Months

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I spent 6 months on building a tool, and got 0 zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product, Summ, that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I spent 6 months on building a web product, and got zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I have stuff to post on Reddit very rarely, but I share how my project is going on, random stuff, and memes on X. Just in case few might want to keep in touch 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

My app has gone viral and I grew from 1k users (take 5months) to 100k user in 5 days

I've always dreamt of building an online side business where I can build once and sell to millions. I love that business model but have never dreamt that I can achieve that, given that I am not a programmer in my career. I have been following side hustle school and some other business podcast for the past years as a drive and motivation to create my own business.  Over the years, I've delve a little on to web development using WordPress and in the hope of earning some money from that. I learnt in the hard way but is a good learning story and journey. I realised that what you put all your efforts building and excited for doesn't mean anything for anyone else and also learnt the importance of UI UX.  Fast forward to 5 months ago (July 2024), I've came across several low code app builder. With the help of the low code tools in combination with chatgpt, I've finally launched my first mobile app - Rolly: AI Money Tracker. But the business challenges doesn't end here, but it's just the beginning. I got no experience and skills on marketing but I've got my drive and passion that keep propelling me forward. By keep listening on people sharing their journey, looking at different apps to brainstorm etc, I've managed to now grow my user base from 1k (in 5 months) to 100k (in 5days). What's happening was my app somehow got viral in Vietnam when people are getting interest funny comments from my AI during entering the transaction and it has been sharing around in the social media and even featured on the news. What a crazy journey as the inflow of users has been too sudden, my server has been down for a few times until I progressively upgrade it until it got stable these couple of days. As for my advice to people dreaming the to be entreprenuer - Don't overthinking about all the problems you will face before starting. You will encounter hundreds of problems along the way and you just need to solve them one by one. You will never start if you think about what's not working and there will never be an answer for everything - even I don't have an answer for everything now.

I spent 6 months on building a web product, and got zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I have stuff to post on Reddit very rarely, but I share how my project is going on, random stuff, and memes on X. Just in case few might want to keep in touch 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I spent 6 months on building a web product, and got zero users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I have stuff to post on Reddit very rarely, but I share how my project is going on, random stuff, and memes on X. Just in case few might want to keep in touch 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2C products beats building B2B products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

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!

What I learn from my $200 MRR App I built 4 months ago?

4 month ago, I am just a 10-years experienced product manager without any software development experience. I have an $3K/month job, but I am so tired, I don’t like my life, don’t like my boss, don’t like my daily work, that make me feeling I already died however I am still living. I yearn for freedom and want to live each day the way I want to. So I quit my job, and become a Indie developer to build my own business, my own app, even my own life. I am so grateful for this time and experience, now my app reach $200 MRR, still very little compared to my previous salary, but I never regret. I have learned lots of things from this time and experience, more than I had in last 10 years. Here is the time-line of my App: \- Sep 2023: Launch first version to iOS App store \- Oct 2023: Release in-app-purchase features and have first subscriber, the revenue in October is $154 \- Nov 2023: Change from subscription to pay per use, and I did lots of marketing jobs in November, however, the revenue reduced to only $40. \- Dec 2023: Change back to subscription, and stop some invalid marketing jobs, only keep the ones that actually work. I almost did nothing in December, and the revenue come to $243. During this process, I have learned lots of things, there are some of them that I think could help you as well. Web or App My App is an iOS app that only can running on Apple’s device such like iPhone/iPad or Mac with Apple silicon. Many people ask me why my product is an iOS app not a website, because they don’t have any Apple device. It's true that promoting an app is much harder than promoting a website. However I am now very glad I made an App and not a website! If I make a website, I don't think it's possible to make $100 in the first month. My App is about keyword research, to help people find some ideas from search keyword, because every keyword people searched in Google are representing a real need of them, also can be used in SEO field. However there are a lot of website tools about keyword research, some of them are famous like Ahrefs, SEMrush… I have no intention of competing with them. Actually I don’t have any chance. While in app store, there are little apps about keyword research, each of them have terrible data and user experience, that means if my app has better data and experience that could be my chance. In fact, the App store brings me 20 organic installs a day that Google would never have been able to bring me if I had a website, at least for the first few months. Furthermore, Apple nearly did everything for developer, I don’t need to care about user login, payment and so on, Apple did everything, I just need to call their API, that save lots of time, if I build a website, I need to implement login and payment by myself, that would add some extra work. Not to mention I'd need to buy servers and domains, that would cost me a lot of money. Although Apple will take 30% of the revenue, I can live with that in the early stages because the most important thing for me is to get the product to market as soon as possible. Actually thought Apple’s SMB program, the take rate is 15% now. So Web or App is not important in the early stage, time is important, if people need my product, it's easy to make a website one. More Users or More Valuable Users In November, I notice some users would like use my app, and they were meet paywall, but they never subscribe. I provided 7 day free trail, but it seem that they don’t like it. So I decide to change subscription to pay per use. Because as a user, I don’t like subscription as well, pay per use seem like more friendly. So I change from subscription to pay per use. People can afford $9.99 to subscribe monthly for unlimited use or pay $1.99 for each data they want(First purchase is $0.99 then $1.99). I was expecting more user to pay, but it was the complete opposite! Some users who would have paid a higher subscription fee are switching to a lower priced single payment. Users are encountering paywalls more often, and each time they need to make a decision about whether or not to pay, which increases the probability that they will abandon payment. This resulted in a 75% decrease in revenue in November. In fact, the mostly of my revenue comes from a handful of long-cycle subscribers, such as annual subscription. \\Few bring in most of the revenue,\\ that is the most important thing I learned. You don't need a lot of customers, you just need more valuable ones. That's why it's only right to design a mechanism to filter out high-value customers and focus on them, all the things you want do is just let more people into the filter, and from that point of view, subscription with free trial period is the best way, even if most people don't like it. The rule of 20/80 will always be there. The most important thing is always focus on the 20 percent things and people. Effort does not always guarantee rewards. Unless one engages in deep thinking, or most efforts are invalid. I have been working very hard to promote my product for a period of time. It’s about in November. I did a lot of job, such as write script to send message to my potential clients on Fiverr, post and write comments on others post on Reddit, find related questions and answer them on Quora, post and comments on Twitte, etc. During that period, I was exhausted every day, but the outcome did not meet my expectations. There is only little growth on App installation, even less revenue than before. That make me frustrated. I finally realized that If I need to put in a tremendous amount of effort just to make a little progress, there is must something wrong. So I stop 80% of promote work I have ever did, only keep app store search ad, which will bring a installation with less than $0.5 cost. Then I dive into long time and deeply thinking, I spent more time on reading books, investigate other product with great MRR, watch interviews with people who are already living the kind of life I aspire to live, for example, u/levelsio. These things have given me great inspiration, and my life has become easier. It seems that the life I anticipated when I resigned is getting closer. I also have a clearer understanding of my app. Meanwhile, MRR has been growing. This experience let me learn that effort does not always guarantee results. Many times, our efforts are just wishful thinking, they are invalid, do the right thing after deeply thinking is more important. What Next? My goal is reach $3K MRR, as same as my job payment, I will never stop to building things, and I will keep my currently lifestyle. I still don't know how to get more people to use my app, but levelsio's interviews give me some inspiration that I can verified something by manually instead of build a software. I plan to launch a trend analysis product based on the keyword data provided by my current app. I have always wanted to combine AI to build such a product, but I didn't know how to do it. Now I intend to manually complete it first and start software development once there are paying users. If you are interested to my App, you could try it.

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. &#x200B; 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 &#x200B; 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 &#x200B; 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 &#x200B; 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 &#x200B; 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!

Spent months patching no-code tools—built a full custom business app in 5 minutes with AI

Hey r/SideProject, I’ve spent months trying to patch together off-the-shelf tools and no-code platforms to create software for small businesses, but I kept running into the same problem—they just don’t fit how businesses actually work. That’s when I realized most small businesses need custom software tailored to their unique workflows, but the time and cost of building it from scratch are out of reach for most of them. So I decided to build a solution. Introducing Crust AI—a tool that lets SMB owners describe their exact needs, and in 5 minutes, it generates a fully functional app: client portals, employee hubs, vendor management systems—anything you need to streamline external collaboration. I went from wasting weeks stitching together no-code tools to having a zero-dev solution up and running in minutes. I’d love to hear your thoughts on it. If you’ve been in the same boat as me, check out trycrust.co and let me know what you think!

I made a bunch of side projects over the last 9 months, and even accrued 500+ accounts and some donations!

I just stumbled upon this subreddit and have a bunch of fun projects I'd like to present, any thoughts/feedback/criticism, etc. all welcome. So, first things first, a little about me, I work full time in an unrelated job, but have picked up full stack and mobile programming. I have two roommates who help a bit in their own way, one is a server expert and happened to have a server in our apartment basement, and the other is my brother and he picked up some frontend programming. We're all avid cyclists and decided to start building about 9 months ago. Our first idea was https://sherpa-map.com a SPA website allowing users to create cycling routes, send them to their Garmin devices, download them as GPX files, etc. This site uses the open-source software Graphhopper on the backend which I've augmented to send back surface type information. This site has a loooonnnggg list of features, from the simple, like a live weather radar, to the extreme like this functionality: &#x200B; AI surface classification This video demonstrates the ability to classify road surface types in real time using high-resolution satellite imagery of road portions with unknown surface types! I trained a Pytorch resnet 50 model with tuned hyperparameters and 10 epochs on 200,000 satellite images of roads with known surface types! (We host a OSM Postgres server with coordinates of roads and their associated surface types, I made a script to pull images of said roads for training). I built the model into a secondary backend written in flask and piped the images being used back through live web sockets to my node.js backend to the person who is logged in! &#x200B; Okay, on to the next side project, a cycling physics simulator! https://sherpa-map.com/cycling-route-calculator.html Cycling Physics Simulation This site lets users enter information about their bike setup, upload or use a preset route, and enter in their physical information to see how different changes in their setup might affect how fast they will be throughout a course! It can also pull complex weather information throughout the course and give a full suite of nutrition details! &#x200B; Okay, Next project! The Activity Racer! https://sherpa-map.com/activity-racer.html Activity Racer This site lets users upload their own or competitors' GPX activity files and line them up against each other at any point in an event, to see who was faster where! It's great if you've done the same even year after year with differing setups, allowing you to get insights as to which might have done better at what point. &#x200B; Okay, final project, this one's pretty half-baked as I'm still in the process of implementing so many other things, a podcast creation app! (I was bored and just started working on this a week or so ago, for no good reason). Currently, this one lives on https://sherpa-map.com/podcast.html This podcasting web app creates a peer to peer to peer... mesh network using webRTC so, small groups can communicate with the highest level of fidelity both in audio and video! Simply enter a room name and have other users enter the room name as well and they're connected! I've already used tensorflow.js AI to allow a blur background option, similar to MS Teams, whereby bodypix classifier AI picks out the person and I use a blur on a JS canvas behind them. I also went a little bit off the deep end and managed to implement the RNNoise background noise suppressor on the frontend, it's written in C, but I was able to use Windows Subsystem for Linux + emscrption to compile it in just the right way, with exposed malloc and free and a JS wrapper to use on the frontend in WASM. I actually use WASM (typically Rust) in many fun ways throughout all of these projects. I'm also in the middle of recreating the first site in React-Native + Maplibre for IOS and Android as individual APPs. In addition, I'm also working on the integration of my main site into a different project for a different group. So, I have a fun collection of side projects with slightly different GUIs, across different platforms with no coherent landing page as of yet but I've been having a blaaaast putting them together. As a final note, I even have a bit of an easter egg in the automated email system I use for account verifications and password resets do\not\reply@sherpa-map.com I hooked it up to ChatGPT API and told it it is a disgruntled worker whose sole task in life is to watch a do\not\reply email box and respond sarcastic/snarky to anyone who dares send a message to it, if AI comes for humanity, I bet I'll be on a list for this one lol.

I spent 6 months on a web app as a side project, and got 0 users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I very rarely have stuff to post on Reddit, but I share how my project is going on, just random stuff, and memes on X. In case few might want to keep up 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2B products beats building B2C products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

I Made $20K in 2 Months by Building in Public on X

Hey everyone, I wanted to share my journey of making $20K in just 2 months by leveraging Twitter (X) and building in public. It’s been an exciting ride, and I hope my story inspires others to take action on their ideas. Here’s exactly what I did: Building in Public I started sharing everything about my work openly. My wins, struggles, and process. I showed: How I build MVPs for clients. The tools I use (Next.js, Supabase, Cursor AI, etc.). The challenges I face and how I solve them. Transparency builds trust, and trust brings clients. Consistency is Key For the past 2 months, I’ve posted consistently on X, even when I felt like no one was watching. Here’s what I focused on: Sharing value (pro tips, workflows, tools). Asking for advice and engaging with my community. Highlighting my projects and client work. Building an audience takes time, but showing up daily pays off. Personal Brand = Inbound Clients I never did any “engagement farming” or gimmicky posts. I just shared my knowledge, and it led to over 35M views on my tweets and 7K followers. Many of these followers turned into inbound client leads. I’ve always believed: Share value for free, and charge for implementation. The Power of Community Engaging with my community on X has been game-changing. People have: Helped refine my processes. Shared valuable tools and advice. Connected me to opportunities I wouldn’t have found otherwise. Key Takeaway: You don’t need a perfect process or a huge following to start. Be consistent. Build in public. Share your journey. In 2 months, I’ve gone from wondering if this would work to making $20K by simply showing up and adding value. If you’re thinking about building in public or starting a personal brand, DO IT. It works. Feel free to ask me anything. I’m happy to share more details about my process, tools, or lessons learned! Let’s build together.

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 :)

I spent 6 months on a web app as a side project, and got 0 users. Here is my story.

Edit Thank you all so much for your time reading my story. Your support, feedback, criticism, and skepticism; all helped me a lot, and I couldn't appreciate it enough \^\_\^ I very rarely have stuff to post on Reddit, but I share how my project is going on, just random stuff, and memes on X. In case few might want to keep up 👀 TL;DR I spent 6 months on a tool that currently has 0 users. Below is what I learned during my journey, sharing because I believe most mistakes are easily avoidable. Do not overestimate your product and assume it will be an exception to fundamental principles. Principles are there for a reason. Always look for validation before you start. Avoid building products with a low money-to-effort ratio/in very competitive fields. Unless you have the means, you probably won't make it. Pick a problem space, pick your target audience, and talk to them before thinking about a solution. Identify and match their pain points. Only then should you think of a solution. If people are not overly excited or willing to pay in advance for a discounted price, it might be a sign to rethink. Sell one and only one feature at a time. Avoid everything else. If people don't pay for that one core feature, no secondary feature will change their mind. Always spend twice as much time marketing as you do building. You will not get users if they don't know it exists. Define success metrics ("1000 users in 3 months" or "$6000 in the account at the end of 6 months") before you start. If you don't meet them, strongly consider quitting the project. If you can't get enough users to keep going, nothing else matters. VALIDATION, VALIDATION, VALIDATION. Success is not random, but most of our first products will not make a success story. Know when to admit failure, and move on. Even if a product of yours doesn't succeed, what you learned during its journey will turn out to be invaluable for your future. My story So, this is the story of a product that I’ve been working on for the last 6 months. As it's the first product I’ve ever built, after watching you all from the sidelines, I have learned a lot, made many mistakes, and did only a few things right. Just sharing what I’ve learned and some insights from my journey so far. I hope that this post will help you avoid the mistakes I made — most of which I consider easily avoidable — while you enjoy reading it, and get to know me a little bit more 🤓. A slow start after many years Summ isn’t the first product I really wanted to build. Lacking enough dev skills to even get started was a huge blocker for so many years. In fact, the first product I would’ve LOVED to build was a smart personal shopping assistant. I had this idea 4 years ago; but with no GPT, no coding skills, no technical co-founder, I didn’t have the means to make it happen. I still do not know if such a tool exists and is good enough. All I wanted was a tool that could make data-based predictions about when to buy stuff (“buy a new toothpaste every three months”) and suggest physical products that I might need or be strongly interested in. AFAIK, Amazon famously still struggles with the second one. Fast-forward a few years, I learned the very basics of HTML, CSS, and Vanilla JS. Still was not there to build a product; but good enough to code my design portfolio from scratch. Yet, I couldn’t imagine myself building a product using Vanilla JS. I really hated it, I really sucked at it. So, back to tutorial hell, and to learn about this framework I just heard about: React.React introduced so many new concepts to me. “Thinking in React” is a phrase we heard a lot, and with quite good reasons. After some time, I was able to build very basic tutorial apps, both in React, and React Native; but I have to say that I really hated coding for mobile. At this point, I was already a fan of productivity apps, and had a concept for a time management assistant app in my design portfolio. So, why not build one? Surely, it must be easy, since every coding tutorial starts with a todo app. ❌ WRONG! Building a basic todo app is easy enough, but building one good enough for a place in the market was a challenge I took and failed. I wasted one month on that until I abandoned the project for good. Even if I continued working on it, as the productivity landscape is overly competitive, I wouldn’t be able to make enough money to cover costs, assuming I make any. Since I was (and still am) in between jobs, I decided to abandon the project. 👉 What I learned: Do not start projects with a low ratio of money to effort and time. Example: Even if I get 500 monthly users, 200 of which are paid users (unrealistically high number), assuming an average subscription fee of $5/m (such apps are quite cheap, mostly due to the high competition), it would make me around $1000 minus any occurring costs. Any founder with a product that has 500 active users should make more. Even if it was relatively successful, due to the high competition, I wouldn’t make any meaningful money. PS: I use Todoist today. Due to local pricing, I pay less than $2/m. There is no way I could beat this competitive pricing, let alone the app itself. But, somehow, with a project that wasn’t even functional — let alone being an MVP — I made my first Wi-Fi money: Someone decided that the domain I preemptively purchased is worth something. By this point, I had already abandoned the project, certainly wasn’t going to renew the domain, was looking for a FT job, and a new project that I could work on. And out of nowhere, someone hands me some free money — who am I not to take it? Of course, I took it. The domain is still unused, no idea why 🤔. Ngl, I still hate the fact that my first Wi-Fi money came from this. A new idea worth pursuing? Fast-forward some weeks now. Around March, I got this crazy idea of building an email productivity tool. We all use emails, yet we all hate them. So, this must be fixed. Everyone uses emails, in fact everyone HAS TO use emails. So, I just needed to build a tool and wait for people to come. This was all, really. After all, the problem space is huge, there is enough room for another product, everyone uses emails, no need for any further validation, right? ❌ WRONG ONCE AGAIN! We all hear from the greatest in the startup landscape that we must validate our ideas with real people, yet at least some of us (guilty here 🥸) think that our product will be hugely successful and prove them to be an exception. Few might, but most are not. I certainly wasn't. 👉 Lesson learned: Always validate your ideas with real people. Ask them how much they’d pay for such a tool (not if they would). Much better if they are willing to pay upfront for a discount, etc. But even this comes later, keep reading. I think the difference between “How much” and “If” is huge for two reasons: (1) By asking them for “How much”, you force them to think in a more realistic setting. (2) You will have a more realistic idea on your profit margins. Based on my competitive analysis, I already had a solution in my mind to improve our email usage standards and email productivity (huge mistake), but I did my best to learn about their problems regarding those without pushing the idea too hard. The idea is this: Generate concise email summaries with suggested actions, combine them into one email, and send it at their preferred times. Save as much as time the AI you end up with allows. After all, everyone loves to save time. So, what kind of validation did I seek for? Talked with only a few people around me about this crazy, internet-breaking idea. The responses I got were, now I see, mediocre; no one got excited about it, just said things along the lines of “Cool idea, OK”. So, any reasonable person in this situation would think “Okay, not might not be working”, right? Well, I did not. I assumed that they were the wrong audience for this product, and there was this magical land of user segments waiting eagerly for my product, yet unknowingly. To this day, I still have not reached this magical place. Perhaps, it didn’t exist in the first place. If I cannot find it, whether it exists or not doesn’t matter. I am certainly searching for it. 👉 What I should have done: Once I decide on a problem space (time management, email productivity, etc.), I should decide on my potential user segments, people who I plan to sell my product to. Then I should go talk to those people, ask them about their pains, then get to the problem-solving/ideation phase only later. ❗️ VALIDATION COMES FROM THE REALITY OUTSIDE. What validation looks like might change from product to product; but what invalidation looks like is more or less the same for every product. Nico Jeannen told me yesterday “validation = money in the account” on Twitter. This is the ultimate form of validation your product could get. If your product doesn’t make any money, then something is invalidated by reality: Your product, you, your idea, who knows? So, at this point, I knew a little bit of Python from spending some time in tutorial hell a few years ago, some HTML/CSS/JS, barely enough React to build a working app. React could work for this project, but I needed easy-to-implement server interactivity. Luckily, around this time, I got to know about this new gen of indie hackers, and learned (but didn’t truly understand) about their approach to indie hacking, and this library called Nextjs. How good Next.js still blows my mind. So, I was back to tutorial hell once again. But, this time, with a promise to myself: This is the last time I would visit tutorial hell. Time to start building this "ground-breaking idea" Learning the fundamentals of Next.js was easier than learning of React unsurprisingly. Yet, the first time I managed to run server actions on Next.js was one of the rarest moments that completely blew my mind. To this day, I reject the idea that it is something else than pure magic under its hood. Did I absolutely need Nextjs for this project though? I do not think so. Did it save me lots of time? Absolutely. Furthermore, learning Nextjs will certainly be quite helpful for other projects that I will be tackling in the future. Already got a few ideas that might be worth pursuing in the head in case I decide to abandon Summ in the future. Fast-forward few weeks again: So, at this stage, I had a barely working MVP-like product. Since the very beginning, I spent every free hour (and more) on this project as speed is essential. But, I am not so sure it was worth it to overwork in retrospect. Yet, I know I couldn’t help myself. Everything is going kinda smooth, so what’s the worst thing that could ever happen? Well, both Apple and Google announced their AIs (Apple Intelligence and Google Gemini, respectively) will have email summarization features for their products. Summarizing singular emails is no big deal, after all there were already so many similar products in the market. I still think that what truly matters is a frictionless user experience, and this is why I built this product in a certain way: You spend less than a few minutes setting up your account, and you get to enjoy your email summaries, without ever visiting its website again. This is still a very cool concept I really like a lot. So, at this point: I had no other idea that could be pursued, already spent too much time on this project. Do I quit or not? This was the question. Of course not. I just have to launch this product as quickly as possible. So, I did something right, a quite rare occurrence I might say: Re-planned my product, dropped everything secondary to the core feature immediately (save time on reading emails), tried launching it asap. 👉 Insight: Sell only one core feature at one time. Drop anything secondary to this core feature. Well, my primary occupation is product design. So one would expect that a product I build must have stellar design. I considered any considerable time spent on design at this stage would be simply wasted. I still think this is both true and wrong: True, because if your product’s core benefits suck, no one will care about your design. False, because if your design looks amateurish, no one will trust you and your product. So, I always targeted an average level design with it and the way this tool works made it quite easy as I had to design only 2 primary pages: Landing page and user portal (which has only settings and analytics pages). However, even though I knew spending time on design was not worth much of my time, I got a bit “greedy”: In fact, I redesigned those pages three times, and still ended up with a so-so design that I am not proud of. 👉 What I would do differently: Unless absolutely necessary, only one iteration per stage as long as it works. This, in my mind, applies to everything. If your product’s A feature works, then no need to rewrite it from scratch for any reason, or even refactor it. When your product becomes a success, and you absolutely need that part of your codebase to be written, do so, but only then. Ready to launch, now is th etime for some marketing, right? By July 26, I already had a “launchable” product that barely works (I marked this date on a Notion docs, this is how I know). Yet, I had spent almost no time on marketing, sales, whatever. After all, “You build and they will come”. Did I know that I needed marketing? Of course I did, but knowingly didn’t. Why, you might ask. Well, from my perspective, it had to be a dev-heavy product; meaning that you spend most of your time on developing it, mostly coding skills. But, this is simply wrong. As a rule of thumb, as noted by one of the greatests, Marc Louvion, you should spend at least twice of the building time on marketing. ❗️ Time spent on building \* 2 people don’t know your product > they don’t use your product > you don’t get users > you don’t make money Easy as that. Following the same reasoning, a slightly different approach to planning a project is possible. Determine an approximate time to complete the project with a high level project plan. Let’s say 6 months. By the reasoning above, 2 months should go into building, and 4 into marketing. If you need 4 months for building instead of 2, then you need 8 months of marketing, which makes the time to complete the project 12 months. If you don’t have that much time, then quit the project. When does a project count as completed? Well, in reality, never. But, I think we have to define success conditions even before we start for indie projects and startups; so we know when to quit when they are not met. A success condition could look like “Make $6000 in 12 months” or “Have 3000 users in 6 months”. It all depends on the project. But, once you set it, it should be set in stone: You don’t change it unless absolutely necessary. I suspect there are few principles that make a solopreneur successful; and knowing when to quit and when to continue is definitely one of them. Marc Louvion is famously known for his success, but he got there after failing so many projects. To my knowledge, the same applies to Nico Jeannen, Pieter Levels, or almost everyone as well. ❗️ Determining when to continue even before you start will definitely help in the long run. A half-aed launch Time-leap again. Around mid August, I “soft launched” my product. By soft launch, I mean lazy marketing. Just tweeting about it, posting it on free directories. Did I get any traffic? Surely I did. Did I get any users? Nope. Only after this time, it hit me: “Either something is wrong with me, or with this product” Marketing might be a much bigger factor for a project’s success after all. Even though I get some traffic, not convincing enough for people to sign up even for a free trial. The product was still perfect in my eyes at the time (well, still is ^(\_),) so the right people are not finding my product, I thought. Then, a question that I should have been asking at the very first place, one that could prevent all these, comes to my mind: “How do even people search for such tools?” If we are to consider this whole journey of me and my so-far-failed product to be an already destined failure, one metric suffices to show why. Search volume: 30. Even if people have such a pain point, they are not looking for email summaries. So, almost no organic traffic coming from Google. But, as a person who did zero marketing on this or any product, who has zero marketing knowledge, who doesn’t have an audience on social media, there is not much I could do. Finally, it was time to give up. Or not… In my eyes, the most important element that makes a founder (solo or not) successful (this, I am not by any means) is to solve problems. ❗️ So, the problem was this: “People are not finding my product by organic search” How do I make sure I get some organic traffic and gets more visibility? Learn digital marketing and SEO as much as I can within very limited time. Thankfully, without spending much time, I came across Neil Patel's YT channel, and as I said many times, it is an absolute gold mine. I learned a lot, especially about the fundamentals, and surely it will be fruitful; but there is no magic trick that could make people visit your website. SEO certainly helps, but only when people are looking for your keywords. However, it is truly a magical solution to get in touch with REAL people that are in your user segments: 👉 Understand your pains, understand their problems, help them to solve them via building products. I did not do this so far, have to admit. But, in case you would like to have a chat about your email usage, and email productivity, just get in touch; I’d be delighted to hear about them. Getting ready for a ProductHunt launch The date was Sept 1. And I unlocked an impossible achievement: Running out of Supabase’s free plan’s Egres limit while having zero users. I was already considering moving out of their Cloud server and managing a Supabase CLI service on my Hetzner VPS for some time; but never ever suspected that I would have to do this quickly. The cheapest plan Supabase offers is $25/month; yet, at that point, I am in between jobs for such a long time, basically broke, and could barely afford that price. One or two months could be okay, but why pay for it if I will eventually move out of their Cloud service? So, instead of paying $25, I spent two days migrating out of Supabase Cloud. Worth my time? Definitely not. But, when you are broke, you gotta do stupid things. This was the first time that I felt lucky to have zero users: I have no idea how I would manage this migration if I had any. I think this is one of the core tenets of an indie hacker: Controlling their own environment. I can’t remember whose quote this is, but I suspect it was Naval: Entrepreneurs have an almost pathological need to control their own fate. They will take any suffering if they can be in charge of their destiny, and not have it in somebody else’s hands. What’s truly scary is, at least in my case, we make people around us suffer at the expense of our attempting to control our own fates. I know this period has been quite hard on my wife as well, as I neglected her quite a bit, but sadly, I know that this will happen again. It is something that I can barely help with. Still, so sorry. After working the last two weeks on a ProductHunt Launch, I finally launched it this Tuesday. Zero ranking, zero new users, but 36 kind people upvoted my product, and many commented and provided invaluable feedback. I couldn't be more grateful for each one of them 🙏. Considering all these, what lies in the future of Summ though? I have no idea, to be honest. On one hand, I have zero users, have no job, no income. So, I need a way to make money asap. On the other hand, the whole idea of it revolves around one core premise (not an assumption) that I am not so willing to share; and I couldn’t have more trust in it. This might not be the best iteration of it, however I certainly believe that email usage is one of the best problem spaces one could work on. 👉 But, one thing is for certain: I need to get in touch with people, and talk with them about this product I built so far. In fact, this is the only item on my agenda. Nothing else will save my brainchild <3. Below are some other insights and notes that I got during my journey; as they do not 100% fit into this story, I think it is more suitable to list them here. I hope you enjoyed reading this. Give Summ a try, it comes with a generous free trial, no credit card required. Some additional notes and insights: Project planning is one of the most underestimated skills for solopreneurs. It saves you enormous time, and helps you to keep your focus up. Building B2B products beats building B2C products. Businesses are very willing to pay big bucks if your product helps them. On the other hand, spending a few hours per user who would pay $5/m probably is not worth your time. It doesn’t matter how brilliant your product is if no one uses it. If you cannot sell a product in a certain category/niche (or do not know how to sell it), it might be a good idea not to start a project in it. Going after new ideas and ventures is quite risky, especially if you don’t know how to market it. On the other hand, an already established category means that there is already demand. Whether this demand is sufficient or not is another issue. As long as there is enough demand for your product to fit in, any category/niche is good. Some might be better, some might be worse. Unless you are going hardcore B2B, you will need people to find your product by means of organic search. Always conduct thorough keyword research as soon as possible.

What I learn from my $200 MRR App I built 4 months ago

4 month ago, I am just a 10-years experienced product manager without any software development experience. I have an $3K/month job, but I am so tired, I don’t like my life, don’t like my boss, don’t like my daily work, that make me feeling I already died however I am still living. I yearn for freedom and want to live each day the way I want to. So I quit my job, and become a Indie developer to build my own business, my own app, even my own life. I am so grateful for this time and experience, now my app reach $200 MRR, still very little compared to my previous salary, but I never regret. I have learned lots of things from this time and experience, more than I had in last 10 years. Here is the time-line of my App: &#x200B; Sep 2023: Launch first version to iOS App store Oct 2023: Release in-app-purchase features and have first subscriber, the revenue in October is $154 Nov 2023: Change from subscription to pay per use, and I did lots of marketing jobs in November, however, the revenue reduced to only $40. Dec 2023: Change back to subscription, and stop some invalid marketing jobs, only keep the ones that actually work. I almost did nothing in December, and the revenue come to $243. During this process, I have learned lots of things, there are some of them that I think could help you as well. Web or App My App is an iOS app that only can running on Apple’s device such like iPhone/iPad or Mac with Apple silicon. Many people ask me why my product is an iOS app not a website, because they don’t have any Apple device. It's true that promoting an app is much harder than promoting a website. However I am now very glad I made an App and not a website! If I make a website, I don't think it's possible to make $100 in the first month. My App is about keyword research, to help people find some ideas from search keyword, because every keyword people searched in Google are representing a real need of them, also can be used in SEO field. However there are a lot of website tools about keyword research, some of them are famous like Ahrefs, SEMrush… I have no intention of competing with them. Actually I don’t have any chance. While in app store, there are little apps about keyword research, each of them have terrible data and user experience, that means if my app has better data and experience that could be my chance. In fact, the App store brings me 20 organic installs a day that Google would never have been able to bring me if I had a website, at least for the first few months. Furthermore, Apple nearly did everything for developer, I don’t need to care about user login, payment and so on, Apple did everything, I just need to call their API, that save lots of time, if I build a website, I need to implement login and payment by myself, that would add some extra work. Not to mention I'd need to buy servers and domains, that would cost me a lot of money. Although Apple will take 30% of the revenue, I can live with that in the early stages because the most important thing for me is to get the product to market as soon as possible. Actually thought Apple’s SMB program, the take rate is 15% now. So Web or App is not important in the early stage, time is important, if people need my product, it's easy to make a website one. More Users or More Valuable Users In November, I notice some users would like use my app, and they were meet paywall, but they never subscribe. I provided 7 day free trail, but it seem that they don’t like it. So I decide to change subscription to pay per use. Because as a user, I don’t like subscription as well, pay per use seem like more friendly. So I change from subscription to pay per use. People can afford $9.99 to subscribe monthly for unlimited use or pay $1.99 for each data they want(First purchase is $0.99 then $1.99). I was expecting more user to pay, but it was the complete opposite! Some users who would have paid a higher subscription fee are switching to a lower priced single payment. Users are encountering paywalls more often, and each time they need to make a decision about whether or not to pay, which increases the probability that they will abandon payment. This resulted in a 75% decrease in revenue in November. In fact, the mostly of my revenue comes from a handful of long-cycle subscribers, such as annual subscription. Few bring in most of the revenue, that is the most important thing I learned. You don't need a lot of customers, you just need more valuable ones. That's why it's only right to design a mechanism to filter out high-value customers and focus on them, all the things you want do is just let more people into the filter, and from that point of view, subscription with free trial period is the best way, even if most people don't like it. The rule of 20/80 will always be there. The most important thing is always focus on the 20 percent things and people. Effort does not always guarantee rewards. Unless one engages in deep thinking, or most efforts are invalid. I have been working very hard to promote my product for a period of time. It’s about in November. I did a lot of job, such as write script to send message to my potential clients on Fiverr, post and write comments on others post on Reddit, find related questions and answer them on Quora, post and comments on Twitte, etc. During that period, I was exhausted every day, but the outcome did not meet my expectations. There is only little growth on App installation, even less revenue than before. That make me frustrated. I finally realized that If I need to put in a tremendous amount of effort just to make a little progress, there is must something wrong. So I stop 80% of promote work I have ever did, only keep app store search ad, which will bring a installation with less than $0.5 cost. Then I dive into long time and deeply thinking, I spent more time on reading books, investigate other product with great MRR, watch interviews with people who are already living the kind of life I aspire to live, for example, u/levelsio. These things have given me great inspiration, and my life has become easier. It seems that the life I anticipated when I resigned is getting closer. I also have a clearer understanding of my app. Meanwhile, MRR has been growing. This experience let me learn that effort does not always guarantee results. Many times, our efforts are just wishful thinking, they are invalid, do the right thing after deeply thinking is more important. What Next? My goal is reach $3K MRR, as same as my job payment, I will never stop to building things, and I will keep my currently lifestyle. I still don't know how to get more people to use my app, but levelsio's interviews give me some inspiration that I can verified something by manually instead of build a software. I plan to launch a trend analysis product based on the keyword data provided by my current app. I have always wanted to combine AI to build such a product, but I didn't know how to do it. Now I intend to manually complete it first and start software development once there are paying users. If you are interested to my App, you could try it. Gotrends

Spent months patching no-code tools—built a full custom business app in 5 minutes with AI

Hey r/SideProject, I’ve spent months trying to patch together off-the-shelf tools and no-code platforms to create software for small businesses, but I kept running into the same problem—they just don’t fit how businesses actually work. That’s when I realized most small businesses need custom software tailored to their unique workflows, but the time and cost of building it from scratch are out of reach for most of them. So I decided to build a solution. Introducing Crust AI—a tool that lets SMB owners describe their exact needs, and in 5 minutes, it generates a fully functional app: client portals, employee hubs, vendor management systems—anything you need to streamline external collaboration. I went from wasting weeks stitching together no-code tools to having a zero-dev solution up and running in minutes. I’d love to hear your thoughts on it. If you’ve been in the same boat as me, check out trycrust.co and let me know what you think!

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 :)

I Quit My Tech Job 6 Months Ago. Built 10+ Products. Made $0. Here's Everything I Learned.

I quit my tech job 6 months ago to go full indie. Had enough savings and didn't want to miss the AI wave. Since then, I've built 10+ products - B2C, B2B, mobile apps, directories, marketplaces, you name it. But I keep repeating the same cycle: have an idea, dream big, build for weeks, "launch" (and by launch, I mean just deploy and go live with zero promotion), then get bored and lose motivation to market it. Then I start looking for new ideas to build. Is it just me, or does anyone else face something similar? Maybe coding is my comfort zone and marketing isn't, that's why... I knew entrepreneurship was hard, but it's MUCH harder than I thought. After these failures, here's everything I've learned: Lessons Learned The Hard Way Don't build something you don't have passion for. Pushing a product is hard and takes tremendous effort. If you don't have passion for it, you won't push through the initial "no interest" zone. Think carefully: would you be proud of what you build after building it? If yes, proceed. If not, don't waste time. Build your audience/network first. This isn't new advice, but it's 100% key for entrepreneurs to succeed. I'm still figuring this out, but one thing is clear: "Value" is the key. Stop posting random stuff and instead give value. People don't care about you and your life, but they do care about what you can offer them. Don't rush. Entrepreneurship isn't a sprint; it's a marathon. Don't rush to build stuff. Take a step back to think, plan, and learn. Coding for 16 hours a day won't do you any good - you'll end up building something people don't want. What I'm Doing Differently Next Time After all these failures, I finally took time with myself to think about how I can approach things differently. Here's my new plan: I will not start a new project if I know I'll ditch it after building it. I will follow best practices: validate the idea, research competitors, look for beta users, and ship fast. I will start building my audience and personal brand through documenting the journey. I've already decided what I'm building next, and yes, this time I'm going all in. I'll apply everything I've learned so far, and hopefully, this time will be different. Will update you all soon. Keep shipping, folks! Hopefully we'll see your "I reached 10k MRR for my SaaS" post soon.

12 months from idea to product - bootstrapping my own mobile app from 0

Introduction It has taken 12 months to develop an app that uses a camera to seamlessly detect fridge ingredients and generate recipes—solving the everyday problem I faced while traveling: "What should I cook for dinner today?" Although the end product has evolved from the initial concept, the ingredient detection feature remains one of the key elements that makes this app truly unique. When I started Keto, the biggest challenge I faced was tracking carbs, typically done through barcode scanning or manual searches. While Swifto offers both of these options, we are proud to introduce a feature that allows you to extract net carb values from a single image with just one click. We’ve combined AI with a great user experience to ensure that anyone embarking on their Keto journey can track their progress with ease. My Experience The app is now at a stage where I can truly seek market validation. Yes, this journey took me around 12 months, starting with the idea, creating the website, and developing the app's UI/UX and backend. At this point, many people might wonder: "Did you validate your idea before? Why create such a complex app without first understanding if there's a market need?" While this approach is undoubtedly risky and may not pay off in the future, I had a strong belief that this product could only be validated when people experienced how it works and saw how seamless the UX is compared to other similar apps. Would I Do It Again? Probably not. While developing the mobile app, I learned a lot about how mobile apps are advertised on the Google Play Store and how challenging it is to break into niche markets. You can develop the best application out there, but if no one sees it, it will never reach the top searches, which is crucial for any app's organic reach. I'll need to devise very creative strategies to gain the attention of those who truly matter for this product's validation and then go from there. However, it seems this will require much more effort than I initially anticipated. I'm open to any questions/suggestions.

[CASE STUDY] From 217/m to $2,836/m in 9 months - Sold for $59,000; I grow and monetise web traffic of 5, 6, 7 figures USD valued passive income content sites [AMA]

Hello Everyone (VERY LONG CASE STUDY AHEAD) - 355% return in 9 months Note: I own a 7-figures USD valued portfolio of 41+ content sites that generates 5-6 figures USD a month in passive income. This is my first time posting in this sub and my goal is to NOT share generic advice but precise numbers, data and highly refined processes so you can also get started with this business yourself or if you already have an existing business, drive huge traffic to it and scale it substantially (get more customers). I will use a case study to explain the whole process. As most of us are entrepreneurs here, explaining an actual project would be more meaningful. In this case study I used AI assisted content to grow an existing site from $217/m to $2,836/m in 9 months (NO BACKLINKS) and sold it for $59,000. ROI of 3 months: 355% Previous case studies (before I give an overview of the model) Amazon Affiliate Content Site: $371/m to $19,263/m in 14 MONTHS - $900K CASE STUDY \[AMA\] Affiliate Website from $267/m to $21,853/m in 19 months (CASE STUDY - Amazon?) \[AMA\] Amazon Affiliate Website from $0 to $7,786/month in 11 months Amazon Affiliate Site from $118/m to $3,103/m in 8 MONTHS (SOLD it for $62,000+) Note: You can check pinned posts on my profile. Do go through the comments as well as a lot of questions are answered in those. However, if you still have any questions, feel free to reach out. This is an \[AMA\]. Quick Overview of the Model Approach: High traffic, niche specific, informative content websites that monetise its traffic through highly automated methods like display ads and affiliate. The same model can be applied to existing businesses to drive traffic and get customers. Main idea: Make passive income in a highly automated way Easy to understand analogy You have real estate (here you have digital asset like a website) You get rental income (here you get ads and affiliate income with no physical hassle, in case you have a business like service, product etc. then you can get customers for that too but if not, it's alright) Real estate has value (this digital asset also has value that can be appreciated with less effort) Real estate can be sold (this can be sold too but faster) IMPORTANT NOTE: Search traffic is the BEST way to reach HUGE target audience and it's important when it comes to scaling. This essentially means that you can either monetise that via affiliate, display etc. or if you have a business then you can reach a bigger audience to scale. Overview of this website's valuation (then and now: Oct. 2022 and June 2023) Oct 2022: $217/m Valuation: $5,750.5 (26.5x) - set it the same as the multiple it was sold for June 2023: $2,836/m Traffic and revenue trend: growing fast Last 3 months avg: $2,223 Valuation now: $59,000 (26.5x) Description: The domain was registered in 2016, it grew and then the project was left unattended. I decided to grow it again using properly planned AI assisted content. Backlink profile: 500+ Referring domains (Ahrefs). Backlinks mean the sites linking back to you. This is important when it comes to ranking. Summary of Results of This Website - Before and After Note: If the terms seem technical, do not worry. I will explain them in detail later. Still if you have any questions. Feel free to comment or reach out. |Metric|Oct 2022|June 2023|Difference|Comments| |:-|:-|:-|:-|:-| |Articles|314|804|\+490|AI Assisted content published in 3 months| |Traffic|9,394|31,972|\+22,578|Organic| |Revenue|$217|$2,836|\+$2,619|Multiple sources| |RPM (revenue/1000 web traffic)|23.09|$88.7|\+$65.61|Result of Conversion rate optimisation (CRO). You make changes to the site for better conversions| |EEAT (expertise, experience, authority and trust of website)|2 main authors|8 authors|6|Tables, video ads and 11 other fixations| |CRO|Nothing|Tables, video ads |Tables, video ads and 11 other fixations || &#x200B; Month by Month Growth |Month|Revenue|Steps| |:-|:-|:-| |Sept 2022|NA|Content Plan| |Oct 2022|$217|Content Production| |Nov 2022|$243|Content production + EEAT authors| |Dec 2022|$320|Content production + EEAT authors| |Jan 2023|$400|Monitoring| |Feb 2023|$223|Content production + EEAT authors| |Mar 2023|$2,128|CRO & Fixations| |April 2023|$1,609|CRO & Fixations| |May 2023|$2,223|Content production + EEAT authors| |June 2023|$2,836|CRO and Fixations| |Total|$10,199|| &#x200B; What will I share Content plan and Website structure Content Writing Content Uploading, formatting and onsite SEO Faster indexing Conversion rate optimisation Guest Posting EEAT (Experience, Expertise, Authority, Trust) Costing ROI The plans moving forward with these sites &#x200B; Website Structure and Content Plan This is probably the most important important part of the whole process. The team spends around a month just to get this right. It's like defining the direction of the project. Description: Complete blueprint of the site's structure in terms of organisation of categories, subcategories and sorting of articles in each one of them. It also includes the essential pages. The sorted articles target main keyword, relevant entities and similar keywords. This has to be highly data driven and we look at over 100 variables just to get it right. It's like beating Google's algorithm to ensure you have a blueprint for a site that will rank. It needs to be done right. If there is a mistake, then even if you do everything right - it's not going to work out and after 8-16 months you will realise that everything went to waste. Process For this project, we had a niche selected already so we didn't need to do a lot of research pertaining to that. We also knew the topic since the website was already getting good traffic on that. We just validated from Ahrefs, SEMRUSH and manual analysis if it would be worth it to move forward with that topic. &#x200B; Find entities related to the topic: We used Ahrefs and InLinks to get an idea about the related entities (topics) to create a proper topical relevance. In order to be certain and have a better idea, we used ChatGPT to find relevant entities as well \> Ahrefs (tool): Enter main keyword in keywords explorer. Check the left pain for popular topics \> Inlinks (tool): Enter the main keyword, check the entity maps \> ChatGPT (tool): Ask it to list down the most important and relevant entities in order of their priority Based on this info, you can map out the most relevant topics that are semantically associated to your main topic Sorting the entities in topics (categories) and subtopics (subcategories): Based on the information above, cluster them properly. The most relevant ones must be grouped together. Each group must be sorted into its relevant category. \> Example: Site about cycling. \> Categories/entities: bicycles, gear and equipment, techniques, safety, routes etc. \> The subcategories/subentities for let's say "techniques" would be: Bike handling, pedaling, drafting etc. Extract keywords for each subcategory/subentity: You can do this using Ahrefs or Semrush. Each keyword would be an article. Ensure that you target the similar keywords in one article. For example: how to ride a bicycle and how can I ride a bicycle will be targeted by one article. Make the more important keyword in terms of volume and difficulty as the main keyword and the other one(s) as secondary Define main focus vs secondary focus: Out of all these categories/entities - there will be one that you would want to dominate in every way. So, focus on just that in the start. This will be your main focus. Try to answer ALL the questions pertaining to that. You can extract the questions using Ahrefs. \> Ahrefs > keywords explorer \> enter keyword \> Questions \> Download the list and cluster the similar ones. This will populate your main focus category/entity and will drive most of the traffic. Now, you need to write in other categories/subentities as well. This is not just important, but crucial to complete the topical map loop. In simple words, if you do this Google sees you as a comprehensive source on the topic - otherwise, it ignores you and you don't get ranked Define the URLs End result: List of all the entities and sub-entities about the main site topic in the form of categories and subcategories respectively. A complete list of ALL the questions about the main focus and at around 10 questions for each one of the subcategories/subentities that are the secondary focus Content Writing So, now that there's a plan. Content needs to be produced. Pick out a keyword (which is going to be a question) and... Answer the question Write about 5 relevant entities Answer 10 relevant questions Write a conclusion Keep the format the same for all the articles. Content Uploading, formatting and onsite SEO Ensure the following is taken care of: H1 Permalink H2s H3s Lists Tables Meta description Socials description Featured image 2 images in text \\Schema Relevant YouTube video (if there is) Note: There are other pointers link internal linking in a semantically relevant way but this should be good to start with. Faster Indexing Indexing means Google has read your page. Ranking only after this step has been done. Otherwise, you can't rank if Google hasn't read the page. Naturally, this is a slow process. But, we expedite it in multiple ways. You can use RankMath to quickly index the content. Since, there are a lot of bulk pages you need a reliable method. Now, this method isn't perfect. But, it's better than most. Use Google Indexing API and developers tools to get indexed. Rank Math plugin is used. I don't want to bore you and write the process here. But, a simple Google search can help you set everything up. Additionally, whenever you post something - there will be an option to INDEX NOW. Just press that and it would be indexed quite fast. Conversion rate optimisation Once you get traffic, try adding tables right after the introduction of an article. These tables would feature a relevant product on Amazon. This step alone increased our earnings significantly. Even though the content is informational and NOT review. This still worked like a charm. Try checking out the top pages every single day in Google analytics and add the table to each one of them. Moreover, we used EZOIC video ads as well. That increased the RPM significantly as well. Both of these steps are highly recommended. Overall, we implemented over 11 fixations but these two contribute the most towards increasing the RPM so I would suggest you stick to these two in the start. Guest Posting We made additional income by selling links on the site as well. However, we were VERY careful about who we offered a backlink to. We didn't entertain any objectionable links. Moreover, we didn't actively reach out to anyone. We had a professional email clearly stated on the website and a particularly designated page for "editorial guidelines" A lot of people reached out to us because of that. As a matter of fact, the guy who bought the website is in the link selling business and plans to use the site primarily for selling links. According to him, he can easily make $4000+ from that alone. Just by replying to the prospects who reached out to us. We didn't allow a lot of people to be published on the site due to strict quality control. However, the new owner is willing to be lenient and cash it out. EEAT (Experience, Expertise, Authority, Trust) This is an important ranking factor. You need to prove on the site that your site has authors that are experienced, have expertise, authority and trust. A lot of people were reaching out to publish on our site and among them were a few established authors as well. We let them publish on our site for free, added them on our official team, connected their socials and shared them on all our socials. In return, we wanted them to write 3 articles each for us and share everything on all the social profiles. You can refer to the tables I shared above to check out the months it was implemented. We added a total of 6 writers (credible authors). Their articles were featured on the homepage and so were their profiles. Costing Well, we already had the site and the backlinks on it. Referring domains (backlinks) were already 500+. We just needed to focus on smart content and content. Here is the summary of the costs involved. Articles: 490 Avg word count per article: 1500 Total words: 735,000 (approximately) Cost per word: 2 cents (includes research, entities, production, quality assurance, uploading, formatting, adding images, featured image, alt texts, onsite SEO, publishing/scheduling etc.) Total: $14,700 ROI (Return on investment) Earning: Oct 22 - June 23 Earnings: $10,199 Sold for: $59,000 Total: $69,199 Expenses: Content: $14,700 Misc (hosting and others): $500 Total: $15,200 ROI over a 9 months period: 355.25% The plans moving forward This website was a part of a research and development experiment we did. With AI, we wanted to test new waters and transition more towards automation. Ideally, we want to use ChatGPT or some other API to produce these articles and bulk publish on the site. The costs with this approach are going to be much lower and the ROI is much more impressive. It's not the the 7-figures projects I created earlier (as you may have checked the older case studies on my profile), but it's highly scalable. We plan to refine this model even further, test more and automate everything completely to bring down our costs significantly. Once we have a model, we are going to scale it to 100s of sites. The process of my existing 7-figures websites portfolio was quite similar. I tested out a few sites, refined the model and scaled it to over 41 sites. Now, the fundamentals are the same however, we are using AI in a smarter way to do the same but at a lower cost, with a smaller team and much better returns. The best thing in my opinion is to run numerous experiments now. Our experimentation was slowed down a lot in the past since we couldn't write using AI but now it's much faster. The costs are 3-6 times lower so when it used to take $50-100k to start, grow and sell a site. Now you can pump 3-6 more sites for the same budget. This is a good news for existing business owners as well who want to grow their brand. Anyway, I am excited to see the results of more sites. In the meantime, if you have any questions - feel free to let me know. Best of luck for everything. Feel free to ask questions. I'd be happy to help. This is an AMA.

