering to get better results from AI toolsHow It Helps EntrepreneursYou'll learn to automate repetitive tasks, freeing up time for strategic thinkingYou'll discover new ways to use AI tools in your business processesYou'll gain confidence in experimenting with AI to solve business challengesGet StartedGo deeper with DeepLearning.AI7. Generative AI for Business Leaders by LinkedIn LearningWhy This Course Focuses on Business ApplicationsThis course is tailored for leaders who want to integrate AI into their business operations. It provides practical insights for improving workflows and decision-making.What You'll LearnStrategies for using AI to optimize your business operationsHow to save time and resources with AI-powered toolsPractical methods for implementing AI in your company, regardless of sizeKey BenefitsThe course is designed for busy professionals, allowing you to learn at your own paceYou'll gain insights you can apply immediately to your businessIt covers both the potential and the limitations of AI in business settingsGet StartedLevel up on LinkedIn Learning8. AI for Beginners by Microsoft: A Structured Learning PathWhy This Course Builds a Strong AI FoundationMicrosoft's AI for Beginners is a comprehensive 12-week program. It covers core AI concepts in a structured, easy-to-follow format. The course combines theoretical knowledge with hands-on practice through quizzes and labs.What You'll LearnThe basics of AI, machine learning, and data scienceStep-by-step guidance to build a strong knowledge basePractical applications of AI in various business contextsHow to Approach This CourseDedicate 2-3 hours per week to complete the curriculumUse the structured format to gradually build your confidence in AI conceptsApply what you learn to real business scenarios as you progressGet StartedBuild foundations with Microsoft9. AI for Business Specialization by UPenn: Strategic Thinking with AIWhy This Course Is Perfect for Business LeadersThis specialization focuses on AI's transformative impact on core business functions. It covers how AI is changing marketing, finance, and operations.What You'll LearnHow to build an AI strategy tailored to your business needsWays to leverage AI to drive innovation across different departmentsTechniques for integrating AI into your business modelHow to Make the Most of This CourseTake detailed notes on how each module applies to your own business challengesUse the specialization to develop a long-term AI vision for your companyNetwork with other business leaders taking the course to share insights and experiencesGet StartedScale up with UPenn's business focusConclusion: Your Path to Becoming an AI-powered EntrepreneurWe've covered nine fantastic free courses that can transform you into an AI-savvy entrepreneur. Let's recap:Google AI Essentials: Perfect for beginners, focusing on practical AI applications.Introduction to Generative AI: A quick start to understand the basics of generative AI.Generative AI with Large Language Models: For those ready to dive into the technical side.AI for Everyone: A non-technical introduction to AI's business impact.Generative AI: Introduction and Applications: A broad look at generative AI across industries.Generative AI for Everyone: Focused on boosting productivity with AI tools.Generative AI for Business Leaders: Tailored for integrating AI into business operations.AI for Beginners: A structured path to build a strong AI foundation.AI for Business Specialization: Strategic thinking about AI in business functions.Remember, you don't need to tackle all these courses at once. Start small and build your knowledge gradually. Pick the course that aligns best with your current needs and business goals.Embracing AI is not just about staying competitive; it's about opening new doors for innovation and growth. These courses will help you see opportunities where AI can solve problems, improve efficiency, and create value for your business.The AI revolution is happening now. The sooner you start learning, the better positioned you'll be to lead in this new era. Each step you take in understanding AI is a step towards future-proofing your business.So, what are you waiting for? Choose a course, dive in, and start your journey to becoming an AI-powered entrepreneur today. The future of your business may depend on it.MORE ARTICLES FOR YOUHumanizzer Fastpass Bundle – OTO1 to OTO4: Get (Humanizzer + All OTOs) Fastpass for Massive 75% Discount Available Limited-Time OneHumanizzer Review: Build Lifelike Human AI Agents That Talk, Listen & Engage Face-To-Face!—In Your Voice, Just Like You!EasyListDetox App Review: A Windows tool with Giveaway Rights for effortlessly cleaning your email lists of duplicates, invalid, and disposable addresses. Simple, efficient, and time-savingAI Copy Kit Review: Google’s Latest AI Tech Tensorflow (Tf) Create Jaw-Dropping And Advanced Ultra HD Videos, Ultra Shorts, 4K Images, Voiceovers, and Any Other GPT 4-Powered Amazing Content In Minutes Without Any Complicated Tools!From Good to Great: 15 Books to Inspire Personal and Business TransformationFTC Affiliate Commission Disclaimer: Some links in this article may earn us a commission if you make a purchase. This doesn't affect our recommendations.