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 :)

I just sold my startup for $200,000 after 11 months. AMA

Last August, I was looking for a startup idea I could grow and made a MVP in a week then launched it. I received the $200,000 wire from the buyer a couple of days ago I found tons of useful info online for free, so I hope this can be my way of giving back :) Here is some background: Idea I got the idea when trying to write a tweet using Google Doc's transcription tool, which was terrible. I was pretty sure I wasn't the only one too lazy to type, I made my own solution using AI to transcribe and reformat voice notes into any kind of content. I called it Talknotes, mainly because it was the only domain available lol Validation: My rule is to only reinvest what the project generates. After listing on startup directories and posting on Twitter, I generated $700 in 10 days. It wasn't much, but enough to show interest and keep me motivated. I added user-requested features, but the launch effect wore off, and daily revenues dropped to $0 after a few weeks. I almost gave up, but friends encouraged me to continue. In October, I launched on ProductHunt and it blew up. It became Product of the Day and reached $1500 MRR thanks to media coverage. I initially built everything using vanilla JS/CSS/HTML + Node for backend. But it's pretty limited for apps with lots of interactivity so, I rebuilt the app using Nuxt.js to make it easier to ship new features. Then, I launched ads on Facebook and I implemented a feedback loop: Get new users Learn about them through onboarding Make more ads based on onboarding data This doubled MRR in about 2 months. Burnout and Sale: In May, I had a bad burnout after emergency bug fixes. This made it hard to work on the app after. At this point MRR was around $7000 and total revenues around $70,0000 I listed it on Acquire.com for $200,000, a very good price for the buyer considering revenues and growth. I could've gotten $300,000 with buyer financing or earn-outs, but I wanted cash, $200,000 today is better than $300,000 in a year. Everything was smooth until we tried using Escrow, which almost fucked up the deal (details here). Long story short, had to threaten them to make a sponsored post on Twitter explaining what they did + legal action. They sent the refund the very next day, and we completed the transfer directly. Now, this isn't an overnight success. It's the result of 7 years of grind. I launched over 40 projects since I started, and most of them failed. I often worked 100 hours per week, and I rarely go out or meet many people. It's not for everyone, but I'm fine with it With the profit from the app + sale, and other projects, I have close to 1/3 of a million dollar. I could retire in Asia if I wanted Just mind blowing to think I wrote funny characters in a code editor and sold it for the price of a house lol Edit 1: A few people got confused. I said it's 7 years of grind and most of my projects failed, not that I was not making money. I also said I OFTEN worked 100h/week, not every week :) Since I learned to code 2 years ago I've made close to $400k from my app's profit + exit (this one + another one for $65k last year). And before that I was making money as a marketing freelancer. Also, I dropped after high-school, so, I had to learn everything from scratch, it takes time! Edit 2: Lots of people asked how/where I learned to code in 2 months. I wrote a blog/journal about it back then with links to resources, you can find it here if you're interested

I Quit My Tech Job 6 Months Ago. Built 10+ Products. Made $0. Here's Everything I Learned.

I quit my tech job 6 months ago to go full indie. Had enough savings and didn't want to miss the AI wave. Since then, I've built 10+ products - B2C, B2B, mobile apps, directories, marketplaces, you name it. But I keep repeating the same cycle: have an idea, dream big, build for weeks, "launch" (and by launch, I mean just deploy and go live with zero promotion), then get bored and lose motivation to market it. Then I start looking for new ideas to build. Is it just me, or does anyone else face something similar? Maybe coding is my comfort zone and marketing isn't, that's why... I knew entrepreneurship was hard, but it's MUCH harder than I thought. After these failures, here's everything I've learned: Lessons Learned The Hard Way Don't build something you don't have passion for. Pushing a product is hard and takes tremendous effort. If you don't have passion for it, you won't push through the initial "no interest" zone. Think carefully: would you be proud of what you build after building it? If yes, proceed. If not, don't waste time. Build your audience/network first. This isn't new advice, but it's 100% key for entrepreneurs to succeed. I'm still figuring this out, but one thing is clear: "Value" is the key. Stop posting random stuff and instead give value. People don't care about you and your life, but they do care about what you can offer them. Don't rush. Entrepreneurship isn't a sprint; it's a marathon. Don't rush to build stuff. Take a step back to think, plan, and learn. Coding for 16 hours a day won't do you any good - you'll end up building something people don't want. What I'm Doing Differently Next Time After all these failures, I finally took time with myself to think about how I can approach things differently. Here's my new plan: I will not start a new project if I know I'll ditch it after building it. I will follow best practices: validate the idea, research competitors, look for beta users, and ship fast. I will start building my audience and personal brand through documenting the journey. I've already decided what I'm building next, and yes, this time I'm going all in. I'll apply everything I've learned so far, and hopefully, this time will be different. Will update you all soon. Keep shipping, folks! Hopefully we'll see your "I reached 10k MRR for my SaaS" post soon.

[CASE STUDY] From 217/m to $2,836/m in 9 months - Sold for $59,000; I grow and monetise web traffic of 5, 6, 7 figures USD valued passive income content sites [AMA]

Hello Everyone (VERY LONG CASE STUDY AHEAD) - 355% return in 9 months Note: I own a 7-figures USD valued portfolio of 41+ content sites that generates 5-6 figures USD a month in passive income. This is my first time posting in this sub and my goal is to NOT share generic advice but precise numbers, data and highly refined processes so you can also get started with this business yourself or if you already have an existing business, drive huge traffic to it and scale it substantially (get more customers). I will use a case study to explain the whole process. As most of us are entrepreneurs here, explaining an actual project would be more meaningful. In this case study I used AI assisted content to grow an existing site from $217/m to $2,836/m in 9 months (NO BACKLINKS) and sold it for $59,000. ROI of 3 months: 355% Previous case studies (before I give an overview of the model) Amazon Affiliate Content Site: $371/m to $19,263/m in 14 MONTHS - $900K CASE STUDY \[AMA\] Affiliate Website from $267/m to $21,853/m in 19 months (CASE STUDY - Amazon?) \[AMA\] Amazon Affiliate Website from $0 to $7,786/month in 11 months Amazon Affiliate Site from $118/m to $3,103/m in 8 MONTHS (SOLD it for $62,000+) Note: You can check pinned posts on my profile. Do go through the comments as well as a lot of questions are answered in those. However, if you still have any questions, feel free to reach out. This is an \[AMA\]. Quick Overview of the Model Approach: High traffic, niche specific, informative content websites that monetise its traffic through highly automated methods like display ads and affiliate. The same model can be applied to existing businesses to drive traffic and get customers. Main idea: Make passive income in a highly automated way Easy to understand analogy You have real estate (here you have digital asset like a website) You get rental income (here you get ads and affiliate income with no physical hassle, in case you have a business like service, product etc. then you can get customers for that too but if not, it's alright) Real estate has value (this digital asset also has value that can be appreciated with less effort) Real estate can be sold (this can be sold too but faster) IMPORTANT NOTE: Search traffic is the BEST way to reach HUGE target audience and it's important when it comes to scaling. This essentially means that you can either monetise that via affiliate, display etc. or if you have a business then you can reach a bigger audience to scale. Overview of this website's valuation (then and now: Oct. 2022 and June 2023) Oct 2022: $217/m Valuation: $5,750.5 (26.5x) - set it the same as the multiple it was sold for June 2023: $2,836/m Traffic and revenue trend: growing fast Last 3 months avg: $2,223 Valuation now: $59,000 (26.5x) Description: The domain was registered in 2016, it grew and then the project was left unattended. I decided to grow it again using properly planned AI assisted content. Backlink profile: 500+ Referring domains (Ahrefs). Backlinks mean the sites linking back to you. This is important when it comes to ranking. Summary of Results of This Website - Before and After Note: If the terms seem technical, do not worry. I will explain them in detail later. Still if you have any questions. Feel free to comment or reach out. |Metric|Oct 2022|June 2023|Difference|Comments| |:-|:-|:-|:-|:-| |Articles|314|804|\+490|AI Assisted content published in 3 months| |Traffic|9,394|31,972|\+22,578|Organic| |Revenue|$217|$2,836|\+$2,619|Multiple sources| |RPM (revenue/1000 web traffic)|23.09|$88.7|\+$65.61|Result of Conversion rate optimisation (CRO). You make changes to the site for better conversions| |EEAT (expertise, experience, authority and trust of website)|2 main authors|8 authors|6|Tables, video ads and 11 other fixations| |CRO|Nothing|Tables, video ads |Tables, video ads and 11 other fixations || &#x200B; Month by Month Growth |Month|Revenue|Steps| |:-|:-|:-| |Sept 2022|NA|Content Plan| |Oct 2022|$217|Content Production| |Nov 2022|$243|Content production + EEAT authors| |Dec 2022|$320|Content production + EEAT authors| |Jan 2023|$400|Monitoring| |Feb 2023|$223|Content production + EEAT authors| |Mar 2023|$2,128|CRO & Fixations| |April 2023|$1,609|CRO & Fixations| |May 2023|$2,223|Content production + EEAT authors| |June 2023|$2,836|CRO and Fixations| |Total|$10,199|| &#x200B; What will I share Content plan and Website structure Content Writing Content Uploading, formatting and onsite SEO Faster indexing Conversion rate optimisation Guest Posting EEAT (Experience, Expertise, Authority, Trust) Costing ROI The plans moving forward with these sites &#x200B; Website Structure and Content Plan This is probably the most important important part of the whole process. The team spends around a month just to get this right. It's like defining the direction of the project. Description: Complete blueprint of the site's structure in terms of organisation of categories, subcategories and sorting of articles in each one of them. It also includes the essential pages. The sorted articles target main keyword, relevant entities and similar keywords. This has to be highly data driven and we look at over 100 variables just to get it right. It's like beating Google's algorithm to ensure you have a blueprint for a site that will rank. It needs to be done right. If there is a mistake, then even if you do everything right - it's not going to work out and after 8-16 months you will realise that everything went to waste. Process For this project, we had a niche selected already so we didn't need to do a lot of research pertaining to that. We also knew the topic since the website was already getting good traffic on that. We just validated from Ahrefs, SEMRUSH and manual analysis if it would be worth it to move forward with that topic. &#x200B; Find entities related to the topic: We used Ahrefs and InLinks to get an idea about the related entities (topics) to create a proper topical relevance. In order to be certain and have a better idea, we used ChatGPT to find relevant entities as well \> Ahrefs (tool): Enter main keyword in keywords explorer. Check the left pain for popular topics \> Inlinks (tool): Enter the main keyword, check the entity maps \> ChatGPT (tool): Ask it to list down the most important and relevant entities in order of their priority Based on this info, you can map out the most relevant topics that are semantically associated to your main topic Sorting the entities in topics (categories) and subtopics (subcategories): Based on the information above, cluster them properly. The most relevant ones must be grouped together. Each group must be sorted into its relevant category. \> Example: Site about cycling. \> Categories/entities: bicycles, gear and equipment, techniques, safety, routes etc. \> The subcategories/subentities for let's say "techniques" would be: Bike handling, pedaling, drafting etc. Extract keywords for each subcategory/subentity: You can do this using Ahrefs or Semrush. Each keyword would be an article. Ensure that you target the similar keywords in one article. For example: how to ride a bicycle and how can I ride a bicycle will be targeted by one article. Make the more important keyword in terms of volume and difficulty as the main keyword and the other one(s) as secondary Define main focus vs secondary focus: Out of all these categories/entities - there will be one that you would want to dominate in every way. So, focus on just that in the start. This will be your main focus. Try to answer ALL the questions pertaining to that. You can extract the questions using Ahrefs. \> Ahrefs > keywords explorer \> enter keyword \> Questions \> Download the list and cluster the similar ones. This will populate your main focus category/entity and will drive most of the traffic. Now, you need to write in other categories/subentities as well. This is not just important, but crucial to complete the topical map loop. In simple words, if you do this Google sees you as a comprehensive source on the topic - otherwise, it ignores you and you don't get ranked Define the URLs End result: List of all the entities and sub-entities about the main site topic in the form of categories and subcategories respectively. A complete list of ALL the questions about the main focus and at around 10 questions for each one of the subcategories/subentities that are the secondary focus Content Writing So, now that there's a plan. Content needs to be produced. Pick out a keyword (which is going to be a question) and... Answer the question Write about 5 relevant entities Answer 10 relevant questions Write a conclusion Keep the format the same for all the articles. Content Uploading, formatting and onsite SEO Ensure the following is taken care of: H1 Permalink H2s H3s Lists Tables Meta description Socials description Featured image 2 images in text \\Schema Relevant YouTube video (if there is) Note: There are other pointers link internal linking in a semantically relevant way but this should be good to start with. Faster Indexing Indexing means Google has read your page. Ranking only after this step has been done. Otherwise, you can't rank if Google hasn't read the page. Naturally, this is a slow process. But, we expedite it in multiple ways. You can use RankMath to quickly index the content. Since, there are a lot of bulk pages you need a reliable method. Now, this method isn't perfect. But, it's better than most. Use Google Indexing API and developers tools to get indexed. Rank Math plugin is used. I don't want to bore you and write the process here. But, a simple Google search can help you set everything up. Additionally, whenever you post something - there will be an option to INDEX NOW. Just press that and it would be indexed quite fast. Conversion rate optimisation Once you get traffic, try adding tables right after the introduction of an article. These tables would feature a relevant product on Amazon. This step alone increased our earnings significantly. Even though the content is informational and NOT review. This still worked like a charm. Try checking out the top pages every single day in Google analytics and add the table to each one of them. Moreover, we used EZOIC video ads as well. That increased the RPM significantly as well. Both of these steps are highly recommended. Overall, we implemented over 11 fixations but these two contribute the most towards increasing the RPM so I would suggest you stick to these two in the start. Guest Posting We made additional income by selling links on the site as well. However, we were VERY careful about who we offered a backlink to. We didn't entertain any objectionable links. Moreover, we didn't actively reach out to anyone. We had a professional email clearly stated on the website and a particularly designated page for "editorial guidelines" A lot of people reached out to us because of that. As a matter of fact, the guy who bought the website is in the link selling business and plans to use the site primarily for selling links. According to him, he can easily make $4000+ from that alone. Just by replying to the prospects who reached out to us. We didn't allow a lot of people to be published on the site due to strict quality control. However, the new owner is willing to be lenient and cash it out. EEAT (Experience, Expertise, Authority, Trust) This is an important ranking factor. You need to prove on the site that your site has authors that are experienced, have expertise, authority and trust. A lot of people were reaching out to publish on our site and among them were a few established authors as well. We let them publish on our site for free, added them on our official team, connected their socials and shared them on all our socials. In return, we wanted them to write 3 articles each for us and share everything on all the social profiles. You can refer to the tables I shared above to check out the months it was implemented. We added a total of 6 writers (credible authors). Their articles were featured on the homepage and so were their profiles. Costing Well, we already had the site and the backlinks on it. Referring domains (backlinks) were already 500+. We just needed to focus on smart content and content. Here is the summary of the costs involved. Articles: 490 Avg word count per article: 1500 Total words: 735,000 (approximately) Cost per word: 2 cents (includes research, entities, production, quality assurance, uploading, formatting, adding images, featured image, alt texts, onsite SEO, publishing/scheduling etc.) Total: $14,700 ROI (Return on investment) Earning: Oct 22 - June 23 Earnings: $10,199 Sold for: $59,000 Total: $69,199 Expenses: Content: $14,700 Misc (hosting and others): $500 Total: $15,200 ROI over a 9 months period: 355.25% The plans moving forward This website was a part of a research and development experiment we did. With AI, we wanted to test new waters and transition more towards automation. Ideally, we want to use ChatGPT or some other API to produce these articles and bulk publish on the site. The costs with this approach are going to be much lower and the ROI is much more impressive. It's not the the 7-figures projects I created earlier (as you may have checked the older case studies on my profile), but it's highly scalable. We plan to refine this model even further, test more and automate everything completely to bring down our costs significantly. Once we have a model, we are going to scale it to 100s of sites. The process of my existing 7-figures websites portfolio was quite similar. I tested out a few sites, refined the model and scaled it to over 41 sites. Now, the fundamentals are the same however, we are using AI in a smarter way to do the same but at a lower cost, with a smaller team and much better returns. The best thing in my opinion is to run numerous experiments now. Our experimentation was slowed down a lot in the past since we couldn't write using AI but now it's much faster. The costs are 3-6 times lower so when it used to take $50-100k to start, grow and sell a site. Now you can pump 3-6 more sites for the same budget. This is a good news for existing business owners as well who want to grow their brand. Anyway, I am excited to see the results of more sites. In the meantime, if you have any questions - feel free to let me know. Best of luck for everything. Feel free to ask questions. I'd be happy to help. This is an AMA.

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.

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.

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.

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!

I just had my best month after 18 months as a solopreneur

Last month I reached important milestones both financially (60+ sales) and in terms of my personal brand (2.500+ new followers) But the most important part is that it has reinforced a belief in myself: it is possible, as long as I keep going, improving, learning and iterating. For the last year and a half, I've been grinding and launching project after project. But there was always something wrong: Product didn't solve a real problem Bad marketing (very often lol) Target market had low purchasing power Super-competitive niche (usually b2c) It's difficult to have failure after failure and keep going on. At times it would feel like everyone was making money, except for me. I was hacking on my projects every single day before and after my 9-5 and had mostly given up all my free time for this. But results were far from being what I wanted. So I would doubt myself all the time. One thing I had going for me is that I really enjoy building things - so that helped me a lot in staying consistent. I always knew this was a long-term thing and that I'd probably have to fail again and again before seeing some success. But even so, it was really hard to keep up the spirits at all time, especially after working so hard for so long. I wasn't going to give up but I also knew that continuing like this would lead nowhere. So I decided that for my next project I would do 2 things: 1) prioritize marketing and 2) build something strategic 1) Prioritize marketing I decided I was going to put in the same amount of effort into marketing as I put into building. Usually my time would be split 90% coding - 10% marketing. Now, for the first time ever it's probably 65% coding - 35% marketing. I organized myself and made an entire gameplan for it. This forced me to learn a lot about: Video editing Cold emails Copywriting Running ads Short-form content There are a lot of items I still need to execute on - but at least I have a good idea of how to approach most things. 2) Build something strategic I had to build something that I would be able to use even if nobody else did. For the last year and a half I had been building AI apps and my plan was to continue doing that. So I decided to leverage that and thought about how I could build something that would give me an unfair advantage + have a compounding effect over the long term: a) Unfair advantage Having AI demo apps that cover all type of AI functionalities would make my life easier & would allow me to ship new apps quickly, regardless of the required model/functionality So even if nobody bought this - I'd have built something really useful for myself & would have a slight edge over other people b) Compound over the long term Building "AnotherWrapper' (my new project) would have a good synergy with my future projects: It would allow me to build new projects faster While building new projects, I'd learn new things, which I would then be able to implement into AnotherWrapper and improve the product that way A win-win. Closing thoughts I did not expect things to go this well - it's been an amazing month and I'm truly grateful to everyone that has been supporting me. But at the end of the day, there is still a lot of work to be done. The initial 'hype' & effects from some viral tweets are starting to wear off. I still don't have a reliable distribution channel that guarantees me traffic. So I need to figure that out. I think the product has a lot of potential - it has been well received and has been a success so far, but my distribution is still lacking. The good thing is that I now have some extra cash to spend on things like ads, influencers, freelancers etc. So it opens some new doors that were previously closed! I also have some other projects down the pipeline which are coming soon. Will keep you guys updated!

I have developed targethub.ai for 2 months as a side project, need your thoughts

Hello everyone, I have built https://targethub.ai to give my children the tools I wished I had at the start of my career and entrepreneurship journey. Now, I’m sharing that same framework with you, so you can transform your ambitions into measurable achievements. Whether you’re a student tackling challenging coursework, a professional climbing the career ladder, an entrepreneur driving innovative business ideas, a startuper disrupting traditional models, an influencer expanding your personal brand, or a blogger turning creative passion into consistent results, Targethub.ai is tailored for you. My AI-powered platform combines proven strategies with real-world insights to empower you to: • Break down complex goals into clear, actionable steps • Strategically plan and execute academic, professional, or personal projects • Maintain focus and track progress using advanced, user-friendly tools • Receive personalized guidance that evolves with your needs Check and advise please your thoughts targethub.ai

I have been applying for my first machine learning full-time job in Germany for past 4-5 months, but now I have just graduated and I am still not getting a single e-mail for next round. I would really appreciate feedback on my resume. I am mostly applying for CV or MLOps roles but also ML/AI Eng/Dev

$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.

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.

How I made a high tech salary in my first selling month

For over 7 years I worked as a full-stack developer, helping other companies bring their ideas to life. But one day, I thought “Why not try making my own dream come true?”. That’s when I decided to quit my job and start my own journey to becoming an entrepreneur. At first, it wasn’t easy. I didn’t make any money for months and had no idea where to start. I felt lost. Then, I decided to focus on something popular and trending. AI was everywhere, and ChatGPT was the most used AI platform. So I looked into it and I found the OpenAI community forum where people had been asking for features that weren’t being added. That gave me an idea. Why not build those features myself? I created a Chrome extension and I worked on some of the most requested features, like: Downloading the advanced voice mode and messages as MP3 Adding folders to organize chats Saving and reusing prompts Pinning important chats Exporting chats to TXT/JSON files Deleting or archiving multiple chats at once Making chat history searches faster and better It took me about a week to build the first version, and when I published it, the response was incredible. People loved it! Some even said things like, “You’re a lifesaver!” That’s when I realized I had something that could not only help people but also turn into a real business. I kept the first version free to see how people would respond. Many users have been downloading my extension, which prompted Chrome to review it to determine if it qualified for the featured badge. I received the badge, and it has significantly boosted traffic to my extension ever since. After all the positive feedback, I launched a paid version one month ago. A few minutes after publishing it, I made my first sale! That moment was so exciting, and it motivated me to keep going. I already have over 4,000 users and have made more than $4,500 in my first selling month. I’ve decided to release 1-2 new features every month to keep improving the extension based on what users ask for. I also created the same extension for Firefox and Edge users because many people have been asking for it! I also started a Reddit community, where I share updates, sales, discount codes, and ideas for new features. It’s been awesome to connect with users directly and get their feedback. Additionally, I’ve started working on another extension for Claude, which I’m hoping will be as successful as this one. My message to you is this: never give up on your dreams. It might feel impossible at first, but with patience, hard work, and some creativity, you can make it happen. I hope this inspires you to go after what you want. Good luck to all of us!

Are no-code tools actually slowing down startups?

I've noticed a concerning trend: while no-code tools promise quick launches for startups, many founders end up rebuilding their entire product from scratch later. Meanwhile, established platforms for startups like Zapier are doubling their prices, pushing teams to reconsider their stack entirely. What I'm seeing in the market: Bubble/FlutterFlow promise "build Uber in weeks" Make. com offers Zapier various automation features, but they are expensive, which made me look for alternatives. AI tools like Cursor + Claude claim to replace coding skills Traditional coding still takes 6+ months to learn basics Successful startups often rebuild their no-code MVPs Here's what makes me wonder: are we choosing speed over sustainability? Edit: I'm so happy that my post sparked so many beautiful minds. I'm going to process all the insights you've shared and publish on my subreddit, because one just can't lose it on the Internet

I'm a dev with zero fucking ideas. Help?

Long-time lurker, first-time poster here. I'm hoping you guys can help me out. I consider myself an above average engineer. With over 8 years of industry experience, I can whip out an MVP fast and iterate quickly. I love coding and learning new tech, but here's the issue—I've got absolutely no clue what to build. It's like I'm the least creative person I know, and can't find even one problem to solve. I've tried everything I can think of: Scrolling through ProductHunt until my eyes bled Asking non-tech friends about their "pain points" Stalking Twitter/X to see what people are building Experimenting with new AI tech to explore possibilities I've even attempted to build products. Almost 6 months ago, I started working on an AI conversation app to help non-native speakers like myself improve their English. But I soon realized there were already hundreds of apps doing this, and doing it much better than I could. I abandoned the project, figuring it wasn't unique enough. Same story with a couple of other projects that I started working on and abandoned later. So my question is how the heck you all come up with ideas? Any advice, commiseration, or hell—even random ideas you don’t want to build—would be greatly appreciated.

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)

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.

$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.

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)

Upselling from $8/mo to $2k/mo

I just closed a client for $1947/mo. But 5 months ago he was spending only $8/mo. Most customers have way more purchasing power than you think. Unlock it with the power of stacking. Here's my 3-steps stacking formula: Step 1 - Build trust with a low-ticket product In a world full of scams and deceit, building trust is damn hard. The best way to combat skepticism is through a free or low-ticket product, where you can go above and beyond to demonstrate your credibility. When I first onboarded this client onto my SaaS, an AI to help you with HARO link-building, my product was at a very early stage with many rough edges. He gave me lots of great feedback. I implemented his suggestions the same day and got more feedback from him. After a couple of back-and-forths, I established myself as a trustworthy hustler, instead of just a stranger online. This is easy to do for an agile startup but impossible for big companies, so make good use of opportunities like this to build long-term relationships. Turn your customers into raving fans. Step 2 - Validate a mid-ticket offer Three months into his subscription, he told me he wanted to cancel. When digging into the why, he suggested a performance-based DFY service to remove all the work on his end. Inspired by his suggestion, I took on him and 6 other clients for $237, a one-time package for 1 backlink. It's sold through my newsletter email blast to 300 subscribers, with a total CAC of $0. I wrote about the details of this launch in another long form. At this price range, impulsive purchases can still happen if you have a strong offer and good copywriting. Use this mid-ticket offer to validate your offer and positioning, build out a team, and establish trust. We went beyond the 1 link for almost all our clients, including this one in particular. For $237, we got him on Forbes, HubSpot, 2 DR50+ sites, and a few other smaller media outlets. By doing this, we further built trust into the relationship and established authority in what we do. Step 3 - Create a high-ticket subscription-based offer By now, you'll hopefully have built enough trust to get through the skepticism filter for something high-ticket. Now, it's time to develop an offer that amplifies your previous one. Something that allows you to let your clients achieve their goals to the maximum extent. For me, this is pitching every relevant media query on every platform for this client every day, to leverage HARO link-building to its full extent, all for a fixed price of $1947/mo. This customized offer is based on direct client feedback, isn't publicized on our website, but we're confident it will directly contribute to achieving this client's goal. A subscription-based offer is much superior because it allows you to create a stable source of revenue, especially at the early stage. That's how I created 3 different offers to solve the same problem for one client. By stacking each offer on top of the previous one, I was able to guide clients from one option to the next. This formula isn't some new rocket science I came up with. It's proven over and over again by other agency owners building in public, like Nick from Baked Design who started with a $9 design kit and now sells $9k/mo design subscriptions at $1M ARR. By stacking offers, you position yourself as a committed partner in your client's long-term success. Lastly, I want to address a common objection: "My customers can't afford $2k/month." But consider this: most people are reading your site on their $3000 MacBook or $1000 iPhone. It's not that they lack the funds, it's more likely that your service isn't meeting their expectations. Talk to them to discover the irresistible offer they'll gladly pay for. Update: lots of DM asking about more specifics so I wrote about it here. https://coldstartblueprint.com/p/ai-agent-email-list-building

New to Startups; Where do I start?

I have an idea for an specialized AI based software system in a particular market that I think, if done well, could be a very helpful and lucrative software/AI (both for its owners as well as its users). It hasn't been properly implemented into any form that I or my associates have been able to find and I believe that now is the perfect time to start its development. I'm an entrepreneur, have started several successful companies over the years and am well experienced in all things business. But, none of my companies have involved creating a brand new product or would fall into the "Startup" category. It's a whole new world to me. That being said, I'm not sure what the proper steps are to make this idea come to fruition and am hoping for a point in the right direction. How do people usually go from idea to launch? I imagine there are 2 distinct things I need right now, funding for the project and a partner to help create the software. Step 1 would be the partner. For this partner, I'm not sure where to start to find this person. I'd imagine I need someone that's experienced in machine learning, AI engineering, software development, programming, etc. Or a combination of people with those skills. Since none of my companies are startup or tech based, I don't have connections to anyone with those skills. If I go around looking for a partner with those skills, I'll surely need to explain my idea to them and will need to be able to protect my idea before hand. Do I copyright it? Make them sign an NDA? What's common business practice? Where do I go to look for a partner with those skills? For funding, I can fund the initial stages of the project for a handful of months. From there, I'd like to find some kind of investment. But that sounds like a bridge to cross when I get further down that road. Looking forward to starting down this road and hopefully making something that benefits and pushes forward this new world of AI!

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.

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.

The #1 Mistake Entrepreneurs Make – And How to Avoid It Before Launching Your Startup (I will not promote)

Why So Many Startups Fail Before They Even Begin A huge number of early-stage entrepreneurs fall into the same trap: They get excited about their idea but don’t validate if the market actually wants it. They invest time and money building something nobody will pay for. They focus on execution first instead of proof of demand. By the time reality hits, they’ve burned months (or years) and thousands of dollars—just to learn the hard way that they started wrong. How do we prevent this? What’s the best way to validate a business idea before wasting resources? According to your unique experiences, what’s the Smartest Way to Validate a Startup Idea? I’ve been working on new approaches to validation that combine: ✔ AI-powered feasibility analysis to assess business potential instantly. ✔ Market research frameworks that help test demand before launching. ✔ Lean execution models that prevent unnecessary risk. But I want to hear from you: How did YOU validate your startup idea before launching? What methods have actually worked to confirm demand? What’s one mistake you made in your early-stage startup that others can avoid? The best insights come from real founders who’ve been in the trenches. Let’s break down what actually works. Drop your thoughts below! 👇 (I will not promote).

Competing with much bigger companies that have lame products? How do I market and carve out a niche? (I will not promote)

I've been working on a product for the last few months that competes with CapCut, Adobe Premier, Veed, Descript, DaVinci Resolve, etc. Basically, it's a fancy video editor. (no link and I will not promote but just some background context) I'm very technical and started creating videos for TikTok but really wanted to take my game to the next level. My channel sort of blew up on me in the first month and I was able to get 2M views and 10k followers. My initial thinking was that I was going to use AI to make video editing fancy/faster and sort of have this as a "script" that I used personally. Basically, give myself a serious competitive advantage. However, it sort of spiraled out of control! What started off as a weekend project, turned into 2 weekends, which turned into about 2 months of continuous hacking. If I'm going to spend a significant amount of time on this, I might as well try to productize it and try to at least make enough money that I break even on my time. The thing I'm worried about, in the back of my mind, is that if I shop this, that my competitors, with their signifiant resources, could clone what I'm doing quickly. However, at the same time, why haven't they done so already? I mean maybe I have a better understanding of the market than they do because they don't actually use their products. I know that sounds like a bit of a cop out in a way but there are plenty of entrepreneurs who have started companies and crushed it just because they were heads down and focused. Another problem I face, is that I think VCs may not be super excited about this because it's B2C-ish and it's not in a super exciting space. Maybe you could say it's in the AI video space, and they're excited about AI video, but it's just an AI video editor, not fully creating AI videos from scratch like SORA. I think since I blew up my TikTok feed before, that I could do it again, and if I get 2M views, and I have a outro on my video, that I could start to convert some of these as customers. Especially, if I started to create videos for creators which is more focused on the target market. So without funding, can I really tackle these existing competitors? PS. "I will not promote" but I have to talk about this somewhat abstractly but I won't link to anything.

People are overthinking with digital products.

All you really need is a checkout link to start. I failed a lot of times. Literally I could build the whole landing page, admin panel, ai automation to handle moderation and content. After spending months in vacuum building more, more, more features. Launching and getting 0 customers in the end. You are literally just getting depressed. You know that feeling, right ? Me too. We missed one important step before building anything - ASKING. We need to ask more clients, users, and do our research based on Google Keywords, forums and subreddits. You probably won't do it. It is your choice. You have all rights to do it. Let me give one piece of advice, instead of building more features and spendings months on your MVP. Set a deadline in 2-4 weeks. Build it, launch it, and go live as soon as possible. You need to get a real feedback and face a reality. Most of the companies that you see, started with simple Excel file, Google Doc, or even paper with pen. Do you know why ? Because they didn't have anything in the beginning. No money, no customers, NOTHING. Remember that.

How I made a high tech salary in my first selling month

For over 7 years I worked as a full-stack developer, helping other companies bring their ideas to life. But one day, I thought “Why not try making my own dream come true?”. That’s when I decided to quit my job and start my own journey to becoming an entrepreneur. At first, it wasn’t easy. I didn’t make any money for months and had no idea where to start. I felt lost. Then, I decided to focus on something popular and trending. AI was everywhere, and ChatGPT was the most used AI platform. So I looked into it and I found the OpenAI community forum where people had been asking for features that weren’t being added. That gave me an idea. Why not build those features myself? I created a Chrome extension and I worked on some of the most requested features, like: Downloading the advanced voice mode and messages as MP3 Adding folders to organize chats Saving and reusing prompts Pinning important chats Exporting chats to TXT/JSON files Deleting or archiving multiple chats at once Making chat history searches faster and better It took me about a week to build the first version, and when I published it, the response was incredible. People loved it! Some even said things like, “You’re a lifesaver!” That’s when I realized I had something that could not only help people but also turn into a real business. I kept the first version free to see how people would respond. Many users have been downloading my extension, which prompted Chrome to review it to determine if it qualified for the featured badge. I received the badge, and it has significantly boosted traffic to my extension ever since. After all the positive feedback, I launched a paid version one month ago. A few minutes after publishing it, I made my first sale! That moment was so exciting, and it motivated me to keep going. I already have over 4,000 users and have made more than $4,500 in my first selling month. I’ve decided to release 1-2 new features every month to keep improving the extension based on what users ask for. I also created the same extension for Firefox and Edge users because many people have been asking for it! I also started a Reddit community, where I share updates, sales, discount codes, and ideas for new features. It’s been awesome to connect with users directly and get their feedback. Additionally, I’ve started working on another extension for Claude, which I’m hoping will be as successful as this one. My message to you is this: never give up on your dreams. It might feel impossible at first, but with patience, hard work, and some creativity, you can make it happen. I hope this inspires you to go after what you want. Good luck to all of us!

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.

How Do I Find My First Customers?

Hi r/startups, I've just launched a SAAS platform for ecommerce and digital advertising - automation without full black box campaign management or "AI" led decisions. My question is how do I go about getting people into my platform so I can get feedback/new ideas of things to add? I'm a one man band and am much more comfortable on the technical side than sales etc. I'm happy to offer a couple of months trial - but am lacking the confidence to do stuff like cold messages on LinkedIn (All I see from my connections is moaning about people selling on there) Any tips of how I should reach potential customers? Thanks!

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.

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.

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!

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... &#x200B; 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!

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.

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.

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... &#x200B; 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!

Feeling stuck—built a startup, got rejected from YC & IVI, met smarter people, and now I don’t know what to do. ( i will not promote ) I will not promote

I will not promote I don’t even know where to start, but I just feel completely stuck right now. I’m 20 years oldI don’t even know where to start, but I just feel completely stuck right now. I’m 20 years old, have been grinding non-stop for months, and it feels like I have nothing to show for it. I built an AI agent that automates workflows for businesses. I can build tech, but I can’t sell. That’s been my biggest realization recently—I thought building would be enough, but it’s not. I need customers, I need a co-founder, I need to figure out the business side… and I have no idea how. I applied to YC, IVI at ISB, and EF, met a lot of insanely smart people—some were impressed with me and my work, but they were wiser, more experienced, and honestly, just better at all of this than I am. It made me realize how much I don’t know. I got rejected from YC & IVI. 💔 YC didn’t even give much feedback—just a standard rejection. 💔 IVI told me: “You're too young, you need more experience, and you should work with a team before trying to start something.” That hit me hard. I had already been struggling to find a co-founder, and this just made me wonder if I even belong in this space yet. The Frustrating Part? I KNOW my tool Has a Unique Edge. I’m not just another AI automation tool—I know my tool has a strong USP that competitors lack. It has the potential to be an AI employee for businesses, not just another workflow tool. But I still haven’t built the “perfect product” I originally envisioned. And that’s what’s eating at me. I see what it COULD be, but I haven’t made it happen yet. At the same time, the competition in the AI agent space is exploding. YC-backed companies are working on AI agent startups. OpenAI is making huge progress with Operator. Competitors are moving fast, while I feel stuck. I’ve delayed development because I’m unsure whether to double down, pivot, or just move on entirely. Where I’m Stuck Right Now 🔹 Do I keep pushing and try to crack sales somehow? 🔹 Do I join a startup as a founding engineer to get experience, make connections, and learn sales before trying again? 🔹 Do I move to Bangalore, meet founders, and figure out what’s next? 🔹 Do I pivot to something nicher instead of competing in the AI agent race? If so, how do I even find a niche worth pursuing? 🔹 Do I even belong in startups? Or am I just forcing something that’s not working? I feel stuck in a weird middle zone where I’m not a beginner, but I’m also not successful. I’ve done enough to see what’s possible, but not enough to make it real. Every rejection makes me question if I’m even on the right path. I don’t know if I’m posting this for advice or just to get it out of my system. Maybe both. Has anyone else felt like this before? If you’ve been in this situation—how did you figure out whether to keep going or move on? TL;DR: I’m 20, built an AI agent for automating workflows, got rejected from YC & IVI, met insanely smart and experienced people, realized I can build tech but can’t sell, struggling to find a co-founder, AI agent competition is growing, delaying development, confused about the future—don’t know whether to double down, pivot, or move on. The frustrating part? I\ know I have a unique edge that others lack, but I still haven’t built the perfect product I originally envisioned.* edit: removed the tool's name

I started a Tech Startup, and I feel totally STUCK.

I made "Visual Love," a Computer Vision/AI-driven matchmaking platform. The idea is that although appearance is one of the biggest factors for starting a relationship, current matchmaking services and dating apps do not have the capability to search for people based on appearance. On Visual Love, you can find your ideal match simply by uploading a picture of your "ideal type." Also, you can connect with someone who thinks of you as their ideal type, simply by uploading your own picture. Or, there might be a perfect (mutually ideal) match. I made this CV/AI algorithm to scan faces, retrieve facial features, and make it possible to find the closest match among millions of others in a second. On average, regular dating app users swipe 8000 times over 8 months until they find their love. On Visual Love, users can find one in a million just in a second. You can try the tech demo on the website if you want to (find the link through my LinkedIn at the bottom of the post; I have to follow the "I will not promote" rule.) I thought this app would have the best chance in Asia, as people care a lot more about appearance in Asia (especially Korea and Japan). Also, my nationality is Korean, and I speak both Korean and Japanese as fluently as I speak English. So I came to Korea, and pitched to a number of VC/AC firms in Korea and Japan, and two of them were typically intersted in making investment. However, they both required me to provide market validation: how much it would cost per user acquisition, how much each user would pay on average, and etc, even after I provided them with a 3-years financial projection including market research based on other dating apps. &#x200B; Everything might be going just as expected, or even better than anticipated, but I'm feeling very stuck now. I am not a business expert, and I don't have much idea on how to proceed from here. The problem is, it wouldn't quite work as expected when there are not many users. If I start with a small group of users, it's not any better than any other dating app. Matching users within a small group doesn't quite reflect the values of Visual Love. So I figured a way around: making a game version of Visual Love targeting 100k to 500k users to work as an initial distribution channel. This version will include finding look-alike celebrities, and solving look-alike face puzzles, and etc. But now, the problem is, I cannot continue this project by myself. I have no social/financial support, and I'm running low on cash. Also, although I'm from Korea, I lived in many different countries. I did my undergraduate in New York (Columbia University) and all my friends are in the US. I don't feel very included here. I can't stop feeling frustrated and distressed :( I'm sure Visual Love can reshape the future of the matchmaking market. But, only if I can continue this project by getting the fund I require. I'm open to any advice, and if you're interested in providing any help or working with me, please contact me through LinkedIn. https://www.linkedin.com/in/don-lee-3853b1264/

We received 25k investment offer, need advice [I will not promote]

We received a $25k for 2.5% on a convertible note offer from a US based investor. The note matures in 18 months with an interest rate of 5%, but the investor said they can extend it further. It’s an AI SaaS in graphic design. We have been bootstrapping till now, and we feel that this money could help us hire better engineers and marketeers, we want to grow it to a good revenue, but don't see it becoming a billion dollar startup as such. Our initial plans were to build it like an indie-hacker, grow it a decent revenue and sell it to someone who can take better care of it. We built it as a side project with full time jobs. We already have decent traction with 10k+ signups and $600+ in revenue per month with <100 dollars spent on marketing. But our AI model costs are high, 0.2 USD per user that we onboard and provide free credits. But we as founders are more interested in another idea that we have been thinking about and see a bigger potential + founder market fit in. The current product is good, and we can foresee that with better hiring and marketing, we can grow our revenue to about 10-20k a month, like a regular online business. What should we do? We don't want to simply let go of the product because it's not that it doesn't work, it's just that we as founders are better fit for something else. We can't sell it yet as the revenue isn't too high and we haven't even incorporated. Is it okay if we think of growing it to 10-20k+ a month and then intend to sell it to someone who can take better care of it? Should we take the investment in such a case, given this investment is definitely gonna help us grow? Process of incorporation will also help us in selling this business later I think?

Just raised and here are the stats (July 2024)

CEO of a startup - bootstrapped for 10 months with a team of 7 - Built a waitlist of $15B AUM (fintech) and here's what it took (with no intended story structure) I didn't want to spam, so I decided to go the old school route and manually write every single email (some copy and paste) In order to feel prepared, I would do my research prior to reaching out, albeit sometimes limited due to time x reward Sent over 350 emails to around 300 funds and we received three yes' (to be honest we received more than three, but they wanted too much equity, or they weren’t a good fit culturally) Pre Seed is different for everyone. Some accept pre revenue others expect 100-300k ARR - this was one of the more frustrating pieces for me, due to the fact that it's extremely subjective to what "Earliest Stage" means to some funds. We're pre-product, we had to remove our CTO in the process due to performance issues, we let go of our front-end, hired a new CTO, hired an AI Engineer, and replaced our front end. It's a numbers game. We received 94% no reply - 5% nos (with meetings) - 1% yes' I used OpenVC as my main resource, highly recommend even their free product. I recommend using discount with a SAFE. Some Angels like it better, some VC’s hate it. You have to be willing to play ball with whoever leads. Mercury for banking, perks (like Carta), and SAFE agreement. All great at Mercury. Raising for a B2B business in an enterprise market is much easier, unless deep tech or science backed. But consumer products right now are not raising pre seed from what I can tell. If it means anything - it's a numbers game. Go get what you deserve, but put in the work because no one will just hand it to you. Love this community, always here to help anyone I can.

How I made a high tech salary in my first selling month

For over 7 years I worked as a full-stack developer, helping other companies bring their ideas to life. But one day, I thought “Why not try making my own dream come true?”. That’s when I decided to quit my job and start my own journey to becoming an entrepreneur. At first, it wasn’t easy. I didn’t make any money for months and had no idea where to start. I felt lost. Then, I decided to focus on something popular and trending. AI was everywhere, and ChatGPT was the most used AI platform. So I looked into it and I found the OpenAI community forum where people had been asking for features that weren’t being added. That gave me an idea. Why not build those features myself? I created a Chrome extension and I worked on some of the most requested features, like: Downloading the advanced voice mode and messages as MP3 Adding folders to organize chats Saving and reusing prompts Pinning important chats Exporting chats to TXT/JSON files Deleting or archiving multiple chats at once Making chat history searches faster and better It took me about a week to build the first version, and when I published it, the response was incredible. People loved it! Some even said things like, “You’re a lifesaver!” That’s when I realized I had something that could not only help people but also turn into a real business. I kept the first version free to see how people would respond. Many users have been downloading my extension, which prompted Chrome to review it to determine if it qualified for the featured badge. I received the badge, and it has significantly boosted traffic to my extension ever since. After all the positive feedback, I launched a paid version one month ago. A few minutes after publishing it, I made my first sale! That moment was so exciting, and it motivated me to keep going. I already have over 4,000 users and have made more than $4,500 in my first selling month. I’ve decided to release 1-2 new features every month to keep improving the extension based on what users ask for. I also created the same extension for Firefox and Edge users because many people have been asking for it! I also started a Reddit community, where I share updates, sales, discount codes, and ideas for new features. It’s been awesome to connect with users directly and get their feedback. Additionally, I’ve started working on another extension for Claude, which I’m hoping will be as successful as this one. My message to you is this: never give up on your dreams. It might feel impossible at first, but with patience, hard work, and some creativity, you can make it happen. I hope this inspires you to go after what you want. Good luck to all of us!

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!

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)

Feeling stuck—built a startup, got rejected from YC & IVI, met smarter people, and now I don’t know what to do. ( i will not promote ) I will not promote

I will not promote I don’t even know where to start, but I just feel completely stuck right now. I’m 20 years oldI don’t even know where to start, but I just feel completely stuck right now. I’m 20 years old, have been grinding non-stop for months, and it feels like I have nothing to show for it. I built an AI agent that automates workflows for businesses. I can build tech, but I can’t sell. That’s been my biggest realization recently—I thought building would be enough, but it’s not. I need customers, I need a co-founder, I need to figure out the business side… and I have no idea how. I applied to YC, IVI at ISB, and EF, met a lot of insanely smart people—some were impressed with me and my work, but they were wiser, more experienced, and honestly, just better at all of this than I am. It made me realize how much I don’t know. I got rejected from YC & IVI. 💔 YC didn’t even give much feedback—just a standard rejection. 💔 IVI told me: “You're too young, you need more experience, and you should work with a team before trying to start something.” That hit me hard. I had already been struggling to find a co-founder, and this just made me wonder if I even belong in this space yet. The Frustrating Part? I KNOW my tool Has a Unique Edge. I’m not just another AI automation tool—I know my tool has a strong USP that competitors lack. It has the potential to be an AI employee for businesses, not just another workflow tool. But I still haven’t built the “perfect product” I originally envisioned. And that’s what’s eating at me. I see what it COULD be, but I haven’t made it happen yet. At the same time, the competition in the AI agent space is exploding. YC-backed companies are working on AI agent startups. OpenAI is making huge progress with Operator. Competitors are moving fast, while I feel stuck. I’ve delayed development because I’m unsure whether to double down, pivot, or just move on entirely. Where I’m Stuck Right Now 🔹 Do I keep pushing and try to crack sales somehow? 🔹 Do I join a startup as a founding engineer to get experience, make connections, and learn sales before trying again? 🔹 Do I move to Bangalore, meet founders, and figure out what’s next? 🔹 Do I pivot to something nicher instead of competing in the AI agent race? If so, how do I even find a niche worth pursuing? 🔹 Do I even belong in startups? Or am I just forcing something that’s not working? I feel stuck in a weird middle zone where I’m not a beginner, but I’m also not successful. I’ve done enough to see what’s possible, but not enough to make it real. Every rejection makes me question if I’m even on the right path. I don’t know if I’m posting this for advice or just to get it out of my system. Maybe both. Has anyone else felt like this before? If you’ve been in this situation—how did you figure out whether to keep going or move on? TL;DR: I’m 20, built an AI agent for automating workflows, got rejected from YC & IVI, met insanely smart and experienced people, realized I can build tech but can’t sell, struggling to find a co-founder, AI agent competition is growing, delaying development, confused about the future—don’t know whether to double down, pivot, or move on. The frustrating part? I\ know I have a unique edge that others lack, but I still haven’t built the perfect product I originally envisioned.* edit: removed the tool's name

Should we give up?

I'm currently very demotivated because we're working on our SaaS startup since 1,5 years and we still haven't found active users, let alone a customer. We're building an AI-first tool that automates user research analysis. We've released two MVPs so far and are planning to build a third. People respond well to outreach (5-7% book a demo from those who received a first message) but then they fail to use it. We are talking with users a lot so we are aware of the problems, and we might be able to solve them if we continue building and testing. I find it hard though to solve these problems efficiently, because there are no similar established AI-first products on the market and it feels like we have to create a new UX standard. Some problems might be very hard to be solved, e.g. there are high cost of switching products for many of our potential users. Also, my time is limited, as I recently (5 months ago) became a mother. I can only work 30 hours per week. It's a competitive area we're in and our competitors have gradually developed into the same direction and it's getting harder to position ourselves. Also, GPTs might soon be able to do what we're doing - for free. I feel like AI tools are generally expected by many to be free. The price we're expecting to be able to bill is getting lower and lower and our finance plan is already looking tight. However, there are adjacent audiences which we could target as well, but none of us knows them. Is it normal as a founder to struggle so much at the beginning? I've read that it took established SaaS 2,5 years on average from founding to first revenue. We haven't founded so far so you could say we're not behind \sarcasm\ Shall we keep pushing? My tech co-founder is optimistic and thinks this is where the wheat is separated from the chaff. We're currently supported financially by a government fund so we haven't spent much private money. However, I feel like my career outlook gets worse with each day that I unsuccessfully try to raise this startup.

Are no-code tools actually slowing down startups?

I've noticed a concerning trend: while no-code tools promise quick launches for startups, many founders end up rebuilding their entire product from scratch later. Meanwhile, established platforms for startups like Zapier are doubling their prices, pushing teams to reconsider their stack entirely. What I'm seeing in the market: Bubble/FlutterFlow promise "build Uber in weeks" Make. com offers Zapier various automation features, but they are expensive, which made me look for alternatives. AI tools like Cursor + Claude claim to replace coding skills Traditional coding still takes 6+ months to learn basics Successful startups often rebuild their no-code MVPs Here's what makes me wonder: are we choosing speed over sustainability? Edit: I'm so happy that my post sparked so many beautiful minds. I'm going to process all the insights you've shared and publish on my subreddit, because one just can't lose it on the Internet

Good at coding, bad at marketing. Summary

Hello. I posted a question on what to do if you are good at coding but bad at marketing four days ago, and I received so many responses and tips. The original post is here. I was really glad and excited to read comments. To return the favor to the community and add some more value, I’ve summarized all the comments I got on the original post. Here are they, with my personal comments on some of the advice I got. You’ll never believe it, but the most common advice was to learn. Really, the first and only thing you should start with if you’re bad at marketing is learning. Yet learning could be different. I highlighted 5 main areas. Educate yourself on general questions. Learn more about some basics. For example, start by finding out what the 4P’s of marketing are, and afterward, you’ll inevitably run into YouTube videos, seminars, Udemy courses, or any other resource that resonates with you on some ideas/avenues you could pursue. Read books and watch videos. There are tons of books on marketing and sales. People shared in the comments books by Dan Kennedy and “Cashvertising”, written by Drew Eric Whitman. (I’ve never heard of them, but already ordered on Amazon). For sales, the most common idea was to start with YouTube videos. For example, Alex Hormozi videos and Startup school delivered by Ycombinator videos. Check out Indie Hackers and scrutinize it for a piece of good advice from developers in the same situation. Also, there was advice to follow up and read some guy on Twitter. (Don't want to get unfairly banned from here, so won't post it) Educate yourself and hire a professional or find a co-founder to help you: Hire a seasoned marketer in this field to help you out. He will help you achieve cost-efficient scales. But it could be a real problem to find the right person. Marketing agencies are expensive. Try to look on LinkedIn or among your acquaintances. Look for professionals with credentials or extensive experience. Seek marketing referrals from startups of a similar size/industry. If you don't have those, try to bring a trusted/experienced marketer friend into the intro meetings to help assess whether the service provider knows what they are doing. Talented freelancers can often get the job done for less than hiring an entire agency. Look for a co-founder who is savvy in marketing, passionate, and ready to work hard towards mutual success. Educate and DIY Being the face of your business is way better than having faceless communication. The startup checklist is made based on the comments is next: At least have your product defined. Define your target audience. Set up the goals you want to achieve. Make domain expertise and understand the market and the direction of its development. The next stage is answering tricky questions: Have you created a business model? How do you plan to compete? What’s your unique selling point? How much do you plan to budget for marketing? Are you planning to work alone, or will you need other devs? Then you start thinking about clients… You need the exposure to truly understand the customer's pain points and build a product that they love. You need to think about how your clients would think, and you should tailor each step you take for them. Get feedback from your early users if you already have a product. Interview your potential customers to learn how they buy. This will help you narrow your choice of marketing channels. Get your product or service used by several startups and help them achieve their goals. Endorsements are very valuable marketing assets. You need a landing to validate your value proposition and start sending traffic, or you can run meta instant form campaigns... It would depend on the category of your startup. You need a benchmark of the competition's ads both in Meta and Google, blog posts, domain authority, their landing page, and average search volumes. Do affiliate marketing for your product since it's an effective strategy. Educate and use AI tools for dealing with marketing. Build an LLM-based product to automate marketing. (Sounds like an idea for a startup, right?) Learn following ChatGPT advice. In 1–3 months, you will be another updated person. Look at marketowl, an AI marketing department for startups and microbusinesses that have no budget or time to do marketing. It will automate the basic tasks your business needs, but it doesn't require your marketing expertise. Check out AI tools that are delivering very good marketing content (gocharlie, jasper, copyai). Educate yourself and run socials Start a blog or YouTube channel where you can share your expertise in coding or anything else you are good at and how your product simplifies life. Engage with your audience on social media platforms like Instagram and LinkedIn, where you can showcase your industry knowledge. Start a page on Twitter and an account on Reddit. Follow and read subreddits and pages where your potential customers are. Learn the pain from the inside. Do not simply promote, people will lose interest immediately. Start by taking focused time to create informational content, so people will eventually be naturally intrigued by what you do and want to support you when they start to “know” you. Educate your potential users about the value of your product. Create content based on what ideal customers are asking at the various stages of marketing. e.g., if they are at the beginning of the process, they may use basic language; if they are further down the process, maybe they’ll be specific. Try to get on podcasts and build as many social links as you can. In other words, don’t live in a shell! Post regularly, and eventually you’ll find sites or people that are willing to promote for you. I omitted here all personal help offers and newsletters, however you could find them in the original post. Hope that will be helpful!

30K MRR from a huge barbershop - 100 automated lost meaning

Hello So in the past 2 years I have developed a sort of a beauty hub in Transylvania where I have about 30-35 people working every day. I am not a programmer but I have some skills in a few NO CODE platforms and managed to develop the entire system 100% automated and for a very low cost. When I say 100% automated I mean that I rarely even show up there and things work perfectly.I had a big dream in this industry but along the way I lost interest and decided 6 months ago that this is it. I will no longer do anything that is not necessary and pivot to other industryThe AI era popped up. The problem with me is that I just can't do meaningless stuff like most of the products out there. Tried a couple of things but lots interest very fast. For example I was able to build a sort of a kids app where I generated stories based on parents input where the kid was the super hero in 3 days. Lost interest even faster. I am in a confort zone producing good cash with zero effort. This is a dangerous area since I do not have the ability to scale so I can grow, simply because I decided I want to do something else. I would really like to use my time in something meaningful, creating something that would really help people or businesses.What are you guys building? Did you ever feel this way after you scaled or sold your business?

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. &#x200B; 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.

Help with short-form video creatives for Tiktok, Youtube Shorts and IG | Apps and Posting Strategy for Skincare brand

Hi everyone, Hope everyone’s January has been going well so far. We are in the process of launching our ecommerce skincare brand in about 1-1.5 months. Last few months have been quite packed with figuring logistics and such. We will be launching IG, FB, TT and Youtube. I am very new to creating short form video creatives. We have some photos for our products from the recent photoshoots, but not much video contents. We are in the process of researching micro influencers on both IG and TK in order to produce UGC contents. However, that will take a few weeks at least. In the mean time, for our pre-launch, we still want to create some followers and a community before we can have authentic UGC contents. What are some best AI apps to do this? I have heard of: Cliptalk Pro Luma Luma Dream Machine Invideo. However, the options are endless and I am quite overwhelmed with the options. Which ones do you guys recommend to create high quality authentic videos? Our target audience is a anywhere from 20-40s, and a more premium/ luxury market since our prices are not cheap. Hence we do not want to create any gimmick Gen Z videos. Any apps that can help us with script, creating realistic videos would be great. Also in terms of posting strategy, what is the best frequency and types of content to post? Would posting once a day be enough? What kinds of hashtags should we be using in order to reach the audience

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.

How To Build An AI-Driven Business That Doesn't Suck In 2024 (My Take).

Hi everyone, this is for those of you wanting a full run through of the formula that scaled our business to around the $100,000 /m mark in less than 18 months. Why am I doing this? Since we started hitting the larger numbers I've been given considerable time back in my day as we elevate ourselves out of scrappy start-up land and have hired a full team. I've always wanted to take this time and pour it into educating others that are following the same path. There's nothing I've loved more in life (at the ripe age of 28) than connecting with other entrepreneurs that are obsessed with the game. Firstly, I want to tell you that this is absolutely possible. The main traits you need are: ➡️ Resilience to work hard around your normal life. ➡️ The willingness to put yourself outside of your comfort zone. ➡️ The awareness to place yourself in a fast-growing market with a great offering. Secondly, I want to tell you that you are probably structuring your day and your approach wrong. Here's why: ➡️ Your operations are the back-bone of your business. When correctly organised you should be in a pattern of understanding a new task, systemising it then automating it. If you do this you will build your business like you would build a lego house. ➡️ You should be setting goals that filter down into daily actions, that are being recorded and tracked so you can improve weekly. ➡️ You should start to get a good grip of cloud software like Hubspot, Trello, Notion & Slack for the various levers you need to pull inside your business. I'm seriously passionate about this and I've recorded my first Youtube video that breaks down our entire front-end and back-end funnel for our business - if you're looking for some no-nonsense education I'd equally love some feedback. You can check out the video here. https://www.youtube.com/watch?v=X6Mq9Xu9EK8 Apart from that, please ask me anything. I'm the Managing Director of doja, a team of 9 based in the UK with a team of 5 offshore. I'd love to connect with other entrepreneurs either ahead of me or following a similar path. I can answer questions on Strategy, R&D, Product, Marketing, Lead Generation, Business Development, Commerical, Onboard & Delivery funnels, as well as extensive knowledge about what's breaking through with the latest technology for small businesses.

Impact of AI on business valuation?

I see many businesses thinking and experimenting with how AI can help improve their business processes. I seem to find far fewer thinking about how AI could impact or even demolish their actual product. I’ve been thinking about this a lot as (thankfully?) I sold my 15 year old business last year. We have teams of specialists that create digital content in narrow but very high value topic areas. Our value has been the ability of our team of experts to distill and explain the impact of the topic. Now, just a few months later, we’ve shown how three specialist AI systems can basically do the same for near zero cost. Our business and model is highly threatened. Anyone else worried about AI on their product, and thereby the value of their business, and perhaps even looking at exiting while the value is high? And yes, I do expect AI will also create new opportunities to create value. Already thinking of ideas…!

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. &#x200B; 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.

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!

40% Of SMBs Still Can't Pay Their Rent, Extending High Delinquency From September Into October

https://www.alignable.com/forum/q4s-off-to-a-rough-start-40-of-smbs-still-cant-pay-their-rent October 31, 2023: While the federal government reported a surge in economic growth for the U.S. last week, that news doesn't hold true for many small business owners. In fact, in October polling by Alignable, only 12% said their companies are experiencing significant growth this month. Beyond that, Alignable’s October Rent Report, released today, shows that a whopping 40% of SMBs couldn't even pay their October rent in full and on time. This marks the second consecutive month of a 40% rent delinquency rate -- extending 2023's record high from September through October. These findings are based on responses from 4,246 randomly selected small business owners surveyed from 10/1/23 to 10/30/23, as well as input from 44,000+ other respondents over the past year. As the chart below shows, October's SMB rent delinquency rate is 10 percentage points higher than it was in January, reflecting cumulative economic struggles: increased rents, high interest rates, still-stifling inflation, rising labor costs, and revenues that have declined since this time last year. Rent delinquency rates among small businesses during 2023 based on Alignable surveys So, Why's Rent Delinquency At 40% For A 2nd Month? Here’s the current list of problems contributing to two months' worth of the highest delinquency rate 2023 has seen so far: Consumer Spending Declines On Main Street: Quarterly, we ask about customer spending habits at retailers. This month, 45% of independent Mom and Pop Shops said spending has been down over the last 30 days. Some said it was due to more people spending money online with big retailers like Amazon. This figure is quite high, especially considering that back in July, only 24% reported a drop in consumer spending -- 21 percentage points less severe than it is now. Revenue Troubles: 42% are making half or less of the income they generated monthly prior to COVID. For businesses that are less than three years old, this situation is even worse: 53% of this group reports making half or less of what they generated this time last year. High Interest Rates: Over half of all SMB owners polled said the past 19 months of high interest rates have hurt their margins, reduced revenues, and put their expansion plans on hold, as they don't want to apply for loans. Increased Rent Prices: 50% say they’re being charged more for rent now than they were six months ago, with 15% saying rent has increased by 20% or more. At present, only 37% of pre-COVID businesses have recovered financially from the pandemic era, leaving 63% still striving to make up for time they lost due to COVID, inflationary pressures, and high interest rates. There's a slight silver lining here, though, as the 37% figure is three percentage points higher than it was in September. But, with that said, a recovery rate of 37% after more than three and a half years is still very low and speaks volumes about the ongoing list of troubles small business owners face looking into the rest of 2023. Tech, Manufacturing, Gyms, Beauty & Retail Struggle Examining the rent delinquency landscape in terms of sectors, there's quite a negative shift occurring among some industries in October. Let's look at the charts below to see what's really happening. Sectors most affected by rent delinquency include tech and retail Details on sectors affected by rent delinquency in October This is alarming for a few reasons: The countless technology layoffs at larger companies over the past year appear to be affecting the small companies now, too, who are often dependent on the larger ones as clients. Right now, 54% of science/technology small companies couldn't pay their October rent, up 10 percentage points from September and 16 percentage points since August. There are also some comments in the surveys of technology roles being reduced or replaced by ChatGPT and other AI, which can write software programs. Gyms have been struggling now for a while and now 50% of them can't afford the rent, up 8 percentage points from September. The biggest shift between October and September occurred among manufacturers, partially due to ongoing fluctuation in the price of gas and other inflationary issues. For quite some time, manufacturers were improving a lot in terms of their rent delinquency rates, but in October, they jumped 25 percentage points, doubling their rate, which is now 50%. This is also a record high for manufacturers in 2023. We hope this is just a blip, but we'll see in November. Also due, in part, to fluctuating gas prices and costs of vehicles, 45% of transportation companies couldn't pay October rent in full and on time. That's up 6 percentage points from last month. Sadly, 47% of salon owners couldn't cover October rent, after showing a lot of stability over the past few months. But that stability ended this month, as salons' rent delinquency rates jumped nine percentage points. Though rates have dropped three percentage points in October, a high percentage of retailers are still having trouble paying the rent. Last month, it was 47%. This month, it's better, but is still over 40%, landing at 44%. This is worrisome, especially since Q4 is a "make it or break it" time for many Main Street merchants. Looking more closely at the industries, there was some good news, in that a few others experienced lower delinquency rates in October, including restaurants, which dipped to 40% from 44% in September. Travel/lodging dropped seven percentage points to 38% (from 45% last month), as did education, which is also at 38%, down from 43%. When looking at rent delinquency from the vantage point of the states that are most affected, many surges can be seen between October and September, while a few states saw some dramatic, encouraging declines, too. Rent Troubles Increase For IL, VA, TX, MA, FL, & CO Looking at the states' charts, you can see how tumultuous the rent story has become this fall. Let's first talk about those with significant jumps in their delinquency rates. Here's the rundown: Illinois leads the list once again. After having a better month in September, its delinquency rate has soared, once more, landing at 54% for October (up from 46% last month). In fact, the 54% figure is the highest rate IL-based SMBs have seen in 2023. Virginia was in great shape last month, with a delinquency rate of just 19%. But Virginia-based small business owners have had a very rough month, at least in terms of rent. Now, 50% of them who took our poll say they couldn't cover rent (an increase of 31 percentage points). Texas is third on the list, with an 11-percentage-point lift from 38% in September to 49% in October. MA is next up at 48%, which marks the largest jump on the chart -- 32 percentage points from a low of just 16% in September. Small businesses in Florida have also experienced two challenging months in terms of rent delinquency. Right now, 45% of SMBs there couldn't afford to pay, up nine percentage points from September and 15 percentage points from August. Colorado's businesses regressed in October, hitting a new record high of 40%. That rent delinquency rate jumped 13 percentage points from September to October. While we just covered states with some very high delinquency rates, there were also several more positive swings that have occurred in October. Though encouraging, we'll have to see how long those delinquency rates continue. Here are the most remarkable: New York -- After reaching a record rate of 55% last month, New York's small business owners now report a more stable number: just 29%. That's down 26 percentage points. New Jersey -- New York's neighbor has an even more impressive story in October: only 20% of New Jersey's SMBs couldn't pay rent this month, a record low over at least the past 14 months, down 34 percentage points from a record high of 54%. Michigan -- Similarly, Michigan's small business owners boast a rate of just 20%, down from 45% in September.

MIT Machine Learning graduate teaches machine learning and deep learning (for free)

I believe that anyone can transition to machine learning, if they decide to do so. For the last 3 months, I started a project to teach machine learning and deep learning. I recorded 70 videos in machine learning and deep learning. Every day, I scripted, recorded and edited 1 video for about 6-7 hours. The result is 2 massive playlists. 1️⃣ Machine Learning Teach by Doing playlist: (a) Topics covered: Regression, Classification, Neural Networks, Convolutional Neural Networks (b) Number of lectures: 35 (c) Lecture instructor: Me (IIT Madras BTech, MIT AI PhD) (d) Playlist link: https://www.youtube.com/playlist?list=PLPTV0NXA\ZSi-nLQ4XV2Mds8Z7bihK68L 2️⃣ Neural Networks from scratch playlist: (a) Topics covered: Neural Network architecture, forward pass, backward pass, optimizers. Completely coded in Python from scratch. No Pytorch. No Tensorflow. Only Numpy. (b) Number of lectures: 35 (c) Lecture instructor: Me (IIT Madras BTech, MIT AI PhD) Playlist link: https://www.youtube.com/playlist?list=PLPTV0NXA\ZSj6tNyn\UadmUeU3Q3oR-hu P.S: Lecturer background: I graduated with a PhD in machine learning from MIT. The video shows my notes in detail. https://i.redd.it/tjxybbqyngcd1.gif

Teaching an AI to Play Mario: A Learning Journey

TLDR: I've always wanted to learn reinforcement learning, but the notation and concepts often seemed overwhelming (and scary). So, \~3 months ago, I set myself a challenge: Train an AI to Speedrun Mario Watch the progression here: https://youtu.be/OQitI066aI0 &#x200B; Full Story: Three months ago, I stared at the dense forest of Reinforcement Learning (RL) papers and felt like Mario facing Bowser for the first time: unequipped and overwhelmingly outmatched. The notation seemed like hieroglyphics, and terms like "policy gradients" felt like they belonged in a sci-fi novel, not a beginner's project. But RL always seemed so cool, and I was really determined to achieve my goal. So, I started with the Sutton & Barto RL textbook, learning things like the Multi-Armed Bandit problem and MDPs working my way up to Actor-Critic methods. That book is literal gold & I highly recommend you work through it (even though it can be tough at times). I tried everything from random courses online to books on amazon & this textbook has been by far the most clear and effective way to learn RL. The biggest issue with the textbook is you learn a lot of theory, but don't learn implementation. So, I would go through a chapter a week & set aside Friday + the weekend to actually implement what I learned (usually by watching youtube tutorials & looking at Github Repos). Eventually, while searching for practical resources for implementing PPO, I stumbled upon a GitHub repository that literally trained an AI to play Mario. Rather than just cloning and running the code, I took a deeper approach. I aimed to understand the repository thoroughly, ensuring each line of code made sense in the context of what I had studied. But of course, this wasn't easy. One of the biggest issues was my hardware limitation. I was working on an old Mac. So, I started using Google Collab, but that had its own problems (session timeouts & limited GPU access). Ultimately, I found AWS Sagemaker to be pretty good. &#x200B; After rewriting the code, I felt confident it would work because I understood every aspect of it. So, I trained the AI to play Mario across a variety of different levels (took a long time and a lot of trial and error with the learning rate). It feels amazing seeing your theoretical knowledge translate into tangible results & this project gave me a big confidence boost. &#x200B; Anyways I made a video showing off the results (Note that I simplified the technical parts for it to reach a wider audience): https://youtu.be/OQitI066aI0 &#x200B; Feel free to drop any questions or feedback, I'm more than happy to help or chat about my experiences. I hope my journey can inspire some of you who might be feeling overwhelmed with the idea of diving into reinforcement learning or any other area of AI. Remember, the hardest part is often taking the first step. Once you start, the momentum will carry you forward. Thank you for reading my super long post and sharing in my little success story! 🚀🕹️🎮

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

MMML | Deploy HuggingFace training model rapidly based on MetaSpore

A few days ago, HuggingFace announced a $100 million Series C funding round, which was big news in open source machine learning and could be a sign of where the industry is headed. Two days before the HuggingFace funding announcement, open-source machine learning platform MetaSpore released a demo based on the HuggingFace Rapid deployment pre-training model. As deep learning technology makes innovative breakthroughs in computer vision, natural language processing, speech understanding, and other fields, more and more unstructured data are perceived, understood, and processed by machines. These advances are mainly due to the powerful learning ability of deep learning. Through pre-training of deep models on massive data, the models can capture the internal data patterns, thus helping many downstream tasks. With the industry and academia investing more and more energy in the research of pre-training technology, the distribution warehouses of pre-training models such as HuggingFace and Timm have emerged one after another. The open-source community release pre-training significant model dividends at an unprecedented speed. In recent years, the data form of machine modeling and understanding has gradually evolved from single-mode to multi-mode, and the semantic gap between different modes is being eliminated, making it possible to retrieve data across modes. Take CLIP, OpenAI’s open-source work, as an example, to pre-train the twin towers of images and texts on a dataset of 400 million pictures and texts and connect the semantics between pictures and texts. Many researchers in the academic world have been solving multimodal problems such as image generation and retrieval based on this technology. Although the frontier technology through the semantic gap between modal data, there is still a heavy and complicated model tuning, offline data processing, high performance online reasoning architecture design, heterogeneous computing, and online algorithm be born multiple processes and challenges, hindering the frontier multimodal retrieval technologies fall to the ground and pratt &whitney. DMetaSoul aims at the above technical pain points, abstracting and uniting many links such as model training optimization, online reasoning, and algorithm experiment, forming a set of solutions that can quickly apply offline pre-training model to online. This paper will introduce how to use the HuggingFace community pre-training model to conduct online reasoning and algorithm experiments based on MetaSpore technology ecology so that the benefits of the pre-training model can be fully released to the specific business or industry and small and medium-sized enterprises. And we will give the text search text and text search graph two multimodal retrieval demonstration examples for your reference. Multimodal semantic retrieval The sample architecture of multimodal retrieval is as follows: Our multimodal retrieval system supports both text search and text search application scenarios, including offline processing, model reasoning, online services, and other core modules: https://preview.redd.it/mdyyv1qmdz291.png?width=1834&format=png&auto=webp&s=e9e10710794c78c64cc05adb75db385aa53aba40 Offline processing, including offline data processing processes for different application scenarios of text search and text search, including model tuning, model export, data index database construction, data push, etc. Model inference. After the offline model training, we deployed our NLP and CV large models based on the MetaSpore Serving framework. MetaSpore Serving helps us conveniently perform online inference, elastic scheduling, load balancing, and resource scheduling in heterogeneous environments. Online services. Based on MetaSpore’s online algorithm application framework, MetaSpore has a complete set of reusable online search services, including Front-end retrieval UI, multimodal data preprocessing, vector recall and sorting algorithm, AB experimental framework, etc. MetaSpore also supports text search by text and image scene search by text and can be migrated to other application scenarios at a low cost. The HuggingFace open source community has provided several excellent baseline models for similar multimodal retrieval problems, which are often the starting point for actual optimization in the industry. MetaSpore also uses the pre-training model of the HuggingFace community in its online services of searching words by words and images by words. Searching words by words is based on the semantic similarity model of the question and answer field optimized by MetaSpore, and searching images by words is based on the community pre-training model. These community open source pre-training models are exported to the general ONNX format and loaded into MetaSpore Serving for online reasoning. The following sections will provide a detailed description of the model export and online retrieval algorithm services. The reasoning part of the model is standardized SAAS services with low coupling with the business. Interested readers can refer to my previous post: The design concept of MetaSpore, a new generation of the one-stop machine learning platform. 1.1 Offline Processing Offline processing mainly involves the export and loading of online models and index building and pushing of the document library. You can follow the step-by-step instructions below to complete the offline processing of text search and image search and see how the offline pre-training model achieves reasoning at MetaSpore. 1.1.1 Search text by text Traditional text retrieval systems are based on literal matching algorithms such as BM25. Due to users’ diverse query words, a semantic gap between query words and documents is often encountered. For example, users misspell “iPhone” as “Phone,” and search terms are incredibly long, such as “1 \~ 3 months old baby autumn small size bag pants”. Traditional text retrieval systems will use spelling correction, synonym expansion, search terms rewriting, and other means to alleviate the semantic gap but fundamentally fail to solve this problem. Only when the retrieval system fully understands users’ query terms and documents can it meet users’ retrieval demands at the semantic level. With the continuous progress of pre-training and representational learning technology, some commercial search engines continue to integrate semantic vector retrieval methods based on symbolic learning into the retrieval ecology. Semantic retrieval model This paper introduces a set of semantic vector retrieval applications. MetaSpore built a set of semantic retrieval systems based on encyclopedia question and answer data. MetaSpore adopted the Sentence-Bert model as the semantic vector representation model, which fine-tunes the twin tower BERT in supervised or unsupervised ways to make the model more suitable for retrieval tasks. The model structure is as follows: The query-Doc symmetric two-tower model is used in text search and question and answer retrieval. The vector representation of online Query and offline DOC share the same vector representation model, so it is necessary to ensure the consistency of the offline DOC library building model and online Query inference model. The case uses MetaSpore’s text representation model Sbert-Chinese-QMC-domain-V1, optimized in the open-source semantically similar data set. This model will express the question and answer data as a vector in offline database construction. The user query will be expressed as a vector by this model in online retrieval, ensuring that query-doc in the same semantic space, users’ semantic retrieval demands can be guaranteed by vector similarity metric calculation. Since the text presentation model does vector encoding for Query online, we need to export the model for use by the online service. Go to the q&A data library code directory and export the model concerning the documentation. In the script, Pytorch Tracing is used to export the model. The models are exported to the “./export “directory. The exported models are mainly ONNX models used for wired reasoning, Tokenizer, and related configuration files. The exported models are loaded into MetaSpore Serving by the online Serving system described below for model reasoning. Since the exported model will be copied to the cloud storage, you need to configure related variables in env.sh. \Build library based on text search \ The retrieval database is built on the million-level encyclopedia question and answer data set. According to the description document, you need to download the data and complete the database construction. The question and answer data will be coded as a vector by the offline model, and then the database construction data will be pushed to the service component. The whole process of database construction is described as follows: Preprocessing, converting the original data into a more general JSonline format for database construction; Build index, use the same model as online “sbert-Chinese-qmc-domain-v1” to index documents (one document object per line); Push inverted (vector) and forward (document field) data to each component server. The following is an example of the database data format. After offline database construction is completed, various data are pushed to corresponding service components, such as Milvus storing vector representation of documents and MongoDB storing summary information of documents. Online retrieval algorithm services will use these service components to obtain relevant data. 1.1.2 Search by text Text and images are easy for humans to relate semantically but difficult for machines. First of all, from the perspective of data form, the text is the discrete ID type of one-dimensional data based on words and words. At the same time, images are continuous two-dimensional or three-dimensional data. Secondly, the text is a subjective creation of human beings, and its expressive ability is vibrant, including various turning points, metaphors, and other expressions, while images are machine representations of the objective world. In short, bridging the semantic gap between text and image data is much more complex than searching text by text. The traditional text search image retrieval technology generally relies on the external text description data of the image or the nearest neighbor retrieval technology and carries out the retrieval through the image associated text, which in essence degrades the problem to text search. However, it will also face many issues, such as obtaining the associated text of pictures and whether the accuracy of text search by text is high enough. The depth model has gradually evolved from single-mode to multi-mode in recent years. Taking the open-source project of OpenAI, CLIP, as an example, train the model through the massive image and text data of the Internet and map the text and image data into the same semantic space, making it possible to implement the text and image search technology based on semantic vector. CLIP graphic model The text search pictures introduced in this paper are implemented based on semantic vector retrieval, and the CLIP pre-training model is used as the two-tower retrieval architecture. Because the CLIP model has trained the semantic alignment of the twin towers’ text and image side models on the massive graphic and text data, it is particularly suitable for the text search graph scene. Due to the different image and text data forms, the Query-Doc asymmetric twin towers model is used for text search image retrieval. The image-side model of the twin towers is used for offline database construction, and the text-side model is used for the online return. In the final online retrieval, the database data of the image side model will be searched after the text side model encodes Query, and the CLIP pre-training model guarantees the semantic correlation between images and texts. The model can draw the graphic pairs closer in vector space by pre-training on a large amount of visual data. Here we need to export the text-side model for online MetaSpore Serving inference. Since the retrieval scene is based on Chinese, the CLIP model supporting Chinese understanding is selected. The exported content includes the ONNX model used for online reasoning and Tokenizer, similar to the text search. MetaSpore Serving can load model reasoning through the exported content. Build library on Image search You need to download the Unsplash Lite library data and complete the construction according to the instructions. The whole process of database construction is described as follows: Preprocessing, specify the image directory, and then generate a more general JSOnline file for library construction; Build index, use OpenAI/Clip-Vit-BASE-Patch32 pre-training model to index the gallery, and output one document object for each line of index data; Push inverted (vector) and forward (document field) data to each component server. Like text search, after offline database construction, relevant data will be pushed to service components, called by online retrieval algorithm services to obtain relevant data. 1.2 Online Services The overall online service architecture diagram is as follows: &#x200B; https://preview.redd.it/nz8zrbbpdz291.png?width=1280&format=png&auto=webp&s=28dae7e031621bc8819519667ed03d8d085d8ace Multi-mode search online service system supports application scenarios such as text search and text search. The whole online service consists of the following parts: Query preprocessing service: encapsulate preprocessing logic (including text/image, etc.) of pre-training model, and provide services through gRPC interface; Retrieval algorithm service: the whole algorithm processing link includes AB experiment tangent flow configuration, MetaSpore Serving call, vector recall, sorting, document summary, etc.; User entry service: provides a Web UI interface for users to debug and track down problems in the retrieval service. From a user request perspective, these services form invocation dependencies from back to front, so to build up a multimodal sample, you need to run each service from front to back first. Before doing this, remember to export the offline model, put it online and build the library first. This article will introduce the various parts of the online service system and make the whole service system step by step according to the following guidance. See the ReadME at the end of this article for more details. 1.2.1 Query preprocessing service Deep learning models tend to be based on tensors, but NLP/CV models often have a preprocessing part that translates raw text and images into tensors that deep learning models can accept. For example, NLP class models often have a pre-tokenizer to transform text data of string type into discrete tensor data. CV class models also have similar processing logic to complete the cropping, scaling, transformation, and other processing of input images through preprocessing. On the one hand, considering that this part of preprocessing logic is decoupled from tensor reasoning of the depth model, on the other hand, the reason of the depth model has an independent technical system based on ONNX, so MetaSpore disassembled this part of preprocessing logic. NLP pretreatment Tokenizer has been integrated into the Query pretreatment service. MetaSpore dismantlement with a relatively general convention. Users only need to provide preprocessing logic files to realize the loading and prediction interface and export the necessary data and configuration files loaded into the preprocessing service. Subsequent CV preprocessing logic will also be integrated in this manner. The preprocessing service currently provides the gRPC interface invocation externally and is dependent on the Query preprocessing (QP) module in the retrieval algorithm service. After the user request reaches the retrieval algorithm service, it will be forwarded to the service to complete the data preprocessing and continue the subsequent processing. The ReadMe provides details on how the preprocessing service is started, how the preprocessing model exported offline to cloud storage enters the service, and how to debug the service. To further improve the efficiency and stability of model reasoning, MetaSpore Serving implements a Python preprocessing submodule. So MetaSpore can provide gRPC services through user-specified preprocessor.py, complete Tokenizer or CV-related preprocessing in NLP, and translate requests into a Tensor that deep models can handle. Finally, the model inference is carried out by MetaSpore, Serving subsequent sub-modules. Presented here on the lot code: https://github.com/meta-soul/MetaSpore/compare/add\python\preprocessor 1.2.2 Retrieval algorithm services Retrieval algorithm service is the core of the whole online service system, which is responsible for the triage of experiments, the assembly of algorithm chains such as preprocessing, recall, sorting, and the invocation of dependent component services. The whole retrieval algorithm service is developed based on the Java Spring framework and supports multi-mode retrieval scenarios of text search and text search graph. Due to good internal abstraction and modular design, it has high flexibility and can be migrated to similar application scenarios at a low cost. Here’s a quick guide to configuring the environment to set up the retrieval algorithm service. See ReadME for more details: Install dependent components. Use Maven to install the online-Serving component Search for service configurations. Copy the template configuration file and replace the MongoDB, Milvus, and other configurations based on the development/production environment. Install and configure Consul. Consul allows you to synchronize the search service configuration in real-time, including cutting the flow of experiments, recall parameters, and sorting parameters. The project’s configuration file shows the current configuration parameters of text search and text search. The parameter modelName in the stage of pretreatment and recall is the corresponding model exported in offline processing. Start the service. Once the above configuration is complete, the retrieval service can be started from the entry script. Once the service is started, you can test it! For example, for a user with userId=10 who wants to query “How to renew ID card,” access the text search service. 1.2.3 User Entry Service Considering that the retrieval algorithm service is in the form of the API interface, it is difficult to locate and trace the problem, especially for the text search image scene can intuitively display the retrieval results to facilitate the iterative optimization of the retrieval algorithm. This paper provides a lightweight Web UI interface for text search and image search, a search input box, and results in a display page for users. Developed by Flask, the service can be easily integrated with other retrieval applications. The service calls the retrieval algorithm service and displays the returned results on the page. It’s also easy to install and start the service. Once you’re done, go to http://127.0.0.1:8090 to see if the search UI service is working correctly. See the ReadME at the end of this article for details. Multimodal system demonstration The multimodal retrieval service can be started when offline processing and online service environment configuration have been completed following the above instructions. Examples of textual searches are shown below. Enter the entry of the text search map application, enter “cat” first, and you can see that the first three digits of the returned result are cats: https://preview.redd.it/d7syq47rdz291.png?width=1280&format=png&auto=webp&s=b43df9abd380b7d9a52e3045dd787f4feeb69635 If you add a color constraint to “cat” to retrieve “black cat,” you can see that it does return a black cat: &#x200B; https://preview.redd.it/aa7pxx8tdz291.png?width=1280&format=png&auto=webp&s=e3727c29d1bde6eea2e1cccf6c46d3cae3f4750e Further, strengthen the constraint on the search term, change it to “black cat on the bed,” and return results containing pictures of a black cat climbing on the bed: &#x200B; https://preview.redd.it/2mw4qpjudz291.png?width=1280&format=png&auto=webp&s=1cf1db667892b9b3a40451993680fbd6980b5520 The cat can still be found through the text search system after the color and scene modification in the above example. Conclusion The cutting-edge pre-training technology can bridge the semantic gap between different modes, and the HuggingFace community can greatly reduce the cost for developers to use the pre-training model. Combined with the technological ecology of MetaSpore online reasoning and online microservices provided by DMetaSpore, the pre-training model is no longer mere offline dabbling. Instead, it can truly achieve end-to-end implementation from cutting-edge technology to industrial scenarios, fully releasing the dividends of the pre-training large model. In the future, DMetaSoul will continue to improve and optimize the MetaSpore technology ecosystem: More automated and wider access to HuggingFace community ecology. MetaSpore will soon release a common model rollout mechanism to make HuggingFace ecologically accessible and will later integrate preprocessing services into online services. Multi-mode retrieval offline algorithm optimization. For multimodal retrieval scenarios, MetaSpore will continuously iteratively optimize offline algorithm components, including text recall/sort model, graphic recall/sort model, etc., to improve the accuracy and efficiency of the retrieval algorithm. For related code and reference documentation in this article, please visit: https://github.com/meta-soul/MetaSpore/tree/main/demo/multimodal/online Some images source: https://github.com/openai/CLIP/raw/main/CLIP.png https://www.sbert.net/examples/training/sts/README.html

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

Learning AI for Business Leaders

Hello Community, For the better part of 2 months I have been reading up on everything in getting a better understanding of the fundamentals of AI - from history of AI to reading the Google 8’s peer reviewed paper on the advent of transformers. I feel as though I am running in circles at times an not following a guided path approach to learning. I’m 40, work in international development in a leadership role - though I have a background in corporate finance and tech. I’m not an engineer, nor do I have the ambition of such a career pivot. However I do want to learn, be abreast, and know enough about the space when evaluating (and proposing) AI related opportunities - my role now should be a path towards a chief innovation officer for a development agency within the next 3-4 years. My sources have been basically everything I can find from tech blogs, WaPo, financial times, economist, and random internet searches. I have completed IBM’s Fundamental on AI course. However, I feel there no structure in learning as I have been piecemealing from so many different sources. Essentially I care about business cases and being able to confidently talk about AI. And not building and deploying a product. MIT and UPenn have some courses on AI for leaders, however, as the space is moving so fast I’m not confident how current their materials are. My ask: Are there any courses (or learning approaches) you recommend that is less-code and more focus on concept and applications I should do? Is my approach to learning too broad and I should focus on a subset of AI such as ML or specifically GenAI since it seems most applications are currently byproducts of it. Many thanks in advance for any support - truly appreciate it.

AI Courses for Business Leaders

I’m been spending a last few months learning the fundamentals of AI through blog post, podcast and did online short course on intro to AI from IBM and Coursera. And looking to take the “next step” either through a certification program (I don’t care about the cert - but more so learning opportunity) offered through MIT, Penn, etc…they seem like a money grab and not confident I will get what I am looking for through them. Are there better options? Willing to spend money, open to learning online/hybrid through a structured curriculum or patch-work solution online —- just need insight on a path forward. I’m not looking to pivot, but rather learn about the technology, seek opportunities to incorporate elements of it into our organization - and for also, I’m genuinely interested in its potential - from an application/deployment/business perspective. I’m 40yrs, senior leader focusing on innovation and entrepreneurship in emerging economies - pretty tech savvy (though not from a CS background) and looking for a new learning opportunity to stay ahead of the curve and leverage it to our organization’s mission. Many thanks in advance!

Backend dev wants to learn ML

Hello ML Experts, I am staff engineer, working in a product based organization, handling the backend services. I see myself becoming Solution Architect and then Enterprise Architect one day. With the AI and ML trending now a days, So i feel ML should be an additional skill that i should acquire which can help me leading and architecting providing solutions to the problems more efficiently, I think however it might not replace the traditional SWEs working on backend APIs completely, but ML will be just an additional diamention similar to the knowledge of Cloud services and DevOps. So i would like to acquire ML knowledge, I dont have any plans to be an expert at it right now, nor i want to become a full time data scientist or ML engineer as of today. But who knows i might diverge, but thats not the plan currently. I did some quick promting with ChatGPT and was able to comeup with below learning path for me. So i would appreciate if some of you ML experts can take a look at below learning path and provide your suggestions 📌 PHASE 1: Core AI/ML & Python for AI (3-4 Months) Goal: Build a solid foundation in AI/ML with Python, focusing on practical applications. 1️⃣ Python for AI/ML (2-3 Weeks) Course: [Python for Data Science and Machine Learning Bootcamp]() (Udemy) Topics: Python, Pandas, NumPy, Matplotlib, Scikit-learn basics 2️⃣ Machine Learning Fundamentals (4-6 Weeks) Course: Machine Learning Specialization by Andrew Ng (C0ursera) Topics: Linear & logistic regression, decision trees, SVMs, overfitting, feature engineering Project: Build an ML model using Scikit-learn (e.g., predicting house prices) 3️⃣ Deep Learning & AI Basics (4-6 Weeks) Course: Deep Learning Specialization by Andrew Ng (C0ursera) Topics: Neural networks, CNNs, RNNs, transformers, generative AI (GPT, Stable Diffusion) Project: Train an image classifier using TensorFlow/Keras 📌 PHASE 2: AI/ML for Enterprise & Cloud Applications (3-4 Months) Goal: Learn how AI is integrated into cloud applications & enterprise solutions. 4️⃣ AI/ML Deployment & MLOps (4 Weeks) Course: MLOps Specialization by Andrew Ng (C0ursera) Topics: Model deployment, monitoring, CI/CD for ML, MLflow, TensorFlow Serving Project: Deploy an ML model as an API using FastAPI & Docker 5️⃣ AI/ML in Cloud (Azure, AWS, OpenAI APIs) (4-6 Weeks) Azure AI Services: Course: Microsoft AI Fundamentals (C0ursera) Topics: Azure ML, Azure OpenAI API, Cognitive Services AWS AI Services: Course: [AWS Certified Machine Learning – Specialty]() (Udemy) Topics: AWS Sagemaker, AI workflows, AutoML 📌 PHASE 3: AI Applications in Software Development & Future Trends (Ongoing Learning) Goal: Explore AI-powered tools & future-ready AI applications. 6️⃣ Generative AI & LLMs (ChatGPT, GPT-4, LangChain, RAG, Vector DBs) (4 Weeks) Course: [ChatGPT Prompt Engineering for Developers]() (DeepLearning.AI) Topics: LangChain, fine-tuning, RAG (Retrieval-Augmented Generation) Project: Build an LLM-based chatbot with Pinecone + OpenAI API 7️⃣ AI-Powered Search & Recommendations (Semantic Search, Personalization) (4 Weeks) Course: [Building Recommendation Systems with Python]() (Udemy) Topics: Collaborative filtering, knowledge graphs, AI search 8️⃣ AI-Driven Software Development (Copilot, AI Code Generation, Security) (Ongoing) Course: AI-Powered Software Engineering (C0ursera) Topics: AI code completion, AI-powered security scanning 🚀 Final Step: Hands-on Projects & Portfolio Once comfortable, work on real-world AI projects: AI-powered document processing (OCR + LLM) AI-enhanced search (Vector Databases) Automated ML pipelines with MLOps Enterprise AI Chatbot using LLMs ⏳ Suggested Timeline 📅 6-9 Months Total (10-12 hours/week) 1️⃣ Core ML & Python (3-4 months) 2️⃣ Enterprise AI/ML & Cloud (3-4 months) 3️⃣ AI Future Trends & Applications (Ongoing) Would you like a customized plan with weekly breakdowns? 🚀

Tried every no-code tool under the sun—finally built a fully custom business app in minutes with AI

Hey r/SideProject, After months of trying to piece together no-code tools to fit small businesses’ needs, I kept hitting a wall. Every setup felt like a workaround, never quite matching the way these businesses actually operate. That’s when I realized most SMBs need software that’s built around their specific workflows, not patched together. But developing something custom from scratch? Not realistic for most small businesses in terms of time or cost. So, I set out to create a new approach. Enter Crust AI—a tool where SMB owners just describe what they need, and in 5 minutes, it generates a fully functional app. Crust can even plug into existing data from Airtable, Monday, or Notion, and builds the entire interface on top with no design limitations—completely generated by AI. From client portals to vendor management systems, Crust delivers an end-to-end solution without the dev work. For once, I didn’t need to wrestle with endless integrations and limitations. If you’ve been through the same, check out trycrust.co and let me know your thoughts. Happy to answer questions or hear about your own experiences!