#github#mastering-ai-for-entrepreneurs-9-free-courses

github

0.236

0.009333333333333334

bogdanmosica•Jan 23, 2025

internet-tools-collection

Internet Tools Collection A collection of tools, website and AI for entrepreneurs, web designers, programmers and for everyone else. Content by category Artificial Intelligence Developers Design Entrepreneur Video Editing Stock videos Stock Photos Stock music Search Engine Optimization Blog Posts Resume Interviews No code website builder No code game builder Side Hustle Browser Extensions Other Students Artificial Intelligence Jasper - The Best AI Writing Assistant [](https://www.jasper.ai/) Create content 5x faster with artificial intelligence. Jasper is the highest quality AI copywriting tool with over 3,000 5-star reviews. Best for writing blog posts, social media content, and marketing copy. AutoDraw [](https://www.autodraw.com/) Fast drawing for everyone. AutoDraw pairs machine learning with drawings from talented artists to help you draw stuff fast. Rytr - Best AI Writer, Content Generator & Writing Assistant [](https://rytr.me/) Rytr is an AI writing assistant that helps you create high-quality content, in just a few seconds, at a fraction of the cost! Neevo - Neevo [](https://www.neevo.ai/) Kinetix Tech [](https://kinetix.tech/) Kinetix is a no-code 3D creation tool powered by Artificial Intelligence. The web-based platform leverages AI motion capture to convert a video into a 3D animation and lets you customize your avatars and environments. We make 3D animation accessible to every creator so they can create engaging stories. LALAL.AI: 100% AI-Powered Vocal and Instrumental Tracks Remover [](https://www.lalal.ai/) Split vocal and instrumental tracks quickly and accurately with LALAL.AI. Upload any audio file and receive high-quality extracted tracks in a few seconds. Copy.ai: Write better marketing copy and content with AI [](https://www.copy.ai/) Get great copy that sells. Copy.ai is an AI-powered copywriter that generates high-quality copy for your business. Get started for free, no credit card required! Marketing simplified! OpenAI [](https://openai.com/) OpenAI is an AI research and deployment company. Our mission is to ensure that artificial general intelligence benefits all of humanity. DALL·E 2 [](https://openai.com/dall-e-2/) DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language. Steve.ai - World’s fastest way to create Videos [](https://www.steve.ai/) Steve.AI is an online Video making software that helps anyone to create Videos and animations in seconds. Octie.ai - Your A.I. ecommerce marketing assistant [](https://octie.ai/) Write emails, product descriptions, and more, with A.I. Created by Octane AI. hypnogram.xyz [](https://hypnogram.xyz/) Generate images from text descriptions using AI FakeYou. Deep Fake Text to Speech. [](https://fakeyou.com/) FakeYou is a text to speech wonderland where all of your dreams come true. Craiyon, formerly DALL-E mini [](https://www.craiyon.com/) Craiyon, formerly DALL-E mini, is an AI model that can draw images from any text prompt! Deck Rocks - Create Pictch Decks [](https://www.deck.rocks/) Writely | Using AI to Improve Your Writing [](https://www.writelyai.com/) Making the art of writing accessible to all Writesonic AI Writer - Best AI Writing Assistant [](https://writesonic.com/) Writesonic is an AI writer that's been trained on top-performing SEO content, high-performing ads, and converting sales copy to help you supercharge your writing and marketing efforts. Smart Copy - AI Copywriting Assistant | Unbounce [](https://unbounce.com/product/smart-copy/) Generate creative AI copy on-the-spot across your favourite tools Synthesia | #1 AI Video Generation Platform [](https://www.synthesia.io/) Create AI videos by simply typing in text. Easy to use, cheap and scalable. Make engaging videos with human presenters — directly from your browser. Free demo. NVIDIA Canvas: Turn Simple Brushstrokes into Realistic Images [](https://www.nvidia.com/en-us/studio/canvas/) Create backgrounds quickly, or speed up your concept exploration so you can spend more time visualizing ideas with the help of NVIDIA Canvas. Hotpot.ai - Hotpot.ai [](https://hotpot.ai/) Hotpot.ai makes graphic design and image editing easy. AI tools allow experts and non-designers to automate tedious tasks while attractive, easy-to-edit templates allow anyone to create device mockups, social media posts, marketing images, app icons, and other work graphics. Klaviyo: Marketing Automation Platform for Email & SMS [](https://www.klaviyo.com/) Klaviyo, an ecommerce marketing automation platform for email marketing and sms syncs your tech stack with your website store to scale your business. Search listening tool for market, customer & content research - AnswerThePublic [](https://answerthepublic.com/) Use our free tool to get instant, raw search insights, direct from the minds of your customers. Upgrade to a paid plan to monitor for new ways that people talk & ask questions about your brand, product or topic. Topic Mojo [](https://topicmojo.com/) Discover unique & newest queries around any topic and find what your customers are searching for. Pulling data from 50+ sources to enhance your topic research. AI Image Enlarger | Enlarge Image Without Losing Quality! [](https://imglarger.com/) AI Image Enlarger is a FREE online image enlarger that could upscale and enhance small images automatically. Make jpg/png pictures big without losing quality. Midjourney [](https://www.midjourney.com/app/) Kaedim - AI for turning 2D images to 3D models [](https://www.kaedim3d.com/webapp) AI for turning 2D images, sketches and photos to 3D models in seconds. Overdub: Ultra realistic text to speech voice cloning - Descript [](https://www.descript.com/overdub) Create a text to speech model of your voice. Try a live demo. Getting Started [](https://magenta.tensorflow.org/get-started) Resources to learn about Magenta Photosonic AI Art Generator | Create Unique Images with AI [](https://photosonic.writesonic.com/) Transform your imagination into stunning digital art with Photosonic - the AI art generator. With its creative suggestions, this Writesonic's AI image generator can help unleash your inner artist and share your creations with the world. Image Computer [](https://image.computer/) Most downloaded Instagram Captions App (+more creator tools) [](https://captionplus.app/) Join 3 Million+ Instagram Creators who use CaptionPlus to find Instagram Captions, Hashtags, Feed Planning, Reel Ideas, IG Story Design and more. Writecream - Best AI Writer & Content Generator - Writecream [](https://www.writecream.com/) Sentence Rewriter is a free tool to reword a sentence, paragraph and even entire essays in a short amount of time. Hypotenuse AI: AI Writing Assistant and Text Generator [](https://www.hypotenuse.ai/) Turn a few keywords into original, insightful articles, product descriptions and social media copy with AI copywriting—all in just minutes. Try it free today. Text to Speach Listnr: Generate realistic Text to Speech voiceovers in seconds [](https://www.listnr.tech/) AI Voiceover Generator with over 600+ voiceovers in 80+ languages, go from Text to Voice in seconds. Get started for Free! Free Text to Speech: Online, App, Software, Commercial license with Natural Sounding Voices. [](https://www.naturalreaders.com/) Free text to speech online app with natural voices, convert text to audio and mp3, for personal and commercial use Developers OverAPI.com | Collecting all the cheat sheets [](https://overapi.com/) OverAPI.com is a site collecting all the cheatsheets,all! Search Engine For Devs [](https://you.com/) Spline - Design tool for 3D web browser experiences [](https://spline.design/) Create web-based 3D browser experiences Image to HTML CSS converter. Convert image to HTML CSS with AI: Fronty [](https://fronty.com/) Fronty - Image to HTML CSS code converter. Convert image to HTML powered by AI. Sketchfab - The best 3D viewer on the web [](https://sketchfab.com/) With a community of over one million creators, we are the world’s largest platform to publish, share, and discover 3D content on web, mobile, AR, and VR. Railway [](https://railway.app/) Railway is an infrastructure platform where you can provision infrastructure, develop with that infrastructure locally, and then deploy to the cloud. JSON Crack - Crack your data into pieces [](https://jsoncrack.com/) Simple visualization tool for your JSON data. No forced structure, paste your JSON and view it instantly. Locofy.ai - ship your products 3-4x faster — with low code [](https://www.locofy.ai/) Turn your designs into production-ready frontend code for mobile apps and web. Ship products 3-4x faster with your existing design tools, tech stacks & workflows. Oh Shit, Git!?! [](https://ohshitgit.com/) Carbon | Create and share beautiful images of your source code [](https://carbon.now.sh/) Carbon is the easiest way to create and share beautiful images of your source code. GPRM : GitHub Profile ReadMe Maker [](https://gprm.itsvg.in/) Best Profile Generator, Create your perfect GitHub Profile ReadMe in the best possible way. Lots of features and tools included, all for free ! HubSpot | Software, Tools, and Resources to Help Your Business Grow Better [](https://www.hubspot.com/) HubSpot’s integrated CRM platform contains the marketing, sales, service, operations, and website-building software you need to grow your business. QuickRef.ME - Quick Reference Cheat Sheet [](https://quickref.me/) Share quick reference and cheat sheet for developers massCode | A free and open source code snippets manager for developers [](https://masscode.io/) Code snippets manager for developers, developed using web technologies. Snyk | Developer security | Develop fast. Stay secure. [](https://snyk.io/) Snyk helps software-driven businesses develop fast and stay secure. Continuously find and fix vulnerabilities for npm, Maven, NuGet, RubyGems, PyPI and more. Developer Roadmaps [](https://roadmap.sh/) Community driven roadmaps, articles, guides, quizzes, tips and resources for developers to learn from, identify their career paths, know what they don't know, find out the knowledge gaps, learn and improve. CSS Generators Get Waves – Create SVG waves for your next design [](https://getwaves.io/) A free SVG wave generator to make unique SVG waves for your next web design. Choose a curve, adjust complexity, randomize! Box Shadows [](https://box-shadow.dev/) Tridiv | CSS 3D Editor [](http://tridiv.com/) Tridiv is a web-based editor for creating 3D shapes in CSS Glassmorphism CSS Generator - Glass UI [](https://ui.glass/generator/) Generate CSS and HTML components using the glassmorphism design specifications based on the Glass UI library. Blobmaker - Make organic SVG shapes for your next design [](https://www.blobmaker.app/) Make organic SVG shapes for your next design. Modify the complexity, contrast, and color, to generate unique SVG blobs every time. Keyframes.app [](https://keyframes.app/) cssFilters.co - Custom and Instagram like photo filters for CSS [](https://www.cssfilters.co/) Visual playground for generating CSS for custom and Instagram like photo filters. Experiment with your own uploaded photo or select one from the Unsplash collection. CSS Animations Animista - CSS Animations on Demand [](https://animista.net/) Animista is a CSS animation library and a place where you can play with a collection of ready-made CSS animations and download only those you will use. Build Internal apps Superblocks | Save 100s of developer hours on internal tools [](https://www.superblocks.com/) Superblocks is the fast, easy and secure way for developers to build custom internal tools fast. Connect your databases & APIs. Drag and drop UI components. Extend with Python or Javascript. Deploy in 1-click. Secure and Monitor using your favorite tools Budibase | Build internal tools in minutes, the easy way [](https://budibase.com/) Budibase is a modern, open source low-code platform for building modern internal applications in minutes. Retool | Build internal tools, remarkably fast. [](https://retool.com/) Retool is the fast way to build internal tools. Drag-and-drop our building blocks and connect them to your databases and APIs to build your own tools, instantly. Connects with Postgres, REST APIs, GraphQL, Firebase, Google Sheets, and more. Built by developers, for developers. Trusted by startups and Fortune 500s. Sign up for free. GitHub Repositories GitHub - vasanthk/how-web-works: What happens behind the scenes when we type www.google.com in a browser? [](https://github.com/vasanthk/how-web-works) What happens behind the scenes when we type www.google.com in a browser? - GitHub - vasanthk/how-web-works: What happens behind the scenes when we type www.google.com in a browser? GitHub - kamranahmedse/developer-roadmap: Interactive roadmaps, guides and other educational content to help developers grow in their careers. [](https://github.com/kamranahmedse/developer-roadmap) Interactive roadmaps, guides and other educational content to help developers grow in their careers. - GitHub - kamranahmedse/developer-roadmap: Interactive roadmaps, guides and other educational content to help developers grow in their careers. GitHub - apptension/developer-handbook: An opinionated guide on how to become a professional Web/Mobile App Developer. [](https://github.com/apptension/developer-handbook) An opinionated guide on how to become a professional Web/Mobile App Developer. - GitHub - apptension/developer-handbook: An opinionated guide on how to become a professional Web/Mobile App Developer. ProfileMe.dev | Create an amazing GitHub profile in minutes [](https://www.profileme.dev/) ProfileMe.dev | Create an amazing GitHub profile in minutes GitHub - Kristories/awesome-guidelines: A curated list of high quality coding style conventions and standards. [](https://github.com/Kristories/awesome-guidelines) A curated list of high quality coding style conventions and standards. - GitHub - Kristories/awesome-guidelines: A curated list of high quality coding style conventions and standards. GitHub - tiimgreen/github-cheat-sheet: A list of cool features of Git and GitHub. [](https://github.com/tiimgreen/github-cheat-sheet) A list of cool features of Git and GitHub. Contribute to tiimgreen/github-cheat-sheet development by creating an account on GitHub. GitHub - andreasbm/web-skills: A visual overview of useful skills to learn as a web developer [](https://github.com/andreasbm/web-skills) A visual overview of useful skills to learn as a web developer - GitHub - andreasbm/web-skills: A visual overview of useful skills to learn as a web developer GitHub - Ebazhanov/linkedin-skill-assessments-quizzes: Full reference of LinkedIn answers 2022 for skill assessments (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, Go, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test LinkedIn test questions and answers [](https://github.com/Ebazhanov/linkedin-skill-assessments-quizzes) Full reference of LinkedIn answers 2022 for skill assessments (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, Go, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test LinkedIn test questions and answers - GitHub - Ebazhanov/linkedin-skill-assessments-quizzes: Full reference of LinkedIn answers 2022 for skill assessments (aws-lambda, rest-api, javascript, react, git, html, jquery, mongodb, java, Go, python, machine-learning, power-point) linkedin excel test lösungen, linkedin machine learning test LinkedIn test questions and answers Blockchain/Crypto Dashboards [](https://dune.com/) Blockchain ecosystem analytics by and for the community. Explore and share data from Ethereum, xDai, Polygon, Optimism, BSC and Solana for free. Introduction - The Anchor Book v0.24.0 [](https://book.anchor-lang.com/introduction/introduction.html) Crypto & Fiat Exchange Super App | Trade, Save & Spend | hi [](https://hi.com/) Buy, Trade, Send and Earn Crypto & Fiat. Deposit Bitcoin, ETH, USDT and other cryptos and start earning. Get the hi Debit Card and Multi-Currency IBAN Account. Moralis Web3 - Enterprise-Grade Web3 APIs [](https://moralis.io/) Bridge the development gap between Web2 and Web3 with Moralis’ powerful Web3 APIs. Mirror [](https://mirror.xyz/) Built on web3 for web3, Mirror’s robust publishing platform pushes the boundaries of writing online—whether it’s the next big white paper or a weekly community update. Makerdao [](https://blog.makerdao.com/) Sholi — software for Investors & Traders / Sholi MetriX [](https://sholi.io/) Sholi — software for Investors & Traders / Sholi MetriX Stock Trading Quiver Quantitative [](https://www.quiverquant.com/) Quiver Quantitative Chart Prime - The only tool you'll need for trading assets across all markets [](https://chartprime.com/) ChartPrime offers a toolkit that will take your trading game to the next level. Visit our site for a full rundown of features and helpful tutorials. Learning Hacker Rank [](https://www.hackerrank.com/) Coderbyte | Code Screening, Challenges, & Interview Prep [](https://coderbyte.com/) Improve your coding skills with our library of 300+ challenges and prepare for coding interviews with content from leading technology companies. Competitive Programming | Participate & Learn | CodeChef [](https://www.codechef.com/) Learn competitive programming with the help of CodeChef's coding competitions. Take part in these online coding contests to level up your skills Learn to Code - for Free | Codecademy [](https://www.codecademy.com/) Learn the technical skills to get the job you want. Join over 50 million people choosing Codecademy to start a new career (or advance in their current one). Free Code Camp [](https://www.freecodecamp.org/) Learn to Code — For Free Sololearn: Learn to Code [](https://www.sololearn.com/home) Join Now to learn the basics or advance your existing skills Mimo: The coding app you need to learn to code! Python, HTML, JavaScript [](https://getmimo.com/) Join more than 17 million learners worldwide. Learn to code for free. Learn Python, JavaScript, CSS, SQL, HTML, and more with our free code learning app. Free for developers [](https://free-for.dev/#/) Your Career in Web Development Starts Here | The Odin Project [](https://www.theodinproject.com/) The Odin Project empowers aspiring web developers to learn together for free Code Learning Games CheckiO - coding games and programming challenges for beginner and advanced [](https://checkio.org/) CheckiO - coding websites and programming games. Improve your coding skills by solving coding challenges and exercises online with your friends in a fun way. Exchanges experience with other users online through fun coding activities Coding for Kids | Game-Based Programming | CodeMonkey [](https://www.codemonkey.com/) CodeMonkey is a leading coding for kids program. Through its award-winning courses, millions of students learn how to code in real programming languages. Coding Games and Programming Challenges to Code Better [](https://www.codingame.com/) CodinGame is a challenge-based training platform for programmers where you can play with the hottest programming topics. Solve games, code AI bots, learn from your peers, have fun. Learn VIM while playing a game - VIM Adventures [](https://vim-adventures.com/) VIM Adventures is an online game based on VIM's keyboard shortcuts. It's the "Zelda meets text editing" game. So come have some fun and learn some VIM! CodeCombat - Coding games to learn Python and JavaScript [](https://codecombat.com/) Learn typed code through a programming game. Learn Python, JavaScript, and HTML as you solve puzzles and learn to make your own coding games and websites. Design Useberry - Codeless prototype analytics [](https://www.useberry.com/) User testing feedback & rich insights in minutes, not months! Figma: the collaborative interface design tool. [](https://www.figma.com/) Build better products as a team. Design, prototype, and gather feedback all in one place with Figma. Dribbble - Discover the World’s Top Designers & Creative Professionals [](https://dribbble.com/) Find Top Designers & Creative Professionals on Dribbble. We are where designers gain inspiration, feedback, community, and jobs. Your best resource to discover and connect with designers worldwide. Photopea | Online Photo Editor [](https://www.photopea.com/) Photopea Online Photo Editor lets you edit photos, apply effects, filters, add text, crop or resize pictures. Do Online Photo Editing in your browser for free! Toools.design – An archive of 1000+ Design Resources [](https://www.toools.design/) A growing archive of over a thousand design resources, weekly updated for the community. Discover highly useful design tools you never thought existed. All Online Tools in One Box | 10015 Tools [](https://10015.io/) All online tools you need in one box for free. Build anything online with “all-in-one toolbox”. All tools are easy-to-use, blazing fast & free. Phase - Digital Design Reinvented| Phase [](https://phase.com/) Design and prototype websites and apps visually and intuitively, in a new powerful product reworked for the digital age. Animated Backgrounds [](https://animatedbackgrounds.me/) A Collection of 30+ animated backgrounds for websites and blogs.With Animated Backgrounds, set a simple, elegant background animations on your websites and blogs. Trianglify.io · Low Poly Pattern Generator [](https://trianglify.io/) Trianglify.io is a tool for generating low poly triangle patterns that can be used as wallpapers and website assets. Cool Backgrounds [](https://coolbackgrounds.io/) Explore a beautifully curated selection of cool backgrounds that you can add to blogs, websites, or as desktop and phone wallpapers. SVG Repo - Free SVG Vectors and Icons [](https://www.svgrepo.com/) Free Vectors and Icons in SVG format. ✅ Download free mono or multi color vectors for commercial use. Search in 300.000+ Free SVG Vectors and Icons. Microcopy - Short copy text for your website. [](https://www.microcopy.me/) Search micro UX copy text: slogans, headlines, notifications, CTA, error messages, email, account preferences, and much more. 3D icons and icon paks - Free3Dicon [](https://free3dicon.com/) All 3D icons you need in one place. This is a collection of free, beautiful, trending 3D icons, that you can use in any project. Love 3D Icon [](https://free3dicons.com/) Downloads free 3D icons GIMP - GNU Image Manipulation Program [](https://www.gimp.org/) GIMP - The GNU Image Manipulation Program: The Free and Open Source Image Editor blender.org - Home of the Blender project - Free and Open 3D Creation Software [](https://www.blender.org/) The Freedom to Create 3D Design Software | 3D Modeling on the Web | SketchUp [](https://www.sketchup.com/) SketchUp is a premier 3D design software that truly makes 3D modeling for everyone, with a simple to learn yet robust toolset that empowers you to create whatever you can imagine. Free Logo Maker - Create a Logo in Seconds - Shopify [](https://www.shopify.com/tools/logo-maker) Free logo maker tool to generate custom design logos in seconds. This logo creator is built for entrepreneurs on the go with hundreds of templates, free vectors, fonts and icons to design your own logo. The easiest way to create business logos online. All your design tools in one place | Renderforest [](https://www.renderforest.com/) Time to get your brand noticed. Create professional videos, logos, mockups, websites, and graphics — all in one place. Get started now! Prompt Hero [](https://prompthero.com/) Type Scale - A Visual Calculator [](https://type-scale.com/) Preview and choose the right type scale for your project. Experiment with font size, scale and different webfonts. DreamFusion: Text-to-3D using 2D Diffusion [](https://dreamfusion3d.github.io/) DreamFusion: Text-to-3D using 2D Diffusion, 2022. The branding style guidelines documents archive [](https://brandingstyleguides.com/) Welcome to the brand design manual documents directory. Search over our worldwide style assets handpicked collection, access to PDF documents for inspiration. Super designer | Create beautiful designs with a few clicks [](https://superdesigner.co/) Create beautiful designs with a few clicks. Simple design tools to generate unique patterns, backgrounds, 3D shapes, colors & images for social media, websites and more Readymag—a design tool to create websites without coding [](https://readymag.com/) Meet the most elegant, simple and powerful web-tool for designing websites, presentations, portfolios and all kinds of digital publications. ffflux: Online SVG Fluid Gradient Background Generator | fffuel [](https://fffuel.co/ffflux/) SVG generator to make fluid gradient backgrounds that feel organic and motion-like. Perfect to add a feeling of motion and fluidity to your web designs. Generate unique SVG design assets | Haikei [](https://haikei.app/) A web-based design tool to generate unique SVG design assets for websites, social media, blog posts, desktop and mobile wallpapers, posters, and more! Our generators let you discover, customize, randomize, and export generative SVG design assets ready to use with your favorite design tools. UI/UX - Inspirational Free Website Builder Software | 10,000+ Free Templates [](https://nicepage.com/) Nicepage is your website builder software breaking limitations common for website builders with revolutionary freehand positioning. 7000+ Free Templates. Easy Drag-n-Drop. No coding. Mobile-friendly. Clean HTML. Super designer | Create beautiful designs with a few clicks [](https://superdesigner.co/) Create beautiful designs with a few clicks. Simple design tools to generate unique patterns, backgrounds, 3D shapes, colors & images for social media, websites and more Pika – Create beautiful mockups from screenshots [](https://pika.style/) Quickly create beautiful website and device mockup from screenshot. Pika lets you capture website screenshots form URL, add device and browser frames, customize background and more LiveTerm [](https://liveterm.vercel.app/) Minimal Gallery – Web design inspiration [](https://minimal.gallery/) For the love of beautiful, clean and functional websites. Awwwards - Website Awards - Best Web Design Trends [](https://www.awwwards.com/) Awwwards are the Website Awards that recognize and promote the talent and effort of the best developers, designers and web agencies in the world. Design Systems For Figma [](https://www.designsystemsforfigma.com/) A collection of Design Systems for Figma from all over the globe. Superside: Design At Scale For Ambitious Brands [](https://www.superside.com/) We are an always-on design company. Get a team of dedicated designers, speedy turnarounds, magical creative collaboration tech and the top 1% of global talent. UXArchive - Made by Waldo [](https://uxarchive.com/) UXArchive the world's largest library of mobile user flows. Be inspired to design the best user experiences. Search by Muzli [](https://search.muz.li/) Search, discover, test and create beautiful color palettes for your projects Siteinspire | Web Design Inspiration [](https://www.siteinspire.com/) SAVEE [](https://savee.it/) The best way to save and share inspiration. A little corner of the internet to find good landing page copywriting examples [](https://greatlandingpagecopy.com/) A little corner of the internet to find great landing page copywriting examples. The Best Landing Page Examples For Design Inspiration - SaaS Landing Page [](https://saaslandingpage.com/) SaaS Landing Page showcases the best landing page examples created by top-class SaaS companies. Get ideas and inspirations for your next design project. Websites Free templates Premium Bootstrap Themes and Templates: Download @ Creative Tim [](https://www.creative-tim.com/) UI Kits, Templates and Dashboards built on top of Bootstrap, Vue.js, React, Angular, Node.js and Laravel. Join over 2,014,387+ creatives to access all our products! Free Bootstrap Themes, Templates, Snippets, and Guides - Start Bootstrap [](https://startbootstrap.com/) Start Bootstrap develops free to download, open source Bootstrap 5 themes, templates, and snippets and creates guides and tutorials to help you learn more about designing and developing with Bootstrap. Free Website Templates [](https://freewebsitetemplates.com/) Get your free website templates here and use them on your website without needing to link back to us. One Page Love - One Page Website Inspiration and Templates [](https://onepagelove.com/) One Page Love is a One Page website design gallery showcasing the best Single Page websites, templates and resources. Free CSS | 3400 Free Website Templates, CSS Templates and Open Source Templates [](https://www.free-css.com/) Free CSS has 3400 free website templates, all templates are free CSS templates, open source templates or creative commons templates. Free Bootstrap Themes and Website Templates | BootstrapMade [](https://bootstrapmade.com/) At BootstrapMade, we create beautiful website templates and bootstrap themes using Bootstrap, the most popular HTML, CSS and JavaScript framework. Free and Premium Bootstrap Themes, Templates by Themesberg [](https://themesberg.com/) Free and Premium Bootstrap themes, templates, admin dashboards and UI kits used by over 38820 web developers and software companies HTML, Vue.js and React templates for startup landing pages - Cruip [](https://cruip.com/) Cruip is a gallery of premium and free HTML, Vue.js and React templates for startups and SaaS. Free Website Templates Download | WordPress Themes - W3Layouts [](https://w3layouts.com/) Want to download free website templates? W3Layouts WordPress themes and website templates are built with responsive web design techniques. Download now! Free HTML Landing Page Templates and UI Kits | UIdeck [](https://uideck.com/) Free HTML Landing Page Templates, Bootstrap Themes, React Templates, HTML Templates, Tailwind Templates, and UI Kits. Create Online Graphics Snappa - Quick & Easy Graphic Design Software [](https://snappa.com/) Snappa makes it easy to create any type of online graphic. Create & publish images for social media, blogs, ads, and more! Canva [](https://www.canva.com/) Polotno Studio - Make graphical designs [](https://studio.polotno.com) Free online design editor. Create images for social media, youtube previews, facebook covers Free Logo Maker: Design Custom Logos | Adobe Express [](https://www.adobe.com/express/create/logo) The Adobe Express logo maker is instant, intuitive, and intelligent. Use it to generate a wide range of possibilities for your own logo. Photo Editor: Fotor – Free Online Photo Editing & Image Editor [](https://www.fotor.com/) Fotor's online photo editor helps you edit photos with free online photo editing tools. Crop photos, resize images, and add effects/filters, text, and graphics in just a few clicks. Photoshop online has never been easier with Fotor's free online photo editor. VistaCreate – Free Graphic Design Software with 70,000+ Free Templates [](https://create.vista.com/) Looking for free graphic design software? Easily create professional designs with VistaCreate, a free design tool with powerful features and 50K+ ready-made templates Draw Freely | Inkscape [](https://inkscape.org/) Inkscape is professional quality vector graphics software which runs on Linux, Mac OS X and Windows desktop computers. Visual & Video Maker Trusted By 11 Million Users - Piktochart [](https://piktochart.com/) With Piktochart, you can create professional-looking infographics, flyers, posters, charts, videos, and more. No design experience needed. Start for free. The Web's Favorite Online Graphic Design Tool | Stencil [](https://getstencil.com/) Stencil is a fantastically easy-to-use online graphic design tool and image editor built for business owners, social media marketers, and bloggers. Pablo by Buffer - Design engaging images for your social media posts in under 30 seconds [](https://pablo.buffer.com/) Buffer makes it super easy to share any page you're reading. Keep your Buffer topped up and we automagically share them for you through the day. Free Online Graphic Design Software | Create stunning designs in seconds. [](https://desygner.com/) Easy drag and drop graphic design tool for anyone to use with 1000's of ready made templates. Create & print professional business cards, flyers, social posts and more. Color Pallet Color Palettes for Designers and Artists - Color Hunt [](https://colorhunt.co/) Discover the newest hand-picked color palettes of Color Hunt. Get color inspiration for your design and art projects. Coolors - The super fast color palettes generator! [](https://coolors.co/) Generate or browse beautiful color combinations for your designs. Get color palette inspiration from nature - colorpalettes.earth [](https://colorpalettes.earth/) Color palettes inspired by beautiful nature photos Color Palette Generator - Create Beautiful Color Schemes [](https://colors.muz.li/) Search, discover, test and create beautiful color palettes for your projects A Most Useful Color Picker | 0to255 [](https://0to255.com/) Find lighter and darker colors based on any color. Discover why over two million people have used 0to255 to choose colors for their website, logo, room interior, and print design projects. Colour Contrast Checker [](https://colourcontrast.cc/) Check the contrast between different colour combinations against WCAG standards Fonts Google Fonts [](https://fonts.google.com/) Making the web more beautiful, fast, and open through great typography Fonts In Use – Type at work in the real world. [](https://fontsinuse.com/) A searchable archive of typographic design, indexed by typeface, format, and topic. Wordmark - Helps you choose fonts! [](https://wordmark.it/) Wordmark helps you choose fonts by quickly displaying your text with your fonts. OH no Type Company [](https://ohnotype.co/) OH no Type Co. Retail and custom typefaces. Life’s a thrill, fonts are chill! Illustrations Illustrations | unDraw [](https://undraw.co/illustrations) The design project with open-source illustrations for any idea you can imagine and create. Create beautiful websites, products and applications with your color, for free. Design Junction [](https://designjunction.xyz/) Design Junction is a one-stop resource library for Designers and Creatives with curated list of best resources handpicked from around the web Humaaans: Mix-&-Match illustration library [](https://www.humaaans.com/) Mix-&-match illustrations of people with a design library for InVIsion Studio and Sketch. Stubborn - Free Illustrations Generator [](https://stubborn.fun/) Free illustrations generator for Figma and Sketch. Get the opportunity to design your characters using symbols and styles. Open Peeps, Hand-Drawn Illustration Library [](https://www.openpeeps.com/) Open Peeps is a hand-drawn illustration library to create scenes of people. You can use them in product illustration, marketing, comics, product states, user flows, personas, storyboarding, quinceañera invitations, or whatever you want! ⠀ Reshot | Free icons & illustrations [](https://www.reshot.com/) Design freely with instant downloads of curated SVG icons and vector illustrations. All free with commercial licensing. No attribution required. Blush: Illustrations for everyone [](https://blush.design/) Blush makes it easy to add free illustrations to your designs. Play with fully customizable graphics made by artists across the globe. Mockups Angle 4 - 5000+ Device Mockups for Figma, Sketch and XD [](https://angle.sh/) Vector mockups for iPhone, iPad, Android and Mac devices, including the new iPhone 13, Pro, Pro Max and Mini. Perfect for presenting your apps. Huge library of components, compositions, wallpapers and plugins made for Figma, Sketch and XD. Make Mockups, Logos, Videos and Designs in Seconds [](https://placeit.net/) Get unlimited downloads on all our 100K templates! You can make a logo, video, mockup, flyer, business card and social media image in seconds right from your browser. Free and premium tools for graphic designers | Lstore Graphics [](https://www.ls.graphics/) Free and premium mockups, UI/UX tools, scene creators for busy designers Logo Design & Brand Identity Platform for Entrepreneurs | Looka [](https://looka.com/) Logojoy is now Looka! Design a Logo, make a website, and create a Brand Identity you’ll love with the power of Artificial Intelligence. 100% free to use. Create stunning product mockups easily and online - Smartmockups [](https://smartmockups.com/) Smartmockups enables you to create stunning high-resolution mockups right inside your browser within one interface across multiple devices. Previewed - Free mockup generator for your app [](https://previewed.app/) Join Previewed to create stunning 3D image shots and animations for your app. Choose from hundreds of ready made mockups, or create your own. Free Design Software - Graphic Online Maker - Glorify [](https://www.glorify.com/) Create professional and high converting social media posts, ads, infographics, presentations, and more with Glorify, a free design software & graphic maker. Other BuiltWith Technology Lookup [](https://builtwith.com/) Web technology information profiler tool. Find out what a website is built with. Compress JPEG Images Online [](https://compressjpeg.com/) Compress JPEG images and photos for displaying on web pages, sharing on social networks or sending by email. PhotoRoom - Remove Background and Create Product Pictures [](https://www.photoroom.com/) Create product and portrait pictures using only your phone. Remove background, change background and showcase products. Magic Eraser - Remove unwanted things from images in seconds [](https://www.magiceraser.io/) Magic Eraser - Use AI to remove unwanted things from images in seconds. Upload an image, mark the bit you need removed, download the fixed up image. Compressor.io - optimize and compress JPEG photos and PNG images [](https://compressor.io/) Optimize and compress JPEG, PNG, SVG, GIF and WEBP images online. Compress, resize and rename your photos for free. Remove Video Background – Unscreen [](https://www.unscreen.com/) Remove the background of any video - 100% automatically, online & free! Goodbye Greenscreen. Hello Unscreen. Noun Project: Free Icons & Stock Photos for Everything [](https://thenounproject.com/) Noun Project features the most diverse collection of icons and stock photos ever. Download SVG and PNG. Browse over 5 million art-quality icons and photos. Design Principles [](https://principles.design/) An Open Source collection of Design Principles and methods Shapefest™ - A massive library of free 3D shapes [](https://www.shapefest.com/) A massive free library of beautifully rendered 3D shapes. 160,000+ high resolution PNG images in one cohesive library. Learning UX Degreeless.design - Everything I Learned in Design School [](https://degreeless.design/) This is a list of everything I've found useful in my journey of learning design, and an ongoing list of things I think you should read. For budding UX, UI, Interaction, or whatever other title designers. UX Tools | Practical UX skills and tools [](https://uxtools.co/) Lessons and resources from two full-time product designers. Built For Mars [](https://builtformars.com/) On a mission to help the world build better user experiences by demystifying UX. Thousands of hours of research packed into UX case studies. Case Study Club – Curated UX Case Study Gallery [](https://www.casestudy.club/) Case Study Club is the biggest curated gallery of the best UI/UX design case studies. Get inspired by industry-leading designers, openly sharing their UX process. The Guide to Design [](https://start.uxdesign.cc/) A self-guided class to help you get started in UX and answer key questions about craft, design, and career Uxcel - Where design careers are built [](https://app.uxcel.com/explore) Available on any device anywhere in the world, Uxcel is the best way to improve and learn UX design online in just 5 minutes per day. UI & UX Design Tips by Jim Raptis. [](https://www.uidesign.tips/) Learn UI & UX Design with practical byte-sized tips and in-depth articles from Jim Raptis. Entrepreneur Instant Username Search [](https://instantusername.com/#/) Instant Username Search checks out if your username is available on more than 100 social media sites. Results appear instantly as you type. Flourish | Data Visualization & Storytelling [](https://flourish.studio/) Beautiful, easy data visualization and storytelling PiPiADS - #1 TikTok Ads Spy Tool [](https://www.pipiads.com/) PiPiADS is the best tiktok ads spy tool .We provide tiktok advertising,advertising on tiktok,tiktok ads examples,tiktok ads library,tiktok ads best practices,so you can understand the tiktok ads cost and master the tiktok ads 2021 and tiktok ads manager. Minea - The best adspy for product search in ecommerce and dropshipping [](https://en.minea.com/) Minea is the ultimate e-commerce product search tool. Minea tracks all ads on all networks. Facebook Ads, influencer product placements, Snapspy, all networks are tracked. Stop paying adspy 149€ for one network and discover Minea. AdSpy [](https://adspy.com/) Google Trends [](https://trends.google.com/) ScoreApp: Advanced Quiz Funnel Marketing | Make a Quiz Today [](https://www.scoreapp.com/) ScoreApp makes quiz funnel marketing easy, so you can attract relevant warm leads, insightful data and increase your sales. Try for free today Mailmodo - Send Interactive Emails That Drive Conversions [](https://www.mailmodo.com/) Use Mailmodo to create and send interactive emails your customers love. Drive conversions and get better email ROI. Sign up for a free trial now. 185 Top E-Commerce Sites Ranked by User Experience Performance – Baymard Institute [](https://baymard.com/ux-benchmark) See the ranked UX performance of the 185 largest e-commerce sites in the US and Europe. The chart summarizes 50,000+ UX performance ratings. Metricool - Analyze, manage and measure your digital content [](https://metricool.com/) Social media scheduling, web analytics, link in bio and reporting. Metricool is free per live for one brand. START HERE Visualping: #1 Website change detection, monitoring and alerts [](https://visualping.io/) More than 1.5 millions users monitor changes in websites with Visualping, the No1 website change detection, website checker, webpage change monitoring and webpage change detection tool. Gumroad – Sell what you know and see what sticks [](https://gumroad.com/) Gumroad is a powerful, but simple, e-commerce platform. We make it easy to earn your first dollar online by selling digital products, memberships and more. Product Hunt – The best new products in tech. [](https://www.producthunt.com/) Product Hunt is a curation of the best new products, every day. Discover the latest mobile apps, websites, and technology products that everyone's talking about. 12ft Ladder [](https://12ft.io/) Show me a 10ft paywall, I’ll show you a 12ft ladder. namecheckr | Social and Domain Name Availability Search For Brand Professionals [](https://www.namecheckr.com/) Social and Domain Name Availability Search For Brand Professionals Excel AI Formula Generator - Excelformulabot.com [](https://excelformulabot.com/) Transform your text instructions into Excel formulas in seconds with the help of AI. Z-Library [](https://z-lib.org/) Global Print On Demand Platform | Gelato [](https://www.gelato.com/) Create and sell custom products online. With local production in 33 countries, easy integration, and 24/7 customer support, Gelato is an all-in-one platform. Freecycle: Front Door [](https://freecycle.org/) Free eBooks | Project Gutenberg [](https://www.gutenberg.org/) Project Gutenberg is a library of free eBooks. Convertio — File Converter [](https://convertio.co/) Convertio - Easy tool to convert files online. More than 309 different document, image, spreadsheet, ebook, archive, presentation, audio and video formats supported. Namechk [](https://namechk.com/) Crazy Egg Website — Optimization | Heatmaps, Recordings, Surveys & A/B Testing [](https://www.crazyegg.com/) Use Crazy Egg to see what's hot and what's not, and to know what your web visitors are doing with tools, such as heatmaps, recordings, surveys, A/B testing & more. Ifttt [](https://ifttt.com/) Also Asked [](https://alsoasked.com/) Business Name Generator - Easily create Brandable Business Names - Namelix [](https://namelix.com/) Namelix uses artificial intelligence to create a short, brandable business name. Search for domain availability, and instantly generate a logo for your new business Merch Informer [](https://merchinformer.com/) Headline Generator [](https://www.title-generator.com/) Title Generator: create 700 headlines with ONE CLICK: Content Ideas + Catchy Headlines + Ad Campaign E-mail Subject Lines + Emotional Titles. Simple - Efficient - One Click Make [](https://www.make.com/en) Create and add calculator widgets to your website | CALCONIC_ [](https://www.calconic.com/) Web calculator builder empowers you to choose from a pre-made templates or build your own calculator widgets from a scratch without any need of programming knowledge Boost Your Views And Subscribers On YouTube - vidIQ [](https://vidiq.com/) vidIQ helps you acquire the tools and knowledge needed to grow your audience faster on YouTube and beyond. Learn More Last Pass [](https://www.lastpass.com/) Starter Story: Learn How People Are Starting Successful Businesses [](https://www.starterstory.com/) Starter Story interviews successful entrepreneurs and shares the stories behind their businesses. In each interview, we ask how they got started, how they grew, and how they run their business today. How To Say No [](https://www.starterstory.com/how-to-say-no) Saying no is hard, but it's also essential for your sanity. Here are some templates for how to say no - so you can take back your life. Think with Google - Discover Marketing Research & Digital Trends [](https://www.thinkwithgoogle.com/) Uncover the latest marketing research and digital trends with data reports, guides, infographics, and articles from Think with Google. ClickUp™ | One app to replace them all [](https://clickup.com/) Our mission is to make the world more productive. To do this, we built one app to replace them all - Tasks, Docs, Goals, and Chat. The Manual [](https://manual.withcompound.com/) Wealth-planning resources for founders and startup employees Software for Amazon FBA Sellers & Walmart Sellers | Helium 10 [](https://www.helium10.com/) If you're looking for the best software for Amazon FBA & Walmart sellers on the market, check out Helium 10's capabilities online today! Buffer: All-you-need social media toolkit for small businesses [](https://buffer.com/) Use Buffer to manage your social media so that you have more time for your business. Join 160,000+ small businesses today. CPGD — The Consumer Packaged Goods Directory [](https://www.cpgd.xyz/) The Consumer Packaged Goods Directory is a platform to discover new brands and resources. We share weekly trends in our newsletter and partner with services to provide vetted, recommended platforms for our Directory brands. Jungle Scout [](https://www.junglescout.com/) BuzzSumo | The World's #1 Content Marketing Platform [](https://buzzsumo.com/) BuzzSumo powers the strategies of 500k+ marketers, with content marketing data on 8b articles, 42m websites, 300t engagements, 500k journalists & 492m questions. Login - Capital [](https://app.capital.xyz/) Raise, hold, spend, and send funds — all in one place. Marketing Pictory – Video Marketing Made Easy - Pictory.ai [](https://pictory.ai/) Pictory's powerful AI enables you to create and edit professional quality videos using text, no technical skills required or software to download. Tolstoy | Communicate with interactive videos [](https://www.gotolstoy.com/) Start having face-to-face conversations with your customers. Create Email Marketing Your Audience Will Love - MailerLite [](https://www.mailerlite.com/) Email marketing tools to grow your audience faster and drive revenue smarter. Get free access to premium features with a 30-day trial! Sign up now! Hypefury - Schedule & Automate Social Media Marketing [](https://hypefury.com/) Save time on social