Why no code tools for building ai models failed?

Business folks have tasks where neural networks could help but they don’t know Python or deep learning, right? Meanwhile ML engineers know AI models but often don’t have an actual problem to solve. So the first group hires the second. Same thing happened with websites a while ago—at first you had to code everything then came drag-and-drop editors, no-code tools, and now even this "vibe coding" stuff. It’s not the most flexible or maintainable, but it works for a lot of people who just need to get something done without spending months learning to code. So why isn’t the same thing happening with building AI models? Like if I run a business I could save a ton of money by automating manual tasks with models trained on my own data. But I have zero clue what Jupyter Notebook or Keras are, and honestly, I don’t want to know. So I have to hire an ML engineer just to get it done because there’s no viable no-code solution for this.

New no-code AI copilot creator: Knolli.ai

Introducing Knolli.ai, a new no-code AI chatbot builder that enables founders and entrepreneurs to develop copilots utilizing their own knowledge bases. Once they have built their copilot, we offer a monetization platform to start generating revenue. CPApilot.com, one of our clients, has experienced rapid growth by utilizing our platform. They have landed major clients and went from idea to revenue in just 3 months. We are genuinely thrilled to collaborate with founders to create new AI startups leveraging diverse knowledge bases and obtaining feedback. Mandeep from Knolli.ai

Looking for beta testers for my AI-powered website builder - no templates, no coding required

Hey r/sideproject, I'm working on an exciting new project since 4 months- an AI-powered website builder that creates completely custom, professional-looking websites from scratch. No templates, no coding The key capabilities of this AI website builder are: Designing unique, mobile-responsive layouts based on your preferences and content Generating custom written content for each page, section, and element Ensuring best practices for things like typography, color schemes, and SEO But the real power comes in the customization. Once the AI generates your initial website, you can easily make changes to any part of it - from the design and layout to the text and images. Simply select the specific element you want to modify, and the AI will make the requested changes, whether that's tweaking the font and colors, rearranging the page structure, or rewriting the copy. It's a truly interactive, AI-driven web building experience. This is perfect for things like: Marketing/informational websites Landing pages Online resumes and portfolios Small business websites When you're ready, you can publish your AI-generated, fully customized website on a free subdomain or download the full code. I'm looking to get a few early users to try this out and provide feedback before the full public launch. If you're interested in being a beta tester, I'd love to hear from you! This could be especially useful for small business owners, freelancers, job seekers, or anyone who needs a professional web presence but doesn't have the time or skills for traditional web development. If you're interested, just leave a comment below or send me a DM. I'll be in touch to get you set up with early access. Thanks for checking it out! Muhammad Bilal Moten

Built an interactive guide using a no-code AI tool. 700 visitors already and growing!

Hey Community, As a Founding Product & Growth Manager, I wanted to level up my ability to ship products end-to-end, so a few months ago, I got a Replit subscription and started building myself. One of the things I created is a Slack Etiquette Guide to help teams use Slack more effectively with best practices. It took me just 4-5 hours to build, no tech team needed! Here’s what I built: Slack Etiquette Guide Would love to get your feedback on what can be improved or added.

The directory boilerplate Mkdirs has run for 100 days making $19K now, AMA

Hello everyone, I posted my product Mkdirs (How I made $2K+ in 10 days after launching Mkdirs) in r/SideProject before, and now 100 days passed, I am here to share some updates about this product. Please allow me to introduce Mkdirs first, it is a directory boilerplate, packed with AI, Listings, Payment, Submission, CMS, Blog, Authentication, Newsletter, SEO, Themes and more. https://mkdirs.com I launced it 3 months ago, and gained 160+ customers, who have launched 40+ directories so far. Recently the Mkdirs template supports submissions with AI assistance to improve efficiency. Simply enter the URL, and the AI model will analyze the website content, generate the description and introduction (in Markdown format), assign categories and tags, detect and upload logo and image, making submissions and launch directories super fast! Thank you for the community, and feel free to ask me anything if you have any questions. mkdirs directory boilerplate, submission with AI assistance

Just hit $6k MRR, ask me anything

Hey everyone! After months (or years) of late nights, countless iterations, and endless learning, my side hustle just hit $6K MRR. It feels surreal to finally hit this milestone, and I wanted to share it with the community that’s been a constant source of inspiration and motivation. I’d love to pay it forward, answer questions, and chat with anyone on a similar journey! Whether you’re just starting out, scaling, or stuck in the grind, ask me anything about: What worked and what didn’t during the early stages How I managed time and stress with a full-time job Building a customer base and retention strategies Tools, tech stack, or marketing strategies that got me here How I’m planning to scale further from here Feel free to ask about the challenges too—because there have been many! 😂 Thanks to everyone who’s been part of the community here—it’s helped me push through. Let’s chat and grow together! 🚀 My app: https://dietapp.ai https://preview.redd.it/0d3mu80fd5xd1.png?width=972&format=png&auto=webp&s=50139d47258bc5910ea51a12d0bff2335d0e9909

How I built my SaaS and earned $273 MRR in the first month

Hi everyone! I’m Alex Varga, an indie developer. Last year, I focused on accelerating my development speed and launched 10 projects in 12 months. One of them called Bulk Image Generation started growing through SEO, so I decided to focus on it. After one month of SEO efforts, it’s generating $273 MRR. I hope my experience will be useful to others. Concept bulkimagegeneration.com website helps to generate up to 100 images in 15 seconds using AI I was using Google, started with keywords like "Bulk Image ..." a lot of them are Bulk Image Resizer, Downloader etc. But there was no Bulk Image Generator. I thought: yeah, this domain is available, let's buy. So I bought bulkimagegeneration.com and bulkimagegenerator.com So, the app concept is to help people generate images with AI at scale: let\`s say 100 images in 15 seconds. Marketing Gap https://preview.redd.it/4luzib02bbie1.png?width=1905&format=png&auto=webp&s=cbe845107aca46ae5729dfe121fefd5e9cdab9ac Most builders create a product first and figure out how to sell it later. I took a completely different approach with Bulk Image Generator. I identified a market gap and secured a domain name that matched exactly what people were searching for and launched app. https://preview.redd.it/h6vwur34bbie1.png?width=1905&format=png&auto=webp&s=9a163ff6f503be4c175c6e5e82e2003b32df1fe0 Growth Strategy SEO has become the main acquisition channel, so I’ve decided to focus even more on it with this experiment. Almost every day, I publish either a new article or a free micro-app (as a lead magnet) for Bulk Image Generator. I also tried Google Ads, spent $20, and got a $0.35 CPC. https://preview.redd.it/3rhnzvs6bbie1.png?width=1905&format=png&auto=webp&s=f9819d1e82d3e2429d6ccb7b00dcac86a7a351c2 In comparison, the Free Image to Text Prompt Converter (one of the lead magnets) has a $0.011 CPC, which is more than 30 times cheaper than Google Ads. So I decided not to focus now on paid ads. https://preview.redd.it/p333fyl9bbie1.png?width=1905&format=png&auto=webp&s=2e96532d7709b44b7459e7ccf37ef9a0fa784728 After using our free tools, some users explore our main product - a bulk image generation service. Users pay a monthly subscription to get credits, which they can spend on image generation, face swaps, and bulk background removal. Currently, this app generates around $250 in Monthly Recurring Revenue: https://preview.redd.it/9wcm0tjfbbie1.png?width=1905&format=png&auto=webp&s=41bcdd4f7594b09087c51cc5044e4b9c94c129c8 SEO Keyword Research I use Semrush or similar tools to find keywords with a search volume greater than 300 and then write articles targeting those keywords. If the topic has enough potential, I might create a free tool (e.g., a Free Image to Text Prompt Converter) to attract more users. Occasions matter. For instance, I wrote an article about creating images for Super Bowl ads, which led to one paying user who replicated the exact creatives showcased in the article https://preview.redd.it/shpax6mlbbie1.png?width=1905&format=png&auto=webp&s=d491385761df126424c2f9ba14c5da15f8cbb603 AI Tools Aggregators This can be an excellent acquisition channel. When BulkImageGeneration.com was featured in an article on Toolify.ai, I immediately gained three paying users (\~$60). I took 2 more AI Aggregators, and on average I had CPC = $0.2, which is a fair price and usually it has ROAs > 100%. However, some major aggregators are expensive ($300–400 per placement). I want to try it once I reach $500+ MRR. Next Steps bulkimagegeneration.com currently ranks #1 in search results for relevant keywords (e.g., “bulk image generation,” “bulk image generator”). I plan to keep producing content targeting niche keywords and timely occasions. buy more places in AI Aggregators I also want to reach out to YouTubers and ask them to include Bulk in their reviews for free

I got 400+ new customers in first 48 hours after launch!!!!

Yesterday I launched my new software and got 400+ customers in 48 hours. I'm gonna break down the product and my launch strategy. What is it? Remember when Elon was taking over Twitter and he emailed the CEO of Twitter Parag Agrawal saying “What did you get done this week?” Well I turned this idea into a software lol. A couple months ago, I had a realization while talking with some friends: I love asking ChatGPT for business advice, but I never remember to actually do it. Now what if there was a pro-active AI business coach that checked in on me every week? Something to keep me accountable and track my progress building my empire. It could have a database where I could see my progress every single week!!! And what if this AI business coach was a simple email that says “What did you get done this week?” So I built this: Elon Email. A weekly 1-on-1 with Elon Musk Every Sunday night for the last month, I’ve been getting a weekly email from Elon Musk saying “What did you get done this week?” I take a few minutes to write back with everything I got done that week: new revenue metrics, a list of the new features I shipped, new employees onboarded, number of workouts, exciting calls and collaboration opportunities, etc. Then an AI trained on Elon would give me tailored advice all in my email. And here's the best part. Rather than a nice friendly soft-spoken AI, I prompted the AI to be as savage and ruthless as Elon with its business advice. And it actually worked. One user said "it's like a slap in the face". I knew with 2025 New Years resolutions coming, I needed to launch it ASAP so I pushed through an all-nighter on Friday and got it launched today. Launch strategy: \> Focus on X (fka Twitter) as main source. I have 31,000 followers on X from the last few years building startups, so I posted my launch this morning there. X is Elon's social media network now so I didn't waste time on other platforms. I basically didn't look up from my phone for like 12 hours (my wife was pissed at me because we're technically on vacation but yolo) and I commented, engaged, and DMed with everyone I could. It paid off with 50,000+ views on the post and nearly 300 likes so far. \> Purposely exclude people. Yes, I know this sounds weird, but you need to purposely exclude some people to focus on the people who will actually use your product. I know a lot of people hate Elon and will hate me for making this. I don't care. I only care about the people who will actually use it aka my customers. The same thing with making it a "savage AI". I know there will be some people who prefer a nice friendly soft AI, but that's not my customer base. The internet is big enough you can find your customer base but you've gotta be willing to exclude some people to speak to the right people! \> Free tier. The weekly Elon email and AI reply is free. I also have a paid tier for a daily email and database access. I know I'm technically losing money on API fees for the free email and AI requests, but it's a loss leader, the costs are actually quite minimal since it's only 1 API request/week, and some % will convert and already have. Doing free was worth it to give people a chance to try it. I hope this helps with your next launch!!!

Just completed a new type of language learning website - read popular stories scaled to different reading levels

As a language learner and software developer, I bootstrapped my project superlang.com over the past year working on the side. There is a mobile friendly web app now, and iOS/Android apps coming in a few months. A year ago I discovered the concept of "comprehensible input" as a way to help me learn German. Even if it's not a silver bullet, it sounded pretty great. Rather than drilling vocab or looking at grammar charts, I could "just read" and acquire the language. I picked up some fairy tales in German, and stories like Alice in Wonderland. Unfortunately, I couldn't really read them. I had to stop every sentence to look up words and try and decipher sentence constructions. Then I turned to some purpose built simple stories for German beginners. But there was a different problem... these were not really stories with any real plot. I could only read so many "Hans goes to the market" type stories before losing interest. My idea was to try to get the best of both worlds somehow. What if I could take a real story, say Alice in Wonderland (or even War and Peace), and dial the difficulty down to my level without losing the plotline. That way, beginners can start right away with something basically comprehensible. Then, you could also re-read the same story at increasing difficulty levels as you gain confidence. As a cherry on top, more illustrations would help with comprehension so each page could have a picture. Is it revolutionary? Maybe, maybe not. I am building off a well established idea of "graded readers" which are simplified stories meant for learning languages. And there are somewhat similar ideas out there now that AI is good at simplifying text, but none that really take this idea where it needs to be with many preloaded stories, multiple difficulty levels, high quality human verified text, and all the bells and whistles. I spent a year building Superlang and it is ready to put out there. Some quick notes: There are 3 languages so far, intended for native English speakers: German, French, and Spanish There are 3 difficulty levels you can set on each story: beginner (roughly A1-A2), intermediate (roughly A2-B1), and advanced (the same level as the original story, but typically B2+) There is premium version as producing the content was somewhat expensive. You can still do a lot of reading on the free version. I have done no marketing yet, except for this post :) The implementation is a combination of AI, and human proofreading and reviewing. In particular, the simplification of stories is very heavily AI driven. The illustrations for each page are AI as well. For translation, as many of you may be aware new LLM models are typically better than Google translate, but still far from perfect. I am very much a proponent of keeping real people in the loop, and so I have real people proofread the translations. That's why there are only about 700 pages of content so far and not tens of thousands. Let me know what you think, and if you find it helpful! Alice in Wonderland - beginner level German Romeo and Juliet - beginner level Spanish

An Algorithm for Making Truly Stand-Out Advertising Content (+ something more | Part 1)

Hi everyone. my friend and I are software engineers and new to marketing. A few months ago we decided to leverage our software skills for a colleague in ecommerce. It started by implementing a Flux.1 model, then began using texture-based recreations with a canny mask, and then found that we could optimize on both with an added layer of inpainting...and the list goes on. This is the first of a series of posts here about it and I look forward to learning from your feedback. I realized that the most difficult parts of the marketing process when I started out (and most likely for other beginners too) are: Customer Acquisition Costs / Brand Differentiation: Competition is intensifying and it is getting more difficult to stand out in crowded markets and target ad spend more effectively. Maintaining Authenticity at Scale / Data Overload: Balancing growth with authenticity and leveraging available data to successfully engage with customers is a big ask. Creative Fatigue: Maintaining multiple marketing channels in hard, and it becomes harder when you're constantly demanding more and more creative content for campaigns. For 1) I tried using AI to help me summarize, systematize, and gain insights from the information available for a given brand or product (from a page link, prompt, input image, etc.). I know AI is everywhere now, many people are using it unnecessarily and many people are skeptical about it. However, I know from experience, that it is quite helpful in gaining insights/summarizing large amounts of data, and helping people make sense of the creative content, strategy, campaign, etc., that should be created. For 2) By leveraging reviews, forums, and other relevant brand information, AI is able to maintain the story that your brand currently tells, and enhance it based on how your customer base. For 3) Faster results means less creative fatigue- this translates to an easier time managing omnichannel marketing efforts and scaling advertising. If you're interested, please have a look at the result at madsimpleads.com You’ll need to log in to access the solution, and I'll add credits to your account to try it out! (we want to prevent from random people or bots using it because I'm paying to multiple providers for model access). DM me here or drop me a line at austin@madsimpleads.com if you need more. Thank you so much, I'll be happy to get your thoughts I hope the website will help with your advertising, please reach out if you like what I do and want to support the project! Disclaimers: the website looks a bit rough in terms of UI/UX, but we tried focusing on the functionality first available on mobile, works better on desktop I hope this doesn't come across as trying to advertise for my business or breaking any of the community rules. genuinely looking for feedback. Thank you

I made a super niche app for sailors and scaled it to 500k downloads

I started developing this app in 2016, and it was my first app ever. I already had several years of programming experience. Since I was studying maritime navigation, I came up with the idea of creating a maritime app to help students with various nautical calculations and learn maritime regulations. Although I had no experience in mobile app development, I chose the Ionic framework and started development gradually. First Version The first version took me about four months to develop because I literally had to learn everything from scratch: how to develop mobile apps, how to publish them, and everything needed to enable downloads on the app stores. Many of you might recognize me from my story about developing Sintelly and its late monetization. I made the same mistake with this maritime app. At that time, in my country, there was no possibility of earning through in-app purchases, only through ad displays. Since the app was predominantly downloaded in countries like India, the Philippines, and Indonesia, the ad revenue was quite low, and after some time, I removed the ads. Abandonment and Realization As I started developing other apps, this one fell into obscurity. I even just remembered that I needed to renew the domain, which resulted in losing it. The domain buyer tried to sell it back to me for years for $20k, which was absurd. All this led me to rebrand and start working on this app again. Interestingly, during these 8 years, the app never showed a declining trend in installations or active users. I'll share some numbers to give you insight: Total installations (Android + iOS): 501,000 Active installations (Android): 48,000 Monthly active users: 20,000 Average rating: Android 4.8, iOS 4.7 When I considered these numbers, I realized they weren't bad at all and that I was far ahead of most competitors. This led to my decision to rebrand and create a new website. I quickly built the website using WordPress and published lots of existing content from the app. What surprises me is that today, after a year and a half, the website has about 8-10k monthly organic visits. Choosing a Direction Based on all this, I decided it was time to create a Premium version and start selling the app. Since I've been working with AI for many years (which I've written about here), I started thinking about using AI to help seafarers speed up some of their tasks. This led to the idea of creating a multi-agent system equipped with numerous tools to help seafarers. I developed various agents with functionalities, including retrieving maritime weather information, locating and tracking ships, doing various nautical calculations, calculating the shortest maritime routes and unit conversions, and learning about all courses and maritime regulations. All this required considerable work, but thanks to tools like Cursor and Claude, I implemented it in less than four weeks. Last week, I published this new version and started selling subscriptions, and I can already boast that I've earned slightly over $100. This isn't much, but I'm happy to see my first app generating some income, which I always thought impossible. Along this journey, I learned many lessons, and the most important one is to never give up or write off a product. With a little effort, everything can be brought back to life and secure at least some passive income, enough for your morning coffee. Additionally, I learned how to develop mobile apps, which has shaped my career since then. If it weren't for this app, I probably would never have become a developer. I have numerous plans for what to add next and how to improve. I'll base everything on AI features and push the app in that direction.

How qre you all launching all this project so quick

Been in this sub for 2 month and i just cant figure it out how are you all finding problems to solve and how are you all launching all this project so fast. I literally saw few post who launch projecgs each month.Are you most of it fone solo or with a team .What trch stack are you all hsing and how are you all implementing AI api so fast while it just taking me months to just learn javascript basics. Is there some thing i am missing or afe all this boiler plate site wuth api implementation

I grew my mobile app to 1.4 million downloads

I started developing the app in early 2017, well before the AI era, when mobile apps were at their peak popularity. My idea was to create an app for emotional and psychological support in the form of helpful articles and various quizzes, such as personality assessments and life satisfaction tests. I named the app "Emotional Intelligence" because this keyword showed good ASO potential for positioning at the top of mobile stores. This proved to be accurate, and the app quickly gained traction in terms of downloads. A major problem I faced then was monetization. Unfortunately, in my country, it wasn't possible to sell through Google Play then, so I could only display ads. I started with Google AdMob, earning $2000 monthly after just a few months. The app then got about 1500 organic downloads daily and quickly surpassed 500,000. Three years after launching the app, I decided it was time for branding to build recognition. By combining the words "sentiment" and "intelligence," I came up with "Sintelly." I then pushed the app toward a social network, which differed from the right move. Adding features like discussion forums for problems, likes, and comments would result in even more growth, but the opposite happened. The app started declining, and I began investing in advertising campaigns. I managed to maintain a balance between income and expenses but without any profit. Then COVID-19 hit, and everything went downhill. I had to give up development and find a job as a developer to ensure my livelihood. Two years passed since I gave up, and that's when ChatGPT started gaining popularity. This immediately showed me how to steer the app towards active support for well-being questions. As I'm not an expert in psychology, I found several external psychotherapists who helped me put together CBT therapy, which I then implemented through a chatbot. This is how the new Sintelly app was born, with its main feature being a chatbot system composed of 17 AI agents that adapt to the user and guide them through a five-phase CBT therapy (I'll write a post about the technology). In addition to the agents, I added various exercises and tests to provide better personalization for the user. Initially, I made all of this free, which was also a mistake. I followed the principle of first showing what the app can do and gathering enough new users before starting to charge. I started selling subscriptions at the beginning of July, and since then, the app has had stable growth. If you want a check app, here is the link. Lessons learned: If things are working, don't touch them Start selling immediately upon app release; there's no need to wait Regularly test prices and types of subscriptions Onboarding is the most essential part of the app because most users buy subscriptions during onboarding It's essential to listen to user feedback. From day one, have a website and work on content to generate organic visits and redirect users from the web to the mobile app Stats: Over 1.4 million downloads 4.4 rating Only 40,000 active users (I had a massive loss during the period when I gave up) 280 active subscribers $3000 monthly revenue Next steps: Work on improving the Agent AI approach Setting up email campaigns and transactional emails Introducing in-app and push notifications Introducing gamification Potential for B2B I hope you can extract useful information from my example and avoid repeating my mistakes. I'm interested in your thoughts and if you have any recommendations for the next steps. I'm always looking to learn and improve.

What are Boilerplates?

What are Boilerplates? Boilerplate originally referred to the rolled steel used to make boilers for steam engines in the 19th century. Over time, the term evolved to describe any standardized piece of text or code that can be reused without significant changes. Interest in SaaS has been on the rise, and many more people now want to build products. However, building products from scratch takes a lot of time, and it can be extremely frustrating. Enter SaaS Boilerplates With the standardization of stacks and basic systems that govern SaaS tools, it has become evident that there was a need, and the time was ripe for SaaS Boilerplates. SaaS Boilerplates come with landing pages, website components, authentication modules, payment modules, and various other standard features that can save developers a significant amount of time and cost. The market is flooded with Boilerplates for various tech stacks, such as NextJS, Laravel, Swift, NuxtJS, and so forth. Pros and Cons of Boilerplates Pros Save a significant amount of time and money Reduce frustration for developers as the redundant tasks are taken care of Boilerplates often follow best practices For anywhere between $49 and $299, they provide terrific value for those looking to build something very quickly Most importantly, Boilerplates also enable aspiring founders and builders with limited technical resources or abilities to ship their products faster and more cheaply. They are beacons of hope for non-technical founders looking to build a product quickly. Cons Limited flexibility May become outdated fairly quickly Setting them up still requires time Similar landing pages and design themes can make the product look like a clone Marc Lou’s Shipfast For most of us, Marc Lou popularized the idea of SaaS Boilerplate. Marc Lou launched Shipfast in August 2023. He had built 27 projects prior to this and Shipfast was nothing but all his basic code organised properly. At that time, there were no solid NextJS boilerplates, and Shipfast just took off. He got traction via Product Hunt, Twitter and Hacker News and soon Shipfast went viral. Shipfast now generates $130K/mo, just 9 months after its launch. Marc has been building Shipfast in public, which has led to a lot of interest in SaaS Boilerplates. The market is now flooded with boilerplates for every major tech stack. Marc reaped the benefits of the first mover’s advantage as well as the social proof via his Shipfast community. I don’t think any other boilerplates are as successful as Shipfast, but there are quite a few good ones out there. Shipixen* has grossed over $20K in the 5 months Makerkit* does \~$3500/mo Moreover, there are many open-source boilerplates available for popular stacks such as NextJS. The Evolution of Boilerplates Boilerplates are quickly turning into no-code/low-code code generation tools. For instance, Shipixen allows you to generate custom code for landing pages, waitlist pages and blogs using a simple User Interface. Boilerplates are perfectly posied to sit between code and no-code. Allow the flexibility of code with the interface of a no-code tool — that will be the core value proposition of SaaS boilerplates. Should you build a Boilerplate? Well, the market is flooded, but I believe there’s still an opportunity to leverage boilerplates. You can build boilerplates for certain types of apps or tools, such as Chrome extensions Boilerplates can act as a great lead funnel for building out a great productized services business No-code/low-code code generation boilerplates can become a big thing if you can help build complex tools Niche tech stack boilerplates may still be lucrative Known strategies for successfully building a boilerplate 👇🏻 Shipfast thrives because of social proof and community SaaSRock generates most of its traffic from its Gumroad listings and blogs Usenextbase and Shipixen are being built in public Many boilerplates start with waitlists They have a very clear value proposition around saving time and cost Design & No-Code Boilerplates Here is the corrected version with improved grammar and clarity: While SaaS (code) boilerplates have become fairly popular, other types of boilerplates are emerging in the market, such as design boilerplates and no-code boilerplates. To be honest, design boilerplates have been around for a while. You will find numerous landing page packs, component libraries, and so forth. Makers are now building kits that leverage standard libraries and technologies such as Tailwind CSS, Daisy UI, and more. Nick Buzz from the famous baked.design has this *50 Landing Page Design Kit* in Tailwind CSS & Figma which is wildly popular. Lastly, there is a trend of no-code boilerplates as well. Mohit is building a Bubble Boilerplate for the popular no-code platform — Bubble. All in all, I think that people want to build products and build them fast. Boilerplates help them save a significant amount of time and cost. More importantly, boilerplates are impulse purchases for people who have not shipped but who want to ship. Introducing BuilderKit.ai We have been building AI SaaS tools for quite a while now. 10+ products across text, image, speech, RAG — we have built em all. We figured that it seems easy but actually building these so called AI Wrappers can be time consuming and frustrating — there is a lot of nuance to it. So we built BuidlerKit.ai — a NextJS SaaS Boilerpalte It takes care of everything from landing pages, authentication, dashboarding, emails, SEO to payments — everything that you need to build your tool. It also comes with 8+ production-ready apps. Moreover, the BuilderKit community is an exclusive community of AI SaaS builders (Pro Only Access) The Pre Orders are now live at https://www.builderkit.ai (First 100 Customers get $100 Off — I think we have already done \~20 odd orders since the announcement yesterday, Grab your seat asap!) Starter Plan $49, Pro Plan @ $99

I just built footyGPT.com , an AI assistant for football stats, data and data-backed predictions

Hey Amigos! I am based in London and I build lots of fun tools and websites in the sports data space to help sports bettors make better data-driven decisions. One of my recently launched ones is footyGPT.com I have tried to launch this earlier in 2023 but my team were not able to achieve the end goal (I am a non-technical founder) Funny story, I bought the domain footygpt(dot)com back in 2023 and let it expire because i felt like since we weren't able to acheieve the end goal, there was no need to keep the domain. But 2 months ago I started working on it one more time with a different team, and since AI has become "more friendly" than it was early in 2023, it was a much smoother ride and i was so scared someone else had already bought the domain, only to find out it was still available to buy! I was so scared I lost such a clean domain. Below is an example of how footyGPT works: Ask FootyGPT for Predictions for a Given Fixture how footyGPT works \(case study\) Ask FootyGPT to Scrape and Summarize Data from a Stats Website using footyGPT to scrape football stats websites Ask FootyGPT for Sentiments and Online Opinion About a Given Match or Events. ask footygpt for up to date sentiments and opinions about football matches Ask FootyGPT to Find Teams with Certain Streaks, Trends, or Stats https://reddit.com/link/1frdk04/video/9oyaj5ldqjrd1/player If you are into football (soccer) please give it a spin and let me know your thoughts! Cheers Amigos

I Launched a Side Project That People Love, But Scaling It Is Brutal

I Built a Side Project with Great Engagement—But It’s Still Not Making Money Six months ago, I started a side project in the consumer AI space: opencharacter.org. It’s been a grind, but I’ve built something people actually love—high retention, strong engagement, and users spending a ton of time on the platform. By all product metrics, it’s a success. But financially? It’s not quite there yet. The biggest challenge hasn’t been technical, managing infrastructure, or even dealing with a community. It’s distribution. Getting people to actually find and use your side project at scale is insanely hard. What’s Worked Reddit – Thoughtful, non-spammy comments in relevant threads drove early users. Instagram – Short-form videos brought in surprising traction. Paid ads – Somewhat effective, but tough to balance customer acquisition costs and revenue. What Hasn’t (Yet) TikTok – Dozens of videos later, still struggling to make it a reliable growth channel. Discord – Great for engagement, but not a strong acquisition channel. Recently, I brought on a co-founder who has done over 100 million views on Instagram Reels in under two years, so I’m hopeful we can crack the growth formula. Because without a scalable system for getting users, even a great side project won’t reach its potential. If I could start over, I’d think much more about distribution before building. Would love to hear from others—how do you drive growth for your side project?

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

I built a free LinkedIn planning tool with integrated GPT-4

Last week I launched my product scribery.eu after building it over the the last 2 months on my own. For that, I used LowCode-Tools like FlutterFlow, Stripe or Firebase, because for me it was the only way to publish it without security risks and having a release date in this year. The main feature is to creating LinkedIn posts with help of AI (GPT-4) and schedule them. In 5 minutes, I scheduled 10 posts for the next 4 weeks! This is an absolute time saver for every entrepreneur who’s not having enough time to advertise their product over LinkedIn. I would be very happy, if you would test my product for free with the code Reddit2024 Normally the one-time-payment is 49€ for Premium, but with the code above you get Premium for free. Comment to learn more about me and scribery scribery in action!

I built an ai startup, got paying customers—then made it free because it felt like a scam

A few months ago, I launched my first AI startup, AppScriptor. It was an AI-powered tool that could generate mobile apps automatically. At first, I was thrilled—I got a lot of reactions, paying customers, and people excited about the idea. But the more I worked on it, the more I realized a major flaw: real-time app previews were nearly impossible. Users wanted instant updates and fast iterations, but the technology just wasn’t there yet. I felt guilty charging people for something that wasn’t delivering the experience they expected. It wasn’t bad, but it wasn’t good enough. I didn’t want to keep collecting payments while knowing I couldn’t improve it quickly enough—so I made it completely free. Eventually, I shut it down. That experience taught me a crucial lesson: people don’t just want an MVP; they want something useful. That’s why I built StarterPilot—an AI-driven platform that helps entrepreneurs validate ideas, generate branding assets, and build landing pages effortlessly. This time, I’m making sure it actually delivers. What’s the hardest part of launching a startup for you? Would love to hear your experiences!

How I went from $27 to $3K as a solopreneur still in a 9-5

My journey started back in November 2023. I was scrolling through Twitter and YouTube and saw a word that I had never come across before. Solopreneur. The word caught my eye. Mainly because I was pretty sure I knew what it meant even though it's not a word you'll find in the dictionary. I liked what it was describing. A solo entrepreneur. A one man business. It completely resonated with me. As a software engineer by trade I'm used to working alone, especially since the pandemic hit and we were forced to work remotely. See, I always wanted to ditch the 9-5 thing but thought that was too big and too scary for a single person to do. Surely you would need a lot of money to get started, right? Surely you would need investors? The whole concept seemed impossible to me. That was until I found all the success stories. I became obsessed with the concept of solopreneurship. As I went further down the rabbit hole I found people like Justin Welsh, Kieran Drew and Marc Louvion to name a few. All of whom have one person businesses making huge money every year. So I thought, if they can do it, why can't I? People like this have cleared the pathway for those looking to escape the 9-5 grind. I decided 2024 would be the year I try this out. My main goal for the year? Build a one man business, earn my first $ online and learn a sh\*t ton along the way. My main goal in general? Build my business to $100K per year, quit my 9-5 and live with freedom. From December 2023 to February 2024 I began brainstorming ideas. I was like a lost puppy looking for his ball. How on earth did people find good ideas? I began writing everything and anything that came to mind down in my notes app on my phone. By February I would have approximately 70 ideas. Each as weird and whacky as the other. I was skeptical though. If I went through all the trouble of building a product for one of these ideas how would I know if anyone would even be interested in using it? I got scared and took a break for a week. All these ideas seemed too big and the chance that they would take off into the atmosphere was slim (in my mind anyways). I was learning more and more about solopreneurship as the weeks went on so I decided to build a product centered around everything I was learning about. The idea was simple. Enter a business idea and use AI to give the user details about how to market it, who their target customers were, what to write on their landing page, etc. All for a measly $27 per use. I quickly built it and launched on March 3rd 2024. I posted about it on Indie Hackers, Reddit and Hacker News. I was so excited about the prospect of earning my first internet $! Surely everyone wanted to use my product! Nope...all I got was crickets. I was quickly brought back down to earth. That was until 5 days later. I looked at my phone and had a new Stripe notification! Cha-ching! My first internet $. What a feeling! That was goal number 1 complete. It would be another 6 days before I would get my second sale...and then another 15 days to get my third. It was an emotional rollercoaster. I went from feeling like quitting the 9-5 was actually possible to thinking that maybe the ups and downs aren't worth it. On one hand I had made my first internet dollar so I should my ecstatic, and don't get me wrong, I was but I wanted more. More validation that I could do this long term. By May I was starting to give up on the product. I had learned so much in the past few months about marketing, SEO, building an audience, etc. and I wanted to build something that I thought could have more success so I focused on one critical thing that I had learned about. What was it? Building a product that had SEO potential. A product that I knew hundreds of people were looking for. See this was my thinking - If I could find a keyword that people were searching for on Google hundreds/thousands of times every month and it was easy to rank high on search engines then I would go all in (in SEO land this equates to a Keyword that has a Keyword Difficulty of = 500). I began researching and found that the keyword "micro saas ideas" was being searched for around 600 times each month. Micro Saas was something that really interested me. It was perfect for solopreneurs. Small software products that 1 person could build. What's not to like if you're in the game of software and solopreneurship? Researching keywords like this became like a game for me. I was hooked. I was doing it every day, finding gems that were being searched for hundreds and thousands of times every month that still had potential. That's when I came up with my next product idea. I decided to create a database of Micro Saas Ideas all with this sort of SEO potential. See if you can build a product that you know people are looking for then that's all the validation you need. So I put this theory to the test. I created a database of Micro Saas Ideas with SEO Potential and launched it in June 2024. This time it was different. I made $700 in the first week of launching. A large contrast to my previous failed attempt at becoming the worlds greatest solopreneur. Since launch I have grown the product to $3K and I couldn't be happier. I know what you're saying, $3K isn't a lot. But it's validation. It's validation that I can earn $ online. Validation that I can grow a business and it gives me hope that one day I'll be able to quit that 9-5 grind. My plan is to keep growing the business. I expect there to be a few challenges up ahead but I'll tackle them as I go and learn from the failures and successes. I have a newsletter where I share Micro Saas Ideas with SEO potential every week which I'll leave below in the first comment. Feel free to come along for the ride. If not I hope this post brings you some value If you're thinking about starting as a solopreneur, stop thinking and start doing, you won't regret it.

I built an app to find who’s interested in your app by monitoring social media

Hi everyone! I hope you’re all doing great folks! I’d love to know your thoughts about what I’ve been working on recently! 🙏 If you’re busy or wanna see the app scroll to the bottom to see the video demo, otherwise, continue reading. Very brief presentation of myself first: I’m Marvin, and I live in Florence, Italy, 👋 This year I decided to go all-in on solopreneurship, I’ve been in tech as Software Engineer first, and then in Engineering Leadership for 10+ years, I’ve always worked in startups, except for last year, when I was the Director of Engineering at the Linux Foundation. Follow me on X or subscribe to my newsletter if you’re curious about this journey. The vision Most founders start building digital startups because they love crafting and being impactful by helping other people or companies. First-time founders then face reality when they realize that nailing distribution is key. All other founders already learned this, most likely the hard way. The outcome is the same: a great product will unlikely succeed without great distribution. Letting people know about your product should be easier and not an unfair advantage. The following meme is so true, but also quite sad. I wanna help this to change by easing the marketing and distribution part. https://preview.redd.it/g52pz46upqtd1.png?width=679&format=png&auto=webp&s=cf8398a3592f25c05c396bb2ff5d028331a36315 The story behind Distribution is a huge space: lead generation, demand generation, content marketing, social media marketing, cold outreach, etc. I cannot solve everything altogether. A few months ago I was checking the traffic to a job board I own (NextCommit). That's when I noticed that the “baseline” traffic increased by almost 10x. 🤯 I started investigating why. I realized that the monthly traffic from Reddit increased from 10-ish to 350+. Yeah, the job board doesn’t get much traffic in total, but this was an interesting finding. After digging more, it seems that all that increase came from a single Reddit comment: https://www.reddit.com/r/remotework/comments/1crwcei/comment/l5fb1yy/ This is the moment when I realized two things: It’s cool that someone quoted it! Engaging with people on Reddit, even just through comments, can be VERY powerful. And this was just one single comment! https://preview.redd.it/nhxcv4h2qqtd1.png?width=1192&format=png&auto=webp&s=d31905f56ae59426108ddbb61f2d6b668eedf27a Some weeks later I started noticing a few apps like ReplyGuy. These were automatically engaging with Reddit posts identified through keywords. I decided to sign up for the free plan of ReplyGuy to know more, but many things didn’t convince me: One of the keywords I used for my job board was “remote” and that caused a lot of false positives, The generated replies were good as a kickstart, but most of the time they needed to be tuned to sound more like me. The latter is expected. In the end, the platform doesn’t know me, doesn’t know my opinions, doesn’t know my story, etc.. The only valuable feature left for me was identifying the posts, but that also didn’t work well for me due to false positives. I ended up using it after only 15 minutes. I’m not saying they did a poor job, but it was not working well for me. In the end, the product got quite some traction, so it helped confirm there’s interest in that kind of tool. What bothered me was the combination of auto-replies that felt non-authentic. It’s not that I’m against bots, automation is becoming more common, and people are getting used to it. But in this context, I believe bots should act as an extension of ourselves, enhancing our interactions rather than just generating generic responses (like tools such as HeyGen, Synthesia, PhotoAI). I’m not there yet with my app, but a lot can be done. I'd love to reach the point where a user feels confident to automate the replies because they sound as written by themselves. I then decided to start from the same space, helping engage with Reddit posts, for these reasons: I experienced myself that it can be impactful, It aligns with my vision to ease distribution, Some competitors validated that there’s interest in this specific feature and I could use it as a starting point, I’m confident I can provide a better experience even with what I already have. The current state The product currently enables you to: Create multiple projects and assign keywords, Find the posts that are relevant for engagement using a fuzzy match of keywords and post-filtered using AI to avoid false positives, Provide an analysis of each post to assess the best way to engage, Generate a helpful reply that you’d need to review and post. So currently the product is more on the demand gen side, but this is just the beginning. I’m speaking with people from Marketing, Sales, RevOps, and Growth agencies to better understand their lives, struggles, and pain points. This will help me ensure that I build a product that enables them to help users find the products they need. I’m currently looking for up to 10 people to join the closed beta for free. If you’re interested in joining or to get notified once generally available you can do it here! https://tally.so/r/3XYbj4 After the closed beta, I will start onboarding people in batches. This will let me gather feedback, iterate, and provide a great experience to everyone aligned with my vision. I’m not going to add auto-reply unless the conditions I explained above are met or someone convinces me there’s a good reason for doing so. Each batch will probably get bigger with an increasing price until I’m confident about making it generally available. The next steps The next steps will depend on the feedback I get from the customers and the learnings from the discovery calls I’m having. I will talk about future developments in another update, but I have some ideas already. Check out the demo video below, and I'd love to hear your thoughts! ❤️ Oh and BTW, the app is called HaveYouHeard! https://reddit.com/link/1fzsnrd/video/34lat9snpqtd1/player This is the link to Loom in case the upload doesn't work: https://www.loom.com/share/460c4033b1f94e3bb5e1d081a05eedfd

How I Automated Amazon Affiliate Marketing: A Developer's Journey

From Manual Labor to 1000x Efficiency As a developer who ventured into affiliate marketing, I discovered a significant gap between technical possibilities and current practices. This revelation led me to create AutoPin, a tool that's now helping hundreds of affiliate marketers reclaim their time. The Problem: A Time-Consuming Reality Every affiliate marketer knows this scenario: you spend hours copying and pasting links, checking prices, and updating product information. I found myself dedicating 4-6 hours daily to these repetitive tasks. As a programmer, this felt fundamentally wrong. The typical affiliate marketing workflow looked like this: Find promising products Generate affiliate links one by one Monitor price changes manually Check product availability regularly Update content when things change Repeat this process daily This manual process had several critical issues: Time Waste: 20-30 hours weekly on repetitive tasks Missed Opportunities: Unable to scale beyond 100 products Human Error: Inevitable mistakes in manual updates Delayed Updates: Lost commissions due to outdated information The Solution: Building AutoPin After three months of development and six months of testing, I created a system that could: Generate hundreds of affiliate links in minutes Monitor price changes automatically Update product availability in real-time Export data in multiple formats Scale infinitely without additional effort Real Results, Real Impact The impact was immediate and significant: 📊 Efficiency Metrics: Link generation: From 2 minutes per link to 0.1 seconds Monitoring capacity: From 50 to 5000+ products Update frequency: From daily to real-time Error rate: Reduced by 99.9% 💡 User Success Stories: "Increased my product portfolio by 10x without adding work hours" "Revenue grew 300% in the first month" "Finally able to focus on content creation instead of link management" Technical Insights The system architecture focuses on three core components: Data Extraction Engine Efficient web scraping Rate limiting and proxy management Data validation and cleaning Real-time Monitoring System Websocket connections for instant updates Queue management for large-scale monitoring Smart scheduling based on price volatility Export Framework Multiple format support (CSV, HTML, Markdown) Custom templating engine Batch processing capabilities The Future of Affiliate Marketing Automation We're currently developing AI capabilities to: Generate product descriptions automatically Optimize link placement for conversion Predict price trends and best promotion times Create content variations for different platforms Key Learnings Automation is Essential The future of affiliate marketing lies in automation. Manual processes simply can't compete with automated systems in terms of efficiency and accuracy. Focus on Value Creation When marketers spend less time on repetitive tasks, they can focus on strategy and content quality. Scale Matters With automation, the difference between managing 10 products and 1000 products becomes minimal. Getting Started If you're an affiliate marketer spending hours on manual tasks, it's time to automate. Here's what you can do: Analyze your current workflow Identify repetitive tasks Start with basic automation Scale gradually Monitor and optimize Conclusion The transformation from manual to automated affiliate marketing isn't just about saving time—it's about unlocking potential. When you remove the tedious aspects of affiliate marketing, you create space for creativity, strategy, and growth. Want to experience the difference? Visit AutoPin at autopin.pro and join the automation revolution. Remember: The best time to automate was yesterday. The second best time is now. About the Author: A developer turned affiliate marketer who believes in the power of automation to transform digital marketing. #AffiliateMarketing #Automation #Programming #DigitalMarketing #SaaS #ProductivityTools

Solo Entrepreneurs, This One’s for You! After Studying 15+ AI Directories, I’m Building a New Hub for AI, SaaS, and Tools (but the concept is unique)—Submit Yours for FREE 🚀 (Big Companies, Please Stay Away)

I’ve been in your shoes—tight budgets, limited resources, and a constant search for marketing solutions that actually work. Lately, I’ve been checking out more than 15 AI directories here on Reddit, and honestly, they all seem to have the same issues. They’re cluttered, confusing, and often filled with sponsored listings that don’t really help anyone. This got me thinking: if these tools aren’t helping users, how can any of our tools succeed? After a lot of thought (and some serious brainstorming), I’ve come up with an idea that I think could be a game-changer. This isn’t just another directory. I’m aiming to build something that’s genuinely useful for solo entrepreneurs and regular users alike. My goal is to create a platform that people actually want to use, because when that happens, your tools get natural, organic exposure. I’m also planning to integrate AI into the platform to make it even more powerful. I can’t spill all the details just yet If you want to get in early, I’m offering to add your tools to the platform for free, especially if you’re a solo entrepreneur. I’m still working out the details, but I’m aiming to launch within the next 1-2 months. Here’s how you can get involved: comment below with the name of your SaaS, AI, or tool, along with a short description of why it’s helpful and why it should be included. I haven’t finalized the domain yet, but for now, I’m planning to host it on my subdomain: toolkit dot unwiring dot tech

I’ve built a gaming recommendation and exploration platform called Which Game Next

Hello there! Me and a few of my best friends are software engineers, and we’ve been working part-time on developing a side project for the past 12 months. It’s called www.whichgamenext.com, and we’ve recently launched into open beta for everyone to check out. Your feedback would be invaluable to us! Our aim has been to build a gaming recommendation engine, alongside providing market oversight for where you can legally and officially purchase or obtain modern games from multiple stores and/or subscriptions. It’s often difficult to figure out what you have access to if you only have a single specific subscription, like Game Pass PC, or if you’re only interested in games on GOG/Nintendo (what a mix!). We started by identifying the available digital stores and subscriptions and slowly compiling our database using multiple automated services to gather data on these games. Think JustWatch, but for games! One major service we’ve partnered with is IGDB, which has been supplying us with JSON data dumps that served as the initial seed for our game data. A massive thank you to them for their continued support! With the data in place, we’ve been focusing on exploring new features. So far, this has included private and public user-generated lists, personal backlog tracking, and the ability to like or dislike games. We’re now improving our recommendation engine, tackling the complexities that come with it, and having a lot of fun along the way. We’re utilising modern AI strategies and solving fascinating problems related to large-scale data aggregation. We truly can’t wait to share this fantastic work! In addition to this, you can soon expect curated collections, articles about games, and supporting links to help you make informed, unbiased purchasing decisions. Your shared data will drive the recommendations. But it doesn’t stop there—we have plenty of other features on our radar, such as importing games from your favourite stores, syncing your gameplay time, surfacing data like “How Long to Beat,” and creating new and exciting ways to interact with this growing community! This is a passion project created by a group of gamers who want to spend their time and money wisely, without purchasing biases. Since it’s a side project, we mostly work on it at night, but we’re excited to grow the community, share our vision, and, who knows, maybe one day make it our full-time job! Let’s dive into the technical details: • Monorepo architecture: This speeds up development by sharing libraries, living style guides, configs, etc. Nx.js has been brilliant, enabling us to create a dependency graph of changes and only build/deploy what’s modified in a PR. • AWS: We’re using the free tier (with a few exceptions where we pay for smaller services). Achieving self-sufficiency is critical for us. Additionally, we applied to the AWS Startup Foundation programme and received $1,000 in AWS credits, which has been incredibly helpful! • Infrastructure: Fully deployed as code with Terraform. • Backends: Built using Express and Nest.js, split into around 40 projects and counting! Each project plays a unique role in gathering and syncing game data. • Scalability: Designed from the ground up, utilising AWS Lambdas with auto-scaling and load balancing. • Databases: We use Postgres with RDS and DynamoDB for storing various data. • Frontend stack: Built with React, Next.js, Tailwind, Zustand, TanStack Query, Jest, and Storybook. • CI/CD: Managed with GitHub Actions and Amplify hooks for deploying the frontends. • Admin portal: We’ve built a bespoke CMS to control the main website. It synchronises with external services, tracks game data changes, and allows us to selectively apply ‘patches’ from sites like IGDB. The system also includes data override and rollback capabilities, ensuring we maintain control over game data. • Automation: Partially automated, so manual intervention is rarely needed. • Scraping tools: Fully integrated into the admin portal with log trail capabilities. • Cloudflare: Used for on-the-fly image transformations; we’re considering moving to it full-time as our CDN for free WebP conversions. • Authentication: Handled by Cognito, with a custom frontend built from scratch. Key learnings so far: • AWS cold starts: Not ideal! While the platform is still new, we ping endpoints to keep them responsive. This won’t be an issue once traffic increases. • Lambda memory matters: We learned the hard way that low-memory configurations can delay responses by 2-3 seconds. • DynamoDB partition keys: If not designed correctly from the start, you might have to start over (yes, we’ve been there!). • GitHub Actions: Setting up node\_modules cache reuse takes time, but it’s worth it—don’t give up! We don’t know where this project will take us yet, but it’s been a fantastic journey so far. We’ve learned a lot, explored technologies we don’t typically use in our day jobs, and built something we’re genuinely passionate about. Your feedback would mean the world to us. What do you think of what we’ve done so far? What would you like to see added? Is this a service you’d use? Do you see the value in it as we do? Thanks for reading, and we hope to see you in the comments! (or our newly created /r/whichgamenext

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!

PlumbingJobs.com - I launched a niche job board with hand-curated jobs for plumbers. Here's the summary of how it's going after the 3rd month

On October 12th 2024, I launched PlumbingJobs.com, and this is my first update (January 2025) in what I hope will be a long journey. To stay accountable and track progress, I’ll be sharing monthly updates about the site's stats, achievements, challenges, and my plans moving forward. While these posts are mostly to document the journey, I hope they’ll also be helpful to others, especially members of r/SideProject who might be working on their own first online projects. If this post isn’t a good fit for this subreddit, I’m happy to remove it or move updates elsewhere. The goal for PlumbingJobs.com is clear: to become the #1 job board for plumber jobs, featuring hand-picked opportunities the plumbing industry. Let’s dive right in: Statistics update ~ 4th Quarter of 2024 |\-|October|November|December| |:-|:-|:-|:-| |Jobs Posted:|2|16|43| |Paid Post:|0|2|2| |Free Post:|0|1|2| |Visitors:|72|138|1,164| |Avg. Time Per Visit:|1 min. 24 sec|2 min. 15 sec|3 min. 41 sec| |Pageviews:|196|308|2,590| |Avg. Actions:|1.1|2.3|2.3| |Bounce Rate:|87%|73%|40%| I'm not a very technical guy and I don't know how to code. So the best way for me was learning to build it using Wordpress through YouTube. Also, I believe in the power of a great .COM domain name, and the stats from the first three months have only reinforced that belief: 49.2% of traffic comes directly from users typing the URL into their browsers. 48% of traffic is from search engines like Google and Bing. The remaining 1.8% comes from social media and other backlinks. Pricing Tiers and Early Wins I offer three pricing tiers for job listings: Free Listing: Basic exposure for job openings. Silver Listing ($45): Greater visibility and placement on the site. Gold Listing ($95): Premium visibility and enhanced promotion. To my surprise, my very first sale in October was a Gold Listing! That initial $95 sale was the motivation I needed to keep building. Later that month, I sold a Silver Listing, bringing my total revenue for October to $140. The same revenue was generated in December 2024, showing consistent early interest. Steps Taken in December To boost SEO and add value to the site, I created a Plumbing Directory, featuring: Plumbing companies across the U.S. Their stories, contact information, logos, addresses, business hours, and more. This directory serves as free marketing for these businesses and increases the likelihood they’ll discover my site and support it by posting job openings. Plans Moving Forward Social Media Marketing: I plan to automate posts using AI to expand reach and drive more traffic to the site. Consistency in Job Postings: I’m committed to posting 2–3 plumbing jobs daily to keep the site fresh and useful for plumbers seeking work. Looking forward to grow this niche job board slowly but surely this 2025. If you have any questions, concerns, come across glitches - feel free to reach out, happy to chat. Thank you all again, and see you in a month. Romel@plumbingjobs.com

Acquired our first 10 customer for Trustty Reporter - an AI first Business Intelligence Platform.

Hi All, My co founder and I have built Trustty Reporter (www.trusttyreporter.com).  We spent the last couple of months working on launch our AI powered BI platform and gain our first 10 users. We wanted to reach out the community to get your feedback on the platform and how we can take it to the next level. Below is a brief introduction of the platform: Trustty Reporter – your AI-first business intelligence partner that transforms data into actionable insights in minutes! Imagine turning complex data and documents into easy-to-understand reports with clear recommendations, all at the click of a button. No more BI complexities—Trustty Reporter makes business insights accessible to everyone, from business owners to CXOs. Here’s Why You’ll Love Trustty Reporter: Instant Insight Generation – Convert raw data into insights in just 5-15 minutes. No expertise needed! Easy Reporting Access – Persistent reports that let you track, compare, and build strategies over time. Tailored Solutions for Business Problems – Just describe your challenge, and Trustty Reporter delivers custom insights. Interactive Reports – Dive deeper with a chat interface that offers further clarification and recommendations. By now you would have realized that this aces any traditional BI tools. That aside, it’s better than the likes of ChatGPT and Claude since you don’t have to supply multiple prompts to get context specific insights catering to your business! File Requirements: For Excel files with multiple sheets/tabs: Please save each sheet as a separate file Upload them as individual files for processing File Format: The first row must contain your column headers Remove any empty rows above the headers https://preview.redd.it/olmk6lfmwuzd1.png?width=3024&format=png&auto=webp&s=aa2bbc8edb4a299dbeee67b692cd4acf1704c2be

Disorganized: The note taking app for busy people (no AI inside)

https://preview.redd.it/27qoz7ihlnpe1.png?width=1774&format=png&auto=webp&s=1658d7a4c619df46cd76c5ff639b6c6c7b65fc50 About one year ago I had enough and set out to create my own note taking app, and have been working on it in my spare time since summer. I had two main goals when creating Disorganized: \- Less friction If I'm walking around and a thought pop ups in my head there should be zero friction to writing it down. That's why Disorganized doesn't ask you to write a title, sort it into the correct folder, etc. You write exactly your thoughts and nothing else. \- A better solution than templates. I wanted one app that I could use to track my workouts, my recipes and one-off notes. Other apps accomplish this with templates but I find templates too rigid - I don't want to create a "recipe" template because a "recipe" is not always the same thing. It's usually a table of ingredients and some instructions in text, but other times it's multiple tables of ingredients, or something else entirely. Templates are too rigid. In Disorganized, you "clone" notes to create a new note with the same structure. This way, you can reuse previous set ups, but you're completely free to evolve your "template" as you go. Please try it out and tell me what you think! iOS, three months premium: https://apps.apple.com/redeem/?ctx=offercodes&id=6738280174&code=THREEMONTHS Android: https://play.google.com/store/apps/details?id=com.disorganized.disorganized&pli=1 Use code "THREEMONTHS" at checkout for three months. Web version: https://app.getdisorganized.com/

My experience trying to scrape google maps with no code

A few months back I was working on a project to help founders that sell to SMBs get better quality leads (Current solutions like Zoominfo and Apollo don’t do very well for the SMB market). Of course, I wanted to do this as quickly as possible with as little code as possible.  We found that people were manually going through Google Maps to find SMBs. They would use the search and manually type in the businesses they were looking for. For example, they would type “restaurants” and manually call/email them. What we decided to do was gather the Google Maps data autonomously and surface that to our customers so they could take all of it. The problem was that we would need a bunch of data from Google Maps to pull it off. We would need to grab all the SMBs across the United States which is a huge undertaking.  Initially, I tried no-code AI web scraping solutions and they worked horribly. For some reason, I couldn’t even get them to scroll down on the page. I was also able to reverse engineer their open-source code and discover that they were taking the entire web page and passing it into GPT to extract data. That just burned my Openai bill.  I then tried the semi-code approach (sorry no-code subreddit) where I would use something like Apify or Google Places API to scrape the businesses. This worked better but still, there was an issue of price at the scale we wanted. Eventually, we ended up writing our scraper for the task.  This experience was so horrible I ended up creating potarix.com. Firstly, we provide scraping as a service in conjunction with AI. We all know AI is shit and keeping this human in the loop allows the AI to do 90% of the work and then for us to tweak the script to 100% completion. Also since we use AI to create the scraper instead of using AI to scrape, we can run it for large scale tasks at a low cost.

Tried every no-code tool under the sun—finally built a fully custom business app in minutes with AI

Hey r/SideProject, After months of trying to piece together no-code tools to fit small businesses’ needs, I kept hitting a wall. Every setup felt like a workaround, never quite matching the way these businesses actually operate. That’s when I realized most SMBs need software that’s built around their specific workflows, not patched together. But developing something custom from scratch? Not realistic for most small businesses in terms of time or cost. So, I set out to create a new approach. Enter Crust AI—a tool where SMB owners just describe what they need, and in 5 minutes, it generates a fully functional app. Crust can even plug into existing data from Airtable, Monday, or Notion, and builds the entire interface on top with no design limitations—completely generated by AI. From client portals to vendor management systems, Crust delivers an end-to-end solution without the dev work. For once, I didn’t need to wrestle with endless integrations and limitations. If you’ve been through the same, check out trycrust.co and let me know your thoughts. Happy to answer questions or hear about your own experiences!

How I'm automating all my SEO research & writing with AI by building an open source software

I make most of my current recurring income from writing articles for a few blogs. Over the years I have developed strategies and writing techniques that increase my chances of landing at the top of Google search results. I’m a writer, but I also write code. With the advent of AI I have been itching to codify many of my previous activities. I tried writing content with the general LLMs like ChatGPT and Claude but the results were terrible, especially for niches with technical information. I didn’t want to lose hope in AI because I realised with A LOT of hand-holding, it got better results. THEN IT HIT ME!  What if I could create a Human-Guided AI for Better AI-Written Articles: enter Building ContentScribe After months of coding with AI tools and trying different approaches, I’m excited to share that ContentScribe is finally taking shape. The journey to this point has been challenging but incredibly rewarding. Over the past six months, we’ve been using ContentScribe ourselves to automate blog content creation. We found other tools in the AI article generation space such as Koala AI and Cuppa that left us wanting more. They basically took a topic from you and let the AI loose. We consider this to be a better Koala AI and Cuppa alternative. I wanted to have more control and freedom from the expense of the credit system most of them use. Even after generation, every article required significant human input to make it truly SEO-friendly, and existing tools couldn’t handle the specific strategies we needed for our niche. So, we decided to build something new: an AI-powered, open-source tool that doesn’t just spit out generic articles, but actually allows users to shape how the content is written. ContentScribe is designed to integrate the SEO techniques that we’ve developed over years of building profitable blogs. It codifies our best practices and turns them into a process that anyone can use to create researched, optimized content, every time. The product works, and it’s live! We’ve been populating our latest blog with human-guided AI-written articles, and the results are already impressive. The coolest part? This project scratches our own itch and addresses the pain points we faced when using other tools. Plus there is nothing to lose because it’s free and open source, you can run it locally or in the cloud. It’s still early days, but I’m excited to share more as we keep building in public. We’re working on tutorials, and adding more features. The feedback we’ve gotten so far from our in-house team has been invaluable, and I’m looking forward to sharing this with more content creators out there. For anyone struggling to get their ideas off the ground: keep experimenting, keep building. ContentScribe is proof that when you combine persistence with innovation, the results can be something you’re genuinely proud of. This is just the beginning!

Why no code tools for building ai models failed?

Business folks have tasks where neural networks could help but they don’t know Python or deep learning, right? Meanwhile ML engineers know AI models but often don’t have an actual problem to solve. So the first group hires the second. Same thing happened with websites a while ago—at first you had to code everything then came drag-and-drop editors, no-code tools, and now even this "vibe coding" stuff. It’s not the most flexible or maintainable, but it works for a lot of people who just need to get something done without spending months learning to code. So why isn’t the same thing happening with building AI models? Like if I run a business I could save a ton of money by automating manual tasks with models trained on my own data. But I have zero clue what Jupyter Notebook or Keras are, and honestly, I don’t want to know. So I have to hire an ML engineer just to get it done because there’s no viable no-code solution for this.

[P] Building an Reinforcement Learning Agent to play The Legend of Zelda

A year go I started trying to use PPO to play the original Legend of Zelda, and I was able to train a model to beat the first boss after a few months of work. I wanted to share the project just for show and tell. I'd love to hear feedback and suggestions as this is just a hobby project. I don't do this for a living. The code for that lives in the original-design branch of my Triforce repo. I'm currently tinkering with new designs so the main branch is much less stable. Here's a video of the agent beating the first dungeon, which was trained with 5,000,000+ steps. At 38 seconds, you can see it learned that it's invulnerable at the screen edge, and it exploits that to avoid damage from a projectile. At 53 seconds it steps up to avoid damage from an unblockable projectile, even though it takes a -0.06 penalty for moving the wrong way (taking damage would be a larger penalty.) At 55 seconds it walks towards the rock projectile to block it. And so on, lots of little things the model does is easy to miss if you don't know the game inside and out. As a TLDR, here's an early version of my new (single) model. This doesn't make it quite as far, but if you watch closely it's combat is already far better, and is only trained on 320,000 steps (~6% of the steps the first model was trained on). This is pretty far along from my very first model. Original Design I got the original project working using stable-baselines's PPO and default neural network (Shared NatureCNN, I believe). SB was great to get started but ultimately stifling. In the new version of the project I've implemented PPO from scratch with torch with my own simple neural network similar to stable-baseline's default. I'm playing with all kinds of changes and designs now that I have more flexibility and control. Here is my rough original design: Overall Strategy My first pass through this project was basically "imagine playing Zelda with your older sibling telling you where to go and what to do". I give the model an objective vector which points to where I want it to go on the screen (as a bird flies, the agent still had to learn path finding to avoid damage and navigate around the map). This includes either point at the nearest enemy I want it to kill or a NSEW vector if it's supposed to move to the next room. Due a few limitations with stable-baselines (especially around action masking), I ended up training unique models for traversing the overworld vs the dungeon (since they have entirely different tilesets). I also trained a different model for when we have sword beams vs not. In the video above you can see what model is being used onscreen. In my current project I've removed this objective vector as it felt too much like cheating. Instead I give it a one-hot encoded objective (move north to the next room, pickup items, kill enemies, etc). So far it's working quite well without that crutch. The new project also does a much better job of combat even without multiple models to handle beams vs not. Observation/Action Space Image - The standard neural network had a really tough time being fed the entire screen. No amount of training seemed to help. I solved this by creating a viewport around Link that keeps him centered. This REALLY helped the model learn. I also had absolutely zero success with stacking frames to give Link a way to see enemy/projectile movement. The model simply never trained with stable-baselines when I implemented frame stacking and I never figured out why. I just added it to my current neural network and it seems to be working... Though my early experiments show that giving it 3 frames (skipping two in between, so frames curr, curr-3, curr-6) doesn't really give us that much better performance. It might if I took away some of the vectors. We'll see. Vectors - Since the model cannot see beyond its little viewport, I gave the model a vector to the closest item, enemy, and projectile onscreen. This made it so the model can shoot enemies across the room outside of its viewport. My new model gives it multiple enemies/items/projectiles and I plan to try to use an attention mechanism as part of the network to see if I can just feed it all of that data. Information - It also gets a couple of one-off datapoints like whether it currently has sword beams. The new model also gives it a "source" room (to help better understand dungeons where we have to backtrack), and a one-hot encoded objective. Action Space My original project just has a few actions, 4 for moving in the cardinal directions and 4 for attacking in each direction (I also added bombs but never spent any time training it). I had an idea to use masking to help speed up training. I.E. if link bumps into a wall, don't let him move in that direction again until he moves elsewhere, as the model would often spend an entire memory buffer running headlong straight into a wall before an update...better to do it once and get a huge negative penalty which is essentially the same result but faster. Unfortunately SB made it really annoying architecturally to pass that info down to the policy layer. I could have hacked it together, but eventually I just reimplemented PPO and my own neural network so I could properly mask actions in the new version. For example, when we start training a fresh model, it cannot attack when there aren't enemies on screen and I can disallow it from leaving certain areas. The new model actually understands splitting swinging the sword short range vs firing sword beams as two different actions, though I haven't yet had a chance to fully train with the split yet. Frameskip/Cooldowns - In the game I don't use a fixed frame skip for actions. Instead I use the internal ram state of game to know when Link is animation locked or not and only allow the agent to take actions when it's actually possible to give meaningful input to the game. This greatly sped up training. We also force movement to be between tiles on the game map. This means that when the agent decides to move it loses control for longer than a player would...a player can make more split second decisions. This made it easier to implement movement rewards though and might be something to clean up in the future. Other interesting details Pathfinding - To facilitate rewards, the original version of this project used A* to pathfind from link to what he should be doing. Here's a video of it in action. This information wasn't giving to the model directly but instead the agent would only be given the rewards if it exactly followed that path or the transposed version of it. It would also pathfind around enemies and not walk through them. This was a nightmare though. The corner cases were significant, and pushing Link towards enemies but not into them was really tricky. The new verison just uses a wavefront algorithm. I calculate a wave from the tiles we want to get to outwards, then make sure we are following the gradient. Also calculating the A* around enemies every frame (even with caching) was super slow. Wavefront was faster, especially because I give the new model no special rewards for walking around enemies...faster to compute and it has to learn from taking damage or not. Either way, the both the old and new models successfully learned how to pathfind around danger and obstacles, with or without the cheaty objective vector. Rewards - I programmed very dense rewards in both the old and new model. At basically every step, the model is getting rewarded or punished for something. I actually have some ideas I can't wait to try out to make the rewards more sparse. Or maybe we start with dense rewards for the first training, then fine-tune the model with sparser rewards. We'll see. Predicting the Future - Speaking of rewards. One interesting wrinkle is that the agent can do a lot of things that will eventually deal damage but not on that frame. For example, when Link sets a bomb it takes several seconds before it explodes, killing things. This can be a massive reward or penalty since he spent an extremely valuable resource, but may have done massive damage. PPO and other RL propagates rewards backwards, of course, but that spike in reward could land on a weird frame where we took damage or moved in the wrong direction. I probably could have just not solved that problem and let it shake out over time, but instead I used the fact that we are in an emulator to just see what the outcome of every decision is. When planting a bomb, shooting sword beams, etc, we let the game run forward until impact, then rewind time and reward the agent appropriately, continuing on from when we first paused. This greatly speeds up training, even if it's expensive to do this savestate, play forward, restore state. Neural Networks - When I first started this project (knowing very little about ML and RL), I thought most of my time would be tuning the shape of the neural network that we are using. In reality, the default provided by stable-baselines and my eventual reimplemnentation has been enough to make massive progress. Now that I have a solid codebase though, I really want to revisit this. I'd like to see if trying CoordConvs and similar networks might make the viewport unncessary. Less interesting details/thoughts Hyperparameters - Setting the entropy coefficinet way lower helped a TON in training stable models. My new PPO implementation is way less stable than stable-baselines (ha, imagine that), but still converges most of the time. Infinite Rewards - As with all reinforcement learning, if you give some way for the model to get infinite rewards, it will do just that and nothing else. I spent days, or maybe weeks tweaking reward functions to just get it to train and not find a spot on the wall it could hump for infinite rewards. Even just neutral rewards, like +0.5 moving forward and -0.5 for moving backwards, would often result in a model that just stepped left, then right infinitely. There has to be a real reward or punishment (non-neutral) for forward progress. Debugging Rewards - In fact, building a rewards debugger was the only way I made progress in this project. If you are tackling something this big, do that very early. Stable-Retro is pretty great - Couldn't be happier with the clean design for implementing emulation for AI. Torch is Awesome - My early versions heavily used numpy and relied on stable-baselines, with its multiproc parallelization support. It worked great. Moving the project over to torch was night and day though. It gave me so much more flexibility, instant multithreading for matrix operations. I have a pretty beefy computer and I'm almost at the same steps per second as 20 proc stable-retro/numpy. Future Ideas This has already gone on too long. I have some ideas for future projects, but maybe I'll just make them another post when I actually do them. Special Thanks A special thanks to Brad Flaugher for help with the early version of this, Fiskbit from the Zelda1 speedrunning community for help pulling apart the raw assembly to build this thing, and MatPoliquin for maintaining Stable-Retro. Happy to answer any questions, really I just love nerding out about this stuff.

[D] Why I'm Lukewarm on Graph Neural Networks

TL;DR: GNNs can provide wins over simpler embedding methods, but we're at a point where other research directions matter more I also posted it on my blog here, has footnotes, a nicer layout with inlined images, etc. I'm only lukewarm on Graph Neural Networks (GNNs). There, I said it. It might sound crazy GNNs are one of the hottest fields in machine learning right now. [There][1] were at least [four][2] [review][3] [papers][4] just in the last few months. I think some progress can come of this research, but we're also focusing on some incorrect places. But first, let's take a step back and go over the basics. Models are about compression We say graphs are a "non-euclidean" data type, but that's not really true. A regular graph is just another way to think about a particular flavor of square matrix called the [adjacency matrix][5], like this. It's weird, we look at run-of-the-mill matrix full of real numbers and decide to call it "non-euclidean". This is for practical reasons. Most graphs are fairly sparse, so the matrix is full of zeros. At this point, where the non-zero numbers are matters most, which makes the problem closer to (computationally hard) discrete math rather than (easy) continuous, gradient-friendly math. If you had the full matrix, life would be easy If we step out of the pesky realm of physics for a minute, and assume carrying the full adjacency matrix around isn't a problem, we solve a bunch of problems. First, network node embeddings aren't a thing anymore. A node is a just row in the matrix, so it's already a vector of numbers. Second, all network prediction problems are solved. A powerful enough and well-tuned model will simply extract all information between the network and whichever target variable we're attaching to nodes. NLP is also just fancy matrix compression Let's take a tangent away from graphs to NLP. Most NLP we do can be [thought of in terms of graphs][6] as we'll see, so it's not a big digression. First, note that Ye Olde word embedding models like [Word2Vec][7] and [GloVe][8] are [just matrix factorization][9]. The GloVe algorithm works on a variation of the old [bag of words][10] matrix. It goes through the sentences and creates a (implicit) [co-occurence][11] graph where nodes are words and the edges are weighed by how often the words appear together in a sentence. Glove then does matrix factorization on the matrix representation of that co-occurence graph, Word2Vec is mathematically equivalent. You can read more on this in my [post on embeddings][12] and the one (with code) on [word embeddings][13]. Even language models are also just matrix compression Language models are all the rage. They dominate most of the [state of the art][14] in NLP. Let's take BERT as our main example. BERT predicts a word given the context of the rest of the sentence. This grows the matrix we're factoring from flat co-occurences on pairs of words to co-occurences conditional on the sentence's context, like this We're growing the "ideal matrix" we're factoring combinatorially. As noted by [Hanh & Futrell][15]: [...] human language—and language modelling—has infinite statistical complexity but that it can be approximated well at lower levels. This observation has two implications: 1) We can obtain good results with comparatively small models; and 2) there is a lot of potential for scaling up our models. Language models tackle such a large problem space that they probably approximate a compression of the entire language in the [Kolmogorov Complexity][16] sense. It's also possible that huge language models just [memorize a lot of it][17] rather than compress the information, for what it's worth. Can we upsample any graph like language models do? We're already doing it. Let's call a first-order embedding of a graph a method that works by directly factoring the graph's adjacency matrix or [Laplacian matrix][18]. If you embed a graph using [Laplacian Eigenmaps][19] or by taking the [principal components][20] of the Laplacian, that's first order. Similarly, GloVe is a first-order method on the graph of word co-occurences. One of my favorites first order methods for graphs is [ProNE][21], which works as well as most methods while being two orders of magnitude faster. A higher-order method embeds the original matrix plus connections of neighbours-of-neighbours (2nd degree) and deeper k-step connections. [GraRep][22], shows you can always generate higher-order representations from first order methods by augmenting the graph matrix. Higher order method are the "upsampling" we do on graphs. GNNs that sample on large neighborhoods and random-walk based methods like node2vec are doing higher-order embeddings. Where are the performance gain? Most GNN papers in the last 5 years present empirical numbers that are useless for practitioners to decide on what to use. As noted in the [OpenGraphsBenchmark][4] (OGB) paper, GNN papers do their empirical section on a handful of tiny graphs (Cora, CiteSeer, PubMed) with 2000-20,000 nodes. These datasets can't seriously differentiate between methods. Recent efforts are directly fixing this, but the reasons why researchers focused on tiny, useless datasets for so long are worth discussing. Performance matters by task One fact that surprises a lot of people is that even though language models have the best performance in a lot of NLP tasks, if all you're doing is cram sentence embeddings into a downstream model, there [isn't much gained][23] from language models embeddings over simple methods like summing the individual Word2Vec word embeddings (This makes sense, because the full context of the sentence is captured in the sentence co-occurence matrix that is generating the Word2Vec embeddings). Similarly, [I find][24] that for many graphs simple first-order methods perform just as well on graph clustering and node label prediction tasks than higher-order embedding methods. In fact higher-order methods are massively computationally wasteful for these usecases. Recommended first order embedding methods are ProNE and my [GGVec with order=1][25]. Higher order methods normally perform better on the link prediction tasks. I'm not the only one to find this. In the BioNEV paper, they find: "A large GraRep order value for link prediction tasks (e.g. 3, 4);a small value for node classification tasks (e.g.1, 2)" (p.9). Interestingly, the gap in link prediction performance is inexistant for artificially created graphs. This suggests higher order methods do learn some of the structure intrinsic to [real world graphs][26]. For visualization, first order methods are better. Visualizations of higher order methods tend to have artifacts of their sampling. For instance, Node2Vec visualizations tend to have elongated/filament-like structures which come from the embeddings coming from long single strand random walks. See the following visualizations by [Owen Cornec][27] created by first embedding the graph to 32-300 dimensions using a node embedding algorithm, then mapping this to 2d or 3d with the excellent UMAP algorithm, like this Lastly, sometimes simple methods soundly beat higher order methods (there's an instance of it in the OGB paper). The problem here is that we don't know when any method is better than another and we definitely don't know the reason. There's definitely a reason different graph types respond better/worse to being represented by various methods. This is currently an open question. A big part of why is that the research space is inundated under useless new algorithms because... Academic incentives work against progress Here's the cynic's view of how machine learning papers are made: Take an existing algorithm Add some new layer/hyperparameter, make a cute mathematical story for why it matters Gridsearch your hyperparameters until you beat baselines from the original paper you aped Absolutely don't gridsearch stuff you're comparing against in your results section Make a cute ACRONYM for your new method, put impossible to use python 2 code on github (Or no code at all!) and bask in the citations I'm [not][28] the [only one][29] with these views on the state reproducible research. At least it's gotten slightly better in the last 2 years. Sidebar: I hate Node2Vec A side project of mine is a [node embedding library][25] and the most popular method in it is by far Node2Vec. Don't use Node2Vec. [Node2Vec][30] with p=1; q=1 is the [Deepwalk][31] algorithm. Deepwalk is an actual innovation. The Node2Vec authors closely followed the steps 1-5 including bonus points on step 5 by getting word2vec name recognition. This is not academic fraud -- the hyperparameters [do help a tiny bit][32] if you gridsearch really hard. But it's the presentable-to-your-parents sister of where you make the ML community worse off to progress your academic career. And certainly Node2Vec doesn't deserve 7500 citations. Progress is all about practical issues We've known how to train neural networks for well over 40 years. Yet they only exploded in popularity with [AlexNet][33] in 2012. This is because implementations and hardware came to a point where deep learning was practical. Similarly, we've known about factoring word co-occurence matrices into Word embeddings for at least 20 years. But word embeddings only exploded in 2013 with Word2Vec. The breakthrough here was that the minibatch-based methods let you train a Wikipedia-scale embedding model on commodity hardware. It's hard for methods in a field to make progress if training on a small amount of data takes days or weeks. You're disincentivized to explore new methods. If you want progress, your stuff has to run in reasonable time on commodity hardware. Even Google's original search algorithm [initially ran on commodity hardware][34]. Efficiency is paramount to progress The reason deep learning research took off the way it did is because of improvements in [efficiency][35] as well as much better libraries and hardware support. Academic code is terrible Any amount of time you spend gridsearching Node2Vec on p and q is all put to better use gridsearching Deepwalk itself (on number of walks, length of walks, or word2vec hyperparameters). The problem is that people don't gridsearch over deepwalk because implementations are all terrible. I wrote the [Nodevectors library][36] to have a fast deepwalk implementation because it took 32 hours to embed a graph with a measly 150,000 nodes using the reference Node2Vec implementation (the same takes 3min with Nodevectors). It's no wonder people don't gridsearch on Deepwalk a gridsearch would take weeks with the terrible reference implementations. To give an example, in the original paper of [GraphSAGE][37] they their algorithm to DeepWalk with walk lengths of 5, which is horrid if you've ever hyperparameter tuned a deepwalk algorithm. From their paper: We did observe DeepWalk’s performance could improve with further training, and in some cases it could become competitive with the unsupervised GraphSAGE approaches (but not the supervised approaches) if we let it run for >1000× longer than the other approaches (in terms of wall clock time for prediction on the test set) I don't even think the GraphSAGE authors had bad intent -- deepwalk implementations are simply so awful that they're turned away from using it properly. It's like trying to do deep learning with 2002 deep learning libraries and hardware. Your architectures don't really matter One of the more important papers this year was [OpenAI's "Scaling laws"][38] paper, where the raw number of parameters in your model is the most predictive feature of overall performance. This was noted even in the original BERT paper and drives 2020's increase in absolutely massive language models. This is really just [Sutton' Bitter Lesson][39] in action: General methods that leverage computation are ultimately the most effective, and by a large margin Transformers might be [replacing convolution][40], too. As [Yannic Kilcher said][41], transformers are ruining everything. [They work on graphs][6], in fact it's one of the [recent approaches][42], and seems to be one of the more succesful [when benchmarked][1] Researchers seem to be putting so much effort into architecture, but it doesn't matter much in the end because you can approximate anything by stacking more layers. Efficiency wins are great -- but neural net architectures are just one way to achieve that, and by tremendously over-researching this area we're leaving a lot of huge gains elsewhere on the table. Current Graph Data Structure Implementations suck NetworkX is a bad library. I mean, it's good if you're working on tiny graphs for babies, but for anything serious it chokes and forces you to rewrite everything in... what library, really? At this point most people working on large graphs end up hand-rolling some data structure. This is tough because your computer's memory is a 1-dimensional array of 1's and 0's and a graph has no obvious 1-d mapping. This is even harder when we take updating the graph (adding/removing some nodes/edges) into account. Here's a few options: Disconnected networks of pointers NetworkX is the best example. Here, every node is an object with a list of pointers to other nodes (the node's edges). This layout is like a linked list. Linked lists are the [root of all performance evil][43]. Linked lists go completely against how modern computers are designed. Fetching things from memory is slow, and operating on memory is fast (by two orders of magnitude). Whenever you do anything in this layout, you make a roundtrip to RAM. It's slow by design, you can write this in Ruby or C or assembly and it'll be slow regardless, because memory fetches are slow in hardware. The main advantage of this layout is that adding a new node is O(1). So if you're maintaining a massive graph where adding and removing nodes happens as often as reading from the graph, it makes sense. Another advantage of this layout is that it "scales". Because everything is decoupled from each other you can put this data structure on a cluster. However, you're really creating a complex solution for a problem you created for yourself. Sparse Adjacency Matrix This layout great for read-only graphs. I use it as the backend in my [nodevectors][25] library, and many other library writers use the [Scipy CSR Matrix][44], you can see graph algorithms implemented on it [here][45]. The most popular layout for this use is the [CSR Format][46] where you have 3 arrays holding the graph. One for edge destinations, one for edge weights and an "index pointer" which says which edges come from which node. Because the CSR layout is simply 3 arrays, it scales on a single computer: a CSR matrix can be laid out on a disk instead of in-memory. You simply [memory map][47] the 3 arrays and use them on-disk from there. With modern NVMe drives random seeks aren't slow anymore, much faster than distributed network calls like you do when scaling the linked list-based graph. I haven't seen anyone actually implement this yet, but it's in the roadmap for my implementation at least. The problem with this representation is that adding a node or edge means rebuilding the whole data structure. Edgelist representations This representation is three arrays: one for the edge sources, one for the edge destinations, and one for edge weights. [DGL][48] uses this representation internally. This is a simple and compact layout which can be good for analysis. The problem compared to CSR Graphs is some seek operations are slower. Say you want all the edges for node #4243. You can't jump there without maintaining an index pointer array. So either you maintain sorted order and binary search your way there (O(log2n)) or unsorted order and linear search (O(n)). This data structure can also work on memory mapped disk array, and node append is fast on unsorted versions (it's slow in the sorted version). Global methods are a dead end Methods that work on the entire graph at once can't leverage computation, because they run out of RAM at a certain scale. So any method that want a chance of being the new standard need to be able to update piecemeal on parts of the graph. Sampling-based methods Sampling Efficiency will matter more in the future Edgewise local methods. The only algorithms I know of that do this are GloVe and GGVec, which they pass through an edge list and update embedding weights on each step. The problem with this approach is that it's hard to use them for higher-order methods. The advantage is that they easily scale even on one computer. Also, incrementally adding a new node is as simple as taking the existing embeddings, adding a new one, and doing another epoch over the data Random Walk sampling. This is used by deepwalk and its descendants, usually for node embeddings rather than GNN methods. This can be computationally expensive and make it hard to add new nodes. But this does scale, for instance [Instagram][49] use it to feed their recommendation system models Neighbourhood sampling. This is currently the most common one in GNNs, and can be low or higher order depending on the neighborhood size. It also scales well, though implementing efficiently can be challenging. It's currently used by [Pinterest][50]'s recommendation algorithms. Conclusion Here are a few interesting questions: What is the relation between graph types and methods? Consolidated benchmarking like OGB We're throwing random models at random benchmarks without understanding why or when they do better More fundamental research. Heree's one I'm curious about: can other representation types like [Poincarre Embeddings][51] effectively encode directed relationships? On the other hand, we should stop focusing on adding spicy new layers to test on the same tiny datasets. No one cares. [1]: https://arxiv.org/pdf/2003.00982.pdf [2]: https://arxiv.org/pdf/2002.11867.pdf [3]: https://arxiv.org/pdf/1812.08434.pdf [4]: https://arxiv.org/pdf/2005.00687.pdf [5]: https://en.wikipedia.org/wiki/Adjacency_matrix [6]: https://thegradient.pub/transformers-are-graph-neural-networks/ [7]: https://en.wikipedia.org/wiki/Word2vec [8]: https://nlp.stanford.edu/pubs/glove.pdf [9]: https://papers.nips.cc/paper/2014/file/feab05aa91085b7a8012516bc3533958-Paper.pdf [10]: https://en.wikipedia.org/wiki/Bag-of-words_model [11]: https://en.wikipedia.org/wiki/Co-occurrence [12]: https://www.singlelunch.com/2020/02/16/embeddings-from-the-ground-up/ [13]: https://www.singlelunch.com/2019/01/27/word-embeddings-from-the-ground-up/ [14]: https://nlpprogress.com/ [15]: http://socsci.uci.edu/~rfutrell/papers/hahn2019estimating.pdf [16]: https://en.wikipedia.org/wiki/Kolmogorov_complexity [17]: https://bair.berkeley.edu/blog/2020/12/20/lmmem/ [18]: https://en.wikipedia.org/wiki/Laplacian_matrix [19]: http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=1F03130B02DC485C78BF364266B6F0CA?doi=10.1.1.19.8100&rep=rep1&type=pdf [20]: https://en.wikipedia.org/wiki/Principalcomponentanalysis [21]: https://www.ijcai.org/Proceedings/2019/0594.pdf [22]: https://dl.acm.org/doi/10.1145/2806416.2806512 [23]: https://openreview.net/pdf?id=SyK00v5xx [24]: https://github.com/VHRanger/nodevectors/blob/master/examples/link%20prediction.ipynb [25]: https://github.com/VHRanger/nodevectors [26]: https://arxiv.org/pdf/1310.2636.pdf [27]: http://byowen.com/ [28]: https://arxiv.org/pdf/1807.03341.pdf [29]: https://www.youtube.com/watch?v=Kee4ch3miVA [30]: https://cs.stanford.edu/~jure/pubs/node2vec-kdd16.pdf [31]: https://arxiv.org/pdf/1403.6652.pdf [32]: https://arxiv.org/pdf/1911.11726.pdf [33]: https://en.wikipedia.org/wiki/AlexNet [34]: https://en.wikipedia.org/wiki/Googledatacenters#Original_hardware [35]: https://openai.com/blog/ai-and-efficiency/ [36]: https://www.singlelunch.com/2019/08/01/700x-faster-node2vec-models-fastest-random-walks-on-a-graph/ [37]: https://arxiv.org/pdf/1706.02216.pdf [38]: https://arxiv.org/pdf/2001.08361.pdf [39]: http://incompleteideas.net/IncIdeas/BitterLesson.html [40]: https://arxiv.org/abs/2010.11929 [41]: https://www.youtube.com/watch?v=TrdevFK_am4 [42]: https://arxiv.org/pdf/1710.10903.pdf [43]: https://www.youtube.com/watch?v=fHNmRkzxHWs [44]: https://docs.scipy.org/doc/scipy/reference/generated/scipy.sparse.csr_matrix.html [45]: https://docs.scipy.org/doc/scipy/reference/sparse.csgraph.html [46]: https://en.wikipedia.org/wiki/Sparsematrix#Compressedsparserow(CSR,CRSorYaleformat) [47]: https://en.wikipedia.org/wiki/Mmap [48]: https://github.com/dmlc/dgl [49]: https://ai.facebook.com/blog/powered-by-ai-instagrams-explore-recommender-system/ [50]: https://medium.com/pinterest-engineering/pinsage-a-new-graph-convolutional-neural-network-for-web-scale-recommender-systems-88795a107f48 [51]: https://arxiv.org/pdf/1705.08039.pdf

[P] Can you distinguish AI-generated content from real art or literature? I made a little test!

Hi everyone, I am no programmer, and I have a very basic knowledge of machine learning, but I am fascinated by the possibilities offered by all the new models we have seen so far. Some people around me say they are not that impressed by what AIs can do, so I built a small test (with a little help by chatGPT to code the whole thing): can you always 100% distinguish between AI art or text and old works of art or literature? Here is the site: http://aiorart.com/ I find that AI-generated text is still generally easy to spot, but of course it is very challenging to go against great literary works. AI images can sometimes be truly deceptive. I wonder what you will all think of it... and how all that will evolve in the coming months! PS: The site is very crude (again, I am no programmer!). It works though.

[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.

[N] Netflix and European Space Agency no longer working with Siraj Raval

According to article in The Register: A Netflix spokesperson confirmed to The Register it wasn’t working with Raval, and the ESA has cancelled the whole workshop altogether. “The situation is as it is. The workshop is cancelled, and that’s all,” Guillaume Belanger, an astrophysicist and the INTEGRAL Science Operations Coordinator at the ESA, told The Register on Monday. Raval isn’t about to quit his work any time soon, however. He promised students who graduated from his course that they would be referred to recruiters at Nvidia, Intel, Google and Amazon for engineering positions, or matched with a startup co-founder or a consulting client. In an unlisted YouTube video recorded live for his students discussing week eight of his course, and seen by El Reg, he read out a question posed to him: “Will your referrals hold any value now?” “Um, yeah they’re going to hold value. I don’t see why they wouldn’t. I mean, yes, some people on Twitter were angry but that has nothing to do with… I mean… I’ve also had tons of support, you know. I’ve had tons of support from people, who, uh, you know, support me, who work at these companies. He continues to justify his actions: “Public figures called me in private to remind me that this happens. You know, people make mistakes. You just have to keep going. They’re basically just telling me to not to stop. Of course, you make mistakes but you just keep going,” he claimed. When The Register asked Raval for comment, he responded: I've hardly taken any time off to relax since I first started my YouTube channel almost four years ago. And despite the enormous amount of work it takes to release two high quality videos a week for my audience, I progressively started to take on multiple other projects simultaneously by myself – a book, a docu-series, podcasts, YouTube videos, the course, the school of AI. Basically, these past few weeks, I've been experiencing a burnout unlike anything I've felt before. As a result, all of my output has been subpar. I made the [neural qubits] video and paper in one week. I remember wishing I had three to six months to really dive into quantum machine-learning and make something awesome, but telling myself I couldn't take that long as it would hinder my other projects. I plagiarized large chunks of the paper to meet my self-imposed one-week deadline. The associated video with animations took a lot more work to make. I didn't expect the paper to be cited as serious research, I considered it an additional reading resource for people who enjoyed the associated video to learn more about quantum machine learning. If I had a second chance, I'd definitely take way more time to write the paper, and in my own words. I've given refunds to every student who's asked so far, and the majority of students are still enrolled in the course. There are many happy students, they're just not as vocal on social media. We're on week 8 of 10 of my course, fully committed to student success. “And, no, I haven't plagiarized research for any other paper,” he added. https://www.theregister.co.uk/2019/10/14/ravelaiyoutube/

[R] Analysis of 400+ ML competitions in 2024

I run mlcontests.com, a website that lists ML competitions from across multiple platforms - Kaggle, DrivenData, AIcrowd, Zindi, etc… I’ve just spent a few months looking through all the info I could find on last year’s competitions, as well as winning solutions.  I found over 400 competitions that happened last year, plus info on the #1 winning solution for 70 of those.  Some highlights: Kaggle is still the biggest platform by total prize money, and also has a much bigger user base than the other platforms - though there are well over a dozen other platforms worth keeping track of, with regular interesting competitions and meaningful prize money. An increase in competitions with $1m+ prize pools (ARC Prize, AI Mathematical Olympiad, Vesuvius Challenge, AI Cyber Challenge) compared to previous years. Python continues to be the language of choice among competition winners, with almost everyone using Python as their main language. One winner used Rust, two used R.  Convolutional neural nets continue to do well in computer vision competitions, and are still more common among competition winners than transformer-based vision models.  PyTorch is still used a lot more than TensorFlow, roughly 9:1. Didn’t find any competition winners implementing neural nets in JAX or other libraries.  There were a few competition winners using AutoML packages, which seem to be getting increasingly useful. Any claims of generalist autonomous grandmaster-level agents seem premature though.  In language/text/sequence-related competitions, quantisation was key for making use of limited resources effectively. Usually 4-, 5-, or 8-bit. LoRA/QLoRA was also used quite often, though not always.  Gradient-boosted decision trees continue to win a lot of tabular/time-series competitions. They’re often ensembled with deep learning models. No tabular/time-series pre-trained foundation models were used by winners in 2024, as far as I can tell.  Starting to see more uptake of Polars for dataframes, with 7 winners using Polars in 2024 (up from 3 in 2023) vs 58 using Pandas. All those who used Polars also still used Pandas in some parts of their code.  In terms of hardware, competition winners almost entirely used NVIDIA GPUs to train their models. Some trained on CPU-only, or used a TPU through Colab. No AMD GPUs. The NVIDIA A100 was the most commonly used GPU among winners. Two of the $1m+ prize pool competitions were won by teams using 8xH100 nodes for training. A lot of other GPUs too though: T4/P100 (through Kaggle Notebooks), or consumer GPUs like RTX 3090/4090/3080/3060. Some spent hundreds of dollars on cloud compute to train their solutions.  An emerging pattern: using generative models to create additional synthetic training data to augment the training data provided.  There’s way more detail in the full report, which you can read here (no paywall): https://mlcontests.com/state-of-machine-learning-competitions-2024?ref=mlcr Processing img xmm4ywg9h9le1... The full report also features: A deep dive into the ARC Prize and the AI Mathematical Olympiad An overview of winning solutions to NLP/sequence competitions A breakdown of Python packages used in winning solutions (e.g. relative popularity of various gradient-boosted tree libraries) If you’d like to support this research, I’d really appreciate it if you could share it with anyone else who might find it interesting. You can also check out my newly-launched online magazine, Jolt ML \- featuring news from top ML conferences as well as long-read articles (just one so far, more to come!).  Thanks to the competition winners who shared info on their solutions, and also to the competition platforms who shared high-level data on their competitions.

[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.”

[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.”

[P] I Trained a Model to Generate Video Game Pages

These past two months I've been working on a project I've called THIS GAME DOES NOT EXIST. I've always wanted to try building something with generative A.I. so this project scratched that itch for me. Here's a video with a few of my favourites read by voice actors: https://www.youtube.com/watch?v=\mTWMLhpJoA &#x200B; THIS GAME DOES NOT EXIST is an experiment in generative artificial intelligence. This site contains 130 video game pages that were generated using an implementation of OpenAI's Generative Pre-trained Transformer 2 (GPT-2) to generate text and a simple implementation of generative adversarial networks (GAN) to generate header images and "screenshots". To generate the names, descriptions, publishers, and developers of the games I finetuned the HuggingFace implementation of GPT-2. I used the Steam Store Games (Clean dataset) from Kaggle with slight modifications and preprocessing.Here is what one training sample looks like: Half-LifeValve ValveNamed Game of the Year by over 50 publications, Valve's debut title blends action and adventure with award-winning technology to create a frighteningly realistic world where players must think to survive. Also includes an exciting multiplayer mode that allows you to play against friends and enemies around the world. The model uses the tokens (e.g. and ) to prompt each class of data while keeping context during the entire generation. Image generation was done by training a custom GAN very similar to the architecture seen in the PyTorch DCGAN Tutorial which was built to generate faces. I created two models for this site: one for generating the header images and one for generating multiple screenshots for each game.To assemble the dataset I wrote a script that downloads the images from the URLs in the Steam Store Games (Clean dataset) dataset. Due to my lack of resources and time to put into this project, the image generation is less than ideal. You may notice though, that the header image model will generate artifacts in images that look like the titles of games, and the screenshot image model with generate what looks like levels of a 2D platformer.