media while creating more value, and growing your audience faster. Schedule & automate your social media experience! Klaviyo: Marketing Automation Platform for Email & SMS [](https://www.klaviyo.com/) Klaviyo, an ecommerce marketing automation platform for email marketing and sms syncs your tech stack with your website store to scale your business. Online Email & Lead Scraper | Klean Leads [](https://www.kleanleads.com/) Klean Leads is an online email scraper & email address finder. Use it to book more appointments, get more replies, and close more sales. PhantomBuster [](https://phantombuster.com/) Call to Action Examples - 300+ CTA Phrases [](https://ctaexamples.com/) See the best CTA example in every situation covered by the library of 300+ CTA goals. Use the examples to create your own CTAs in minutes. Creative Center: one-stop creative solution for TikTok [](https://ads.tiktok.com/business/creativecenter/pc/en?from=001010) Come to get your next great idea for TikTok. Here you can find the best performing ads, viral videos, and trending hashtags across regions and verticals. Groove.cm GrooveFunnels, GrooveMail with CRM and Digital Marketing Automation Platform - Groove.cm with GrooveFunnels, GroovePages, GrooveKart [](https://groove.cm/) Groove is a website creator, page builder, sales funnel maker, membership site platform, email autoresponder, blog tool, shopping cart system, ecommerce store solution, affiliate manager, video marketing software and more apps to help build your online business. SurveyMonkey: The World’s Most Popular Free Online Survey Tool [](https://www.surveymonkey.com/) Use SurveyMonkey to drive your business forward by using our free online survey tool to capture the voices and opinions of the people who matter most to you. Video Maker | Create Videos Online | Promo.com [](https://promo.com/) Free customizable video maker to help boost your business. Video creator for ads, social media, product and explainer videos, and for anything else you need! beehiiv — The newsletter platform built for growth [](https://www.beehiiv.com/) Access the best tools available in email, helping your newsletter scale and monetize like never before. GetResponse | Professional Email Marketing for Everyone [](https://www.getresponse.com/) No matter your level of expertise, we have a solution for you. At GetResponse, it's email marketing done right. Start your free account today! Search Email Newsletter Archives : Email Tuna [](https://emailtuna.com/) Explore newsletters without subscribing. Get email design ideas, discount coupon codes and exclusive newsletters deals. Database of email newsletters archived from all over the internet. Other Tools Simplescraper — Scrape Websites and turn them into APIs [](https://simplescraper.io/) Web scraping made easy — a powerful and free Chrome extension for scraping websites in your browser, automated in the cloud, or via API. No code required. Exploding Topics - Discover the hottest new trends. [](https://explodingtopics.com/) See new market opportunities, trending topics, emerging technology, hot startups and more on Exploding Topics. Scribe | Visual step-by-step guides [](https://scribehow.com/) By capturing your process while you work, Scribe automatically generates a visual guide, ready to share with the click of a button. Get It Free – The internet's BEST place to find free stuff! [](https://getitfree.us/) The internet's BEST place to find free stuff! Inflact by Ingramer – Marketing toolkit for Instagram [](https://inflact.com/) Sell on Instagram, build your audience, curate content with the right set of tools. Free Online Form Builder & Form Creator | Jotform [](https://www.jotform.com/) We believe the right form makes all the difference. Go from busywork to less work with powerful forms that use conditional logic, accept payments, generate reports, and automate workflows. Manage Your Team’s Projects From Anywhere | Trello [](https://trello.com/en) Trello is the ultimate project management tool. Start up a board in seconds, automate tedious tasks, and collaborate anywhere, even on mobile. TikTok hashtag generator - tiktokhashtags.com [](https://tiktokhashtags.com/) Find out which are the best hashtags for your TikTok post. Create Infographics, Reports and Maps - Infogram [](https://infogram.com/) Infogram is an easy to use infographic and chart maker. Create and share beautiful infographics, online reports, and interactive maps. Make your own here. Confetto - Create Instagram content in minutes [](https://www.confet.to/) Confetto is an all-in-one social media marketing tool built for SMBs and Social Media Managers. Confetto helps you create high-quality content for your audience that maximizes your reach and engagement on social media. Design, copy-write, plan and schedule content all in one place. Find email addresses in seconds • Hunter (Email Hunter) [](https://hunter.io/) Hunter is the leading solution to find and verify professional email addresses. Start using Hunter and connect with the people that matter for your business. PlayPhrase.me: Site for cinema archaeologists. [](https://playphrase.me/) Travel and explore the world of cinema. Largest collection of video quotes from movies on the web. #1 Free SEO Tools → SEO Review Tools [](https://www.seoreviewtools.com/) SEO Review Tools: 42+ Free Online SEO Tools build with ❤! → Rank checker → Domain Authority Checker → Keyword Tool → Backlink Checker Podcastle: Seamless Podcast Recording & Editing [](https://podcastle.ai/) Podcastle is the simplest way to create professional-quality podcasts. Record, edit, transcribe, and export your content with the power of AI, in an intuitive web-based platform. Save Ads from TikTok & Facebook Ad Library - Foreplay [](https://www.foreplay.co/) The best way to save ads from TikTok Creative Center and Facebook Ad Library, Organize them into boards and share ad inspiration with your team. Supercharge your creative strategy. SiteRight - Automate Your Business [](https://www.siteright.co/) SiteRight combines the abilities of multiple online resources into a single dashboard allowing you to have full control over how you manage your business. Diffchecker - Compare text online to find the difference between two text files [](https://www.diffchecker.com/) Diffchecker will compare text to find the difference between two text files. Just paste your files and click Find Difference! Yout.com [](https://yout.com/) Yout.com allows you to record videos from YouTube, FaceBook, SoundCloud, VK and others too many formats with clipping. Intuitively easy to use, with Yout the Internet DVR, with a bit of extra. AI Content Generation | Competitor Analysis - Predis.ai [](https://predis.ai/) Predis helps brands and influencers communicate better on social media by providing AI-powered content strategy analysis, content and hashtag recommendations. Castr | #1 Live Video Streaming Solution With Video Hosting [](https://castr.io/) Castr is a live video streaming solution platform that delivers enterprise-grade live videos globally with CDN. Live event streaming, video hosting, pre-recorded live, multi stream – all in one place using Castr. Headliner - Promote your podcast, radio show or blog with video [](https://www.headliner.app/) Easily create videos to promote your podcast, radio show or blog. Share to Instagram, Facebook, Twitter, YouTube, Linkedin and anywhere video lives Create Presentations, Infographics, Design & Video | Visme [](https://www.visme.co/) Create professional presentations, interactive infographics, beautiful design and engaging videos, all in one place. Start using Visme today. Designrr - Create eBooks, Kindle books, Leadmagnets, Flipbooks and Blog posts from your content in 2 minutes [](https://designrr.io/) Upload any web page, MS Word, Video, Podcast or YouTube and it will create a stunning ebook and convert it to pdf, epub, Kindle or Flipbook. Quick and Easy to use. Full Training, 24x7 Support and Facebook Group Included. SwipeWell | Swipe File Software [](https://www.swipewell.app/) The only Chrome extension dedicated to helping you save, organize, and reference marketing examples (so you never feel stumped). Tango | Create how-to guides, in seconds [](https://www.tango.us/) Tango takes the pain out of documenting processes by automatically generating how-to guides while you work. Empower your team to do their best work. Ad Creative Bank [](https://www.theadcreativebank.com/) Get inspired by ads from across industries, learn new best practices, and start thinking creatively about your brand’s digital creative. Signature Hound • Free Email Signature and Template Generator [](https://signaturehound.com/) Our email signature generator is free and easy to use. Our customizable templates work with Gmail, Outlook, Office 365, Apple Mail and more. Organize All Of Your Marketing In One Place - CoSchedule [](https://coschedule.com/) Get more done in less time with the only work management software for marketers. B Ok - Books [](https://b-ok.xyz/categories) OmmWriter [](https://ommwriter.com/) Ommwriter Rebrandly | Custom URL Shortener, Branded Link Management, API [](https://www.rebrandly.com/) URL Shortener with custom domains. Shorten, brand and track URLs with the industry-leading link management platform. Free to try. API, Short URL, Custom Domains. Common Tools [](https://www.commontools.org/) Book Bolt [](https://bookbolt.io/) Zazzle [](https://www.zazzle.com/) InspiroBot [](https://inspirobot.me/) Download Free Cheat Sheets or Create Your Own! - Cheatography.com: Cheat Sheets For Every Occasion [](https://cheatography.com/) Find thousands of incredible, original programming cheat sheets, all free to download. No Code Chatbot Platform | Free Chatbot Platform | WotNot [](https://wotnot.io/) WotNot is the best no code chatbot platform to build AI bot easily without coding. Deploy bots and live chat on the Website, Messenger, WhatsApp, and more. SpyFu - Competitor Keyword Research Tools for Google Ads PPC & SEO [](https://www.spyfu.com/) Systeme.io - The only tool you need to launch your online business [](https://systeme.io/) Systeme.io has all the tools you need to grow your online business. Click here to create your FREE account! Productivity Temp Mail [](https://temp-mail.org/en/) The Visual Collaboration Platform for Every Team | Miro [](https://miro.com/) Scalable, secure, cross-device and enterprise-ready team collaboration whiteboard for distributed teams. Join 35M+ users from around the world. Grammarly: Free Online Writing Assistant [](https://www.grammarly.com/) Millions trust Grammarly’s free writing app to make their online writing clear and effective. Getting started is simple — download Grammarly’s extension today. Rize · Maximize Your Productivity [](https://rize.io/) Rize is a smart time tracker that improves your focus and helps you build better work habits. Motion | Manage calendars, meetings, projects & tasks in one app [](https://www.usemotion.com/) Automatically prioritize tasks, schedule meetings, and resolve calendar conflicts. Used by over 10k CEOs and professionals to improve focus, get more done, and streamline workday. Notion – One workspace. Every team. [](https://www.notion.so/) We’re more than a doc. Or a table. Customize Notion to work the way you do. Loom: Async Video Messaging for Work | Loom [](https://www.loom.com/) Record your screen, share your thoughts, and get things done faster with async video. Zapier | Automation that moves you forward [](https://zapier.com/) Workflow automation for everyone. Zapier automates your work across 5,000+ app integrations, so you can focus on what matters. Rows — The spreadsheet with superpowers [](https://rows.com/) Combine the power of a spreadsheet with built-in integrations from your business apps. Automate workflows and build tools that make work simpler. Free Online Form Builder | Tally [](https://tally.so/) Tally is the simplest way to create free forms & surveys. Create any type of form in seconds, without knowing how to code, and for free. Highbrow | Learn Something New Every Day. Join for Free! [](https://gohighbrow.com/) Highbrow helps you learn something new every day with 5-minute lessons delivered to your inbox every morning. Join over 400,000 lifelong learners today! Slick Write | Check your grammar. Proofread online. [](https://www.slickwrite.com/#!home) Slick Write is a powerful, FREE application that makes it easy to check your writing for grammar errors, potential stylistic mistakes, and other features of interest. Whether you're a blogger, novelist, SEO professional, or student writing an essay for school, Slick Write can help take your writing to the next level. Reverso [](https://www.reverso.net) Hemingway Editor [](https://hemingwayapp.com/) Web Apps by 123apps - Edit, Convert, Create [](https://123apps.com/) Splitbee – Your all-in-one analytics and conversion platform [](https://splitbee.io/) Track and optimize your online business with Splitbee. Analytics, Funnels, Automations, A/B Testing and more. PDF Tools Free PDF, Video, Image & Other Online Tools - TinyWow [](https://tinywow.com/) Smallpdf.com - A Free Solution to all your PDF Problems [](https://smallpdf.com/) Smallpdf - the platform that makes it super easy to convert and edit all your PDF files. Solving all your PDF problems in one place - and yes, free. Sejda helps with your PDF tasks [](https://www.sejda.com/) Sejda helps with your PDF tasks. Quick and simple online service, no installation required! Split, merge or convert PDF to images, alternate mix or split scans and many other. iLovePDF | Online PDF tools for PDF lovers [](https://www.ilovepdf.com/) iLovePDF is an online service to work with PDF files completely free and easy to use. Merge PDF, split PDF, compress PDF, office to PDF, PDF to JPG and more! Text rewrite QuillBot [](https://quillbot.com/) Pre Post SEO : Online SEO Tools [](https://www.prepostseo.com/) Free Online SEO Tools: plagiarism checker, grammar checker, image compressor, website seo checker, article rewriter, back link checker Wordtune | Your personal writing assistant & editor [](https://www.wordtune.com/) Wordtune is the ultimate AI writing tool that rewrites, rephrases, and rewords your writing! Trusted by over 1,000,000 users, Wordtune strengthens articles, academic papers, essays, emails and any other online content. Aliexpress alternatives CJdropshipping - Dropshipping from Worldwide to Worldwide! [](https://cjdropshipping.com/) China's reliable eCommerce dropshipping fulfillment supplier, helps small businesses ship worldwide, dropship and fulfillment services that are friendly to start-ups and small businesses, Shopify dropshipping. SaleHoo [](https://www.salehoo.com/) Alibaba.com: Manufacturers, Suppliers, Exporters & Importers from the world's largest online B2B marketplace [](https://www.alibaba.com/) Find quality Manufacturers, Suppliers, Exporters, Importers, Buyers, Wholesalers, Products and Trade Leads from our award-winning International Trade Site. Import & Export on alibaba.com Best Dropshipping Suppliers for US + EU Products | Spocket [](https://www.spocket.co/) Spocket allows you to easily start dropshipping top products from US and EU suppliers. Get started for free and see why Spocket consistently gets 5 stars. Best dropshipping supplier to the US [](https://www.usadrop.com/) THE ONLY AMERICAN-MADE FULFILLMENT CENTER IN CHINA. Our knowledge of the Worldwide dropshipping market and the Chinese Supply-Chain can't be beat! 阿里1688 [](https://www.1688.com/) 阿里巴巴（1688.com）是全球企业间（B2B）电子商务的著名品牌，为数千万网商提供海量商机信息和便捷安全的在线交易市场，也是商人们以商会友、真实互动的社区平台。目前1688.com已覆盖原材料、工业品、服装服饰、家居百货、小商品等12个行业大类，提供从原料--生产--加工--现货等一系列的供应产品和服务 Dropshipping Tools Oberlo | Where Self Made is Made [](https://www.oberlo.com/) Start selling online now with Shopify. All the videos, podcasts, ebooks, and dropshipping tools you'll need to build your online empire. Klaviyo: Marketing Automation Platform for Email & SMS [](https://www.klaviyo.com/) Klaviyo, an ecommerce marketing automation platform for email marketing and sms syncs your tech stack with your website store to scale your business. SMSBump | SMS Marketing E-Commerce App for Shopify [](https://smsbump.com/) SMSBump is an SMS marketing & automation app for Shopify. Segment customers, recover orders, send campaign text messages with a 35%+ click through rate. AfterShip: The #1 Shipment Tracking Platform [](https://www.aftership.com/) Order status lookup, branded tracking page, and multi-carrier tracking API for eCommerce. Supports USPS, FedEx, UPS, and 900+ carriers worldwide. #1 Dropshipping App | Zendrop [](https://zendrop.com/) Start and scale your own dropshipping business with Zendrop. Sell and easily fulfill your orders with the fastest shipping in the industry. Best Dropshipping Suppliers for US + EU Products | Spocket [](https://www.spocket.co/) Spocket allows you to easily start dropshipping top products from US and EU suppliers. Get started for free and see why Spocket consistently gets 5 stars. Video Editing Jitter • The simplest motion design tool on the web. [](https://jitter.video/) Animate your designs easily. Export your creations as videos or GIFs. All in your browser. DaVinci Resolve 18 | Blackmagic Design [](https://www.blackmagicdesign.com/products/davinciresolve) Professional video editing, color correction, visual effects and audio post production all in a single application. Free and paid versions for Mac, Windows and Linux. Online Video Editor | Video Creator | InVideo [](https://invideo.io/) InVideo's Online Video Editor Helps You Make Professional Videos From Premium Templates, Images, And Music. All your video needs in one place | Clipchamp [](https://clipchamp.com/) Fast-forward your creations with our video editing platform. Start with a video template or record your webcam or screen. Get the pro look with filters, transitions, text and more. Then, export in minutes and share in an instant. Descript | All-in-one audio/video editing, as easy as a doc. [](https://www.descript.com/) Record, transcribe, edit, mix, collaborate, and master your audio and video with Descript. Download for free →. Kapwing — Reach more people with your content [](https://www.kapwing.com/) Kapwing is a collaborative, online content creation platform that you can use to edit video and create content. Join over 10 million modern creators who trust Kapwing to create, edit, and grow their content on every channel. Panzoid [](https://panzoid.com/) Powerful, free online apps and community for creating beautiful custom content. Google Web Designer - Home [](https://webdesigner.withgoogle.com/) Kapwing — Reach more people with your content [](https://www.kapwing.com/) Kapwing is a collaborative, online content creation platform that you can use to edit video and create content. Join over 10 million modern creators who trust Kapwing to create, edit, and grow their content on every channel. ClipDrop [](https://clipdrop.co/) Create professional visuals without a photo studio CapCut [](https://www.capcut.com/) CapCut is an all-in-one online video editing software which makes creation, upload & share easier, with frame by frame track editor, cloud drive etc. VEED - Online Video Editor - Video Editing Made Simple [](https://www.veed.io/) Make stunning videos with a single click. Cut, trim, crop, add subtitles and more. Online, no account needed. Try it now, free. VEED Free Video Maker | Create & Edit Your Videos Easily - Animoto [](https://animoto.com/k/welcome) Create, edit, and share videos with our online video maker. Combine your photos, video clips, and music to make quality videos in minutes. Get started free! Runway - Online Video Editor | Everything you need to make content, fast. [](https://runwayml.com/) Discover advanced video editing capabilities to take your creations to the next level. CreatorKit - A.I. video creator for marketers [](https://creatorkit.com/) Create videos with just one click, using our A.I. video editor purpose built for marketers. Create scroll stopping videos, Instagram stories, Ads, Reels, and TikTok videos. Pixar in a Box | Computing | Khan Academy [](https://www.khanacademy.org/computing/pixar) 3D Video Motions Plask - AI Motion Capture and 3D Animation Tool [](https://plask.ai/) Plask is an all-in-one browser-based AI motion capture tool and animation editor that anybody can use, from motion designers to every day content creators. Captions Captions [](https://www.getcaptions.app/) Say hello to Captions, the only camera and editing app that automatically transcribes, captions and clips your talking videos for you. Stock videos Pexels [](https://www.pexels.com/) Pixabay [](https://pixabay.com/) Mixkit - Awesome free assets for your next video project [](https://mixkit.co/) Download Free Stock Video Footage, Stock Music & Premiere Pro Templates for your next video editing project. All assets can be downloaded for free! Free Stock Video Footage HD 4K Download Royalty-Free Clips [](https://www.videvo.net/) Download free stock video footage with over 300,000 video clips in 4K and HD. We also offer a wide selection of music and sound effect files with over 180,000 clips available. Click here to download royalty-free licensing videos, motion graphics, music and sound effects from Videvo today. Free Stock Video Footage HD Royalty-Free Videos Download [](https://mazwai.com/) Download free stock video footage with clips available in HD. Click here to download royalty-free licensing videos from Mazwai now. Royalty Free Stock Video Footage Clips | Vidsplay.com [](https://www.vidsplay.com/) Royalty Free Stock Video Footage Clips Free Stock Video Footage, Royalty Free Videos for Download [](https://coverr.co/) Download royalty free (for personal and commercial use), unique and beautiful video footage for your website or any project. No attribution required. Stock Photos Beautiful Free Images & Pictures | Unsplash [](https://unsplash.com/) Beautiful, free images and photos that you can download and use for any project. Better than any royalty free or stock photos. When we share, everyone wins - Creative Commons [](https://creativecommons.org/) Creative Commons licenses are 20! Honoring 20 years of open sharing using CC licenses, join us in 2022 to celebrate Better Sharing — advancing universal access to knowledge and culture, and fostering creativity, innovation, and collaboration. Help us reach our goal of raising $15 million for a future of Better Sharing.  20 Years of Better … Read More "When we share, everyone wins" Food Pictures • Foodiesfeed • Free Food Photos [](https://www.foodiesfeed.com/) Download 2000+ food pictures ⋆ The best free food photos for commercial use ⋆ CC0 license Free Stock Photos and Images for Websites & Commercial Use [](https://burst.shopify.com/) Browse thousands of beautiful copyright-free images. All our pictures are free to download for personal and commercial use, no attribution required. EyeEm | Authentic Stock Photography and Royalty-Free Images [](https://www.eyeem.com/) Explore high-quality, royalty-free stock photos for commercial use. License individual images or save money with our flexible subscription and image pack plans. picjumbo: Free Stock Photos [](https://picjumbo.com/) Free stock photos and images for your projects and websites.️ Beautiful 100% free high-resolution stock images with no watermark. Free Stock Photos, Images, and Vectors [](https://www.stockvault.net/) 139.738 free stock photos, textures, backgrounds and graphics for your next project. No attribution required. Free Stock Photos, PNGs, Templates & Mockups | rawpixel [](https://www.rawpixel.com/) Free images, PNGs, stickers, backgrounds, wallpapers, graphic templates and PSD mockups. All safe to use with commercial licenses. Free Commercial Stock Photos & Royalty Free Images | PikWizard [](https://pikwizard.com/) Free images, videos & free stock photos. Unlimited downloads ✓ Royalty-free Images ✓Copyright-free for commercial use ✓ No Attribution Required Design Bundles [](https://designbundles.net/) Stock music Royalty Free Music for video creators | Epidemic Sound [](https://www.epidemicsound.com/) Download premium Royalty free Music and SFX! Our free trial gives you access to over 35,000 tracks and 90,000 sound effects for video, streaming and more! Royalty-Free Music & SFX for Video Creators | Artlist [](https://artlist.io/) Explore the ultimate royalty-free music & sound effects catalogs for unlimited use in YouTube videos, social media & films created by inspiring indie artists worldwide. The go-to music licensing choice for all creators Royalty Free Audio Tracks - Envato Elements [](https://elements.envato.com/audio) Download Royalty Free Stock Audio Tracks for your next project from Envato Elements. Premium, High Quality handpicked Audio files ideal for any genre. License popular music for videos • Lickd [](https://lickd.co/) The only place you can license popular music for videos. Access 1M+ mainstream tracks, plus high-quality stock music for content creators NCS (NoCopyrightSounds) - free music for content creators [](https://ncs.io/) NCS is a Record Label dedicated to giving a platform to the next generation of Artists in electronic music, representing genres from house to dubstep via trap, drum & bass, electro pop and more. Search Engine Optimization Keyword Tool For Monthly Search Volume, CPC & Competition [](https://keywordseverywhere.com/) Keywords Everywhere is a browser add-on for Chrome & Firefox that shows search volume, CPC & competition on multiple websites. Semrush - Online Marketing Can Be Easy [](https://www.semrush.com/) Turn the algorithm into a friend. Make your business visible online with 55+ tools for SEO, PPC, content, social media, competitive research, and more. DuckDuckGo — Privacy, simplified. [](https://duckduckgo.com/) The Internet privacy company that empowers you to seamlessly take control of your personal information online, without any tradeoffs. SEO Software for 360° Analysis of Your Website [](https://seranking.com/) Leading SEO software for business owners, agencies, and SEO specialists. Track your rankings, monitor competitors, spot technical errors, and more. Skyrocket your organic traffic with Surfer [](https://surferseo.com/) Use Surfer to research, write, optimize, and audit! Everything you need to create a comprehensive content strategy that yields real results is right here. Ahrefs - SEO Tools & Resources To Grow Your Search Traffic [](https://ahrefs.com/) You don't have to be an SEO pro to rank higher and get more traffic. Join Ahrefs – we're a powerful but easy to learn SEO toolset with a passionate community. Neon Tools [](https://neontools.io/) Google Index Search [](https://lumpysoft.com/) Google Index Search SEO Backlink Checker & Link Building Toolset | Majestic.com [](https://majestic.com/) Develop backlink strategies with our Link Intelligence data, build the strongest SEO backlink campaigns to drive organic traffic and boost your rankings today. PageOptimizer Pro [](https://pageoptimizer.pro/) Plans Services SEO Consulting Learn SEO About Blog POP SEO Community Podcast Support POP On Page Workshops With Kyle Roof POP Chrome Extension Guide Tutorial Videos Frequently Asked Questions Best Practices Login Cancel Anytime Plans Services SEO Consulting Learn SEO About Blog POP SEO Community Podcast Support POP On Page… Keyword Chef - Keywords for Publishers [](https://keywordchef.com/) Rank Insanely Fast for Keywords Your Competition Can’t Find “Every long-tail keyword I find ends up ranking within a day” – Dane Eyerly, Owner at TextGoods.com Keyword Chef automatically finds and filters keywords for you. Real-time SERP analysis lets you find keywords nearly guaranteed to rank. Try for free → Let’s face it, most keyword tools ... Read more Notifier - Social Listening for Social Media and More! [](https://notifier.so/) Track keywords. Market your product for free. Drive the conversation. Easy. Free Trial. No obligation ever. Simple. Fast. Trusted by Top Companies. Free Keyword Research Tool from Wordtracker [](https://www.wordtracker.com/) The best FREE alternative to the Keyword Planner. Use Wordtracker to reveal 1000s of profitable longtail keywords with up to 10,000 results per search Blog Posts The 60 Hottest Front-end Tools of 2021 | CSS-Tricks - CSS-Tricks [](https://css-tricks.com/hottest-front-end-tools-in-2021/) A complete list of the most popular front-end tools in 2021, according to the Web Tools Weekly newsletter. See which resources made the list. Resume ResumeGlow - AI Powered Resume Builder [](https://resumeglow.com/) Get hired fast with a resume that grabs attention. Designed by a team of HR experts and typographers. Customizable templates with more than a million possible Create Your Job-winning Resume - (Free) Resume maker · Resume.io [](https://resume.io/) Free online resume maker, allows you to create a perfect Resume or Cover Letter in 5 minutes. See how easy it is to write a professional resume - apply for jobs today! Rezi - The Leading AI-Powered Free Resume Builder [](https://www.rezi.ai/) Rezi’s award-winning AI-powered resume builder is trusted by hundreds of thousands of job seekers. Create your perfect resume in minutes with Rezi. Create a Perfect Resume | Free Resume Builder | Resumaker.ai [](https://resumaker.ai/) Create your professional resume with this online resume maker. Choose a designer-made template and grab any employer attention in seconds. Trusted AI Resume Maker Helps You Get Hired Fast [](https://skillroads.com/) Reach a 96.4% success rate in the job hunt race with the best resume creator. Our innovative technologies and 24/7 support help you to become a perfect candidate for any job. Do not lose your chance to become the One. Kickresume | Best Online Resume & Cover Letter Builder [](https://www.kickresume.com/) Create your best resume yet. Online resume and cover letter builder used by 1,300,000 job seekers worldwide. Professional templates approved by recruiters. ResumeMaker.Online | Create a Professional Resume for Free [](https://www.resumemaker.online/) Save time with the easiest-to-use Resume Maker Online. Create an effective resume in just minutes and land your dream job. No Sign-up required, start now! Interviews Interview Warmup - Grow with Google [](https://grow.google/certificates/interview-warmup/) A quick way to prepare for your next interview. Practice key questions, get insights about your answers, and get more comfortable interviewing. No code website builder Carrd - Simple, free, fully responsive one-page sites for pretty much anything [](https://carrd.co/) A free platform for building simple, fully responsive one-page sites for pretty much anything. Webflow: Create a custom website | No-code website builder [](https://webflow.com/) Create professional, custom websites in a completely visual canvas with no code. Learn how to create a website by trying Webflow for free! Google Sites: Sign-in [](https://sites.google.com/) FlutterFlow - Build beautiful, modern apps incredibly fast! [](https://flutterflow.io/) FlutterFlow lets you build apps incredibly fast in your browser. Build fully functional apps with Firebase integration, API support, animations, and more. Export your code or even easier deploy directly to the app stores! Free Website Builder: Build a Free Website or Online Store | Weebly [](https://www.weebly.com/) Weebly’s free website builder makes it easy to create a website, blog, or online store. Find customizable templates, domains, and easy-to-use tools for any type of business website. Glide • No Code App Builder • Nocode Application Development [](https://www.glideapps.com/) Create the apps your business needs, without coding, waiting or overpaying. Get started for free and build an app today Adalo - Build Your Own No Code App [](https://www.adalo.com/) Adalo makes creating apps as easy as putting together a slide deck. Turn your idea into a real native app — no code needed! Siter.io - The collaborative web design tool, no-code website builder [](https://siter.io/) Siter.io is a visual website builder for designers. Prototype, design, and create responsive websites in the browser. Work together with your team in one place. Elementor: #1 Free WordPress Website Builder | Elementor.com [](https://elementor.com/) Elementor is the platform web creators choose to build professional WordPress websites, grow their skills, and build their business. Start for free today! No code app builder | Bravo Studio [](https://www.bravostudio.app/) Your no-code mobile app builder for iOS and Android. Create MVP’s, validate ideas and publish on App Store and Google Play Store. Home [](https://typedream.com/) The simplest way to build a website with no-code, as easy as writing on Notion. Try Typedream for free and upgrade for custom domains, collaborators, and unlimited pages. Free Website Builder | Create a Free Website | Wix.com [](https://www.wix.com/) Create a website with Wix’s robust website builder. With 900+ strategically designed templates and advanced SEO and marketing tools, build your brand online today. Free responsive Emails & Landing Pages drag-and-drop Editor | BEE [](https://beefree.io/) Free responsive emails and landing pages editor. With BEE drag-and-drop builders embedded in many software applications you can start designing now! Home [](https://typedream.com/) The simplest way to build a website with no-code, as easy as writing on Notion. Try Typedream for free and upgrade for custom domains, collaborators, and unlimited pages. Ownit Connected Checkout [](https://www.ownit.co/) Ownit Connected Checkout Bookmark.com | No-code Website Builder to Start Your Business [](https://www.bookmark.com/) Our AI powered platform ensures your business is future proof. Try Bookmark for free. The best way to build web apps without code | Bubble [](https://bubble.io/) Bubble introduces a new way to build software. It’s a no-code tool that lets you build SaaS platforms, marketplaces and CRMs without code. Bubble hosts all web apps on its cloud platform. Responsive Web Design | Website Creation | Editor X [](https://www.editorx.com/) Experience the future of website design with responsive layouts, CSS precision and smooth drag and drop. Create a Website for Free. Tilda Website Builder [](https://tilda.cc/) Create a website, online store, landing page with Tilda intuitive website builder. Build your site from hundreds of pre-designed templates and publish it today. No code required. No-code headless commerce and websites | Unstack Inc. [](https://www.unstack.com/) Deploy high performance eCommerce storefronts and websites without the engineering overhead using Unstack's no-code CMS Best Drag-and-Drop Website Builder | Jemi [](https://jemi.so/) The modern website builder for creatives, entrepreneurs, and dreamers. Build a beautiful link in bio site, portfolio, or landing page in minutes. No-code website builder that works like Notion [](https://popsy.co/) Create a beautiful no-code website in minutes. Popsy works just like Notion but is built from the ground up for building websites. Choose a free template. Edit content just like in Notion. Customize styles without code. Free Notion icons and illustrations. Unbounce - The Landing Page Builder & Platform [](https://unbounce.com/) Grow your relevance, leads, and sales with Unbounce. Use Unbounce to easily create and optimize landing pages for your small business and boost conversions with AI insights. Low-code Front-end Design & Development Platform | TeleportHQ [](https://teleporthq.io/) Front-end development platform, with a visual builder and headless content modelling capabilities. Static website creation, and UI development tools. Other tools used in no code website MemberSpace - Turn any part of your website into members-only with just a few clicks [](https://www.memberspace.com/) Create memberships on your website for anything you want like courses, video tutorials, member directories, and more while having 100% control over look & feel. Triggre | The number one true no-code platform to run your business [](https://www.triggre.com/) The best no-code platform to create highly advanced business applications in hours, without programming. Try it now for free! No code game builder Welcome to Buildbox [](https://signup.buildbox.com/) Welcome to Buildbox Flowlab Game Creator - Make games online [](https://flowlab.io/) Flowlab is an online game creator. Make your own games to share with friends. Make 2D Games With GameMaker | Free Video Game Maker [](https://gamemaker.io/) Make a game with GameMaker, the best free video game engine. Perfect for beginners and professionals. Learn to build your own 2D games with our simple tutorials. Side Hustle Side Hustle Stack [](https://sidehustlestack.co/) Side Hustle Stack is a resource for finding platform-based work, ranging from gig work and side hustles to platforms that help you start a small business that can grow. Fiverr [](https://www.fiverr.com/) Remotasks: Work From Home, Online Bootcamp Training [](https://www.remotasks.com/en) Make money doing tasks. Start earning today! Free bootcamp training offered online. Sign up for a free Remotasks account and work from home. Earn up to $200/month. Transcribe Speech to Text | Rev [](https://www.rev.com/) Transcribe Speech to Text with Rev. Reach your audience with clear and accurate captions, transcripts, and subtitles. AI Training Data and other Data Management Services [](https://www.clickworker.com/) AI training data, SEO texts, web research, tagging, surveys and more - Use the crowdsourcing principle with the power of >4.5M Clickworkers. Automate your Busy Work - Byron People-Powered Assistants [](https://www.hibyron.com/) Byron is an on demand US based virtual assistant platform that gives individuals and teams the ability to quickly outsource their non-essential tasks. Jobs Websites - Remote Latest Crypto Jobs, Web3 Jobs and Blockchain Jobs in the leading tech companies. [](https://cryptojobslist.com/) New Cryptocurrency Jobs, Web3 Jobs and Blockchain Jobs on CryptoJobsList — the leading site to find and post jobs. Connect with companies hiring in a few clicks and begin your next experience in the industry. Updated daily. Remote Jobs: Design, Marketing, Programming, Writing & More [](https://justremote.co/) Discover Remote Jobs from around the world. Give up the commute, work remotely and do what you love, daily, from anywhere. Find your perfect remote development, design, sales or marketing job today. Remote Ok [](https://remoteok.com/) Hire Freelancers & Remote Workers For Free [](https://talent.hubstaff.com/) Find and hire the highest quality freelancers from around the world - for free. Choose from thousands of developers, digital marketers, creatives and more. We Work Remotely: Remote jobs in design, programming, marketing and more [](https://weworkremotely.com/) Find the most qualified people in the most unexpected places: Hire remote! We Work Remotely is the best place to find and list remote jobs that aren't restricted by commutes or a particular geographic area. Browse thousands of remote work jobs today. Angel [](https://angel.co/) Remote Work: Jobs, Companies & Virtual Teams - Remote.co [](https://remote.co/) Remote.co is the definitive remote work job board for online job seekers and companies hiring. Start your remote job search here! FlexJobs: Best Remote Jobs, Work from Home Jobs, Online Jobs & More [](https://www.flexjobs.com/) The #1 job search site for hand-screened flexible and remote jobs (work from home jobs) since 2007. Plus get resume, coaching and career help. Join today! Remote jobs remotefront.io [](https://remotefront.io/) All remote jobs at remotefront.io Daily Virtual Events Helping You Grow Professionally [](https://powertofly.com/) PowerToFly is where you receive expert career advice, free video training, coaching and exclusive access to jobs and events at top companies. Best Remote and Work from Home Jobs - Virtual Vocations [](https://www.virtualvocations.com/) Best work from home jobs and remote jobs in over 50 categories for professionals, digital nomads, telecommuting workers and entry level jobseekers. Education, healthcare, medical, customer support and tech job openings. Remote Jobs | Working Nomads [](https://www.workingnomads.com/jobs) Remote jobs for digital working nomads. Start your telecommuting career and work remotely from home or places around the world. Job Search, Companies Hiring Near Me, and Advice | The Muse [](https://www.themuse.com/) Find jobs at the best companies hiring near you and get free career advice. Startupers [](https://www.startupers.com/) NoDesk - Where Everyone Works Remote [](https://nodesk.co/) Browse and apply to the best new remote jobs at leading remote companies and startups for free. Join hundreds of companies that use NoDesk to build their remote teams. Browser Extensions Blackbox - Select. Copy. Paste & Search - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/blackbox-select-copy-past/mcgbeeipkmelnpldkobichboakdfaeon) Fastest Way to Copy Text from Videos & Images Octotree - GitHub code tree - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/octotree-github-code-tree/bkhaagjahfmjljalopjnoealnfndnagc) GitHub on steroids WhatFont - Chrome Web Store [](https://chrome.google.com/webstore/detail/whatfont/jabopobgcpjmedljpbcaablpmlmfcogm?hl=en) The easiest way to identify fonts on web pages. Window Resizer - Chrome Web Store [](https://chrome.google.com/webstore/detail/window-resizer/kkelicaakdanhinjdeammmilcgefonfh?hl=en) Resize the browser window to emulate various screen resolutions. Amino: CSS Editor - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/amino-css-editor/pbcpfbcibpcbfbmddogfhcijfpboeaaf) Live CSS Editor. Write custom CSS for any website and see your changes in real time. Checkbot: SEO, Web Speed & Security Tester 🚀 - Chrome Web Store [](https://chrome.google.com/webstore/detail/checkbot-seo-web-speed-se/dagohlmlhagincbfilmkadjgmdnkjinl?hl=en) Test SEO/speed/security of 100s of pages in a click! Check broken links, HTML/JavaScript/CSS, URL redirects, duplicate titles... Honey: Automatic Coupons & Rewards - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/honey-automatic-coupons-r/bmnlcjabgnpnenekpadlanbbkooimhnj) Save money and earn rewards when you shop online. Tango: screenshots, training, & documentation - Magazinul web Chrome [](https://chrome.google.com/webstore/detail/tango-screenshots-trainin/lggdbpblkekjjbobadliahffoaobaknh) Automatically create beautiful step-by-step guides with screenshots, in seconds. No code browser automation | axiom.ai [](https://axiom.ai/) Build browser bots quickly, without code. Automate website actions and repetitive tasks using just your browser, on any website or web app. No Code Browser extensions builder Bildr - Visual Web Development in your Browser [](https://www.bildr.com/) Visually build SaaS products, Chrome extensions, and web3 dApps Other Repurposing content for social media the easy way » Repurpose.io [](https://repurpose.io/) Repurposing content for social media made easy. Automatically repurpose YouTube, TikTok, Lives, Podcasts, and Zoom calls. Try it for FREE. Smart Serials: Your serial numbers database [](https://smartserials.com/) This is your main source of free serial numbers, unlock keys in a clean environment safe to browse by all ages. Old versions of Windows, Mac and Linux Software, Apps & Abandonware Games - Download at OldVersion.com [](http://www.oldversion.com/) Online Room Planner - Design Your Room [](http://www.planyourroom.com/) Planyourroom.com is a wonderful website to redesign each room in your house by picking out perfect furniture options to fit your unique space. BoredHumans.com - Fun AI Programs You Can Use Online [](https://boredhumans.com/) Fun AI programs you can use online. AI games, fake people, computer generated art, machine learning demos, and more. BNProject | Home [](https://buynothingproject.org/) Open Source Alternatives to Proprietary Software [](https://www.opensourcealternative.to/) Discover 400+ popular open source alternatives to proprietary SaaS. URL Shortener - Short URLs & Custom Free Link Shortener | Bitly [](https://bitly.com/) Bitly’s Connections Platform is more than a free URL shortener, with robust link management software, advanced QR Code features, and a Link-in-bio solution. TinEye Reverse Image Search [](https://tineye.com/) Good Books | Books recommended by successful people [](https://www.goodbooks.io/) Looking for the best books to read in 2022? Discover the best book recommendations from the world's most successful, influential and interesting people. Directory - Website Recommendations [](https://tokapps.com/directory/) 0 TRIED & TESTED WEBSITES LISTED Insanely Useful Websites A combination of useful websites for businesses, freelancers, DIYers, and individuals in a centralised area.All websites have been tried and tested. Filter Websites Audio Business Tools Copywriting Design Entertainment Graphics Guides Health Marketing PC Resources Savings SEO Software Travel Video Apply filter Watch Anime Online, Free Anime Streaming Online on Zoro.to Anime Website [](https://zoro.to/) Zoro is a Free anime streaming website which you can watch English Subbed and Dubbed Anime online with No Account and Daily update. WATCH NOW! Animated Drawings [](https://sketch.metademolab.com/) Bring children's drawings to life, by animating characters to move around! Alternativeto [](https://alternativeto.net/) Chatroulette [](https://chatroulette.com/) Random meetings around the world Tiktok Downloader - Download Video tiktok Without Watermark - SnapTik [](https://snaptik.app/en) TikTok Video Downloader - SnapTik.App is one of the best free Download video Tiktok No Watermark tool available online. You can download TikTok video from any device you have. Imgflip - Create and Share Awesome Images [](https://imgflip.com/) Flip through memes, gifs, and other funny images. Make your own images with our Meme Generator or Animated GIF Maker. Fake Text Message | Make Fake Text Conversation [](https://ifaketextmessage.com/) Fake Text Message is a tool to create a Fake Text Conversation and a Fake iMessage. ✂Templatemaker ︎ [](https://www.templatemaker.nl/en/) Omni Calculator [](https://www.omnicalculator.com/) Omni Calculator solves 2960 problems anywhere from finance and business to health. It’s so fast and easy you won’t want to do the math again! Watch Movies Online Free | Watch Series HD Free [](https://hdtoday.tv/) Free Access to the Biggest library of HD Movies and HD Series online - NO ADS - No Account Required - Fast Free Streaming Students Answers - The Most Trusted Place for Answering Life's Questions [](https://www.answers.com/) Answers is the place to go to get the answers you need and to ask the questions you want Wolfram|Alpha: Computational Intelligence [](https://www.wolframalpha.com/) Compute answers using Wolfram's breakthrough technology & knowledgebase, relied on by millions of students & professionals. For math, science, nutrition, history, geography, engineering, mathematics, linguistics, sports, finance, music… Online Math Tools - Simple, free and easy to use math utilities [](https://onlinemathtools.com/) World's simplest collection of useful mathematics utilities. Generate number sequences, draw fractals, do quick matrix and numerical calculations and more! edX | Free Online Courses by Harvard, MIT, & more | edX [](https://www.edx.org/) Access 2000 free online courses from 140 leading institutions worldwide. Gain new skills and earn a certificate of completion. Join today. Sci-Hub [](https://sci-hub.hkvisa.net/) Sci-Hub,mg.scihub.ltd,sci-hub.tw,The project is supported by user donations. Imagine the world with free access to knowledge for everyone ‐ a world without any paywalls. DigitalDefynd - Find the Best + Free Courses Online [](https://digitaldefynd.com/) 4 Million+ Learners | 96,000+ Courses | 45,000+ Free Courses | 1200+ Free Certificates Learn Anything [](https://learn-anything.xyz/) Search Interactive Mind Maps to learn anything HubSpot Academy - Homepage [](https://academy.hubspot.com/) HubSpot Academy is the worldwide leader in inbound marketing, sales, and customer service/support training.