[P] Open-source Neural Search framework to implement semantic search & multimedia search. Just released 2.0, seeking your feedback.

I heard your feedback on 1.0 release post on my project Jina, many people were keen to use Jina for multimedia search because that's where use of Neural Networks makes significant difference. So I focused on that part and I was able to transform it from 1.0 to 2.0 within 3 months. Last post on 1.0 release to give you some idea what this project is about Actually, I should say - "'we' made this", because there were more than 155 contributors who did it, not just me. The primary changes we made We saw MachineLearning beginners struggle in using Jina 1.0, so we separated the codebase where Machine Learning expertise is required(jina-hub) and the one which MachineLearning beginners can use(the jina core). Now ML beginners don't need to worry about jina-hub and can use jina hub packages directly to implement ML specific tasks without the need to understand advanced ML concepts. While advanced ML users can create their own jina-hub packages. We cut down a lots of abstractions to make it easy to use for beginners Made python APIs more intuitive to use Improved performance(3.6x faster on startup) Here's Jina 2.0 and here's Jina 1.0. I seek feedback from people who are looking at this project for the first time, as well as people who have tried their hands before but had some challenges in using it. Few questions, I'm seeking answers to Do you feel that we have reduced complexity by a lot of margin? How easy it is to use for a beginner now? What questions are still unanswered?

[D] Why can't you guys comment your fucking code?

Seriously. I spent the last few years doing web app development. Dug into DL a couple months ago. Supposedly, compared to the post-post-post-docs doing AI stuff, JavaScript developers should be inbred peasants. But every project these peasants release, even a fucking library that colorizes CLI output, has a catchy name, extensive docs, shitloads of comments, fuckton of tests, semantic versioning, changelog, and, oh my god, better variable names than ctxh or langhs or fuckyoufortryingto_understand. The concepts and ideas behind DL, GANs, LSTMs, CNNs, whatever – it's clear, it's simple, it's intuitive. The slog is to go through the jargon (that keeps changing beneath your feet - what's the point of using fancy words if you can't keep them consistent?), the unnecessary equations, trying to squeeze meaning from bullshit language used in papers, figuring out the super important steps, preprocessing, hyperparameters optimization that the authors, oops, failed to mention. Sorry for singling out, but look at this - what the fuck? If a developer anywhere else at Facebook would get this code for a review they would throw up. Do you intentionally try to obfuscate your papers? Is pseudo-code a fucking premium? Can you at least try to give some intuition before showering the reader with equations? How the fuck do you dare to release a paper without source code? Why the fuck do you never ever add comments to you code? When naming things, are you charged by the character? Do you get a bonus for acronyms? Do you realize that OpenAI having needed to release a "baseline" TRPO implementation is a fucking disgrace to your profession? Jesus christ, who decided to name a tensor concatenation function cat?

[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.”

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.

[P]MMML | Deploy HuggingFace training model rapidly based on MetaSpore

A few days ago, HuggingFace announced a $100 million Series C funding round, which was big news in open source machine learning and could be a sign of where the industry is headed. Two days before the HuggingFace funding announcement, open-source machine learning platform MetaSpore released a demo based on the HuggingFace Rapid deployment pre-training model. As deep learning technology makes innovative breakthroughs in computer vision, natural language processing, speech understanding, and other fields, more and more unstructured data are perceived, understood, and processed by machines. These advances are mainly due to the powerful learning ability of deep learning. Through pre-training of deep models on massive data, the models can capture the internal data patterns, thus helping many downstream tasks. With the industry and academia investing more and more energy in the research of pre-training technology, the distribution warehouses of pre-training models such as HuggingFace and Timm have emerged one after another. The open-source community release pre-training significant model dividends at an unprecedented speed. In recent years, the data form of machine modeling and understanding has gradually evolved from single-mode to multi-mode, and the semantic gap between different modes is being eliminated, making it possible to retrieve data across modes. Take CLIP, OpenAI’s open-source work, as an example, to pre-train the twin towers of images and texts on a dataset of 400 million pictures and texts and connect the semantics between pictures and texts. Many researchers in the academic world have been solving multimodal problems such as image generation and retrieval based on this technology. Although the frontier technology through the semantic gap between modal data, there is still a heavy and complicated model tuning, offline data processing, high performance online reasoning architecture design, heterogeneous computing, and online algorithm be born multiple processes and challenges, hindering the frontier multimodal retrieval technologies fall to the ground and pratt &whitney. DMetaSoul aims at the above technical pain points, abstracting and uniting many links such as model training optimization, online reasoning, and algorithm experiment, forming a set of solutions that can quickly apply offline pre-training model to online. This paper will introduce how to use the HuggingFace community pre-training model to conduct online reasoning and algorithm experiments based on MetaSpore technology ecology so that the benefits of the pre-training model can be fully released to the specific business or industry and small and medium-sized enterprises. And we will give the text search text and text search graph two multimodal retrieval demonstration examples for your reference. Multimodal semantic retrieval The sample architecture of multimodal retrieval is as follows: Our multimodal retrieval system supports both text search and text search application scenarios, including offline processing, model reasoning, online services, and other core modules: &#x200B; https://preview.redd.it/w4v4c7vcez291.png?width=1834&format=png&auto=webp&s=0687efb1fddb26e8e30cb844d398ec712b947f31 Offline processing, including offline data processing processes for different application scenarios of text search and text search, including model tuning, model export, data index database construction, data push, etc. Model inference. After the offline model training, we deployed our NLP and CV large models based on the MetaSpore Serving framework. MetaSpore Serving helps us conveniently perform online inference, elastic scheduling, load balancing, and resource scheduling in heterogeneous environments. Online services. Based on MetaSpore’s online algorithm application framework, MetaSpore has a complete set of reusable online search services, including Front-end retrieval UI, multimodal data preprocessing, vector recall and sorting algorithm, AB experimental framework, etc. MetaSpore also supports text search by text and image scene search by text and can be migrated to other application scenarios at a low cost. The HuggingFace open source community has provided several excellent baseline models for similar multimodal retrieval problems, which are often the starting point for actual optimization in the industry. MetaSpore also uses the pre-training model of the HuggingFace community in its online services of searching words by words and images by words. Searching words by words is based on the semantic similarity model of the question and answer field optimized by MetaSpore, and searching images by words is based on the community pre-training model. These community open source pre-training models are exported to the general ONNX format and loaded into MetaSpore Serving for online reasoning. The following sections will provide a detailed description of the model export and online retrieval algorithm services. The reasoning part of the model is standardized SAAS services with low coupling with the business. Interested readers can refer to my previous post: The design concept of MetaSpore, a new generation of the one-stop machine learning platform. 1.1 Offline Processing Offline processing mainly involves the export and loading of online models and index building and pushing of the document library. You can follow the step-by-step instructions below to complete the offline processing of text search and image search and see how the offline pre-training model achieves reasoning at MetaSpore. 1.1.1 Search text by text Traditional text retrieval systems are based on literal matching algorithms such as BM25. Due to users’ diverse query words, a semantic gap between query words and documents is often encountered. For example, users misspell “iPhone” as “Phone,” and search terms are incredibly long, such as “1 \~ 3 months old baby autumn small size bag pants”. Traditional text retrieval systems will use spelling correction, synonym expansion, search terms rewriting, and other means to alleviate the semantic gap but fundamentally fail to solve this problem. Only when the retrieval system fully understands users’ query terms and documents can it meet users’ retrieval demands at the semantic level. With the continuous progress of pre-training and representational learning technology, some commercial search engines continue to integrate semantic vector retrieval methods based on symbolic learning into the retrieval ecology. Semantic retrieval model This paper introduces a set of semantic vector retrieval applications. MetaSpore built a set of semantic retrieval systems based on encyclopedia question and answer data. MetaSpore adopted the Sentence-Bert model as the semantic vector representation model, which fine-tunes the twin tower BERT in supervised or unsupervised ways to make the model more suitable for retrieval tasks. The model structure is as follows: The query-Doc symmetric two-tower model is used in text search and question and answer retrieval. The vector representation of online Query and offline DOC share the same vector representation model, so it is necessary to ensure the consistency of the offline DOC library building model and online Query inference model. The case uses MetaSpore’s text representation model Sbert-Chinese-QMC-domain-V1, optimized in the open-source semantically similar data set. This model will express the question and answer data as a vector in offline database construction. The user query will be expressed as a vector by this model in online retrieval, ensuring that query-doc in the same semantic space, users’ semantic retrieval demands can be guaranteed by vector similarity metric calculation. Since the text presentation model does vector encoding for Query online, we need to export the model for use by the online service. Go to the q&A data library code directory and export the model concerning the documentation. In the script, Pytorch Tracing is used to export the model. The models are exported to the “./export “directory. The exported models are mainly ONNX models used for wired reasoning, Tokenizer, and related configuration files. The exported models are loaded into MetaSpore Serving by the online Serving system described below for model reasoning. Since the exported model will be copied to the cloud storage, you need to configure related variables in env.sh. \Build library based on text search \ The retrieval database is built on the million-level encyclopedia question and answer data set. According to the description document, you need to download the data and complete the database construction. The question and answer data will be coded as a vector by the offline model, and then the database construction data will be pushed to the service component. The whole process of database construction is described as follows: Preprocessing, converting the original data into a more general JSonline format for database construction; Build index, use the same model as online “sbert-Chinese-qmc-domain-v1” to index documents (one document object per line); Push inverted (vector) and forward (document field) data to each component server. The following is an example of the database data format. After offline database construction is completed, various data are pushed to corresponding service components, such as Milvus storing vector representation of documents and MongoDB storing summary information of documents. Online retrieval algorithm services will use these service components to obtain relevant data. 1.1.2 Search by text Text and images are easy for humans to relate semantically but difficult for machines. First of all, from the perspective of data form, the text is the discrete ID type of one-dimensional data based on words and words. At the same time, images are continuous two-dimensional or three-dimensional data. Secondly, the text is a subjective creation of human beings, and its expressive ability is vibrant, including various turning points, metaphors, and other expressions, while images are machine representations of the objective world. In short, bridging the semantic gap between text and image data is much more complex than searching text by text. The traditional text search image retrieval technology generally relies on the external text description data of the image or the nearest neighbor retrieval technology and carries out the retrieval through the image associated text, which in essence degrades the problem to text search. However, it will also face many issues, such as obtaining the associated text of pictures and whether the accuracy of text search by text is high enough. The depth model has gradually evolved from single-mode to multi-mode in recent years. Taking the open-source project of OpenAI, CLIP, as an example, train the model through the massive image and text data of the Internet and map the text and image data into the same semantic space, making it possible to implement the text and image search technology based on semantic vector. CLIP graphic model The text search pictures introduced in this paper are implemented based on semantic vector retrieval, and the CLIP pre-training model is used as the two-tower retrieval architecture. Because the CLIP model has trained the semantic alignment of the twin towers’ text and image side models on the massive graphic and text data, it is particularly suitable for the text search graph scene. Due to the different image and text data forms, the Query-Doc asymmetric twin towers model is used for text search image retrieval. The image-side model of the twin towers is used for offline database construction, and the text-side model is used for the online return. In the final online retrieval, the database data of the image side model will be searched after the text side model encodes Query, and the CLIP pre-training model guarantees the semantic correlation between images and texts. The model can draw the graphic pairs closer in vector space by pre-training on a large amount of visual data. Here we need to export the text-side model for online MetaSpore Serving inference. Since the retrieval scene is based on Chinese, the CLIP model supporting Chinese understanding is selected. The exported content includes the ONNX model used for online reasoning and Tokenizer, similar to the text search. MetaSpore Serving can load model reasoning through the exported content. Build library on Image search You need to download the Unsplash Lite library data and complete the construction according to the instructions. The whole process of database construction is described as follows: Preprocessing, specify the image directory, and then generate a more general JSOnline file for library construction; Build index, use OpenAI/Clip-Vit-BASE-Patch32 pre-training model to index the gallery, and output one document object for each line of index data; Push inverted (vector) and forward (document field) data to each component server. Like text search, after offline database construction, relevant data will be pushed to service components, called by online retrieval algorithm services to obtain relevant data. 1.2 Online Services The overall online service architecture diagram is as follows: https://preview.redd.it/jfsl8hdfez291.png?width=1280&format=png&auto=webp&s=a858e2304a0c93e78ba5429612ca08cbee69b35a Multi-mode search online service system supports application scenarios such as text search and text search. The whole online service consists of the following parts: Query preprocessing service: encapsulate preprocessing logic (including text/image, etc.) of pre-training model, and provide services through gRPC interface; Retrieval algorithm service: the whole algorithm processing link includes AB experiment tangent flow configuration, MetaSpore Serving call, vector recall, sorting, document summary, etc.; User entry service: provides a Web UI interface for users to debug and track down problems in the retrieval service. From a user request perspective, these services form invocation dependencies from back to front, so to build up a multimodal sample, you need to run each service from front to back first. Before doing this, remember to export the offline model, put it online and build the library first. This article will introduce the various parts of the online service system and make the whole service system step by step according to the following guidance. See the ReadME at the end of this article for more details. 1.2.1 Query preprocessing service Deep learning models tend to be based on tensors, but NLP/CV models often have a preprocessing part that translates raw text and images into tensors that deep learning models can accept. For example, NLP class models often have a pre-tokenizer to transform text data of string type into discrete tensor data. CV class models also have similar processing logic to complete the cropping, scaling, transformation, and other processing of input images through preprocessing. On the one hand, considering that this part of preprocessing logic is decoupled from tensor reasoning of the depth model, on the other hand, the reason of the depth model has an independent technical system based on ONNX, so MetaSpore disassembled this part of preprocessing logic. NLP pretreatment Tokenizer has been integrated into the Query pretreatment service. MetaSpore dismantlement with a relatively general convention. Users only need to provide preprocessing logic files to realize the loading and prediction interface and export the necessary data and configuration files loaded into the preprocessing service. Subsequent CV preprocessing logic will also be integrated in this manner. The preprocessing service currently provides the gRPC interface invocation externally and is dependent on the Query preprocessing (QP) module in the retrieval algorithm service. After the user request reaches the retrieval algorithm service, it will be forwarded to the service to complete the data preprocessing and continue the subsequent processing. The ReadMe provides details on how the preprocessing service is started, how the preprocessing model exported offline to cloud storage enters the service, and how to debug the service. To further improve the efficiency and stability of model reasoning, MetaSpore Serving implements a Python preprocessing submodule. So MetaSpore can provide gRPC services through user-specified preprocessor.py, complete Tokenizer or CV-related preprocessing in NLP, and translate requests into a Tensor that deep models can handle. Finally, the model inference is carried out by MetaSpore, Serving subsequent sub-modules. Presented here on the lot code: https://github.com/meta-soul/MetaSpore/compare/add\python\preprocessor 1.2.2 Retrieval algorithm services Retrieval algorithm service is the core of the whole online service system, which is responsible for the triage of experiments, the assembly of algorithm chains such as preprocessing, recall, sorting, and the invocation of dependent component services. The whole retrieval algorithm service is developed based on the Java Spring framework and supports multi-mode retrieval scenarios of text search and text search graph. Due to good internal abstraction and modular design, it has high flexibility and can be migrated to similar application scenarios at a low cost. Here’s a quick guide to configuring the environment to set up the retrieval algorithm service. See ReadME for more details: Install dependent components. Use Maven to install the online-Serving component Search for service configurations. Copy the template configuration file and replace the MongoDB, Milvus, and other configurations based on the development/production environment. Install and configure Consul. Consul allows you to synchronize the search service configuration in real-time, including cutting the flow of experiments, recall parameters, and sorting parameters. The project’s configuration file shows the current configuration parameters of text search and text search. The parameter modelName in the stage of pretreatment and recall is the corresponding model exported in offline processing. Start the service. Once the above configuration is complete, the retrieval service can be started from the entry script. Once the service is started, you can test it! For example, for a user with userId=10 who wants to query “How to renew ID card,” access the text search service. 1.2.3 User Entry Service Considering that the retrieval algorithm service is in the form of the API interface, it is difficult to locate and trace the problem, especially for the text search image scene can intuitively display the retrieval results to facilitate the iterative optimization of the retrieval algorithm. This paper provides a lightweight Web UI interface for text search and image search, a search input box, and results in a display page for users. Developed by Flask, the service can be easily integrated with other retrieval applications. The service calls the retrieval algorithm service and displays the returned results on the page. It’s also easy to install and start the service. Once you’re done, go to http://127.0.0.1:8090 to see if the search UI service is working correctly. See the ReadME at the end of this article for details. Multimodal system demonstration The multimodal retrieval service can be started when offline processing and online service environment configuration have been completed following the above instructions. Examples of textual searches are shown below. Enter the entry of the text search map application, enter “cat” first, and you can see that the first three digits of the returned result are cats: https://preview.redd.it/0n5nuyvhez291.png?width=1280&format=png&auto=webp&s=1e9c054f541d53381674b8d6001b4bf524506bd2 If you add a color constraint to “cat” to retrieve “black cat,” you can see that it does return a black cat: https://preview.redd.it/rzc0qjyjez291.png?width=1280&format=png&auto=webp&s=d5bcc503ef0fb3360c7740e60e295cf372dcad47 Further, strengthen the constraint on the search term, change it to “black cat on the bed,” and return results containing pictures of a black cat climbing on the bed: &#x200B; https://preview.redd.it/c4b2q8olez291.png?width=1280&format=png&auto=webp&s=4f3817b0b9f07e1e68d1d4a8281702ba3834a00a The cat can still be found through the text search system after the color and scene modification in the above example. Conclusion The cutting-edge pre-training technology can bridge the semantic gap between different modes, and the HuggingFace community can greatly reduce the cost for developers to use the pre-training model. Combined with the technological ecology of MetaSpore online reasoning and online microservices provided by DMetaSpore, the pre-training model is no longer mere offline dabbling. Instead, it can truly achieve end-to-end implementation from cutting-edge technology to industrial scenarios, fully releasing the dividends of the pre-training large model. In the future, DMetaSoul will continue to improve and optimize the MetaSpore technology ecosystem: More automated and wider access to HuggingFace community ecology. MetaSpore will soon release a common model rollout mechanism to make HuggingFace ecologically accessible and will later integrate preprocessing services into online services. Multi-mode retrieval offline algorithm optimization. For multimodal retrieval scenarios, MetaSpore will continuously iteratively optimize offline algorithm components, including text recall/sort model, graphic recall/sort model, etc., to improve the accuracy and efficiency of the retrieval algorithm. For related code and reference documentation in this article, please visit: https://github.com/meta-soul/MetaSpore/tree/main/demo/multimodal/online Some images source: https://github.com/openai/CLIP/raw/main/CLIP.png https://www.sbert.net/examples/training/sts/README.html

[P]MMML | Deploy HuggingFace training model rapidly based on MetaSpore

A few days ago, HuggingFace announced a $100 million Series C funding round, which was big news in open source machine learning and could be a sign of where the industry is headed. Two days before the HuggingFace funding announcement, open-source machine learning platform MetaSpore released a demo based on the HuggingFace Rapid deployment pre-training model. As deep learning technology makes innovative breakthroughs in computer vision, natural language processing, speech understanding, and other fields, more and more unstructured data are perceived, understood, and processed by machines. These advances are mainly due to the powerful learning ability of deep learning. Through pre-training of deep models on massive data, the models can capture the internal data patterns, thus helping many downstream tasks. With the industry and academia investing more and more energy in the research of pre-training technology, the distribution warehouses of pre-training models such as HuggingFace and Timm have emerged one after another. The open-source community release pre-training significant model dividends at an unprecedented speed. In recent years, the data form of machine modeling and understanding has gradually evolved from single-mode to multi-mode, and the semantic gap between different modes is being eliminated, making it possible to retrieve data across modes. Take CLIP, OpenAI’s open-source work, as an example, to pre-train the twin towers of images and texts on a dataset of 400 million pictures and texts and connect the semantics between pictures and texts. Many researchers in the academic world have been solving multimodal problems such as image generation and retrieval based on this technology. Although the frontier technology through the semantic gap between modal data, there is still a heavy and complicated model tuning, offline data processing, high performance online reasoning architecture design, heterogeneous computing, and online algorithm be born multiple processes and challenges, hindering the frontier multimodal retrieval technologies fall to the ground and pratt &whitney. DMetaSoul aims at the above technical pain points, abstracting and uniting many links such as model training optimization, online reasoning, and algorithm experiment, forming a set of solutions that can quickly apply offline pre-training model to online. This paper will introduce how to use the HuggingFace community pre-training model to conduct online reasoning and algorithm experiments based on MetaSpore technology ecology so that the benefits of the pre-training model can be fully released to the specific business or industry and small and medium-sized enterprises. And we will give the text search text and text search graph two multimodal retrieval demonstration examples for your reference. Multimodal semantic retrieval The sample architecture of multimodal retrieval is as follows: Our multimodal retrieval system supports both text search and text search application scenarios, including offline processing, model reasoning, online services, and other core modules: &#x200B; https://preview.redd.it/w4v4c7vcez291.png?width=1834&format=png&auto=webp&s=0687efb1fddb26e8e30cb844d398ec712b947f31 Offline processing, including offline data processing processes for different application scenarios of text search and text search, including model tuning, model export, data index database construction, data push, etc. Model inference. After the offline model training, we deployed our NLP and CV large models based on the MetaSpore Serving framework. MetaSpore Serving helps us conveniently perform online inference, elastic scheduling, load balancing, and resource scheduling in heterogeneous environments. Online services. Based on MetaSpore’s online algorithm application framework, MetaSpore has a complete set of reusable online search services, including Front-end retrieval UI, multimodal data preprocessing, vector recall and sorting algorithm, AB experimental framework, etc. MetaSpore also supports text search by text and image scene search by text and can be migrated to other application scenarios at a low cost. The HuggingFace open source community has provided several excellent baseline models for similar multimodal retrieval problems, which are often the starting point for actual optimization in the industry. MetaSpore also uses the pre-training model of the HuggingFace community in its online services of searching words by words and images by words. Searching words by words is based on the semantic similarity model of the question and answer field optimized by MetaSpore, and searching images by words is based on the community pre-training model. These community open source pre-training models are exported to the general ONNX format and loaded into MetaSpore Serving for online reasoning. The following sections will provide a detailed description of the model export and online retrieval algorithm services. The reasoning part of the model is standardized SAAS services with low coupling with the business. Interested readers can refer to my previous post: The design concept of MetaSpore, a new generation of the one-stop machine learning platform. 1.1 Offline Processing Offline processing mainly involves the export and loading of online models and index building and pushing of the document library. You can follow the step-by-step instructions below to complete the offline processing of text search and image search and see how the offline pre-training model achieves reasoning at MetaSpore. 1.1.1 Search text by text Traditional text retrieval systems are based on literal matching algorithms such as BM25. Due to users’ diverse query words, a semantic gap between query words and documents is often encountered. For example, users misspell “iPhone” as “Phone,” and search terms are incredibly long, such as “1 \~ 3 months old baby autumn small size bag pants”. Traditional text retrieval systems will use spelling correction, synonym expansion, search terms rewriting, and other means to alleviate the semantic gap but fundamentally fail to solve this problem. Only when the retrieval system fully understands users’ query terms and documents can it meet users’ retrieval demands at the semantic level. With the continuous progress of pre-training and representational learning technology, some commercial search engines continue to integrate semantic vector retrieval methods based on symbolic learning into the retrieval ecology. Semantic retrieval model This paper introduces a set of semantic vector retrieval applications. MetaSpore built a set of semantic retrieval systems based on encyclopedia question and answer data. MetaSpore adopted the Sentence-Bert model as the semantic vector representation model, which fine-tunes the twin tower BERT in supervised or unsupervised ways to make the model more suitable for retrieval tasks. The model structure is as follows: The query-Doc symmetric two-tower model is used in text search and question and answer retrieval. The vector representation of online Query and offline DOC share the same vector representation model, so it is necessary to ensure the consistency of the offline DOC library building model and online Query inference model. The case uses MetaSpore’s text representation model Sbert-Chinese-QMC-domain-V1, optimized in the open-source semantically similar data set. This model will express the question and answer data as a vector in offline database construction. The user query will be expressed as a vector by this model in online retrieval, ensuring that query-doc in the same semantic space, users’ semantic retrieval demands can be guaranteed by vector similarity metric calculation. Since the text presentation model does vector encoding for Query online, we need to export the model for use by the online service. Go to the q&A data library code directory and export the model concerning the documentation. In the script, Pytorch Tracing is used to export the model. The models are exported to the “./export “directory. The exported models are mainly ONNX models used for wired reasoning, Tokenizer, and related configuration files. The exported models are loaded into MetaSpore Serving by the online Serving system described below for model reasoning. Since the exported model will be copied to the cloud storage, you need to configure related variables in env.sh. \Build library based on text search \ The retrieval database is built on the million-level encyclopedia question and answer data set. According to the description document, you need to download the data and complete the database construction. The question and answer data will be coded as a vector by the offline model, and then the database construction data will be pushed to the service component. The whole process of database construction is described as follows: Preprocessing, converting the original data into a more general JSonline format for database construction; Build index, use the same model as online “sbert-Chinese-qmc-domain-v1” to index documents (one document object per line); Push inverted (vector) and forward (document field) data to each component server. The following is an example of the database data format. After offline database construction is completed, various data are pushed to corresponding service components, such as Milvus storing vector representation of documents and MongoDB storing summary information of documents. Online retrieval algorithm services will use these service components to obtain relevant data. 1.1.2 Search by text Text and images are easy for humans to relate semantically but difficult for machines. First of all, from the perspective of data form, the text is the discrete ID type of one-dimensional data based on words and words. At the same time, images are continuous two-dimensional or three-dimensional data. Secondly, the text is a subjective creation of human beings, and its expressive ability is vibrant, including various turning points, metaphors, and other expressions, while images are machine representations of the objective world. In short, bridging the semantic gap between text and image data is much more complex than searching text by text. The traditional text search image retrieval technology generally relies on the external text description data of the image or the nearest neighbor retrieval technology and carries out the retrieval through the image associated text, which in essence degrades the problem to text search. However, it will also face many issues, such as obtaining the associated text of pictures and whether the accuracy of text search by text is high enough. The depth model has gradually evolved from single-mode to multi-mode in recent years. Taking the open-source project of OpenAI, CLIP, as an example, train the model through the massive image and text data of the Internet and map the text and image data into the same semantic space, making it possible to implement the text and image search technology based on semantic vector. CLIP graphic model The text search pictures introduced in this paper are implemented based on semantic vector retrieval, and the CLIP pre-training model is used as the two-tower retrieval architecture. Because the CLIP model has trained the semantic alignment of the twin towers’ text and image side models on the massive graphic and text data, it is particularly suitable for the text search graph scene. Due to the different image and text data forms, the Query-Doc asymmetric twin towers model is used for text search image retrieval. The image-side model of the twin towers is used for offline database construction, and the text-side model is used for the online return. In the final online retrieval, the database data of the image side model will be searched after the text side model encodes Query, and the CLIP pre-training model guarantees the semantic correlation between images and texts. The model can draw the graphic pairs closer in vector space by pre-training on a large amount of visual data. Here we need to export the text-side model for online MetaSpore Serving inference. Since the retrieval scene is based on Chinese, the CLIP model supporting Chinese understanding is selected. The exported content includes the ONNX model used for online reasoning and Tokenizer, similar to the text search. MetaSpore Serving can load model reasoning through the exported content. Build library on Image search You need to download the Unsplash Lite library data and complete the construction according to the instructions. The whole process of database construction is described as follows: Preprocessing, specify the image directory, and then generate a more general JSOnline file for library construction; Build index, use OpenAI/Clip-Vit-BASE-Patch32 pre-training model to index the gallery, and output one document object for each line of index data; Push inverted (vector) and forward (document field) data to each component server. Like text search, after offline database construction, relevant data will be pushed to service components, called by online retrieval algorithm services to obtain relevant data. 1.2 Online Services The overall online service architecture diagram is as follows: https://preview.redd.it/jfsl8hdfez291.png?width=1280&format=png&auto=webp&s=a858e2304a0c93e78ba5429612ca08cbee69b35a Multi-mode search online service system supports application scenarios such as text search and text search. The whole online service consists of the following parts: Query preprocessing service: encapsulate preprocessing logic (including text/image, etc.) of pre-training model, and provide services through gRPC interface; Retrieval algorithm service: the whole algorithm processing link includes AB experiment tangent flow configuration, MetaSpore Serving call, vector recall, sorting, document summary, etc.; User entry service: provides a Web UI interface for users to debug and track down problems in the retrieval service. From a user request perspective, these services form invocation dependencies from back to front, so to build up a multimodal sample, you need to run each service from front to back first. Before doing this, remember to export the offline model, put it online and build the library first. This article will introduce the various parts of the online service system and make the whole service system step by step according to the following guidance. See the ReadME at the end of this article for more details. 1.2.1 Query preprocessing service Deep learning models tend to be based on tensors, but NLP/CV models often have a preprocessing part that translates raw text and images into tensors that deep learning models can accept. For example, NLP class models often have a pre-tokenizer to transform text data of string type into discrete tensor data. CV class models also have similar processing logic to complete the cropping, scaling, transformation, and other processing of input images through preprocessing. On the one hand, considering that this part of preprocessing logic is decoupled from tensor reasoning of the depth model, on the other hand, the reason of the depth model has an independent technical system based on ONNX, so MetaSpore disassembled this part of preprocessing logic. NLP pretreatment Tokenizer has been integrated into the Query pretreatment service. MetaSpore dismantlement with a relatively general convention. Users only need to provide preprocessing logic files to realize the loading and prediction interface and export the necessary data and configuration files loaded into the preprocessing service. Subsequent CV preprocessing logic will also be integrated in this manner. The preprocessing service currently provides the gRPC interface invocation externally and is dependent on the Query preprocessing (QP) module in the retrieval algorithm service. After the user request reaches the retrieval algorithm service, it will be forwarded to the service to complete the data preprocessing and continue the subsequent processing. The ReadMe provides details on how the preprocessing service is started, how the preprocessing model exported offline to cloud storage enters the service, and how to debug the service. To further improve the efficiency and stability of model reasoning, MetaSpore Serving implements a Python preprocessing submodule. So MetaSpore can provide gRPC services through user-specified preprocessor.py, complete Tokenizer or CV-related preprocessing in NLP, and translate requests into a Tensor that deep models can handle. Finally, the model inference is carried out by MetaSpore, Serving subsequent sub-modules. Presented here on the lot code: https://github.com/meta-soul/MetaSpore/compare/add\python\preprocessor 1.2.2 Retrieval algorithm services Retrieval algorithm service is the core of the whole online service system, which is responsible for the triage of experiments, the assembly of algorithm chains such as preprocessing, recall, sorting, and the invocation of dependent component services. The whole retrieval algorithm service is developed based on the Java Spring framework and supports multi-mode retrieval scenarios of text search and text search graph. Due to good internal abstraction and modular design, it has high flexibility and can be migrated to similar application scenarios at a low cost. Here’s a quick guide to configuring the environment to set up the retrieval algorithm service. See ReadME for more details: Install dependent components. Use Maven to install the online-Serving component Search for service configurations. Copy the template configuration file and replace the MongoDB, Milvus, and other configurations based on the development/production environment. Install and configure Consul. Consul allows you to synchronize the search service configuration in real-time, including cutting the flow of experiments, recall parameters, and sorting parameters. The project’s configuration file shows the current configuration parameters of text search and text search. The parameter modelName in the stage of pretreatment and recall is the corresponding model exported in offline processing. Start the service. Once the above configuration is complete, the retrieval service can be started from the entry script. Once the service is started, you can test it! For example, for a user with userId=10 who wants to query “How to renew ID card,” access the text search service. 1.2.3 User Entry Service Considering that the retrieval algorithm service is in the form of the API interface, it is difficult to locate and trace the problem, especially for the text search image scene can intuitively display the retrieval results to facilitate the iterative optimization of the retrieval algorithm. This paper provides a lightweight Web UI interface for text search and image search, a search input box, and results in a display page for users. Developed by Flask, the service can be easily integrated with other retrieval applications. The service calls the retrieval algorithm service and displays the returned results on the page. It’s also easy to install and start the service. Once you’re done, go to http://127.0.0.1:8090 to see if the search UI service is working correctly. See the ReadME at the end of this article for details. Multimodal system demonstration The multimodal retrieval service can be started when offline processing and online service environment configuration have been completed following the above instructions. Examples of textual searches are shown below. Enter the entry of the text search map application, enter “cat” first, and you can see that the first three digits of the returned result are cats: https://preview.redd.it/0n5nuyvhez291.png?width=1280&format=png&auto=webp&s=1e9c054f541d53381674b8d6001b4bf524506bd2 If you add a color constraint to “cat” to retrieve “black cat,” you can see that it does return a black cat: https://preview.redd.it/rzc0qjyjez291.png?width=1280&format=png&auto=webp&s=d5bcc503ef0fb3360c7740e60e295cf372dcad47 Further, strengthen the constraint on the search term, change it to “black cat on the bed,” and return results containing pictures of a black cat climbing on the bed: &#x200B; https://preview.redd.it/c4b2q8olez291.png?width=1280&format=png&auto=webp&s=4f3817b0b9f07e1e68d1d4a8281702ba3834a00a The cat can still be found through the text search system after the color and scene modification in the above example. Conclusion The cutting-edge pre-training technology can bridge the semantic gap between different modes, and the HuggingFace community can greatly reduce the cost for developers to use the pre-training model. Combined with the technological ecology of MetaSpore online reasoning and online microservices provided by DMetaSpore, the pre-training model is no longer mere offline dabbling. Instead, it can truly achieve end-to-end implementation from cutting-edge technology to industrial scenarios, fully releasing the dividends of the pre-training large model. In the future, DMetaSoul will continue to improve and optimize the MetaSpore technology ecosystem: More automated and wider access to HuggingFace community ecology. MetaSpore will soon release a common model rollout mechanism to make HuggingFace ecologically accessible and will later integrate preprocessing services into online services. Multi-mode retrieval offline algorithm optimization. For multimodal retrieval scenarios, MetaSpore will continuously iteratively optimize offline algorithm components, including text recall/sort model, graphic recall/sort model, etc., to improve the accuracy and efficiency of the retrieval algorithm. For related code and reference documentation in this article, please visit: https://github.com/meta-soul/MetaSpore/tree/main/demo/multimodal/online Some images source: https://github.com/openai/CLIP/raw/main/CLIP.png https://www.sbert.net/examples/training/sts/README.html

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.

[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."

[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.

[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.

[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.”

[D] Working with Various OpenAI Models - My Thoughts and Experiences

I'd like to share some of my insights from working with OpenAI models on my project. I'm not exactly a tech person, so some of these observations might be obvious to some of you, but I think they're worth sharing for those with less experience or who aren't directly in the field. Intro: In early February, my friends and I started a side project where we aimed to build an AI portal called DoMoreAI. For the first two months, we focused on creating an AI tools catalog. Our experiment is based on the idea that in the future, companies will be "Managed by AI, and Driven by Humans." So, our goal was to leave as much as possible to AI and automation, with all the consequences that come with it. As mentioned before, I'm not a tech guy, but I've been playing with OpenAI models for the past few years, so I had some experience when starting this project. Tasks We Assigned to AI: Based on an AI tool's front page, we had the AI write a one-sentence summary of an AI project + write a more in-depth review of the project, categorize the project into different categories (WHAT category, like blog; TASK category, like writing; FOR category, like content creator), decide if the project offers iOS app, Android app, browser extension, API, find social media links, process information about prices and pricing policy, and more. Interesting Findings: When working on a more complex prompt, particularly one with several tasks, you have to be patient when crafting it. You might eventually find the right wording to achieve the desired results, but it takes time and lots of trial and error. You might even be surprised by what works and what doesn't. If cost isn't an issue, you can always break up one complex prompt into several smaller prompts. However, the more requests you send, the higher the chance of encountering errors like the 429 error, which may require setting up more sophisticated error handlers for the whole process. You need error handlers because, without them, the automation process will suffer. With more complex prompts, there are no prompts that always yield the expected results, so you have to plan for what to do if the results aren't satisfactory and how to determine if the result meets your expectations or not. GPT-3.0 struggled with outputting JSON strings as requested, but GPT-3.5 is much better at this task. I'd say the number of errors from improperly formatting the response in JSON is 3-4 times lower for GPT-3.5. AI models have trouble distinguishing words singular forms from plural forms. Just because you can use AI for a given task doesn't mean you should. Often, standard techniques like using regex can yield better results when extracting something from text than relying solely on AI. A hybrid solution often provides the best results. We're using ADA vector embeddings and Pinecone for semantic search in our catalog, and I was really surprised to find that this kind of semantic search works in any language. Even if all the content on our page is in English, you can search in another language and still get decent results. The Best Mishaps: As you may know, there's a token limit for requests, so we have to ensure that we don't send too long a part of the front page to the model. Sometimes, this led to funny situations. If the HTML of the page consists mainly of styles and the model is fed only with styles, then when you ask the AI to write a review of the project, it writes about how beautiful, mobile-friendly, etc., the project is. For one project, instead of writing the one-sentence summary, the model's output only included the prompt we were using to generate the summary (needless to say, it was automatically published on our website ;)) &#x200B; I hope this post will be useful. We are currently running a campaign on Product Hunt: https://www.producthunt.com/posts/domore-ai So, if you have any feedback for us or think what we're doing is cool, don't hesitate to support us :)

[D] Is this close enough to be usable? Need your inputs: Automated RAG testing tool. AI Data Pipelines for Real-World Production (Part 3)

Hey there, Redditors! I'm back with the latest installment on creating dependable AI data pipelines for real-world production. If you've been following along, you know I'm on a mission to move beyond the "thin OpenAI wrapper" trend and tackle the challenges of building robust data pipelines. With 18 months of hands-on experience and many user interviews, I realized that with the probabilistic nature of systems, we need better\_testing.gpt: As you build you should test The world of AI is a fast-moving one, and we've realized that just working on systems is not an optimal design choice. By the time your product ships, it might already be using outdated technology. So, what's the lesson here? Embrace change, test along, but be prepared to switch pace. No Best Practices Yet for RAGs In this rapidly evolving landscape, there are no established best practices. You'll need to make educated bets on tools and processes, knowing that things will change. With the RAG testing tool, I tried allowing for testing many potential parameter combinations automatically Testing Frameworks If your generative AI product doesn't have users giving feedback, then you are building in isolation. I used Deepeval to generate test sets, and they will soon support synthetic test set generation Infographics only go so far AI researchers and data scientists, while brilliant, end up in a loop of pursuing Twitter promotional content. New ways are promoted via new content pieces, but ideally, we need something above simple tracing but less than full-fledged analytics. To do this, I stored test outputs in Postgres and created a Superset instance to visualize the results Bridging the Gap between VectorDBs There's a noticeable number of Vector DBs. To ensure smooth product development, we need to be able to switch to best best-performing one, especially since user interviews signal that they might start deteriorating after loading 50 million rows &#x200B; Github repo is here Next steps: I have questions for you: What variables do you change when building RAGs? What is the set of strategies I should add to the solution? (parent-son etc.) How can I improve it in general? Is anyone interested in a leaderboard for best parameter configs? Check out the blog post: Link to part 3 Remember to give this post an upvote if you found it insightful! And also star our Github repo

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.

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.

I built a no-code solution for UI-driven AI applications, But I'm lost on the business side - How to market and transform it into a viable business?

Hey everyone! sorry for the "no-code solution for UI-driven AI applications" (counted 3 buzzwords), couldn't find a way to describe it so I asked claude I'm in a bit of a pickle and could use some wisdom from this awesome community. A few months back, I developed a tool that I'm pretty excited about, but I hit a wall and shelved it. Now I'm feeling the itch to dive back in, but I'm struggling with the business side of things. Here's the gist: It's a drag-and-drop UI builder You can define buttons to execute logic and AI behind the scenes (using no-code) It uses the UI built for both input and output The good news: The site is functional and looks pretty slick (except the produced UI from the builder). Most features are implemented, though I still need to polish up the UI blocks and add more workflow nodes. The not-so-good news: I have zero users and no clear monetization strategy. The tool is so versatile that I'm having trouble figuring out how to even approach marketing it effectively. So, I turn to you guys in hopes of finding a direction: Any ideas on potential monetization strategies for a tool like this? How would you approach marketing such a multi-purpose product? Has anyone been in a similar situation? How did you move forward? generally I'd love to hear your thoughts, experiences, or even wild ideas! Thanks in advance for any insights you can share. The site is withui.com you can test it out

If only someone told me this before my first startup

If only someone told me this before my first startup: Validate idea first. I wasted a decade building stuff nobody needed. Incubators and VCs served to me as a validation, but I was so wrong. Kill my EGO. It’s not about me, but the user. I must want what the user wants, not what I want. My taste isn't important. The user has expectations, and I must fulfill them. Don’t chaise investors. Chase users, and then investors will be chasing me. I've never had more incoming interest from VC than now when I'm the least interested in them. Never hire managers. Only hire doers until PMF. So many people know how to manage people and so few can actually get sh\*t done barehand. Landing page is the least important thing in a startup. Pick a simple template, edit texts with a no-code website builder in less than an hour and that's it! At the early stage, I win traffic outside of my website, people are already interested, so don't make them search for the signup button among the texts! Focus on conversion optimization only when the traffic is consistent. Keep it to one page. Nobody gonna browse this website. Hire only fullstack devs. There is nothing less productive in this world than a team of developers for an early-stage product. One full stack dev building the whole product. That’s it. Chase global market from day 1. If the product and marketing are good, it will work on the global market too, if it’s bad, it won’t work on the local market too. So better go global from day 1, so that if it works, the upside is 100x bigger. I launched all startups for the Norwegian market, hoping we will scale to international at some point. I wish I launched to international from day 1 as I do now. The size of the market is 10000x bigger. I can validate and grow products in days, not in years as it used to be. Do SEO from day 2. As early as I can. I ignored this for 14 years. It’s my biggest regret. It takes just 5 minutes to get it done on my landing page. I go to Google Keyword Planner, enter a few keywords around my product, sort them by traffic, filter out high competition kws, pick the top 10, and place them natively on my home page and meta tags. Add one blog article every week. Either manually or by paying for an AI blogging tool. Sell features, before building them. Ask existing users if they want this feature. I run DMs with 10-20 users every day, where I chat about all my ideas and features I wanna add. I clearly see what resonates with me most and only go build those. If I don't have followers, try HN, Reddit, or just search on X for posts and ask it in the replies. People are helpful, they will reply if the question is easy to understand. Hire only people I would wanna hug. My cofounder, an old Danish man said this to me in 2015. And it was a big shift. I realized that if I don’t wanna hug the person, it means I dislike them on a chemical/animal level. Even if I can’t say why, but that’s the fact. Sooner or later, we would have a conflict and eventually break up. It takes up to 10 years to build a startup, make sure I do it with people I have this connection with. Invest all money into my startups and friends. Not crypt0, not stockmarket, not properties. I did some math, if I kept investing all my money into all my friends’ startups, that would be about 70 investments. 3 of them turned into unicorns eventually. Even 1 would have made the bank. Since 2022, I have invested all my money into my products, friends, and network. If I don't have friends who do startups, invest it in myself. Post on Twitter daily. I started posting here in March last year. It’s my primary source of new connections and growth. I could have started it earlier, I don't know why I didn't. Don’t work/partner with corporates. Corporations always seem like an amazing opportunity. They’re big and rich, they promise huge stuff, millions of users, etc. But every single time none of this happens. Because I talk to a regular employees there. They waste my time, destroy focus, shift priorities, and eventually bring in no users/money. Don’t get ever distracted by hype e.g. crypt0. I lost 1.5 years of my life this way. I met the worst people along the way. Fricks, scammers, thieves. Some of my close friends turned into thieves along the way, just because it was so common in that space. I wish this didn’t happen to me. I wish I was stronger and stayed on my mission. Don’t build consumer apps. Only b2b. Consumer apps are so hard, like a lottery. It’s just 0.00001% who make it big. The rest don’t. Even if I got many users, then there is a monetization challenge. I’ve spent 4 years in consumer apps and regret it. Don’t hold on bad project for too long, max 1 year. Some projects just don’t work. In most cases, it’s either the idea that’s so wrong that I can’t even pivot it or it’s a team that is good one by one but can’t make it as a team. Don’t drag this out for years. Tech conferences are a waste of time. They cost money, take energy, and time and I never really meet anyone there. Most people there are the “good” employees of corporations who were sent there as a perk for being loyal to the corporation. Very few fellow makers. Scrum is a Scam. For small teams and bootstrapped teams. If I had a team that had to be nagged every morning with questions as if they were children in kindergarten, then things would eventually fail. The only good stuff I managed to do happened with people who were grownups and could manage their stuff on their own. We would just do everything over chat as a sync on goals and plans. Outsource nothing at all until PMF. In a startup, almost everything needs to be done in a slightly different way, more creative, and more integrated into the vision. When outsourcing, the external members get no love and no case for the product. It’s just yet another assignment in their boring job. Instead of coming up with great ideas for my project they will be just focusing on ramping up their skills to get a promotion or a better job offer. Bootstrap. I spent way too much time raising money. I raised more than 10 times, preseed, seeded, and series A. But each time it was a 3-9 month project, meetings every week, and lots of destruction. I could afford to bootstrap, but I still went the VC-funded way, I don’t know why. To be honest, I didn’t know bootstrapping was a thing I could do or anyone does. It may take a decade. When I was 20, I was convinced it takes a few years to build and succeed with a startup. So I kept pushing my plans forward, to do it once I exited. Family, kids. I wish I married earlier. I wish I had kids earlier. No Free Tier. I'd launch a tool with a free tier, and it'd get sign-ups, but very few would convert. I'd treat free sign-ups as KPIs and run on it for years. I'd brag about signups and visitors. I'd even raise VC money with these stats. But eventually, I would fail to reach PMF. Because my main feedback would come from free users and the product turned into a perfect free product. Once I switched to "paid only" until I validated the product, things went really well. Free and paid users often need different products. Don't fall into this trap as I did. Being To Cheap. I always started by checking all competitors and setting the lowest price. I thought this would be one of the key advantages of my product. But no, I was wrong. The audience on $5 and $50 are totally different. $5: pain in the \*ss, never happy, never recommend me to a friend, leave in 4 months. $50: polite, give genuine feedback, happy, share with friends, become my big fan if I solve their request. I will fail. When I started my first startup. I thought if I did everything right, it would work out. But it turned out that almost every startup fails. I wish I knew that and I tried to fail faster, to get to the second iteration, then to the third, and keep going on, until I either find out nothing works or make it work. Use boilerplates. I wasted years of dev time and millions of VC money to pay for basic things. To build yet another sidebar, yet another dashboard, and payment integration... I had too much pride, I couldn't see myself taking someone else code as a basis for my product. I wanted it to be 100% mine, original, from scratch. Because my product seems special to me. Spend more time with Family & Friends. I missed the weddings of all my best friends and family. I was so busy. I thought if I didn't do it on time, the world would end. Looking back today, it was so wrong. I meet my friends and can't share those memories with them, which makes me very sad. I realized now, that spending 10% of my time with family and friends would practically make no negative impact on my startups. Build Products For Audiences I Love. I never thought of this. I'd often build products either for corporates, consumers, or for developers. It turns out I have no love for all 3. But I deeply love indie founders. Because they are risk-takers and partly kids in their hearts. Once I switched the focus to indie makers on my products, my level of joy increased by 100x for me. Ignore Badges and Awards I was chasing those awards just like everyone else. Going to ceremonies, signing up for events and stuff. I've won tons of awards, but none of those were eventually useful to my business. I better focused on my business and users. Write Every Single Day. When I was a kid, I loved writing stories. In school, they would give an assignment, and I'd often write a long story for it, however, the teacher would put an F on it. The reason was simple, I had an issue with the direction of the letters and the sequence of letters in the words. I still have it, it's just the Grammarly app helping me to correct these issues. So the teacher would fail my stories because almost every sentence had a spelling mistake that I couldn't even see. It made me think I'm made at writing. So I stopped, for 15 years. But I kept telling stories all these years. Recently I realized that in any group, the setup ends up turning into me telling stories to everyone. So I tried it all again, here on X 10 months ago. I love it, the process, the feedback from people. I write every day. I wish I had done it all these years. The End. \ this is an updated version of my post on the same topic from 2 months ago. I've edited some of the points and added 9 new ones.* \\ This is not advice, it's my self-reflection that might help you avoid same mistakes if you think those were mistakes

We made $325k in 2023 from AI products, starting from 0, with no-code, no funding and no audience

I met my co-founder in late 2022 after an introduction from a mutual friend to talk about how to find contract Product Management roles. I was sporadically contracting at start-up at the time and he had just come out of another start-up that was wiped out by the pandemic. We hit it off, talking about ideas, sharing what other indie-hackers were doing, and given GPT-3’s prominence at the time, we started throwing around ideas about things we could build with it, if nothing else, just to learn. I should caveat, neither of us were AI experts when starting out, everything we learned has been through Twitter and blogs, my background is as an accountant, and his a consultant. Here’s how it went since then: &#x200B; Nov 2022 (+$50) \- We built a simple tool in around a week using GPT-3 fine-tuning and a no-code tool (Bubble) that helped UK university students write their personal statements for their applications \- We set some Google Ads going and managed to make a few sales (\~$50) in the first week \- OpenAI were still approving applications at the time and said this went against their “ethics” so we had to take it down &#x200B; Dec 2022 (+$200) \- We couldn’t stop coming up with ideas related to AI fine-tuning, but realised it was almost impossible to decide which to pursue \- We needed a deadline to force us so we signed up for the Ben’s Bites hackathon in late December \- In a week, we built and launched a no-code fine-tuning platform, allowing people to create fine-tuned models by dragging and dropping an Excel file onto it \- We launched it on Product Hunt, having no idea how to price it, and somehow managed to get \~2,000 visitors on the site and make 2 sales at $99 &#x200B; Jan 2023 (+$3,000) \- We doubled down on the fine-tuning idea and managed to get up to \~$300 MRR, plus a bunch of one-time sales and a few paid calls to help people get the most out of their models \- We quickly realised that people didn’t want to curate models themselves, they just wanted to dump data and get magic out \- That was when we saw people building “Talk with x book/podcast” on Twitter as side projects and realised that was the missing piece, we needed to turn it into a tool \- We started working on the new product in late January &#x200B; Feb 2023 (+$9,000) \- We started pre-selling access to an MVP for the new product, which allowed people to “chat with their data/content”, we got $5,000 in pre-sales, more than we made from the previous product in total \- By mid-February, after 3 weeks of building we were able to launch and immediately managed to get traction, getting to $1k MRR in < 1 week, building on the hype of ChatGPT and AI (we were very lucky here) &#x200B; Mar - Jul 2023 (+$98,000) \- We worked all the waking hours to keep up with customer demand, bugs, OpenAI issues \- We built integrations for a bunch of services like Slack, Teams, Wordpress etc, added tons of new functionality and continue talking to customers every day \- We managed to grow to $17k MRR (just about enough to cover our living expenses and costs in London) through building in public on Twitter, newsletters and AI directories (and a million other little things) \- We sold our fine-tuning platform for \~$20k and our university project for \~$3k on Acquire &#x200B; Aug 2023 (+$100,000) \- We did some custom development work based on our own product for a customer that proved pretty lucrative &#x200B; Sep - Oct 2023 (+$62,000) \- After 8 months of building constantly, we started digging more seriously into our usage and saw subscriptions plateauing \- We talked to and analysed all our paying users to identify the main use cases and found 75% were for SaaS customer support \- We took the leap to completely rebuild a version of our product around this use case, our biggest to date (especially given most features with no-code took us <1 day) &#x200B; Nov - Dec 2023 (+$53,000) \- We picked up some small custom development work that utilised our own tech \- We’re sitting at around $22k MRR now with a few bigger clients signed up and coming soon \- After 2 months of building and talking to users, we managed to finish our “v2” of our product, focussed squarely on SaaS customer support and launched it today. &#x200B; We have no idea what the response will be to this new version, but we’re pretty happy with it, but couldn’t have planned anything that happened to us in 2023 so who knows what will come of 2024, we just know that we are going to be learning a ton more. &#x200B; Overall, it is probably the most I have had to think in my life - other jobs you can zone out from time to time or rely on someone else if you aren’t feeling it - not when you are doing this, case and point, I am writing this with a banging head-cold right now, but wanted to get this done. A few more things we have learned along the way - context switching is unreal, as is keeping up with, learning and reacting to AI. There isn’t a moment of the day I am not thinking about what we do next. But while in some way we now have hundreds of bosses (our customers) I still haven’t felt this free and can’t imagine ever going back to work for someone else. Next year we’re really hoping to figure out some repeatable distribution channels and personally, I want to get a lot better at creating content/writing, this is a first step! Hope this helps someone else reading this to just try starting something and see what happens.