#github#internet-tools-collection

youtube

0.358

0.31

Ishan Sharma•Jan 12, 2025

DO THIS To Get RICH With AI in 2025

Ishan Sharma: DO THIS To Get RICH With AI in 2025 How AI is CHANGING the Startup World! 🤯 Sam Altman, CEO of Open AI, predicts how one person could build a billion dollar startup, only using AI tools and software. It is crazy to think that the next billion dollar company might just be yours or mine with our AI toolset. This is a glimpse from the podcast where me and Saheli discussed freelancing, how to master personal branding as a beginner, how to talk with clients and much more. 📸 Instagram: https://bit.ly/ishansharma7390ig Join MarkitUpX Discord Server: https://discord.gg/fwSpTje4rh 😁 About Me: https://bit.ly/aboutishansharma 📱 Twitter: https://bit.ly/ishansharma7390twt 📝 LinkedIn: https://bit.ly/ishansharma7390li 🌟 Please leave a LIKE ❤️ and SUBSCRIBE for more AMAZING content! 🌟 3 Books You Should Read 📈Psychology of Money: https://amzn.to/30wx4bW 👀Subtle Art of Not Giving a F: https://amzn.to/30zwWbP 💼Rework: https://amzn.to/3ALsAuz Tech I use every day 💻MacBook Air M1: https://amzn.to/2YWKPjG 📺LG 29' Ultrawide Monitor: https://amzn.to/3aG0p5p 🎥Sony ZV1: https://amzn.to/3ANqgDb 🎙Blue Yeti Mic: https://amzn.to/2YYbiNN ⽴Tripod Stand: https://amzn.to/3mVUiQc 🔅Ring Light: https://amzn.to/2YQlzLJ 🎧Marshall Major II Headphone: https://amzn.to/3lLhTDQ 🖱Logitech mouse: https://amzn.to/3p8edOC 💺Green Soul Chair: https://amzn.to/3mWIxZP ✨ Tags ✨ ishan sharma,DO THIS To Get RICH With AI in 2025,ai agent,ai agents,low investment business ideas,business ideas with low investment,zero investment business ideas,best business ideas 2024,business ideas for students,business ideas for beginners,best business ideas,how to start a business,online business ideas,new business ideas 2024,startup business ideas,money,ai business ideas,business ideas using ai,ai,artificial intelligence,chatgpt,bard,gemini,google ✨ Hashtags ✨ #business #businessideas #ai

#business#businessideas#ai

github

0.443

0.018525334165293606

aenyne•Jan 9, 2025

teach-AI-in-business

Teaching AI in Business ![HitCount] I am collecting material for teaching AI-related issues to non-tech people. The links should provide for a general understanding of AI without going too deep into technical issues. Please contribute! Make this Issue your First Issue I am collecting material for teaching AI-related issues to non-tech people. The links should have provide for a general understanding of AI without going too deep into technical issues. Please contribute! Kindly use only those Resources with NO CODE NEW Check out also the AI Wiki NEW Online Videos & Courses | Link to Issue | Description | |---|---| | Top Trending Technologies | Youtube Channel to master top trending technologyies including artificial intelligence | | AI4All | AI 4 All is a resource for AI facilitators to bring AI to scholars and students | | Elements of AI | Elements of AI is a free open online course to teach AI principles | | Visual Introduction to Machine Learning | Visual introduction to Machine Learning is a beautiful website that gives a comprehensive introduction and easily understood first encounter with machine learning | | CS50's Introduction to Artificial Intelligence with Python | Learn to use machine learning in Python in this introductory course on artificial intelligence.| | Crash course for AI | This is a fun video series that introduces students and educators to Artificial Intelligence and also offers additional more advanced videos. Learn about the basics, neural networks, algorithms, and more. | Youtuber Channel Machine Learning Tutorial | Youtube Channel Turorial Teachable Machine for beginner | | Artificial Intelligence (AI) |Learn the fundamentals of Artificial Intelligence (AI), and apply them. Design intelligent agents to solve real-world problems including, search, games, machine learning, logic, and constraint satisfaction problems | | AI For Everyone by Andrew Ng | AI For Everyone is a course especially for people from a non-technical background to understand AI strategies | | How far is too far? The age of AI| This is a Youtube Orignals series by Robert Downey| | Fundamentals of Artificial Intelligence|This course is for absolute beginners with no technical knowledge.| | Bandit Algorithm (Online Machine Learning)|No requirement of technical knowledge, but a basic understending of Probability Ttheory would help| | An Executive's Guide to AI|This is an interactive guide to teaching business professionals how they might employ artificial intelligence in their business| | AI Business School|Series of videos that teach how AI may be incorporated in various business industries| | Artificial Intelligence Tutorial for Beginners | This video will provide you with a comprehensive and detailed knowledge of Artificial Intelligence concepts with hands-on examples. | | Indonesian Machine Learning Tutorial | Turorial Teachable Machine to train a computer for beginner | | Indonesian Youtube Playlist AI Tutorial | Youtube Playlist AI Tutorial For Beginner | | Artificial Intelligence Search Methods For Problem Solving By Prof. Deepak Khemani|These video lectures are for absolute beginners with no technical knowledge| | AI Basics Tutorial | This video starts from the very basics of AI and ML, and finally has a hands-on demo of the standard MNIST Dataset Number Detection model using Keras and Tensorflow.| | Simple brain.js Tutorial | This video explains a very simple javascript AI library called brain.js so you can easily run AI in the browser.| | Google AI| A complete kit for by google official for non-tech guy to start all over from basics, till advanced | | Microsoft AI for Beginners| A self-driven curriculum by Microsoft, which includes 24 lessons on AI. | Train Your Own AI | Link to Issue | Description | |---|---| | Teachable Machine | Use Teachable Machine to train a computer to recognize your own images, sounds, & poses | | eCraft2Learn | Resource and interactive space (Snap, a visual programming environment like Scratch) to learn how to create AI programs | | Google Quick Draw | Train an AI to guess from drawings| | Deepdream Generator| Merge Pictures to Deep Dreams using the Deepdream Generator| | Create ML|Quickly build and train Core ML models on your Mac with no code.| | What-If Tool|Visually probe the behavior of trained machine learning models, with minimal coding.| | Metaranx|Use and build artificial intelligence tools to analyze and make decisions about your data. Drag-and-drop. No code.| | obviously.ai|The total process of building ML algorithms, explaining results, and predicting outcomes in one single click.| Articles | By & Title | Description | |---|---| | Artificial Intelligence | Wikipedia Page of AI | | The Non-Technical AI Guide | One of the good blog post that could help AI more understandable for people without technical background | | LIAI | A detailed introduction to AI and neural networks | | Layman's Intro | A layman's introduction to AI | | AI and Machine Learning: A Nontechnical Overview | AI and Machine Learning: A Nontechnical Overview from OREILLY themselves is a guide to learn anyone everything they need to know about AI, focussed on non-tech people | | What business leaders need to know about artifical intelligence|Short article that summarizes the essential aspects of AI that business leaders need to understand| | How Will No-Code Impact the Future of Conversational AI | A humble explanation to the current state of converstational AI i.e.Chatbots and how it coul evolve with the current trend of no coding. | | Investopedia | Basic explanation of what AI is in a very basic and comprehensive way | | Packtpub | A non programmer’s guide to learning Machine learning | | Builtin | Artificial Intelligence.What is Artificial Intelligence? How Does AI Work? | | Future Of Life | Benefits & Risks of Artificial Intelligence | | NSDM India -Arpit | 100+ AI Tools For Non-Coders That Will Make Your Marketing Better. | | AI in Marketing for Startups & Non-technical Marketers | A practical guide for non-technical people | | Blog - Machine Learning MAstery | Blogs and Articles by Jason Browniee on ML | | AI Chatbots without programming| Chatbots are increasingly in demand among global businesses. This course will teach you how to build, analyze, deploy and monetize chatbots - with the help of IBM Watson and the power of AI.| Book Resources for Further Reading | Author | Book | Description & Notes | |---|---|---| | Ethem Alpaydin|Machine Learning: The New AI | Graph Theory with Applications to Engineering & Computer Science. A concise overview of machine learning—computer programs that learn from data—which underlies applications that include recommendation systems, face recognition, and driverless cars. | | Charu C. Aggarwal| Neural Networks and Deep Learning | This book covers both classical and modern models in deep learning. The primary focus is on the theory and algorithms of deep learning. The book is also rich in discussing different applications in order to give the practitioner a flavor of how neural architectures are designed for different types of problems. | | Hal Daumé III | A Course in Machine Learning | The purpose of this book is to provide a gentle and pedagogically organized introduction to the field. A second goal of this book is to provide a view of machine learning that focuses on ideas and models, not on math. | | Ian Goodfellow and Yoshua Bengio and Aaron Courville| Deep Learning | The book starts with a discussion on machine learning basics, including the applied mathematics and algorithms needed to effectively study deep learning from an academic perspective. There is no code covered in the book, making it perfect for a non-technical AI enthusiast. | | Peter Harrington|Machine Learning in Action| (Source: https://github.com/kerasking/book-1/blob/master/ML%20Machine%20Learning%20in%20Action.pdf) This book acts as a guide to walk newcomers through the techniques needed for machine learning as well as the concepts behind the practices.| | Jeff Heaton| Artificial Intelligence for Humans |This book helps its readers get an overview and understanding of AI algorithms. It is meant to teach AI for those who don’t have an extensive mathematical background. The readers need to have only a basic knowledge of computer programming and college algebra.| | John D. Kelleher, Brian Mac Namee and Aoife D'Arcy|Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies (The MIT Press)|This book covers all the fundamentals of machine learning, diving into the theory of the subject and using practical applications, working examples, and case studies to drive the knowledge home.| | Deepak Khemani| [A First Course in Artificial Intelligence] | It is an introductory course on Artificial Intelligence, a knowledge-based approach using agents all across and detailed, well-structured algorithms with proofs. This book mainly follows a bottom-up approach exploring the basic strategies needed problem-solving on the intelligence part. | | Maxim Lapan | Deep Reinforcement Learning Hands-On - Second Edition | Deep Reinforcement Learning Hands-On, Second Edition is an updated and expanded version of the bestselling guide to the very latest reinforcement learning (RL) tools and techniques. It provides you with an introduction to the fundamentals of RL, along with the hands-on ability to code intelligent learning agents to perform a range of practical tasks. | | Tom M Mitchell | Machine Learning | This book covers the field of machine learning, which is the study of algorithms that allow computer programs to automatically improve through experience. The book is intended to support upper level undergraduate and introductory level graduate courses in machine learning. | | John Paul Mueller and Luca Massaron|Machine Learning For Dummies|This book aims to get readers familiar with the basic concepts and theories of machine learning and how it applies to the real world. And "Dummies" here refers to absolute beginners with no technical background.The book introduces a little coding in Python and R used to teach machines to find patterns and analyze results. From those small tasks and patterns, we can extrapolate how machine learning is useful in daily lives through web searches, internet ads, email filters, fraud detection, and so on. With this book, you can take a small step into the realm of machine learning and we can learn some basic coding in Pyton and R (if interested)| | Michael Nielsen| Neural Networks and Deep Learning |Introduction to the core principles of Neural Networks and Deep Learning in AI| | Simon Rogers and Mark Girolami| A Course in Machine Learning |A First Course in Machine Learning by Simon Rogers and Mark Girolami is the best introductory book for ML currently available. It combines rigor and precision with accessibility, starts from a detailed explanation of the basic foundations of Bayesian analysis in the simplest of settings, and goes all the way to the frontiers of the subject such as infinite mixture models, GPs, and MCMC.| |Peter Norvig| Paradigm of Artificial Intelligence Programming |Paradigms of AI Programming is the first text to teach advanced Common Lisp techniques in the context of building major AI systems. By reconstructing authentic, complex AI programs using state-of-the-art Common Lisp, the book teaches students and professionals how to build and debug robust practical programs, while demonstrating superior programming style and important AI concepts.| | Stuart Russel & Peter Norvig | Artificial Intelligence: A Modern Approach, 3rd Edition | This is the prescribed text book for my Introduction to AI university course. It starts off explaining all the basics and definitions of what AI is, before launching into agents, algorithms, and how to apply them. Russel is from the University of California at Berkeley. Norvig is from Google.| | Richard S. Sutton and Andrew G. Barto| Reinforcement Learning: An Introduction |Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives while interacting with a complex, uncertain environment.| | Alex Smola and S.V.N. Vishwanathan | Introduction to Machine Learning | Provides the reader with an overview of the vast applications of ML, including some basic tools of statistics and probability theory. Also includes discussions on sophisticated ideas and concepts. | | Shai Shalev-Shwartz and Shai Ben-David | Understanding Machine Learning From Theory to Algorithms |The primary goal of this book is to provide a rigorous, yet easy to follow, introduction to the main concepts underlying machine learning. | | Chandra S.S.V | Artificial Intelligence and Machine Learning | This book is primarily intended for undergraduate and postgraduate students of computer science and engineering. This textbook covers the gap between the difficult contexts of Artificial Intelligence and Machine Learning. It provides the most number of case studies and worked-out examples. In addition to Artificial Intelligence and Machine Learning, it also covers various types of learning like reinforced, supervised, unsupervised and statistical learning. It features well-explained algorithms and pseudo-codes for each topic which makes this book very useful for students. | | Oliver Theobald|Machine Learning For Absolute Beginners: A Plain English Introduction|This is an absolute beginners ML guide.No mathematical background is needed, nor coding experience — this is the most basic introduction to the topic for anyone interested in machine learning.“Plain” language is highly valued here to prevent beginners from being overwhelmed by technical jargon. Clear, accessible explanations and visual examples accompany the various algorithms to make sure things are easy to follow.| | Tom Taulli | Artificial Intelligence Basics: A Non-Technical Introduction | This book equips you with a fundamental grasp of Artificial Intelligence and its impact. It provides a non-technical introduction to important concepts such as Machine Learning, Deep Learning, Natural Language Processing, Robotics and more. Further the author expands on the questions surrounding the future impact of AI on aspects that include societal trends, ethics, governments, company structures and daily life. | |Cornelius Weber, Mark Elshaw, N. Michael Mayer| Reinforcement Learning |Learning is a very important aspect. This book is on reinforcement learning which involves performing actions to achieve a goal. The first 11 chapters of this book describe and extend the scope of reinforcement learning.| |John D. Kelleher, Brian Mac Namee, Aoife D'arcy| Algorithms, Worked Examples, and Case Studies | A comprehensive introduction to the most important machine learning approaches used in predictive data analytics, covering both theoretical concepts and practical applications. |

#github#teach-ai-in-business

youtube

0.383

0.34

The AI Entrepreneurs•Sep 20, 2024

🔥 AI Agents Will Skyrocket in the Coming Years—Jensen Huang Explains! 🚀#shorts #youtubeshorts #ai

🔔 Subscribe to our Newsletter: https://aientrepreneurs.standout.digital?utm_source=yt 🔔 Subscribe for more tech insights: https://www.youtube.com/channel/UCjMceG0jS4Lr5ZACzpYjHf In this exciting video, Jensen Huang shares his vision for the future of AI agents over the coming years. As AI continues to evolve, Huang explains how these agents will make massive strides in problem-solving, automation, and innovation, transforming industries worldwide. 🔹 Learn about the future progress of AI agents from NVIDIA’s CEO. 🔹 Discover how AI agents will revolutionize business and technology. 🔹 Explore the advancements AI agents will bring in the coming years. #JensenHuang #NVIDIA #AIAgents #AIProgress #ArtificialIntelligence #FutureOfAI #AIRevolution #TechInnovation #Automation #TrendingNow Join 66,000+ AI lovers with 4 free gifts🎁: 100 ChatGPT prompts, AI writer to go viral, "Building A Minimum Viable Business In Record Time" Course AND "4-Hour AI Workweek" course! Click here: https://aientrepreneurs.standout.digital?utm_source=yt ✨Exclusive Freebies and Tools: 📙 (Free Course) The 4 Hour AI Workweek: https://aientrepreneurs.standout.digital?utm_source=yt 📑 Bubble No Code AI Template: https://launchai.pro/?aff=wqp8K 🛠️ #1 AI SEO Tool: https://tryjournalist.com?aff=ge 🐤 Grow on Twitter with AI: http://app.tweethunter.io/?via=george-p 📚 Free Lead Magnets Playbook: https://aientrepreneurs.gumroad.com/l/yndih 👨‍💻 AI UI Design Tool: https://get.uizard.io/affc?offerid=3&aff_id=683 📹 Free YouTube Growth Playbook: https://aientrepreneurs.gumroad.com/l/qbswh ✍️ Free Script Writing Guide: https://aientrepreneurs.gumroad.com/l/yfhxgk 🤖 Free 100 ChatGPT Prompts: https://aientrepreneurs.gumroad.com/l/npyks ✨OUR OTHER SOCIALS: 🎙️ Podcast Deep Dive- https://podcast.standout.digital/ 💻 Check out our blog- https://www.standout.digital/blog/ 🐤 Follow us on Twitter- https://twitter.com/EntrepreneursAI 🤳 Check out our Instagram- https://www.instagram.com/standoutaientrepreneurs 📷 Dive into our TikTok- https://www.tiktok.com/@theaientrepreneurs 👨‍💼 Connect on LinkedIn- https://www.linkedin.com/company/theaientrepreneurs Video credits: @CNET Full video: https://youtu.be/kfe3ajUYSdc?feature=shared Some links may be referral links* Thank you!

#JensenHuang#NVIDIA#AIAgents

youtube

0.394

0.63

codebasics•Sep 20, 2024

What is AI Agent in Artificial Intelligence? | AI Agent Explained

What exactly is an AI Agent? I will explain this topic using a simple analogy in this video. Agentic frameworks such as Langgraph, Crew AI, Microsoft Autogen has become a talk of the town, all of them are based on one central concept "AI Agent". Dialogflow food order chatbot: https://youtu.be/2e5pQqBvGco?si=VNw1LxRsuIBy95Xr Do you want to learn technology from me? Check https://codebasics.io/?utmsource=description&utmmedium=yt&utmcampaign=description&utmid=description for my affordable video courses. Need help building software or data analytics/AI solutions? My company https://www.atliq.com/ can help. Click on the Contact button on that website. 🎥 Codebasics Hindi channel: https://www.youtube.com/channel/UCTmFBhuhMibVoSfYom1uXEg #️⃣ Social Media #️⃣ 🧑‍🤝‍🧑 Discord for Community Support: https://discord.gg/r42Kbuk 📸 Codebasics' Instagram: https://www.instagram.com/codebasicshub/ 📝 Codebasics' Linkedin : https://www.linkedin.com/company/codebasics/ 📝 Dhaval's Linkedin : https://www.linkedin.com/in/dhavalsays/ 📝 Hem's Linkedin: https://www.linkedin.com/in/hemvad/ 📽️ Hem's Instagram for daily tips: https://www.instagram.com/hemvadivel/ 📸 Dhaval's Personal Instagram: https://www.instagram.com/dhavalsays/ 🔗 Patreon: https://www.patreon.com/codebasics?fan_landing=true

youtube

0.269

0.26

Punit Chawla•Sep 7, 2024

These Are Better Than Figma AI! — Motiff, Visily, Uizard #shorts #figma #ai

Figma Al is amazing But, it isn't available to everyone and it will soon be a paid feature. Here are three great alternatives to Figma Al and Figma Design Tool. Motiff - A powerful Ai design tool to do Ul designs, add content, and build design systems Visily - Brand new UI design tool that can convert screenshots into editable designs in seconds. It also has a unique set of design tools in built. Uizard - The company that pioneered Al in design, with its amazing wireframing and UI design capabilities. #figma #shorts #ai

#figma#shorts#ai

youtube

0.409

0.71

AI Foundations•Aug 13, 2024

Automate any task using Claude! (my full Claude projects workflow)

This 25 minutes will save you hours. Automate any task with Claude! 👉🏼AI Foundations Community: https://swiy.co/aif-community-2 Claude custom instructions template for automation: https://docs.google.com/document/d/1jvYalwLY5f_6cUJre74FhYReMmomSLyEgujxhoYZ7P0/edit?usp=sharing 🛒AI Templates, Prompts and Courses for ChatGPT and Midjourney: https://aifoundations.io/shop 📰Subscribe to my newsletter: https://aifoundations.io 🔗Follow me on Linkedin: https://www.linkedin.com/in/drake-surach-823530203/ 🐥Follow me on twitter: https://twitter.com/drake0DTE ⌚Chapters: 0:00 - Claude for task automation 0:47 - Ai Community 2:05 - Creating a Claude Project 3:40 - How to use ‘Project Knowledge’ in Claude 8:17 - The task I will automate 9:40 - Adding company goals PDF 11:19 - Creating custom instructions in Claude 17:50 - Referencing project knowledge in custom instructions 20:22 - Testing my automation 21:40 - The results of the automation 23:35 - The BEST way to Learn AI #claude #anthropic

#claude#anthropic

youtube

0.368

0.48

Nick Saraev•Aug 13, 2024

How To Service Your First AI Automation Agency Client In 2024 (Make.com)

GET THE FREE GAMMA + TEMPLATES HERE 🙏 https://gamma.app/docs/How-to-Successfully-Service-Your-First-Automation-Client-in-2024-3xpyq1tyhppm1jv JOIN MY AUTOMATION COMMUNITY & GET YOUR FIRST CUSTOMER, GUARANTEED 👑 https://www.skool.com/makerschool/about SUMMARY ⤵️ Complete guide on servicing your first AI automation agency client in 2024. I run you through the workflow from end-to-end, including pre-project, kickoff, onboarding, progress updates, delivery emails, and upsells. WHAT TO WATCH NEXT 🍿 How I Hit $25K/Mo Selling Automation: https://youtube.com/watch?v=T7qAiuWDwLw My $21K/Mo Make.com Proposal System: https://youtube.com/watch?v=UVLeX600irk Generate Content Automatically With AI: https://youtube.com/watch?v=P2Y_DVW1TSQ MY SOFTWARE, TOOLS, & DEALS (some of these give me kickbacks—thank you!) 🚀 INSTANTLY: https://link.nicksaraev.com/instantly-short 📧 ANYMAIL FINDER: https://link.nicksaraev.com/amf-short 👻 PHANTOMBUSTER: https://link.nicksaraev.com/pb-short ✅ CLICKUP: https://link.nicksaraev.com/clickup-short 📈 RIZE: https://link.nicksaraev.com/rize-short (use promo code NICK for addn 25% off) WHAT TO WATCH NEXT 🍿 HOW I HIT $25K/MO SELLING AUTOMATION: https://youtube.com/watch?v=T7qAiuWDwLw MY $21K/MO MAKE.COM PROPOSAL SYSTEM: https://youtube.com/watch?v=UVLeX600irk GENERATE CONTENT AUTOMATICALLY WITH AI: https://youtube.com/watch?v=P2Y_DVW1TSQ FOLLOW ME ✍🏻 My content writing agency: https://1secondcopy.com 🦾 My automation agency: https://leftclick.ai 🕊️ My Twitter/X: https://twitter.com/nicksaraev 🤙 My blog (followed by the founder of HubSpot!): https://nicksaraev.com WHY ME? If this is your first watch—hi, I’m Nick! TLDR: I spent five years building automated businesses with Make.com (most notably 1SecondCopy, a content company that hit 7 figures). Today a lot of people talk about automation, but I’ve noticed that very few have practical, real world success making money with it. So this channel is me chiming in and showing you what real systems that make real revenue look like! Hopefully I can help you improve your business, and in doing so, the rest of your life :-) Please like, subscribe, and leave me a comment if you have a specific request! Thanks. Timestamps 0:00 Introduction to Servicing Your Automation Client 0:39 The Importance of Client Retention 2:03 Understanding Your Role as a Service Provider 2:54 The Significance of Client Acquisition Time 8:06 Setting Expectations with the Client 14:53 Implementing a Structured Onboarding Process 16:11 Testing the Flow of the Project 18:18 Delivering Progress Updates to Clients 19:13 Utilizing Templates for Project Efficiency 22:32 Utilizing Project Update and Delivery Templates 25:46 Enhancing Client Relationships with Delivery Templates 28:12 Importance of Service in Service Provider Role