How a Small Startup in Asia Secured a Contract with the US Department of Homeland Security

Uzair Javaid, a Ph.D. with a passion for data privacy, co-founded Betterdata to tackle one of AI's most pressing challenges: protecting privacy while enabling innovation. Recently, Betterdata secured a lucrative contract with the US Department of Homeland Security, 1 of only 4 companies worldwide to do so and the only one in Asia. Here's how he did it: The Story So what's your story? I grew up in Peshawar, Pakistan, excelling in coding despite studying electrical engineering. Inspired by my professors, I set my sights on studying abroad and eventually earned a Ph.D. scholarship at NUS Singapore, specializing in data security and privacy. During my research, I ethically hacked Ethereum and published 15 papers—three times the requirement. While wrapping up my Ph.D., I explored startup ideas and joined Entrepreneur First, where I met Kevin Yee. With his expertise in generative models and mine in privacy, we founded Betterdata. Now, nearly three years in, we’ve secured a major contract with the U.S. Department of Homeland Security—one of only four companies globally and the only one from Asia. The Startup In a nutshell, what does your startup do? Betterdata is a startup that uses AI and synthetic data generation to address two major challenges: data privacy and the scarcity of high-quality data for training AI models. By leveraging generative models and privacy-enhancing technologies, Betterdata enables businesses, such as banks, to use customer data without breaching privacy regulations. The platform trains AI on real data, learns its patterns, and generates synthetic data that mimics the real thing without containing any personal or sensitive information. This allows companies to innovate and develop AI solutions safely and ethically, all while tackling the growing need for diverse, high-quality data in AI development. How did you conduct ideation and validation for your startup? The initial idea for Betterdata came from personal experience. During my Ph.D., I ethically hacked Ethereum’s blockchain, exposing flaws in encryption-based data sharing. This led me to explore AI-driven deep synthesis technology—similar to deepfakes but for structured data privacy. With GDPR impacting 28M+ businesses, I saw a massive opportunity to help enterprises securely share data while staying compliant. To validate the idea, I spoke to 50 potential customers—a number that strikes the right balance. Some say 100, but that’s impractical for early-stage founders. At 50, patterns emerge: if 3 out of 10 mention the same problem, and this repeats across 50, you have 10–15 strong signals, making it a solid foundation for an MVP. Instead of outbound sales, which I dislike, we used three key methods: Account-Based Marketing (ABM)—targeting technically savvy users with solutions for niche problems, like scaling synthetic data for banks. Targeted Content Marketing—regular customer conversations shaped our thought leadership and outreach. Raising Awareness Through Partnerships—collaborating with NUS, Singapore’s PDPC, and Plug and Play to build credibility and educate the market. These strategies attracted serious customers willing to pay, guiding Betterdata’s product development and market fit. How did you approach the initial building and ongoing product development? In the early stages, we built synthetic data generation algorithms and a basic UI for proof-of-concept, using open-source datasets to engage with banks. We quickly learned that banks wouldn't share actual customer data due to privacy concerns, so we had to conduct on-site installations and gather feedback to refine our MVP. Through continuous consultation with customers, we discovered real enterprise data posed challenges, such as missing values, which led us to adapt our prototype accordingly. This iterative approach of listening to customer feedback and observing their usage allowed us to improve our product, enhance UX, and address unmet needs while building trust and loyalty. Working closely with our customers also gives us a data advantage. Our solution’s effectiveness depends on customer data, which we can't fully access, but bridging this knowledge gap gives us a competitive edge. The more customers we test on, the more our algorithms adapt to diverse use cases, making it harder for competitors to replicate our insights. My approach to iteration is simple: focus solely on customer feedback and ignore external noise like trends or advice. The key question for the team is: which customer is asking for this feature or solution? As long as there's a clear answer, we move forward. External influences, such as AI hype, often bring more confusion than clarity. True long-term success comes from solving real customer problems, not chasing trends. Customers may not always know exactly what they want, but they understand their problems. Our job is to identify these problems and solve them in innovative ways. While customers may suggest specific features, we stay focused on solving the core issue rather than just fulfilling their exact requests. The idea aligns with the quote often attributed to Henry Ford: "If I asked people what they wanted, they would have said faster horses." The key is understanding their problems, not just taking requests at face value. How do you assess product-market fit? To assess product-market fit, we track two key metrics: Customers' Willingness to Pay: We measure both the quantity and quality of meetings with potential customers. A high number of meetings with key decision-makers signals genuine interest. At Betterdata, we focused on getting meetings with people in banks and large enterprises to gauge our product's resonance with the target market. How Much Customers Are Willing to Pay: We monitor the price customers are willing to pay, especially in the early stages. For us, large enterprises, like banks, were willing to pay a premium for our synthetic data platform due to the growing need for privacy tech. This feedback guided our product refinement and scaling strategy. By focusing on these metrics, we refined our product and positioned it for scaling. What is your business model? We employ a structured, phase-driven approach for out business model, as a B2B startup. I initially struggled with focusing on the core value proposition in sales, often becoming overly educational. Eventually, we developed a product roadmap with models that allowed us to match customer needs to specific offerings and justify our pricing. Our pricing structure includes project-based pilots and annual contracts for successful deployments. At Betterdata, our customer engagement unfolds across three phases: Phase 1: Trial and Benchmarking \- We start with outreach and use open-source datasets to showcase results, offering customers a trial period to evaluate the solution. Phase 2: Pilot or PoC \- After positive trial results, we conduct a PoC or pilot using the customer’s private data, with the understanding that successful pilots lead to an annual contract. Phase 3: Multi-Year Contracts \- Following a successful pilot, we transition to long-term commercial contracts, focusing on multi-year agreements to ensure stability and ongoing partnerships. How do you do marketing for your brand? We take a non-conventional approach to marketing, focusing on answering one key question: Which customers are willing to pay, and how much? This drives our messaging to show how our solution meets their needs. Our strategy centers around two main components: Building a network of lead magnets \- These are influential figures like senior advisors, thought leaders, and strategic partners. Engaging with institutions like IMDA, SUTD, and investors like Plug and Play helps us gain access to the right people and foster warm introductions, which shorten our sales cycle and ensure we’re reaching the right audience. Thought leadership \- We build our brand through customer traction, technology evidence, and regulatory guidelines. This helps us establish credibility in the market and position ourselves as trusted leaders in our field. This holistic approach has enabled us to navigate diverse market conditions in Asia and grow our B2B relationships. By focusing on these areas, we drive business growth and establish strong trust with stakeholders. What's your advice for fundraising? Here are my key takeaways for other founders when it comes to fundraising: Fundraise When You Don’t Need To We closed our seed round in April 2023, a time when we weren't actively raising. Founders should always be in fundraising mode, even when they're not immediately in need of capital. Don’t wait until you have only a few months of runway left. Keep the pipeline open and build relationships. When the timing is right, execution becomes much easier. For us, our investment came through a combination of referrals and inbound interest. Even our lead investor initially rejected us, but after re-engaging, things eventually fell into place. It’s crucial to stay humble, treat everyone with respect, and maintain those relationships for when the time is right. Be Mindful of How You Present Information When fundraising, how you present information matters a lot. We created a comprehensive, easily digestible investment memo, hosted on Notion, which included everything an investor might need—problem, solution, market, team, risks, opportunities, and data. The goal was for investors to be able to get the full picture within 30 minutes without chasing down extra details. We also focused on making our financial model clear and meaningful, even though a 5-year forecast might be overkill at the seed stage. The key was clarity and conciseness, and making it as easy as possible for investors to understand the opportunity. I learned that brevity and simplicity are often the best ways to make a memorable impact. For the pitch itself, keep it simple and focus on 4 things: problem, solution, team, and market. If you can summarize each of these clearly and concisely, you’ll have a compelling pitch. Later on, you can expand into market segments, traction, and other metrics, but for seed-stage, focus on those four areas, and make sure you’re strong in at least three of them. If you do, you'll have a compelling case. How do you run things day-to-day? i.e what's your operational workflow and team structure? Here's an overview of our team structure and process: Internally: Our team is divided into two main areas: backend (internal team) and frontend (market-facing team). There's no formal hierarchy within the backend team. We all operate as equals, defining our goals based on what needs to be developed, assigning tasks, and meeting weekly to share updates and review progress. The focus is on full ownership of tasks and accountability for getting things done. I also contribute to product development, identifying challenges and clearing obstacles to help the team move forward. Backend Team: We approach tasks based on the scope defined by customers, with no blame or hierarchy. It's like a sports team—sometimes someone excels, and other times they struggle, but we support each other and move forward together. Everyone has the creative freedom to work in the way that suits them best, but we establish regular meetings and check-ins to ensure alignment and progress. Frontend Team: For the market-facing side, we implement a hierarchy because the market expects this structure. If I present myself as "CEO," it signals authority and credibility. This distinction affects how we communicate with the market and how we build our brand. The frontend team is split into four main areas: Business Product (Software Engineering) Machine Learning Engineering R&D The C-suite sits at the top, followed by team leads, and then the executors. We distill market expectations into actionable tasks, ensuring that everyone is clear on their role and responsibilities. Process: We start by receiving market expectations and defining tasks based on them. Tasks are assigned to relevant teams, and execution happens with no communication barriers between team members. This ensures seamless collaboration and focused execution. The main goal is always effectiveness—getting things done efficiently while maintaining flexibility in how individuals approach their work. In both teams, there's an emphasis on accountability, collaboration, and clear communication, but the structure varies according to the nature of the work and external expectations.

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. &#x200B; I originally posted this on my blog here. Welcoming all of your thoughts, comments, questions and I'll do my best to answer them :)

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.

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.

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.

[Ultimate List] A list of Marketing Tools That I’ve tested over the years and found helpful to do better marketing with less work. More than 50 Tools To Help you with Marketing, Copywriting & Sales!

Starting to focus on marketing for your business, You will come across the same tools mentioned over and over by marketers. I would like to mention here tools that you might haven’t seen going viral in the community but actually will help you grow faster and efficiently. Starting off with My favourite Marketing Channel! #Email Marketing For SMBs Convertkit / Mailerlite / Mailchimp - These 3 Platforms are the best options for SMBs and entrepreneurs just starting out with email marketing. All 3 have free plans up to 1,000 subscribers. Scribe - Email Signature Tool, Create Great Email signatures for your emails. Liramail - Most Email marketing platforms don’t offer great email templates. This tool will help you build great email templates with drag and drop. Quick mail Auto-Warmer - Most Businesses at the beginning don’t know what to do when open rate drops. You need to use an email warmer like this to keep it up. #Email Marketing For Big Businesses SendGrid - Overall Email Marketing Tools, this tool is best for brands that have huge email lists and email marketing is the key marketing channel. Braze - This tool is leading in email marketing for large Email senders. When I was working for agencies, this was one of the best email marketing tools I had used. NeoCertified - Protect your emails for spammers and threats. To keep your email list healthy, this is a must have! Sparkloop - Referral Marketing For Email Campaigns. Email can generate great huge amount of referrals for you and Sparkloop makes it easier. #Cold Emails & Lead Generation Hunter - A Great Tool to scrape emails from domain names. The tool comes with a green free plan but Pro plan is worth the amount of features it provides. Icyleads - It’s better than Hunter as it’s heavily focused on the sales and prospecting to help you derive great results from your campaigns. Mailshake - Beginner Friend Cold Email Tool with Great features like email list warming. #Communication Tools Twilio - One do the best customer engagement platform used by Companies like Stripe and mine too. Chatlio - Use Live chat feature on your website with slack integration. My favourite easier to catch up on conversations through slack integration. Intercom - Used by Most Marketers, Industry Leading customer communication platform. Great for beginners! Chatwoot - Another Amazing Communication Tool but the best part is they have a great free plan useful for new businesses. Loom - Communicate with your audience through Videos. Loom is great for SaaS and to show human interaction to close new visitors effectively. #CRM Outseta - This tool provides great CRM and their billing system is better than other tools out their which makes it stands out! Hubspot - I don’t think this tool needs an introduction because Hubspot’s CRM is the best in industry. Salesflare - This CRM is a great alternative to hubspot as it’s beginner friendly and helpful for SMBs. #SEO Tools Ahrefs - One of the best SEO tool in the industry. They also just launched a bunch of free tools to help SEO beginners. Screaming frog - The only website crawler I have used since I bought my first domain. It’s the best! Ubersuggest- The Tool by Neil Patel is the best SEO tool for you. (I’m Joking, it’s the worst) Contentking - This tool is good at Real-time SEO Auditing, they do a lot of Marketing work through Newsletters. If you are subscribed to any SEO newsletter. You may have seen this tool. SEOquake & Semrush - SEOquake is a great tool to conduct on-page analysis, SERP, and much more. Great tool but it’s owned by Semrush. You should go for Semrush because that tool will cover all SEO aspects for you. #Content Marketing Buzzsumo - This tool is great for content research and but you may find the regular emails pretty annoying sometimes. Contentrow - Analyse Your Content and find it’s strength. Highly recommended who are weak at content structuring like me. Grammarly - If you are not a native English speaker like me, you might think you need it or not. You need it for sure for grammar corrections. #Graphic Design Tools Visme - At agencies, Infographics can be more effective than usual postscript. Visme is a graphic design tool focused on infographics and designs related to B2B and B2C. It’s great for agencies! Glorify - A Graphic Design Tool focused on E-commerce, filled with Designs useful for E-commerce store owners. Canva - All-in-one Industry leading Graphic Design Tool that everyone knows and every template is overused now. Adobe Creative Cloud ( previously Sparkpost) - It’s a great alternative to Canva filled with Amazing Stock images to use in your visuals but the only backlash is the exports in this tool are not high quality. Snaps - A Canva Alternative that might not have overused templates for your Social Accounts. #Advertising Tools Plai - It’s a great PPC tool to create Ads for Instagram and Tiktok. Wordstream - It’s an industry leading PPC Tool, great for Ad Grading and auditing. AdEspresso - This Is a tool by Hootsuite. They have a lot of Data sourced at the backend, which helps in Ad optimisation through this tool. That’s the reason I recommend this tool. #Video Editing Tools Veed Studio - I have been using Veed from last year. It’s one of the best Video Marketing Tool Optimized for Instagram & Tiktok. Synthesia - It’s a new AI video generation platform. From last few months, if you have seen marketing agencies including Videos in Emails. The chances are that’s not a Agency member taking but AI generated Human. Motionbox - It’s also a great video editing tool focused on video editing for Digital Marketers. Jitter Video - It’s a great motion design tool. Comes with great templates, the only place where other tools I mentioned lacks. It’s great and beginner friendly. #Copywriting Jasper AI - Google’s John Mueller says AI generated content is banned on Search but I think with Jasper AI you can generate SEO optimised Content but you have to put in some efforts like at least give 30 minutes for editing the Copy by yourself. Copy AI - Another AI tool to help you write better copy. This one is more focused on helping you write copy suitable for Ads and Social media campaigns. Hemingway App - To help you write more clearly and Bold. This tool is better than Grammarly if you look for writing perspective and it’s free. #Social Media Management App I’ve used a Lot of SMM Tools and that’s why going to mention all of them with a short review. Sprout social - The Best with deep insights coverage. Hootsuite - Great Scheduling tool just under sprout social. Later - Heavily Focused on Instagram from beginning and Now Tiktok too. SkedSocial - It’s like a Later alternative with great addition features like link-in-bio. Facebook’s Business Manager- Great but sometimes bugs can make a huge issue for you and customer support is like dead. Tweet Hunter & Hypefury- Both are Twitter Scheduling tools growing very fast on platform and are great for growth. Buffer - It’s a great tool but I haven’t seen any new updates to help with management. Zoho Social - It’s a great SMM tool and if you use other marketing solutions from Zoho. It’s a must have! #Market Research Tool • SparkToro - That’s the only one I have ever used. It’s great for audience research and comes with great customer service. Founded by Rand Fishkin, it’s one of the best research tool. #Influencer Marketing & UGC InfluenceGrid - A free search engine To find Tiktok & Instagram Influencers for your campaigns. Tiktok Creative Center- TikTok’s in-built tool called “Creative Center” is the best to find content trends, audience demographics and much more. Archive - Find Instagram Stories and Posts mentioning Your brands and use them as Ads for your business Marketing. #Landing Page Builders Leadpages - Its a great landing page builder because the integration and drag-and-drop features makes it easier to work with! Cardd co - A Great Landing page builder with easy step up but it lacks the copywriting and tracking features. Instapage - It’s one of the best out and I think the overall product is effective enough to help you stand out with your landing page. Unbounce - It’s a great alternative to Instapage due its well polished landing page templates that might be helpful for you. #Community Building Mighty Networks - A Great Community building platform, and you can also sell courses within the platform. Circle so - A great alternative to Mighty networks focused on Communities specifically. We are currently using for small community Of ours. #Sales Tools Drift - You can get much more out of Drift than just sales tools but The Sales solutions provided in Drift are one of the best. Salesforce - It’s the industry Sales solution provider. A go-to and have various pricing plans making it suitable for majority of SMBs. #Social Proof Tools People don’t have enough time to search across internet to decide to trust you after seeing your Ad first time. That’s what you might be facing too. Here are two tools I absolutely love for social proof! Use Proof - Show Recent Activities occurring on your website and build the trust of your visitors. Testimonial to - Gather Testimonials across Social Media platforms related to your business with this tool. Capture tweets and comments mentioning your brands and mention them. #Analytics Tools Plausible Analytics- A privacy friendly Analytics alternative to Google Analytics if you hate Analytics 4 like me. Mixpanel - Product Analytics and funnel reports better than Google Analytics. #Reddit Marketing Gummysearch- This tool will help To find your target audience on Reddit and interact with them with its help and close your new customers. Howitzer- It’s another pretty similar tool to Gummysearch focused on Reddit cold outreach to get clients and new customers. Both are great but Gummysearch provides better customer support while Howtizer is helpful on a large scale Reddit Marketing. #Text Marketing Klaviyo - It’s an email + SMS marketing tool, it’s taking up space in marketing industry very quickly as an industry leader due to its great integrations but you need to learn the platform usage to maximise the outcome. Cartloop - This tool provides great text marketing solutions with integration with Spotify and other e-commerce marketing tools. Attentive Mobile - This is my favourite Text marketing tool due to the interactive dashboard + they have a library of Text marketing examples to help you out with your campaigns. #Other Tools I have used throughout my journey! Triple Whale - It’s a great E-commerce marketing tools with Triple pixel to help you track your campaigns more efficiently. Fastory - To create well optimized Instagram & Tiktok Stories for your business. Jotform - Online Form Builder with integrations with leading marketing tools. Gated - As an entrepreneur and marketer, you may receive a bunch of unwanted emails. Use Gated to get rid of them and receive useful mails only! ClickUp- The main Tool for Project Management, one of the best and highly recommended. Riverside - Forget Zoom or Google Meet, For your Podcast Interviews and Marketing conferences. You need riverside with great video quality and recording features. Manychat- Automate your Instagram DMs and interact with your followers more efficiently + sell out your products/ services when you are offline. Calendy - To schedule meetings with your ideal clients. ServiceProviderPro - It’s a client portal for SEO & Growing Agencies, very helpful in scaling agencies. SendCheckit - Compare your Email Subject Lines with 100,000+ others in the database for free. Otter AI - Using AI track your meetings more effectively, you can easily edit, annotate and share notes from the meetings. Ryte - Optimise your website User experience with this tool focused on UX aspects + SEO too. PhantomBuster - Scrape LinkedIn Profile and Data from Facebook/LinkedIn groups. I clearly love this tool! #Honourable Mentions Zapier - The Only tool you need to integrate your favourite tool with a new effective tool. Elementor - That’s what I use for web design and it’s great! Marketer Hire - To hire world class marketers to work with you. InShot & Capcut - I create Instagram Reels and TikTok’s and life without these tools isn’t possible. Nira - It’s a great tool to Manage your workspace and this tool has launched many marketing templates in-built helpful for marketers and also entrepreneurs. X - The tool you love that wasn’t mentioned here is valuable and I honour that tool and share that if you would like to! I mean thanks for reading what I have curated all over my life as a marketer. I share 5 Marketing Tools, 5 Marketing Resources and 1 Free Resourceevery week in my newsletter, you can subscribe here to receive that for free. Also, You can read an expanded list of email marketing tools in this Reddit post!

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! &#x200B; \*EDIT: Wasn't expecting this sort of response. I posted this right before I went to sleep so I'll get to responding soon.

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.

We made $325k in 2023 from AI products, starting from 0, with no-code, no funding and no audience

I met my co-founder in late 2022 after an introduction from a mutual friend to talk about how to find contract Product Management roles. I was sporadically contracting at start-up at the time and he had just come out of another start-up that was wiped out by the pandemic. We hit it off, talking about ideas, sharing what other indie-hackers were doing, and given GPT-3’s prominence at the time, we started throwing around ideas about things we could build with it, if nothing else, just to learn. I should caveat, neither of us were AI experts when starting out, everything we learned has been through Twitter and blogs, my background is as an accountant, and his a consultant. Here’s how it went since then: &#x200B; Nov 2022 (+$50) \- We built a simple tool in around a week using GPT-3 fine-tuning and a no-code tool (Bubble) that helped UK university students write their personal statements for their applications \- We set some Google Ads going and managed to make a few sales (\~$50) in the first week \- OpenAI were still approving applications at the time and said this went against their “ethics” so we had to take it down &#x200B; Dec 2022 (+$200) \- We couldn’t stop coming up with ideas related to AI fine-tuning, but realised it was almost impossible to decide which to pursue \- We needed a deadline to force us so we signed up for the Ben’s Bites hackathon in late December \- In a week, we built and launched a no-code fine-tuning platform, allowing people to create fine-tuned models by dragging and dropping an Excel file onto it \- We launched it on Product Hunt, having no idea how to price it, and somehow managed to get \~2,000 visitors on the site and make 2 sales at $99 &#x200B; Jan 2023 (+$3,000) \- We doubled down on the fine-tuning idea and managed to get up to \~$300 MRR, plus a bunch of one-time sales and a few paid calls to help people get the most out of their models \- We quickly realised that people didn’t want to curate models themselves, they just wanted to dump data and get magic out \- That was when we saw people building “Talk with x book/podcast” on Twitter as side projects and realised that was the missing piece, we needed to turn it into a tool \- We started working on the new product in late January &#x200B; Feb 2023 (+$9,000) \- We started pre-selling access to an MVP for the new product, which allowed people to “chat with their data/content”, we got $5,000 in pre-sales, more than we made from the previous product in total \- By mid-February, after 3 weeks of building we were able to launch and immediately managed to get traction, getting to $1k MRR in < 1 week, building on the hype of ChatGPT and AI (we were very lucky here) &#x200B; Mar - Jul 2023 (+$98,000) \- We worked all the waking hours to keep up with customer demand, bugs, OpenAI issues \- We built integrations for a bunch of services like Slack, Teams, Wordpress etc, added tons of new functionality and continue talking to customers every day \- We managed to grow to $17k MRR (just about enough to cover our living expenses and costs in London) through building in public on Twitter, newsletters and AI directories (and a million other little things) \- We sold our fine-tuning platform for \~$20k and our university project for \~$3k on Acquire &#x200B; Aug 2023 (+$100,000) \- We did some custom development work based on our own product for a customer that proved pretty lucrative &#x200B; Sep - Oct 2023 (+$62,000) \- After 8 months of building constantly, we started digging more seriously into our usage and saw subscriptions plateauing \- We talked to and analysed all our paying users to identify the main use cases and found 75% were for SaaS customer support \- We took the leap to completely rebuild a version of our product around this use case, our biggest to date (especially given most features with no-code took us <1 day) &#x200B; Nov - Dec 2023 (+$53,000) \- We picked up some small custom development work that utilised our own tech \- We’re sitting at around $22k MRR now with a few bigger clients signed up and coming soon \- After 2 months of building and talking to users, we managed to finish our “v2” of our product, focussed squarely on SaaS customer support and launched it today. &#x200B; We have no idea what the response will be to this new version, but we’re pretty happy with it, but couldn’t have planned anything that happened to us in 2023 so who knows what will come of 2024, we just know that we are going to be learning a ton more. &#x200B; Overall, it is probably the most I have had to think in my life - other jobs you can zone out from time to time or rely on someone else if you aren’t feeling it - not when you are doing this, case and point, I am writing this with a banging head-cold right now, but wanted to get this done. A few more things we have learned along the way - context switching is unreal, as is keeping up with, learning and reacting to AI. There isn’t a moment of the day I am not thinking about what we do next. But while in some way we now have hundreds of bosses (our customers) I still haven’t felt this free and can’t imagine ever going back to work for someone else. Next year we’re really hoping to figure out some repeatable distribution channels and personally, I want to get a lot better at creating content/writing, this is a first step! Hope this helps someone else reading this to just try starting something and see what happens.

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.

boring passive site... now 42k monthly visitors and $2540 MRR

people underestimate SEO... It is evergreen... passive... digital real estate. it can do magic... if you are consistent. Especially now with AI you can 2X your traffic growth and automate 85% of the work. For the past 6 months... we've been building an online directory. we just reached $2540 MRR... with SEO only... from a complete zero. I did share this on other subreddits. Maybe this gives ideas to someone. \+ This can be easily replicated if you have a website lol Current metrics: $2540 MRR - businesses pay us to list on the directory + display ads + pay to be featured. 43k monthly visitors - in the past couple of weeks our SEO growth is a hockey stick. DR (Domain Rating) 35 - it took us 2.5 months to get to that. 51 okay-ish quality referring domains (90% of them are do-follow) and 1.6k backlinks. There are probably 3 main pillars I try to focus on: keywords --> which then is the basis for ALL the content pieces we do blogs, landing pages, about us pages, competitor comparisons etc --> we use a DIY excel file to automate content production at scale. backlinks --> boost DR --> one of the main things to boost ranking on google. website health --> this is technical stuff like internal and external linking, schemas, canonical tags, alt texts, load speeds, compressed images, meta descriptions, titles etc --> do this once... and do it GOOD. $0.07 per SEO optimised blog at scale with AI Yep... we've literally built our own SEO blog tool... and it is a Spreadsheet with bunch of app scripts :D NOTE that we add a little bit of human touch to those blogs that are picked up by Google rank top in 25 How it works... is that we paste in bunch of links (other websites, blogs, news articles) and with a click of a button we can get up to 2000 SEO optimised content pieces... from an Excel file... $0.07 per blog. The spreadsheet is integrated with Chat gpt (obviously). We use GPT-4 for meta descriptions, titles, transforming the content from text to html code since it is more powerful, and GPT-4o for content itself because it is cheaper and faster for "general text". The spreadsheet repurposes content. The spreadsheet generates: Meta descriptions and titles FAQs sections - DON'T skip FAQ sections! They are a must for SEO. On Ahrefs... there is a section of questions people are searching about your keyword... that's your FAQs It can find contextual youtube videos (links to those videos) - to show google that our content is not "just text" thus higher quality. Screenshots and images of the original source (the website link we inputed) I then download a csv version of the excel and import it into our Webflow. The csv file column names match our webflow CMS field names. tbh... we didn't even know that it can be done with a spreadsheet. We "tried" building it because every other tool we were using is (1) expensive from $0.59 per SEO content piece (2) they didn't provide the scale we wanted (3) we wanted more control over the output. Focus on DR 35+ backlinks... easier We bought backlinks only once... rest of the backlinks was a manual work from us. Bunch of free listing databases (about 65% of our backlinks) You can comment on open forums with your link to get a backlink (be careful tho) Post a blog on Medium com --> DR 94 backlink (takes time to Index) If you pay for Notion you can get a DR 94 backlink from Notion If you use Beehiiv you can get a DR 86 backlink from Beehiiv Google product stacking (Google sites, Google notes etc) --> backlink from almighty Google itself A lot of work goes into backlinks because they are THAT important. I have tried bunch of "black hat" strategies as well... but note that all of these strategies won't work if you don't index the primary source from where your backlink is coming from. BIG search volume and low KD Key things I'm looking for in keywords: I use Ahrefs Keyword research tool... it is literally free BIG search volume - 2k+ is oaky-ish for a single keyword EASY to rank - KD (keyword difficulty) below 15 Look for long tail keywords (these are golden nuggets since they have a VERY clear search intent) - "how to edit..." "how to change..." "how to delete..." "how to paint..." I hope you got the idea. on Ahrefs you can use "\" to get BIG volume long tail keywords... like this "my keyword\". Ahrefs then populates the "\" with the tail. Check SERP (Search Engine Result Page) for your keywords - it shows current top 10 pages for those KWs. Check their content. Can you improve it? Have they missed anything? Keyword gap from your competitors - shows EASY keywords that your competitors have missed and also shows what keywords overlap with you. Also one cool thing... if you don't type any keywords on Ahrefs and press "Enter"... you can browse all the keywords out there... it is magical. Once we have the keywords, we run our spreadsheet. And that's pretty much it. I hope that you can get some ideas from this little silly project. Also... if you have any questions about this... I might share the SEO blog automation excel file/help if people are interested...

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.

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.

I need 10 agencies doing $1K+ MRR looking for new clients

For the past year, we've been building Surfkey. It started as a Reddit keyword alert tool focused on helping SaaS get new users from Reddit by jumping into relevant conversations, providing value, and plugging their product when it makes sense. We spent the last 3 months implementing AI to find relevant conversations without noise and once again made the beginner mistake of building for way too long. After the release, it's clear it's hard for product founders to attribute new customers to being part of Reddit conversations. But an interesting pattern appeared - agencies, freelancers, and productized services started subscribing and sending us their success stories. They got new leads from Reddit ranging from $2-$10k deals. I realized it's very hard for a product owner to see the impact of commenting on Reddit, but it's easy to connect your new lead to the conversation you were part of yesterday. And there are so many people on Reddit asking for help, looking for a new hire or just being stuck. But at the right stage of becoming a client. We are mid-pivot looking for 10 agencies that will be happy to test-drive Surfkey with us. It's fairly simple, it serves you all the posts where it makes sense to jump in, share your knowledge and then offer your service.Happy to answer any Q's!

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/

I've been building stuff for years, I can build your idea

If anyone is interested at all, I'm a college student whose been massively passionate for entrepreneur and business stuff for years and can build anything from a marketplace to a social network, a booking app, a live streaming app, AI app*, what not. I'm really flexible in general and I'm also very reasonable with pricing. I like this community so I'd like to work on something I enjoy... (indeed... get out of my tabs please). Im a little passionate in general let's say, and I build all the time for fun. But I need money. So I'm here. Viola! Since I'm a college student, and this is my first time ever offering my services as well, chances are I won't expect anything past $500. I might even do it for cheaper if it looks doable for me. If you're generous that's up to you (lol). I'm happy to share my work and live previews you can interact with before we start. And, I'm happy to build things before you pay, so you can see it literally working :) THE "NEGATIVE"/catch: There will be no code from scratch as we'd build using no-code (www.bubble.io) and implement code as needed. This means you will not have the source code ever (even if we wanted to) and if you ever want your own from scratch platform/app you will have to find someone/a team to do it from scratch, as there's no option to export source code out. If you plan to grow past 1 million users, you may consider migrating to something built from scratch at this point scaling wise (and you can't get your source code - so you'll have to pay an entire dev team separately. If you have an app, you'll need a website developed, and Android and iOS developers for the app). For an MVP however, I personally think it's a faster, easier and cheaper way to get things running without investing a lot. THE GOOD: No-code/low-code will be a thousand times more easy, cheap, and fast to maintain. And if you're a startup, chances are you WILL need to tweak things... possibly a lot (100s vs. 1,000s difference in my opinion..). We can still build almost anything and also turn it into a mobile app for iOS / Android, though I'm more comfortable with getting a web app up first and the main posting here. But it depends on the complexity so just ask. Maintenance is likely to end up FAR cheaper and you can even do it free yourself if you decided to learn (which you could totally do in some days, and master in some weeks/months fully). I can build and document everything to be as beginner friendly as possible for you to be able to maintain it yourself if you wanted to learn. Send me a message describing what you need if you're interested. I will give you an estimate on price, time, and can send you some live previews. If we agree, I will start to build before any down payments to a (reasonable) point!:)

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.

I got fired due to automation — lessons learned. Two-month overview.

UPD: Guys, I'm not promoting myself as some of the redditors decided. That's why to deal with contradictions I'll do next things: make additional post with short review and description of the general tools and processes you could apply. help only those who have already written me. So I won't answer on new offers or DMs. As mentioned, damn robots have taken my job. PRE-HISTORY During Covid times, I found myself without my offline job, and since I was interested in marketing and SMM, I began searching for a job there. Completed free Google and Udemy courses and finally landed my first SMM manager position with a business owner. He had several projects so, finally, I started managing three Twitter accounts, two Facebook accs, two IGs, and one TikTok. I handled posting, content editing and responding routine, while freelancers usually took care of video creation for IG and TT. THE STORY ITSELF Things took a turn for the worse in April when my employer introduced ChatGPT and Midjourney, tools I was already using. The owner insisted on integrating them into the workflow, and my wages took a 20% hit. I thought I could roll with it, but it was just the beginning. By midsummer, the owner implemented second-layer AI tools like Visla, Pictory, and Woxo for video (bye freelancers, lol), as well as TweetHunter, Jasper, and Perplexity for content. Midjourney and Firefly joined for image generation. All together, my paycheck was slashed by 50%. Finally, at the end of October, my boss told me he automated stuff with Zapier, cutting costs that way. Additionally, he adopted MarketOwl, autoposting tool for Twitter, and SocialBee for Facebook. He stated that he didn’t need me, as by now he could manage the social media accounts himself. I feel so pissed then and even thought that there's no point in searching for similar jobs. HOW I SPENT TWO MONTHS Well, for the first two weeks, I did nothing but being miserable, drinking and staring at the wall. My gf said it's unbearable and threatened to leave if I not pull myself together. It was not the final push, but definitely made me rethink things. So I decided to learn more about the capabilities of these automation covers and eventually became an AI adviser for small businesses. It's ironic that now I sometimes earn money advising on how to optimize marketing, possibly contributing to other people's job loss. FINAL THOUGHTS I am fully aware of the instability of such a job and have invested my last savings in taking an online marketing course at Columbia to gain more marketing experience and got something more stable afterwards. Message for mods: I'm not promoting myself or anything mentioned here; just sharing the experience that someone might find helpful.

If I hadn’t done this, I wouldn’t have made any money

If you’re just starting out, and you have an idea but aren’t sure whether it will work or not, just DO IT. I started my solopreneur journey 3 months ago with the idea of building an AI website builder. In the process, I learned a ton: integrating services like payment systems, authentication, and email, copywriting, design, analytics, UX, implementing features, prioritizing tasks, and so much more. Yet, I feel like this is just the tip of the iceberg. Even though I didn’t make a single penny with my first project, I learned a ton of sh\*. Now, I’m building something that works. It took me 3–4 days to create the MVP and, just 7 days later, I made my first sale. If I hadn’t built my first project, I wouldn’t have realized how important it is to differentiate from the competition, to solve a real problem with a unique solution. That realization led me to the idea I’m building now. It's by scratching my own itch from the first idea, that I am building something of value now. And this cycle will probably continue, as long as I’m willing to learn from my mistakes and stay determined to succeed. I GUARANTEE it works this way. I don’t know how long it’ll take to hit $5K or $10K MRR, but I know one thing: if I don’t stop, it’s just a matter of time.

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

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.

Switching Gears: Implementing AI for My Agency’s Marketing After a Decade

Hi there, I’ve been running a software development and design agency for the last 10 years, mainly focusing on building custom solutions for businesses and SaaS. For the last 2 years, I’ve consistently recommended that clients use AI technologies, especially for social media and content creation to generate traffic. Funny enough, I wasn’t practicing what I preached. Most of my client projects came from platforms like Upwork and word-of-mouth referrals from clients or people from networking events. Background I started my journey in 2014, switching from an employee to a freelancer. Within the first 10 months, my initial projects grew beyond what I could handle alone, prompting me to hire additional developers. This shift turned my role from a full-stack developer to a team lead and developer. Over the years, my focus has been a blend of tech and product. About five years ago, I realized the importance of design, leading me to adding designers to the agency to provide full-cycle service development—from product ideation and design to development, testing, launch, and support. I still continue to set up dedicated teams for some clients, maintaining a strong technical role as a tech lead, solution architect, and head product designer. To enhance my skills, I even completed UI/UX design courses to offer better product solutions. Despite these changes, building products has always been the easy part. The challenge was ensuring these client products didn’t end up in the graveyard due to poor product-market fit, often caused by inadequate marketing and sales strategies but more often just absence of them. (we are talking about startup and first time founders here 🙂 ) My Journey and Observations Advising Clients: I often found myself advising clients on increasing traffic for their SaaS products and crafting strategic marketing plans. Learning: I’ve gained most of my knowledge from consuming internet materials, courses, and blog posts and learning from successful client project launches. Realization: Despite giving this advice, I wasn’t applying these strategies to my own business, leading to low visits to my agency’s website. Initial Solution: Hiring a Marketer Hiring: I brought in a marketer with a solid background in content creating and interview video editing from an educational organization. Goal: The aim was to increase website visits through a comprehensive marketing strategy. Outcome: Although the content produced was high-quality and useful for pitching services, it didn’t lead to significant traffic increases. Issue: The marketer focused more on content creation rather than distribution channels, which limited effectiveness. Shift to AI-Driven Strategy Experiment: I decided to try using AI for content creation and distribution, which aligns with my agency’s specialization in design-driven development and AI integrations. Implementation plan: I will be generating all content with minimal edits using AI and implementing a strategic backlinking approach. Backlinking Strategy Initial Plan: I initially thought of hiring a specialist for backlinks. Realization: The costs and profiles of freelancers didn’t seem promising. Solution: I found AI-driven services for backlinks, which seem more efficient and cost-effective. Plan: My plan is to use these tools for programmatic SEO-driven AI-generated articles and third-party backlinking services over the next two to three months. Current Approach Management: This approach can be managed and executed by 1 person and monitored weekly, reducing human error and optimizing efficiency. I will start it myself and then replace myself with an editor with managing skills. Reflection: It’s a bit ironic and funny that it took me 10 years to start implementing these strategies in my own agency business, but I now feel more confident with AI and automation in place. Why Increase Website Visitors? You might ask, why do I want to increase the number of visitors to the site, and how can I ensure these visitors will be qualified? Hands-On Experience: To gain hands-on experience and perform this exercise effectively. Introduce Packaged Services: I want to introduce a set of low-cost packaged services tailored for non-technical people who want to build things for themselves - the DIY kits for non-technical folks. These services will provide a foundational template for them to build upon on top of existing established solutions such as Wix, Square Why am I Posting and Sharing Here? You might also wonder, why am I posting it here and sharing this? Well, I'm doing this more for myself. Most of my career, the things I’ve done have been behind the curtains. With this small project, I want to make it public to see the reaction of the community. Perhaps there will be good and smart suggestions offered, and maybe some insights or highlights of tools I wasn’t aware of or didn’t consider. I’ll keep sharing updates on this journey of website promotion, marketing, and SEO. My current goal is to reach 2,000 visits per month, which is a modest start. Looking forward to any thoughts or advice from this community! Disclaimer: This content was not generated by AI, but it was edited by it 😛

Switching Gears: Implementing AI for My Agency’s Marketing After a Decade

Hi there, I’ve been running a software development and design agency for the last 10 years, mainly focusing on building custom solutions for businesses and SaaS. For the last 2 years, I’ve consistently recommended that clients use AI technologies, especially for social media and content creation to generate traffic. Funny enough, I wasn’t practicing what I preached. Most of my client projects came from platforms like Upwork and word-of-mouth referrals from clients or people from networking events. Background I started my journey in 2014, switching from an employee to a freelancer. Within the first 10 months, my initial projects grew beyond what I could handle alone, prompting me to hire additional developers. This shift turned my role from a full-stack developer to a team lead and developer. Over the years, my focus has been a blend of tech and product. About five years ago, I realized the importance of design, leading me to adding designers to the agency to provide full-cycle service development—from product ideation and design to development, testing, launch, and support. I still continue to set up dedicated teams for some clients, maintaining a strong technical role as a tech lead, solution architect, and head product designer. To enhance my skills, I even completed UI/UX design courses to offer better product solutions. Despite these changes, building products has always been the easy part. The challenge was ensuring these client products didn’t end up in the graveyard due to poor product-market fit, often caused by inadequate marketing and sales strategies but more often just absence of them. (we are talking about startup and first time founders here 🙂 ) My Journey and Observations Advising Clients: I often found myself advising clients on increasing traffic for their SaaS products and crafting strategic marketing plans. Learning: I’ve gained most of my knowledge from consuming internet materials, courses, and blog posts and learning from successful client project launches. Realization: Despite giving this advice, I wasn’t applying these strategies to my own business, leading to low visits to my agency’s website. Initial Solution: Hiring a Marketer Hiring: I brought in a marketer with a solid background in content creating and interview video editing from an educational organization. Goal: The aim was to increase website visits through a comprehensive marketing strategy. Outcome: Although the content produced was high-quality and useful for pitching services, it didn’t lead to significant traffic increases. Issue: The marketer focused more on content creation rather than distribution channels, which limited effectiveness. Shift to AI-Driven Strategy Experiment: I decided to try using AI for content creation and distribution, which aligns with my agency’s specialization in design-driven development and AI integrations. Implementation plan: I will be generating all content with minimal edits using AI and implementing a strategic backlinking approach. Backlinking Strategy Initial Plan: I initially thought of hiring a specialist for backlinks. Realization: The costs and profiles of freelancers didn’t seem promising. Solution: I found AI-driven services for backlinks, which seem more efficient and cost-effective. Plan: My plan is to use these tools for programmatic SEO-driven AI-generated articles and third-party backlinking services over the next two to three months. Current Approach Management: This approach can be managed and executed by 1 person and monitored weekly, reducing human error and optimizing efficiency. I will start it myself and then replace myself with an editor with managing skills. Reflection: It’s a bit ironic and funny that it took me 10 years to start implementing these strategies in my own agency business, but I now feel more confident with AI and automation in place. Why Increase Website Visitors? You might ask, why do I want to increase the number of visitors to the site, and how can I ensure these visitors will be qualified? Hands-On Experience: To gain hands-on experience and perform this exercise effectively. Introduce Packaged Services: I want to introduce a set of low-cost packaged services tailored for non-technical people who want to build things for themselves - the DIY kits for non-technical folks. These services will provide a foundational template for them to build upon on top of existing established solutions such as Wix, Square Why am I Posting and Sharing Here? You might also wonder, why am I posting it here and sharing this? Well, I'm doing this more for myself. Most of my career, the things I’ve done have been behind the curtains. With this small project, I want to make it public to see the reaction of the community. Perhaps there will be good and smart suggestions offered, and maybe some insights or highlights of tools I wasn’t aware of or didn’t consider. I’ll keep sharing updates on this journey of website promotion, marketing, and SEO. My current goal is to reach 2,000 visits per month, which is a modest start. Looking forward to any thoughts or advice from this community! Disclaimer: This content was not generated by AI, but it was edited by it 😛

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!