youtube

0.391

0.61

systemHUB•Jul 26, 2024

AI Agents For Small Business - Mark Zuckerberg

Mark Zuckerberg envisions a world with billions of AI agents, outnumbering humans. His focus: empowering creators and small businesses to create their own AI agents. Soon, every business may have an AI agent for customer support and sales, as essential as having a website or email today. The future of business communication is here, and it's AI-powered. 🎬 Watch our most recent videos: https://www.youtube.com/c/systemHUB/videos?view=0&sort=dd&flow=grid ✅ Download FREE system templates: https://www.systemology.com/launchpad/ ✅ Grab SYSTEMology, the book: https://www.systemology.com/book ✅ FREE 30-day systemHUB trial: https://www.systemhub.com/30-day-trial/ Follow us on social media: ➡️ Dave's LinkedIn - https://www.linkedin.com/in/david-jenyns/ ➡️ LinkedIn Page - https://www.linkedin.com/company/systemhub/ ➡️ Facebook Page – https://www.facebook.com/thesystemhub ➡️ Twitter - https://twitter.com/systemhub

youtube

0.426

0.81

codebasics•Mar 19, 2024

AI Career Opportunities | Career in AI with Salaries

In this video, we will explore both technical and non-technical career options available in the field of AI. We will discuss the skills and salaries required for each of these roles. Some free learning resources to learn these skills are mentioned in the video as well. Part 2 of this video (AI career selection guide): https://youtu.be/bA_w1wnpRqs AI Career PDF File: https://codebasics.io/resources/ai-career-opportunities Data Science Roadmap: https://youtu.be/PFPt6PQNslE AI Engineer Roadmap: https://youtu.be/MhCHrvfAXlc Data Analyst Roadmap: https://youtu.be/bCLBdxfe57o ⭐️ Timestamps ⭐️ 00:00 Introduction 00:50 Data Scientist 02:11 AI Engineer 04:24 NLP Engineer, CV Engineer 06:18 ML Ops Engineer 09:13 AI Product Manager 10:43 AI Ethics Executive 11:16 AI Sales Representative Do you want to learn technology from me? Check https://codebasics.io/?utmsource=description&utmmedium=yt&utmcampaign=description&utmid=description for my affordable video courses. Need help building software or data analytics/AI solutions? My company https://www.atliq.com/ can help. Click on the Contact button on that website. 🎥 Codebasics Hindi channel: https://www.youtube.com/channel/UCTmFBhuhMibVoSfYom1uXEg #️⃣ Social Media #️⃣ 🧑‍🤝‍🧑 Discord for Community Support: https://discord.gg/r42Kbuk 📸 Codebasics' Instagram: https://www.instagram.com/codebasicshub/ 📝 Codebasics' Linkedin : https://www.linkedin.com/company/codebasics/ 📝 Dhaval's Linkedin : https://www.linkedin.com/in/dhavalsays/ 📝 Hem's Linkedin: https://www.linkedin.com/in/hemvad/ 📽️ Hem's Instagram for daily tips: https://www.instagram.com/hemvadivel/ 📸 Dhaval's Personal Instagram: https://www.instagram.com/dhavalsays/ 🔗 Patreon: https://www.patreon.com/codebasics?fan_landing=true

youtube

0.538

0.62

Backstage with Millionaires•Feb 14, 2024

He is taking on Google 😮😮 #startup #ai #perplexity

This IITian is taking on Google, with his AI startup Perplexity. Aravind Srinivas studied engineering at IIT Madras before getting a PhD in computer science from the University of Berkley. And before starting Perplexity, Arvind worked at Google’s Deepmind and OpenAI, which is where his love for ‘search’ started. Arvind was convinced that the future of search would be to give the users answers to their questions, not a bunch of links. To make it happen, he started Perplexity. He got together a great team that wanted to work on the future of search and cold-emailed two potential investors, who invested 3.1 Million dollars just on the idea. Since its launch, Perplexity has taken off and is today being used by over 10 Million monthly users. The company is backed by investors like Jeff Bezos and Nvidia, who have put in over 100 Million dollars, valuing the company at 520 Million dollars.

youtube

0.435

0.86

TED•Dec 12, 2023

What Will Happen to Marketing in the Age of AI? | Jessica Apotheker | TED

Generative AI is poised to transform the workplace, but we still need human brains for new ideas, says marketing expert Jessica Apotheker. She explores how marketers can find their niche in the world of AI based on their preference for data or creativity, offering a pragmatic and hopeful look at the future of business. If you love watching TED Talks like this one, become a TED Member to support our mission of spreading ideas: https://ted.com/membership Follow TED! Twitter: https://twitter.com/TEDTalks Instagram: https://www.instagram.com/ted Facebook: https://facebook.com/TED LinkedIn: https://www.linkedin.com/company/ted-conferences TikTok: https://www.tiktok.com/@tedtoks The TED Talks channel features talks, performances and original series from the world's leading thinkers and doers. Subscribe to our channel for videos on Technology, Entertainment and Design — plus science, business, global issues, the arts and more. Visit https://TED.com to get our entire library of TED Talks, transcripts, translations, personalized talk recommendations and more. Watch more: https://go.ted.com/jessicaapotheker https://youtu.be/3MwMII8n1qM TED's videos may be used for non-commercial purposes under a Creative Commons License, Attribution–Non Commercial–No Derivatives (or the CC BY – NC – ND 4.0 International) and in accordance with our TED Talks Usage Policy: https://www.ted.com/about/our-organization/our-policies-terms/ted-talks-usage-policy. For more information on using TED for commercial purposes (e.g. employee learning, in a film or online course), please submit a Media Request at https://media-requests.ted.com #TED #TEDTalks #marketing

#TED#TEDTalks#marketing

youtube

0.388

0.37

CXOTalk•Oct 23, 2023

Workflow Automation with AI and Zapier | CXOTalk #808

#zapier #workflowautomation #workflow #aiautomation The rising significance of enterprise AI presents a unique hurdle: seamlessly integrating AI-based business workflows into operational systems, especially for non-programmers. On CXOTalk episode 808, we explore these issues with Mike Knoop, co-founder of Zapier and the company's AI lead. The conversation with Mike covers the rationale behind integrating AI, the technological advancements AI brings to workflow automation solutions, and its broader impact on business agility. Join the CXOTalk community: www.cxotalk.com/subscribe Read the full transcript: https://www.cxotalk.com/episode/ai-workflows-in-business-a-practical-guide Key points in the discussion include: ► The potential of AI-powered automation to empower more business users with customized workflows. But governance, accuracy, and security are key challenges to consider when implementing AI workflows. ► Initial use cases include generating creative ideas, summarizing unstructured data, and making powerful business process automations easier to build for non-technical users. ► Customer service and marketing are excellent starting points for AI automation. Watch this conversation to gain practical advice on using low-code, no-code tools to automate AI in the enterprise. Mike Knoop is the co-founder and Head of Zapier AI at Zapier. Mike has a B.S. in mechanical engineering from the University of Missouri, where his research topic was focused on finite element modeling and optimization. Michael Krigsman is an industry analyst and publisher of CXOTalk. For three decades, he has advised enterprise technology companies on market messaging and positioning strategy. He has written over 1,000 blogs on leadership and digital transformation and created almost 1,000 video interviews with the world’s top business leaders on these topics. His work has been referenced in the media over 1,000 times and in over 50 books. He has presented and moderated panels at numerous industry events around the world.

#zapier#workflowautomation#workflow

youtube

0.318

0.2

Sidd Ahmed•Jun 16, 2023

Course option: AI or Data science? Which is better? | Ask Sidd a question | Sidd Ahmed

Hope I help you embark on your journey towards a successful degree program. GET MOTIVATED, log on to https://siddahmed.com/ Interact with me on Facebook: https://www.facebook.com/siddahmedinc Instagram: https://instagram.com/siddahmed Linkedin: https://www.linkedin.com/company/siddahmed/

youtube

0.282

0.22

Microsoft Mechanics•Jun 2, 2023

Not a code expert? AI and Copilot can assist you. Check out AI updates to Power Platform.

Use AI Large Language Models with Microsoft’s Power Platform to create automated workflows, apps, web pages and bots—without knowing how to write code. Watch the full video here: https://youtu.be/WXb_g23GEbg AI and Copilot help build fully functional experiences. Generate workflows using only natural language prompts in Power Automate, create apps in seconds in Power Apps, build professional websites with Power Pages, and use the new Boost Conversations capability with GPT to create FAQ bots with Power Virtual Agents. Stephen Siciliano, Vice President of Microsoft Power Automate, joins Jeremy Chapman to tour the latest Power Platform updates. ► Unfamiliar with Microsoft Mechanics? As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft. • Subscribe to our YouTube: https://www.youtube.com/c/MicrosoftMechanicsSeries • Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog • Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast ► Keep getting this insider knowledge, join us on social: • Follow us on Twitter: https://twitter.com/MSFTMechanics • Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/ • Enjoy us on Instagram: https://www.instagram.com/msftmechanics/ • Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics #PowerPlatform #ChatGPT #Copilot #OpenAI

#PowerPlatform#ChatGPT#Copilot

youtube

0.471

0.61

GaryVee•May 9, 2023

The future of AI

When voice and ai hit scale … shits gonna get interesting… — Thanks for watching! Join My Discord!: https://www.garyvee.com/discord Check out another series on my channel: Keynotes: https://www.youtube.com/watch?v=6vCDlmhRmBo&list=PLfA33-E9P7FCEF1izpctGGoak841XYzrJ NFTs: https://www.youtube.com/watch?v=AwMJ6bScB2s&list=PLfA33-E9P7FAcvsVSFqzSuJhHu3SkW2Ma Business Meetings: https://www.youtube.com/watch?v=wILI_VV6z4Y&list=PLfA33-E9P7FCTIY62wkqZ-E1cwpc2hxBJ Gary Vaynerchuk Original Films: https://youtube.com/playlist?list=PLfA33-E9P7FAvnrOcgy4MvIcCXxoyjuku Trash Talk: https://youtube.com/playlist?list=PLfA33-E9P7FDelN4bXFgtJuczC9HHmm2- WeeklyVee: https://youtube.com/playlist?list=PLfA33-E9P7FBPjdQcF6uedz9fdk8XKn-b — Gary Vaynerchuk is a serial entrepreneur, and serves as the Chairman of VaynerX, the CEO of VaynerMedia and the Creator & CEO of VeeFriends. Gary is considered one of the leading global minds on what’s next in culture, relevance and the internet. Known as “GaryVee” he is described as one of the most forward thinkers in business – he acutely recognizes trends and patterns early to help others understand how these shifts impact markets and consumer behavior. Whether its emerging artists, esports, NFT investing or digital communications, Gary understands how to bring brand relevance to the forefront. He is a prolific angel investor with early investments in companies such as Facebook, Twitter, Tumblr, Venmo, Snapchat, Coinbase and Uber. Gary is an entrepreneur at heart — he builds businesses. Today, he helps Fortune 1000 brands leverage consumer attention through his full service advertising agency, VaynerMedia which has offices in NY, LA, London, Mexico City, LATAM and Singapore. VaynerMedia is part of the VaynerX holding company which also includes VaynerProductions, VaynerNFT, Gallery Media Group, The Sasha Group, Tracer, VaynerSpeakers, VaynerTalent, and VaynerCommerce. Gary is also the Co-Founder of VaynerSports, Resy and Empathy Wines. Gary guided both Resy and Empathy to successful exits — both were sold respectively to American Express and Constellation Brands. He’s also a Board Member at Candy Digital, Co-Founder of VCR Group, Co-Founder of ArtOfficial, and Creator & CEO of VeeFriends. Gary was recently named to the Fortune list of the Top 50 Influential people in the NFT industry. In addition to running multiple businesses, Gary documents his life daily as a CEO through his social media channels which has more than 34 million followers and garnishes over 272 million monthly impressions/views across all platforms. His podcast ‘The GaryVee Audio Experience’ ranks among the top podcasts globally. He is a five-time New York Times Best-Selling Author and one of the most highly sought after public speakers. Gary serves on the board of MikMak, Bojangles Restaurants, and Pencils of Promise. He is also a longtime Well Member of Charity:Water.

youtube

0.414

0.63

Anik Singal•Apr 25, 2023

How to use AI to make extra money

FREE Courses from LURN == https://www.Lurn.com/getfreecourses ============================================ How to use AI to make extra money ============================================ 👇Subscribe To The Channel By Clicking Below!👇 https://www.youtube.com/user/aniksingalcom?sub_confirmation=1 CHECK OUT THESE TOP TRENDING PLAYLISTS NOW! Fighting Entrepreneur - https://www.youtube.com/watch?v=D9nsNOu3gIE&list=PLEmF7qw7SECK1hy5U5nodHoCg7ANzXukz Master Copywriting With Anik Singal - https://www.youtube.com/watch?v=CjOAWP1DKAk&list=PLEmF7qw7SECKouq97MqF5zFi1Xb-VFyMY&index=2&t=0s Facebook Advertising Strategies - https://www.youtube.com/watch?v=BMQh6zA3HUY&list=PLEmF7qw7SECJUULNlnAGHvcegeQbIAHZp How To Become A Better Entrepreneur - https://www.youtube.com/playlist?list=PLEmF7qw7SECKVlP2eOsF_XpYBYhlTGAVU ============================================ “Lead Fighter” — That’s the title Anik Singal gives himself as a high-energy, trailblazing Entrepreneur. Anik got his start in the online scene back in 2003 from his college dorm room. Ever since then he’s gone on to build 6 successful companies, launched 22 top brands, generated over $250 Million in sales, and taught over 250,000 students worldwide - how to start, grow, and scale a successful online business. As the founder of Lurn, Inc., Anik Singal’s passion is in creating dynamic online classroom environments that teach people how to enhance their business, financial, and personal lives. Anik Singal has become a go-to authority in the areas of... ✅Digital Publishing. ✅Event-Based Marketing. ✅Product Launches. ✅Email Marketing. Anik has been voted one of the Top 3 Young Entrepreneurs by BusinessWeek Magazine. In addition, his company earned the prestigious Inc. 500 Fastest Growing Companies in America two years in a row. All of Anik’s experiences have made him the person he is today… From struggling for 18 months when he first started, then successfully building his business to over $10 Million a year. Then losing it all and falling to $1.7 Million in debt and almost declaring bankruptcy. Bouncing back and generating over $10 million in 16 months, paying back all of his debt and he hasn’t looked back since. He’s worked with and has been endorsed by some of the most influential Entrepreneurs of our time... Including Robert Kiyosaki, Les Brown, Daymond John, Bob Proctor, Grant Cardone, and many more. Anik is a dreamer. A thinker. A fighter. Most importantly, Anik is a teacher. His immediate goal is empowering 1 Million Entrepreneurs to live the life of their dreams by the end of 2019. ============================================ CONNECT WITH ANIK ON SOCIAL MEDIA YouTube: https://www.youtube.com/channel/UCinyEr-Fly9Yp1zMFxD0cQ?viewas=subscriber Anik Singal Blog: https://lurn.com/blog/ Facebook: https://www.facebook.com/aniksingal Instagram: https://www.instagram.com/anik/ LinkedIn: https://www.linkedin.com/company/lurn-inc/ Podcast: https://podcast.lurnworkshop.com iTunes: https://itunes.apple.com/us/podcast/the-fighting-entrepreneur/id1446089516?mt=2 Spotify: https://open.spotify.com/show/0HbielkIU1f88Bv4VuMHmh?si=Q1ujyoiMRF2LlHdBgTdAzw Soundcloud: https://soundcloud.com/thefightingentrepreneur Google Play: https://play.google.com/music/listen#/ps/Irckjhwglqgjnbia5t3zpyj4xcq #AnikSingal #Lurn #LurnNation ============================================ Join Lurn Nation: https://lurn.com/ Lurn is the Transformational home for modern entrepreneurs. We have 60+ training courses and programs to help you reach your business goals - join our community today!

#AnikSingal#Lurn#LurnNation