How a Small Startup in Asia Secured a Contract with the US Department of Homeland Security

Uzair Javaid, a Ph.D. with a passion for data privacy, co-founded Betterdata to tackle one of AI's most pressing challenges: protecting privacy while enabling innovation. Recently, Betterdata secured a lucrative contract with the US Department of Homeland Security, 1 of only 4 companies worldwide to do so and the only one in Asia. Here's how he did it: The Story So what's your story? I grew up in Peshawar, Pakistan, excelling in coding despite studying electrical engineering. Inspired by my professors, I set my sights on studying abroad and eventually earned a Ph.D. scholarship at NUS Singapore, specializing in data security and privacy. During my research, I ethically hacked Ethereum and published 15 papers—three times the requirement. While wrapping up my Ph.D., I explored startup ideas and joined Entrepreneur First, where I met Kevin Yee. With his expertise in generative models and mine in privacy, we founded Betterdata. Now, nearly three years in, we’ve secured a major contract with the U.S. Department of Homeland Security—one of only four companies globally and the only one from Asia. The Startup In a nutshell, what does your startup do? Betterdata is a startup that uses AI and synthetic data generation to address two major challenges: data privacy and the scarcity of high-quality data for training AI models. By leveraging generative models and privacy-enhancing technologies, Betterdata enables businesses, such as banks, to use customer data without breaching privacy regulations. The platform trains AI on real data, learns its patterns, and generates synthetic data that mimics the real thing without containing any personal or sensitive information. This allows companies to innovate and develop AI solutions safely and ethically, all while tackling the growing need for diverse, high-quality data in AI development. How did you conduct ideation and validation for your startup? The initial idea for Betterdata came from personal experience. During my Ph.D., I ethically hacked Ethereum’s blockchain, exposing flaws in encryption-based data sharing. This led me to explore AI-driven deep synthesis technology—similar to deepfakes but for structured data privacy. With GDPR impacting 28M+ businesses, I saw a massive opportunity to help enterprises securely share data while staying compliant. To validate the idea, I spoke to 50 potential customers—a number that strikes the right balance. Some say 100, but that’s impractical for early-stage founders. At 50, patterns emerge: if 3 out of 10 mention the same problem, and this repeats across 50, you have 10–15 strong signals, making it a solid foundation for an MVP. Instead of outbound sales, which I dislike, we used three key methods: Account-Based Marketing (ABM)—targeting technically savvy users with solutions for niche problems, like scaling synthetic data for banks. Targeted Content Marketing—regular customer conversations shaped our thought leadership and outreach. Raising Awareness Through Partnerships—collaborating with NUS, Singapore’s PDPC, and Plug and Play to build credibility and educate the market. These strategies attracted serious customers willing to pay, guiding Betterdata’s product development and market fit. How did you approach the initial building and ongoing product development? In the early stages, we built synthetic data generation algorithms and a basic UI for proof-of-concept, using open-source datasets to engage with banks. We quickly learned that banks wouldn't share actual customer data due to privacy concerns, so we had to conduct on-site installations and gather feedback to refine our MVP. Through continuous consultation with customers, we discovered real enterprise data posed challenges, such as missing values, which led us to adapt our prototype accordingly. This iterative approach of listening to customer feedback and observing their usage allowed us to improve our product, enhance UX, and address unmet needs while building trust and loyalty. Working closely with our customers also gives us a data advantage. Our solution’s effectiveness depends on customer data, which we can't fully access, but bridging this knowledge gap gives us a competitive edge. The more customers we test on, the more our algorithms adapt to diverse use cases, making it harder for competitors to replicate our insights. My approach to iteration is simple: focus solely on customer feedback and ignore external noise like trends or advice. The key question for the team is: which customer is asking for this feature or solution? As long as there's a clear answer, we move forward. External influences, such as AI hype, often bring more confusion than clarity. True long-term success comes from solving real customer problems, not chasing trends. Customers may not always know exactly what they want, but they understand their problems. Our job is to identify these problems and solve them in innovative ways. While customers may suggest specific features, we stay focused on solving the core issue rather than just fulfilling their exact requests. The idea aligns with the quote often attributed to Henry Ford: "If I asked people what they wanted, they would have said faster horses." The key is understanding their problems, not just taking requests at face value. How do you assess product-market fit? To assess product-market fit, we track two key metrics: Customers' Willingness to Pay: We measure both the quantity and quality of meetings with potential customers. A high number of meetings with key decision-makers signals genuine interest. At Betterdata, we focused on getting meetings with people in banks and large enterprises to gauge our product's resonance with the target market. How Much Customers Are Willing to Pay: We monitor the price customers are willing to pay, especially in the early stages. For us, large enterprises, like banks, were willing to pay a premium for our synthetic data platform due to the growing need for privacy tech. This feedback guided our product refinement and scaling strategy. By focusing on these metrics, we refined our product and positioned it for scaling. What is your business model? We employ a structured, phase-driven approach for out business model, as a B2B startup. I initially struggled with focusing on the core value proposition in sales, often becoming overly educational. Eventually, we developed a product roadmap with models that allowed us to match customer needs to specific offerings and justify our pricing. Our pricing structure includes project-based pilots and annual contracts for successful deployments. At Betterdata, our customer engagement unfolds across three phases: Phase 1: Trial and Benchmarking \- We start with outreach and use open-source datasets to showcase results, offering customers a trial period to evaluate the solution. Phase 2: Pilot or PoC \- After positive trial results, we conduct a PoC or pilot using the customer’s private data, with the understanding that successful pilots lead to an annual contract. Phase 3: Multi-Year Contracts \- Following a successful pilot, we transition to long-term commercial contracts, focusing on multi-year agreements to ensure stability and ongoing partnerships. How do you do marketing for your brand? We take a non-conventional approach to marketing, focusing on answering one key question: Which customers are willing to pay, and how much? This drives our messaging to show how our solution meets their needs. Our strategy centers around two main components: Building a network of lead magnets \- These are influential figures like senior advisors, thought leaders, and strategic partners. Engaging with institutions like IMDA, SUTD, and investors like Plug and Play helps us gain access to the right people and foster warm introductions, which shorten our sales cycle and ensure we’re reaching the right audience. Thought leadership \- We build our brand through customer traction, technology evidence, and regulatory guidelines. This helps us establish credibility in the market and position ourselves as trusted leaders in our field. This holistic approach has enabled us to navigate diverse market conditions in Asia and grow our B2B relationships. By focusing on these areas, we drive business growth and establish strong trust with stakeholders. What's your advice for fundraising? Here are my key takeaways for other founders when it comes to fundraising: Fundraise When You Don’t Need To We closed our seed round in April 2023, a time when we weren't actively raising. Founders should always be in fundraising mode, even when they're not immediately in need of capital. Don’t wait until you have only a few months of runway left. Keep the pipeline open and build relationships. When the timing is right, execution becomes much easier. For us, our investment came through a combination of referrals and inbound interest. Even our lead investor initially rejected us, but after re-engaging, things eventually fell into place. It’s crucial to stay humble, treat everyone with respect, and maintain those relationships for when the time is right. Be Mindful of How You Present Information When fundraising, how you present information matters a lot. We created a comprehensive, easily digestible investment memo, hosted on Notion, which included everything an investor might need—problem, solution, market, team, risks, opportunities, and data. The goal was for investors to be able to get the full picture within 30 minutes without chasing down extra details. We also focused on making our financial model clear and meaningful, even though a 5-year forecast might be overkill at the seed stage. The key was clarity and conciseness, and making it as easy as possible for investors to understand the opportunity. I learned that brevity and simplicity are often the best ways to make a memorable impact. For the pitch itself, keep it simple and focus on 4 things: problem, solution, team, and market. If you can summarize each of these clearly and concisely, you’ll have a compelling pitch. Later on, you can expand into market segments, traction, and other metrics, but for seed-stage, focus on those four areas, and make sure you’re strong in at least three of them. If you do, you'll have a compelling case. How do you run things day-to-day? i.e what's your operational workflow and team structure? Here's an overview of our team structure and process: Internally: Our team is divided into two main areas: backend (internal team) and frontend (market-facing team). There's no formal hierarchy within the backend team. We all operate as equals, defining our goals based on what needs to be developed, assigning tasks, and meeting weekly to share updates and review progress. The focus is on full ownership of tasks and accountability for getting things done. I also contribute to product development, identifying challenges and clearing obstacles to help the team move forward. Backend Team: We approach tasks based on the scope defined by customers, with no blame or hierarchy. It's like a sports team—sometimes someone excels, and other times they struggle, but we support each other and move forward together. Everyone has the creative freedom to work in the way that suits them best, but we establish regular meetings and check-ins to ensure alignment and progress. Frontend Team: For the market-facing side, we implement a hierarchy because the market expects this structure. If I present myself as "CEO," it signals authority and credibility. This distinction affects how we communicate with the market and how we build our brand. The frontend team is split into four main areas: Business Product (Software Engineering) Machine Learning Engineering R&D The C-suite sits at the top, followed by team leads, and then the executors. We distill market expectations into actionable tasks, ensuring that everyone is clear on their role and responsibilities. Process: We start by receiving market expectations and defining tasks based on them. Tasks are assigned to relevant teams, and execution happens with no communication barriers between team members. This ensures seamless collaboration and focused execution. The main goal is always effectiveness—getting things done efficiently while maintaining flexibility in how individuals approach their work. In both teams, there's an emphasis on accountability, collaboration, and clear communication, but the structure varies according to the nature of the work and external expectations.

10 Side Projects in 10 Years: Lessons from Failures and a $700 Exit

Hey folks, I'm sharing my journey so far in case it can help others. Entrepreneurship can sometimes be demotivating. In my case, I've always been involved in side projects and what I've realized is that every time you crash a project, the next one makes it a bit further. So this is a long-term game and consistency ends up paying off The $1 Android Game (2015, age 18) What Happened: 500 downloads, 1€ in ad revenue Ugly UI, performance issues Key Lessons: Don’t be afraid of launching. Delaying for “perfection” is often a sign that you fear being ignored. I was trying to perfect every aspect of the game. In reality, I was delaying the launch because I feared no one would download the app. Commit to the project or kill it. At some point, this project was no longer fun (it was just about fixing device responsiveness). Most importantly, I wasn't learning anything new so I moved to smth else. The Forex Bot Regret (2016, age 19) What Happened: Lost months identifying inexistent chart patterns Created a Trading bot that was never profitable Key Lessons: Day trading’s real winners are usually brokers. There are plenty of guys selling a bot or systems that are not making money trading, why would they sell a “money-printing machine” otherwise... Develop an unfair advantage. With these projects, I developed a strong coding foundation that gave me an edge when dealing with non-technical business people. Invest countless hours to create a skills gap between you and others, one that becomes increasingly difficult for them to close (coding, public speaking, networking, etc.) The $700 Instagram Exit (2018, age 21) What Happened: Grew a motivational account to 60k followers Sold it for $700 90% of followers were in low-income countries (hard to monetize) Key Lessons: Follower quality > quantity. I focused on growth and ended up with an audience I couldn’t truly define. If brands don’t see value, you won’t generate revenue. Also, if you do not know who you are creating content for, you'll end up demotivated and stop posting. Great 3rd party product + domain authority = Affiliate marketing works. In this case, I could easily promote an IG growing service because my 50k+ followers conveyed trust. Most importantly, the service I was promoting worked amazingly. The Illegal Amazon Review Marketplace (2020, age 23) What Happened: Sellers were reimbursing buyers for positive reviews Built a WordPress marketplace to facilitate “free products for reviews” Realized it violated Amazon’s terms Key Lessons: Check for “red flags” when doing idea assessment. There will always be red and orange flags. It’s about learning to differentiate between them (e.g. illegality, 100% dependence on a platform, etc.) If there’s competition, it’s good, if they are making money it’s even better. I was thrilled when I saw no competition for my “unique idea”. Later, I discovered the obvious reason. Copying a “Proven” Business Model (2020, age 23) What Happened: Tried recreating an Instagram “comment for comment” growth tool Instagram changed the algorithm and killed the growth strategy that the product used. Key Lessons: Do not build a business that depends 100% on another business, it is too risky. Mr. Musk can increase Twitter on API pricing to $42,000 monthly without notice and Tik Tok can be banned in the US. Due to the IG algorithm change, we had built a product that was not useful, and worse, now we had no idea how to grow an IG account. Consider future project synergies before selling. I regret having sold the 60k follower IG account since it could have saved me a lot of time when convincing users to try the service. NFT Marathon Medals (2021, age 24) What Happened: Created NFT race medals Sold 20 for 5€ each, but spent 95% of meetings explaining “what is an NFT?” Key Lessons: Market timing is crucial. As with every new technology, it is only useful as long as society is ready to adopt it. No matter how promising the tech is in the eyes of SV, society will end up dictating its success (blockchain, AI, etc). In this case, the runner community was not ready to adopt blockchain (it is not even prepared today). Race organizers did not know what they were selling, and runners did not know what they were buying. The 30-day rule in Fanatical Prospecting. Do not stop prospecting. I did prospecting and closed deals 3 months after the outbound efforts. Then I was busy executing the projects and had no clients once the projects were finished. AI Portal & Co-Founder Misalignment (2023, age 26) What Happened: Built a portal for SMEs to find AI use cases Co-founders disagreed on vision and execution Platform still gets \~1 new user/day Key Lessons: Define roles and equity clearly. Our biggest strength ended up killing us. Both founders had strong strategic skills and we were constantly arguing about decisions. NextJS + Vercel + Supabase: Great stack to create a SaaS MVP. (but do not use AI with frameworks unless you know how they work conceptually) SEO is king. One of our users creates a use case on “Changing Song Lyrics with AI.” Not being our target use case, it brings 90% of our traffic. Building an AI Tool & Getting Ghosted (2024, age 27) What Happened: SEO agency wanted to automate rewriting product descriptions Built it in 3 weeks, but the client vanished Key Lessons: Validate manually first. Don’t code a full-blown solution for a problem you haven’t tested in real-world workflows. I kept rewriting code only to throw it away. Jumping straight into building a solution ended up costing more time than it saved. Use templates, no-code, and open-source for prototyping. In my case, using a Next.js template saved me about four weeks of development only to hit the same dead end, but much faster. Fall in love with your ICP or walk away. I realized I didn’t enjoy working with SEO agencies. Looking back, I should have been honest with myself and admitted that I wasn’t motivated enough by this type of customer. Ignoring Code Perfection Doubled Traffic (2025, age 28) What Happened: Partnered with an ex-colleague to build an AI agents directory Focused on content & marketing, not endless bug fixes Traffic soared organically Key Lessons: Measure the impact of your actions and double down on what works. We set up an analytics system with PostHog and found wild imbalances (e.g. 1 post about frameworks outperformed 20 promotional posts). You have to start somewhere. For us, the AI agents directory is much more than just a standalone site, it's a strategic project that will allow us to discover new products, gain domain authority, and boost other projects. It builds the path for bigger opportunities. Less coding, more traction. Every day I have to fight against myself not to code “indispensable features”. Surprisingly, the directory keeps gaining consistent traffic despite being far from perfect Quitting My Job & Looking Ahead (2025, age 28) What Happened: Left full-time work to go all-in Plan to build vertical AI agents that handle entire business workflows (support, marketing, sales) Key Lessons: Bet on yourself. The opportunity cost of staying in my full-time job outweighed the benefits. It might be your case too I hope this post helps anyone struggling with their project and inspires those considering quitting their full-time job to take the leap with confidence.

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!

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.

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.

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

A Free Course for Entrepreneurs to use AI text-to-image for real-life use cases

Hi there👋 We are flooded by text-to-image generators and how cool they are to generate cute photos of cats. Around a month ago I asked myself, how can I, an entrepreneur (kinda?), use this tool for my real-life professional use? I am very actively involved in running my stuff, including an e-commerce shop and an ed-tech startup. At the same time, I am a co-founder at an AI venture studio, thus spending a lot of time in that field, especially for the last 6-8 months. I decided to share my journey of figuring out how to use generative Art for my projects. In this 2-hour exploration-type course, I share tactics and use cases that I found to be very useful, and hope to be useful for some of you as well. Here are the main takeaways that I have regarding text-to-image generators: There is a learning curve for diving deep into different parameters, but once you do, you can create very useful visual assets for your projects It is an amazingly well fit for visual explorations \- creating draft mood boards, crafting visual identity for new projects and marketing materials If your project/startup can not afford top designers, generative Art is the only option to level up your project's visual communication capabilities. I would love to hear about your experience with using text-to-image generators for your real-life cases.

Made my second f***ing sale of $15k with my agency business

A few months back, I quit my full-time software engineering job, where I was making $5k a month.  I started my business to help founders build their products by partnering with them as a Tech Founder. After two months of getting everything on the road, I closed my first deal of $15k, where I am working with a founder who is building an AI-based A/B testing tool for websites, graphics, and sales copywriting. Today, I am closing my second deal of $15k more, where I will be helping a non-technical founder build Wedding Planner software. I am grateful to have made the decision, as I am on track to make more than my yearly salary within the next three months, as per my plan.  Not a millionaire yet, but I will grow my business to a million dollars in the next year. Back to work; I will keep everyone posted here! Edit: Thanks for all the wishes. This blew up more than I expected, I tried to answer all of the queries. I have received many DMs for sharing the business details. You can find it linked above.

Feedback appreciated 🙏🏻 : a tool for solo entrepreneurs and small startups to help with marketing | app.maestrix.ai

Hey friends, I've run a boutique marketing agency for almost 8 years and since chatGPT has arrived a year ago, the game has really changed. I'm sure there are here a handful of you who have tried AI in some fashion for a marketing-related task; My realization has quickly been that this could (and will) make my (and a ton of ) marketing jobs obsolete. That made me start to go very serious about writing extremely specific instructions for marketing tasks. I started to map out all my knowledge and operating frameworks that I knew with 20+ years of experience. I ended up organizing these core marketing activities with AI: positioning and value proposition canvases, buyer's journey analysis target audience analysis SEO strategy campaign messaging blog and social copywriting landing pages — Fast forward 6 months today, I''ve built the no-code tool that runs with OpenAi's latest model (LLM) available via API (GPT-4-Turbo-preview for the geeks) : app.maestrix.ai I'd love to get your feedback on the following items: \- the quality of the outputs generated for your product/service \- the tasks that are missing for your current projects. \- how I can make it more useful down the road Your feedbacks are very precious 🙏🏻 Guillaume — P.S: DM me if you have tested it so I can give you thank-you task credits 🎁

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.

How I went from $27 to $3K as a solopreneur still in a 9-5

My journey started back in November 2023. I was scrolling through Twitter and YouTube and saw a word that I had never come across before. Solopreneur. The word caught my eye. Mainly because I was pretty sure I knew what it meant even though it's not a word you'll find in the dictionary. I liked what it was describing. A solo entrepreneur. A one man business. It completely resonated with me. As a software engineer by trade I'm used to working alone, especially since the pandemic hit and we were forced to work remotely. See, I always wanted to ditch the 9-5 thing but thought that was too big and too scary for a single person to do. Surely you would need a lot of money to get started, right? Surely you would need investors? The whole concept seemed impossible to me. That was until I found all the success stories. I became obsessed with the concept of solopreneurship. As I went further down the rabbit hole I found people like Justin Welsh, Kieran Drew and Marc Louvion to name a few. All of whom have one person businesses making huge money every year. So I thought, if they can do it, why can't I? People like this have cleared the pathway for those looking to escape the 9-5 grind. I decided 2024 would be the year I try this out. My main goal for the year? Build a one man business, earn my first $ online and learn a sh\*t ton along the way. My main goal in general? Build my business to $100K per year, quit my 9-5 and live with freedom. From December 2023 to February 2024 I began brainstorming ideas. I was like a lost puppy looking for his ball. How on earth did people find good ideas? I began writing everything and anything that came to mind down in my notes app on my phone. By February I would have approximately 70 ideas. Each as weird and whacky as the other. I was skeptical though. If I went through all the trouble of building a product for one of these ideas how would I know if anyone would even be interested in using it? I got scared and took a break for a week. All these ideas seemed too big and the chance that they would take off into the atmosphere was slim (in my mind anyways). I was learning more and more about solopreneurship as the weeks went on so I decided to build a product centered around everything I was learning about. The idea was simple. Enter a business idea and use AI to give the user details about how to market it, who their target customers were, what to write on their landing page, etc. All for a measly $27 per use. I quickly built it and launched on March 3rd 2024. I posted about it on Indie Hackers, Reddit and Hacker News. I was so excited about the prospect of earning my first internet $! Surely everyone wanted to use my product! Nope...all I got was crickets. I was quickly brought back down to earth. That was until 5 days later. I looked at my phone and had a new Stripe notification! Cha-ching! My first internet $. What a feeling! That was goal number 1 complete. It would be another 6 days before I would get my second sale...and then another 15 days to get my third. It was an emotional rollercoaster. I went from feeling like quitting the 9-5 was actually possible to thinking that maybe the ups and downs aren't worth it. On one hand I had made my first internet dollar so I should my ecstatic, and don't get me wrong, I was but I wanted more. More validation that I could do this long term. By May I was starting to give up on the product. I had learned so much in the past few months about marketing, SEO, building an audience, etc. and I wanted to build something that I thought could have more success so I focused on one critical thing that I had learned about. What was it? Building a product that had SEO potential. A product that I knew hundreds of people were looking for. See this was my thinking - If I could find a keyword that people were searching for on Google hundreds/thousands of times every month and it was easy to rank high on search engines then I would go all in (in SEO land this equates to a Keyword that has a Keyword Difficulty of = 500). I began researching and found that the keyword "micro saas ideas" was being searched for around 600 times each month. Micro Saas was something that really interested me. It was perfect for solopreneurs. Small software products that 1 person could build. What's not to like if you're in the game of software and solopreneurship? Researching keywords like this became like a game for me. I was hooked. I was doing it every day, finding gems that were being searched for hundreds and thousands of times every month that still had potential. That's when I came up with my next product idea. I decided to create a database of Micro Saas Ideas all with this sort of SEO potential. See if you can build a product that you know people are looking for then that's all the validation you need. So I put this theory to the test. I created a database of Micro Saas Ideas with SEO Potential and launched it in June 2024. This time it was different. I made $700 in the first week of launching. A large contrast to my previous failed attempt at becoming the worlds greatest solopreneur. Since launch I have grown the product to $3K and I couldn't be happier. I know what you're saying, $3K isn't a lot. But it's validation. It's validation that I can earn $ online. Validation that I can grow a business and it gives me hope that one day I'll be able to quit that 9-5 grind. My plan is to keep growing the business. I expect there to be a few challenges up ahead but I'll tackle them as I go and learn from the failures and successes. I have a newsletter where I share Micro Saas Ideas with SEO potential every week which I'll leave below in the first comment. Feel free to come along for the ride. If not I hope this post brings you some value If you're thinking about starting as a solopreneur, stop thinking and start doing, you won't regret it.

I sold my AI tool for $35,000

Hey Entrepreneurs, Marc here. Last month I wrote here about how sold a habit tracker for $10,000 in October. Earlier this month, I got $35,000 in my bank account after selling a landing page maker with AI. Here's the story: &#x200B; April 2023: Just like everyone, I get massive FOMO with AI. I played with GPT and decided to build a landing page generator with AI: Input text and the AI prefills a template with copy and AI-generated images. I'm working on it with a good friend of mine named Martin. May: The product is called LandingAI. It's an MVP but we launched and made \~$8,000. Unfortunately, Martin and I had different visions for the project so we forked. &#x200B; June: LandingAI is the name of a big corp (bummer) so I rebranded it to MakeLanding. I ditch 90% of the code because users want a very different product: So here I am, building an entire website builder powered with AI... &#x200B; July: I launched again, but made a BIG mistake: I swapped the one-time payment for a monthly subscription and got $20 MRR for 15k visitors... If you can avoid subscriptions, do it New pricing means new positioning—users compared the app to Framer & Webflow August: I removed the subscription and sales came back: \~$7,000 in 3 months. But I realized this was going nowhere... September: I don't use the product The market is gigantic and crowded As a solopreneur, nothing is more important for me than building cool stuff for people I care about. And I didn't really care about this big market so... October: I called my friend Dan and he said: SELL. He was right. I bought my shares of LandingAI from Martin and listed MakeLanding on Acquire: Asking $38,000 for $14,000 TTM (3x profit) Within hours, I received dozens of NDAs and a buyer started the process 🤯 After a few weeks of NDA, LOI, Escrow, etc. the buyer sent the money but... Only a fraction of the transaction. Then he ghosted me. So I canceled the transition. Back to Acquire... Luckily, in 24 hours I got another buyer! &#x200B; November: Within weeks, the money was in my bank account. The buyer and I never called, just a few messages. It's mind-blowing. &#x200B; My takeaways: Don't build AI products just because Don't go on a massive market you don't care Sell if you don't know how to grow the product It's my 3rd acquisition this year. I love the freedom of build, sell, repeat.

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

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.

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.

This is why most of AI wrappers will die

We began building our AI product in public as a tool to help people quickly build online stores using AI during June of 2023. It was quite a hot AI time. The tool was using ChatGPT to create a fully-functinal eCommerce store with a demo products from Amazon. And we managed to get such impression among people so they started to share it with words: "Look, I made my own store in 20 seconds." We got about 2,000 users that way, mainly people telling their friends to try it out. We built a toy Back in 2023, this idea was exciting. It was great for getting people to talk about us and for getting random people to check us out. We burned \~2k$ on various API we used then with an expectations: people will start to pay. Nobody paid. It was a train called AI and we all were the passengers, but not all of us were able to understand how to monitize this and in reality most of AI wrappers have the lack of this. Most of AI wrappers would be eaten by a bigger players, other will be not able to proceed due to fact of investment. We had a few benefits: 1) We are developers with skills in design and a bit in marketing 2) We spent years in development of eCommerce products So to keep things going it was important to focus on: 1) Longer game, there is no quick wins, unfortunatelly or fortunatelly 2) Narrower niche and smaller auditory 3) Patience 4) Building network and product authority The road to actual product So to attract real users, we had to start solving a real problem for them, to offer them something valuable. We do this already 5 months since October. We made like 5 pivots... Today our product proposition "Marketsy allows busy people to own a business: a simple in management store of digital products as a source of income" So all AI thing right now is hidden under "busy", AI helps to automate the process, but not the primary thing in the product anymore. Even eCommerce SaaS market is huge and comeptition is hight. We are going to test this approach upcoming weeks, we believe it will be a right step. Anyway we are sure we will find the right proposition and our audience, one way or another. All the best to other product builders here!

[Ultimate List] A list of Marketing Tools That I’ve tested over the years and found helpful to do better marketing with less work. More than 50 Tools To Help you with Marketing, Copywriting & Sales!

Starting to focus on marketing for your business, You will come across the same tools mentioned over and over by marketers. I would like to mention here tools that you might haven’t seen going viral in the community but actually will help you grow faster and efficiently. Starting off with My favourite Marketing Channel! #Email Marketing For SMBs Convertkit / Mailerlite / Mailchimp - These 3 Platforms are the best options for SMBs and entrepreneurs just starting out with email marketing. All 3 have free plans up to 1,000 subscribers. Scribe - Email Signature Tool, Create Great Email signatures for your emails. Liramail - Most Email marketing platforms don’t offer great email templates. This tool will help you build great email templates with drag and drop. Quick mail Auto-Warmer - Most Businesses at the beginning don’t know what to do when open rate drops. You need to use an email warmer like this to keep it up. #Email Marketing For Big Businesses SendGrid - Overall Email Marketing Tools, this tool is best for brands that have huge email lists and email marketing is the key marketing channel. Braze - This tool is leading in email marketing for large Email senders. When I was working for agencies, this was one of the best email marketing tools I had used. NeoCertified - Protect your emails for spammers and threats. To keep your email list healthy, this is a must have! Sparkloop - Referral Marketing For Email Campaigns. Email can generate great huge amount of referrals for you and Sparkloop makes it easier. #Cold Emails & Lead Generation Hunter - A Great Tool to scrape emails from domain names. The tool comes with a green free plan but Pro plan is worth the amount of features it provides. Icyleads - It’s better than Hunter as it’s heavily focused on the sales and prospecting to help you derive great results from your campaigns. Mailshake - Beginner Friend Cold Email Tool with Great features like email list warming. #Communication Tools Twilio - One do the best customer engagement platform used by Companies like Stripe and mine too. Chatlio - Use Live chat feature on your website with slack integration. My favourite easier to catch up on conversations through slack integration. Intercom - Used by Most Marketers, Industry Leading customer communication platform. Great for beginners! Chatwoot - Another Amazing Communication Tool but the best part is they have a great free plan useful for new businesses. Loom - Communicate with your audience through Videos. Loom is great for SaaS and to show human interaction to close new visitors effectively. #CRM Outseta - This tool provides great CRM and their billing system is better than other tools out their which makes it stands out! Hubspot - I don’t think this tool needs an introduction because Hubspot’s CRM is the best in industry. Salesflare - This CRM is a great alternative to hubspot as it’s beginner friendly and helpful for SMBs. #SEO Tools Ahrefs - One of the best SEO tool in the industry. They also just launched a bunch of free tools to help SEO beginners. Screaming frog - The only website crawler I have used since I bought my first domain. It’s the best! Ubersuggest- The Tool by Neil Patel is the best SEO tool for you. (I’m Joking, it’s the worst) Contentking - This tool is good at Real-time SEO Auditing, they do a lot of Marketing work through Newsletters. If you are subscribed to any SEO newsletter. You may have seen this tool. SEOquake & Semrush - SEOquake is a great tool to conduct on-page analysis, SERP, and much more. Great tool but it’s owned by Semrush. You should go for Semrush because that tool will cover all SEO aspects for you. #Content Marketing Buzzsumo - This tool is great for content research and but you may find the regular emails pretty annoying sometimes. Contentrow - Analyse Your Content and find it’s strength. Highly recommended who are weak at content structuring like me. Grammarly - If you are not a native English speaker like me, you might think you need it or not. You need it for sure for grammar corrections. #Graphic Design Tools Visme - At agencies, Infographics can be more effective than usual postscript. Visme is a graphic design tool focused on infographics and designs related to B2B and B2C. It’s great for agencies! Glorify - A Graphic Design Tool focused on E-commerce, filled with Designs useful for E-commerce store owners. Canva - All-in-one Industry leading Graphic Design Tool that everyone knows and every template is overused now. Adobe Creative Cloud ( previously Sparkpost) - It’s a great alternative to Canva filled with Amazing Stock images to use in your visuals but the only backlash is the exports in this tool are not high quality. Snaps - A Canva Alternative that might not have overused templates for your Social Accounts. #Advertising Tools Plai - It’s a great PPC tool to create Ads for Instagram and Tiktok. Wordstream - It’s an industry leading PPC Tool, great for Ad Grading and auditing. AdEspresso - This Is a tool by Hootsuite. They have a lot of Data sourced at the backend, which helps in Ad optimisation through this tool. That’s the reason I recommend this tool. #Video Editing Tools Veed Studio - I have been using Veed from last year. It’s one of the best Video Marketing Tool Optimized for Instagram & Tiktok. Synthesia - It’s a new AI video generation platform. From last few months, if you have seen marketing agencies including Videos in Emails. The chances are that’s not a Agency member taking but AI generated Human. Motionbox - It’s also a great video editing tool focused on video editing for Digital Marketers. Jitter Video - It’s a great motion design tool. Comes with great templates, the only place where other tools I mentioned lacks. It’s great and beginner friendly. #Copywriting Jasper AI - Google’s John Mueller says AI generated content is banned on Search but I think with Jasper AI you can generate SEO optimised Content but you have to put in some efforts like at least give 30 minutes for editing the Copy by yourself. Copy AI - Another AI tool to help you write better copy. This one is more focused on helping you write copy suitable for Ads and Social media campaigns. Hemingway App - To help you write more clearly and Bold. This tool is better than Grammarly if you look for writing perspective and it’s free. #Social Media Management App I’ve used a Lot of SMM Tools and that’s why going to mention all of them with a short review. Sprout social - The Best with deep insights coverage. Hootsuite - Great Scheduling tool just under sprout social. Later - Heavily Focused on Instagram from beginning and Now Tiktok too. SkedSocial - It’s like a Later alternative with great addition features like link-in-bio. Facebook’s Business Manager- Great but sometimes bugs can make a huge issue for you and customer support is like dead. Tweet Hunter & Hypefury- Both are Twitter Scheduling tools growing very fast on platform and are great for growth. Buffer - It’s a great tool but I haven’t seen any new updates to help with management. Zoho Social - It’s a great SMM tool and if you use other marketing solutions from Zoho. It’s a must have! #Market Research Tool • SparkToro - That’s the only one I have ever used. It’s great for audience research and comes with great customer service. Founded by Rand Fishkin, it’s one of the best research tool. #Influencer Marketing & UGC InfluenceGrid - A free search engine To find Tiktok & Instagram Influencers for your campaigns. Tiktok Creative Center- TikTok’s in-built tool called “Creative Center” is the best to find content trends, audience demographics and much more. Archive - Find Instagram Stories and Posts mentioning Your brands and use them as Ads for your business Marketing. #Landing Page Builders Leadpages - Its a great landing page builder because the integration and drag-and-drop features makes it easier to work with! Cardd co - A Great Landing page builder with easy step up but it lacks the copywriting and tracking features. Instapage - It’s one of the best out and I think the overall product is effective enough to help you stand out with your landing page. Unbounce - It’s a great alternative to Instapage due its well polished landing page templates that might be helpful for you. #Community Building Mighty Networks - A Great Community building platform, and you can also sell courses within the platform. Circle so - A great alternative to Mighty networks focused on Communities specifically. We are currently using for small community Of ours. #Sales Tools Drift - You can get much more out of Drift than just sales tools but The Sales solutions provided in Drift are one of the best. Salesforce - It’s the industry Sales solution provider. A go-to and have various pricing plans making it suitable for majority of SMBs. #Social Proof Tools People don’t have enough time to search across internet to decide to trust you after seeing your Ad first time. That’s what you might be facing too. Here are two tools I absolutely love for social proof! Use Proof - Show Recent Activities occurring on your website and build the trust of your visitors. Testimonial to - Gather Testimonials across Social Media platforms related to your business with this tool. Capture tweets and comments mentioning your brands and mention them. #Analytics Tools Plausible Analytics- A privacy friendly Analytics alternative to Google Analytics if you hate Analytics 4 like me. Mixpanel - Product Analytics and funnel reports better than Google Analytics. #Reddit Marketing Gummysearch- This tool will help To find your target audience on Reddit and interact with them with its help and close your new customers. Howitzer- It’s another pretty similar tool to Gummysearch focused on Reddit cold outreach to get clients and new customers. Both are great but Gummysearch provides better customer support while Howtizer is helpful on a large scale Reddit Marketing. #Text Marketing Klaviyo - It’s an email + SMS marketing tool, it’s taking up space in marketing industry very quickly as an industry leader due to its great integrations but you need to learn the platform usage to maximise the outcome. Cartloop - This tool provides great text marketing solutions with integration with Spotify and other e-commerce marketing tools. Attentive Mobile - This is my favourite Text marketing tool due to the interactive dashboard + they have a library of Text marketing examples to help you out with your campaigns. #Other Tools I have used throughout my journey! Triple Whale - It’s a great E-commerce marketing tools with Triple pixel to help you track your campaigns more efficiently. Fastory - To create well optimized Instagram & Tiktok Stories for your business. Jotform - Online Form Builder with integrations with leading marketing tools. Gated - As an entrepreneur and marketer, you may receive a bunch of unwanted emails. Use Gated to get rid of them and receive useful mails only! ClickUp- The main Tool for Project Management, one of the best and highly recommended. Riverside - Forget Zoom or Google Meet, For your Podcast Interviews and Marketing conferences. You need riverside with great video quality and recording features. Manychat- Automate your Instagram DMs and interact with your followers more efficiently + sell out your products/ services when you are offline. Calendy - To schedule meetings with your ideal clients. ServiceProviderPro - It’s a client portal for SEO & Growing Agencies, very helpful in scaling agencies. SendCheckit - Compare your Email Subject Lines with 100,000+ others in the database for free. Otter AI - Using AI track your meetings more effectively, you can easily edit, annotate and share notes from the meetings. Ryte - Optimise your website User experience with this tool focused on UX aspects + SEO too. PhantomBuster - Scrape LinkedIn Profile and Data from Facebook/LinkedIn groups. I clearly love this tool! #Honourable Mentions Zapier - The Only tool you need to integrate your favourite tool with a new effective tool. Elementor - That’s what I use for web design and it’s great! Marketer Hire - To hire world class marketers to work with you. InShot & Capcut - I create Instagram Reels and TikTok’s and life without these tools isn’t possible. Nira - It’s a great tool to Manage your workspace and this tool has launched many marketing templates in-built helpful for marketers and also entrepreneurs. X - The tool you love that wasn’t mentioned here is valuable and I honour that tool and share that if you would like to! I mean thanks for reading what I have curated all over my life as a marketer. I share 5 Marketing Tools, 5 Marketing Resources and 1 Free Resourceevery week in my newsletter, you can subscribe here to receive that for free. Also, You can read an expanded list of email marketing tools in this Reddit post!

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.

I spent 18 hours every week tracking marketing trends and latest news. Here are my predictions for 2024

1/ Securing Digital Footprint becomes #1 Priority For Chronically Online Users, Protecting their digital footprint will become one of the main things. We saw influencers getting cancelled over Old Content and Brands used Old Travis Kelce Tweets, we saw what could happen without digital footprint protection. Online Engagement Precautions will be taken again with Twitter & IG showing your usernames above ‘Algorithm Suggested Content’. What you like is more visible to other people in UI Design of these apps, another reason behind why Digital Footprint preservation will matter a lot in 2024. This will impact likes to viewership ratio on your organic and paid content. &#x200B; 2/  TikTok wants Long Videos with Storytelling As I was writing this report, TikTok also released their What’s Next 2024 Report. It focuses heavily on how the audiences on the app demand better storytelling and from the examples in the report, you can judge what TikTok wants. They also rolled out a 30-minute video upload limit. Engaging Content over 1-Minute Mark to keep the audiences longer on the app. I highlighted in the first trend, every social media platform wants the same thing, more time spent. 3/ Use of Shop the Look While Streaming Netflix or Amazon Prime. This year’s one of the most successful TV series, The Bear caused Men to go mad for the T-Shirt worn by Jeremy Allen White in the show. Showing us how TV Shows influence or encourage us to dress in a particular way. It’s nothing new, TV Shows like Friends & Gossip Girl influenced all demographics when they came out. But now, Streamings Services such as Roku & Amazon enable consumers to shop the look while watching the TV Shows. Many Brands will jump on these opportunities in upcoming months. 4/ Brands in Comments & Memes are the new norm By Summer 2024, Most Online Users & Creators will no longer feel too excited or answered when they see your brand in the comments. Why? It’s becoming too common for Brands to show in comments under viral content about them. Or Brands being funny with Internet Culture Trends is known to most users. The Saturation of Every Brand being funny and being present leads to increased competition of levitating the content quality. &#x200B; 5/ Marketers decrease their focus on Traffic & Views With AI recommendations taking over, The Structure of content distributing on social media is changing, the same goes for SEO. Conversational AIs are changing how web traffic is distributed to publishers. An Increased focus on managing the conversion rate and landing page relevancy will be the main focus. 6/ OOH is kind of making a comeback. First, US OOH Ads Industry grew 1.1% in Q3 2023. Second, Outfront Media reported slight revenue increase in Q3 as Billboard Ad Revenue grew in Q3. Many Brands in UK are also aligning more toward traditional media Channels. With Burger King in UK focusing on only OOH for Christmas this year and Fashion Brands like SSENSE launching Billboards as Branding Play. 7/ Rise of Curation Continues This Year, we witnessed success of Pinterest Shuffles App, Gen-Z loved it. Similar Success with formats like IG photo dump & TikTok ‘My Fav Finds’ Carousels being the center of Gen-Z Content. Just look at this recent trend and tell me Curation isn’t personal to Online Teens. Spotify won with their idea of curating Songs with Astrology-type signs. The Fashion Products with Curated Emojis and Stickers on them, that scrappy curated approach is predicted to grow in 2024, data from Pinterest. 8/ Use of AI to Trace Consumers in the wild This year we saw a huge trend of people using Image/ face recognition tools to find or dig dirt about famous people. The biggest example was Dillion Dannis exposing Multiple images of Logan Paul’s girlfriend using AI tools. (Which was Obviously bad) But next year, I believe with better rules, big brands like Adidas or Nike will be able to find worldwide micro-influencers & Online Consumers seen wearing adidas. And partnering with them on a large scale through automated outreach. 9/ More Cartoons than Influencer-Brand Products. All the Cartoon shows are seeing huge rise on IG and TikTok, Shaun the sheep is viral, Snoopy was big this year, Sesame Street’s TikTok is working. Aussie Show Bluey is making a huge spark in the US. More Brand collaborations are on the road. Why? Cartoons have built a very consistent identity and they have social channels. I know many see Cartoons as Kids Content but on social, looking at TikTok Account of Sesame Street & Snoopy. Last month, Powerpuff Girls launched a collaboration with Nike. &#x200B; 10/ The Best Trend to get people off social media &#x200B; Try to get people off the social media apps, build your own loops. You can’t rely on social and you clearly shouldn’t burn out trying to win on social and streaming with Paid Ads or without them. This matters a lot because data shares most of your customers buy from you once or twice a year. And then they interact with your content, how bad will you feel if the only thing they remember as your content is being on TikTok. Nothing about your brand. 11/ The Internet Aesthetic will Die for Cafes & Restaurants When I wrote my post about Instagram Marketing, I mentioned this issue of Every Account looking the same. In reality, It isn’t limited to IG Feeds, This Creator points out the same Problem, mentioning the aesthetic Standards from Internet are changing how new businesses approach their whole business. More Content from Cafes & Restaurants need to be around their people and neighbourhood. 12/ Echo Chambers & Sonic Influence All Podcasts are Echo Chambers because if people wanted a new perspective in form of value. We would have chosen debates, but we chose Podcasts to find new value while being in comfort. People are now looking for more value in comfort than ever, Podcasts will continue to rise. 13/ Clever AI Integration to Better Customer Journeys in B2B & B2C Marketing Agencies can provide clever solutions to B2B Companies, and help them overcome the tag of Boring Ads only. How? Ogilvy India created an AI Ad Campaign for Cadbury, allowing SMBs to have the Bollywood Actor endorse them. They used the AI voice generation allowing businesses to alter the voice and have Shah Rukh Khan endorse their shop. A similar approach was taken by IPG India, An AI Ad with Shah Rukh Khan allowing everyone to add their face in the Branded Content. &#x200B; If I sounded like an Old head in this report or I missed on some elements like Programmatic Advertising and PPC. I will try to include better analysis and new content about future trends. You can find the post shared with examples & research, linked here.

boring passive site... now 42k monthly visitors and $2540 MRR

people underestimate SEO... It is evergreen... passive... digital real estate. it can do magic... if you are consistent. Especially now with AI you can 2X your traffic growth and automate 85% of the work. For the past 6 months... we've been building an online directory. we just reached $2540 MRR... with SEO only... from a complete zero. I did share this on other subreddits. Maybe this gives ideas to someone. \+ This can be easily replicated if you have a website lol Current metrics: $2540 MRR - businesses pay us to list on the directory + display ads + pay to be featured. 43k monthly visitors - in the past couple of weeks our SEO growth is a hockey stick. DR (Domain Rating) 35 - it took us 2.5 months to get to that. 51 okay-ish quality referring domains (90% of them are do-follow) and 1.6k backlinks. There are probably 3 main pillars I try to focus on: keywords --> which then is the basis for ALL the content pieces we do blogs, landing pages, about us pages, competitor comparisons etc --> we use a DIY excel file to automate content production at scale. backlinks --> boost DR --> one of the main things to boost ranking on google. website health --> this is technical stuff like internal and external linking, schemas, canonical tags, alt texts, load speeds, compressed images, meta descriptions, titles etc --> do this once... and do it GOOD. $0.07 per SEO optimised blog at scale with AI Yep... we've literally built our own SEO blog tool... and it is a Spreadsheet with bunch of app scripts :D NOTE that we add a little bit of human touch to those blogs that are picked up by Google rank top in 25 How it works... is that we paste in bunch of links (other websites, blogs, news articles) and with a click of a button we can get up to 2000 SEO optimised content pieces... from an Excel file... $0.07 per blog. The spreadsheet is integrated with Chat gpt (obviously). We use GPT-4 for meta descriptions, titles, transforming the content from text to html code since it is more powerful, and GPT-4o for content itself because it is cheaper and faster for "general text". The spreadsheet repurposes content. The spreadsheet generates: Meta descriptions and titles FAQs sections - DON'T skip FAQ sections! They are a must for SEO. On Ahrefs... there is a section of questions people are searching about your keyword... that's your FAQs It can find contextual youtube videos (links to those videos) - to show google that our content is not "just text" thus higher quality. Screenshots and images of the original source (the website link we inputed) I then download a csv version of the excel and import it into our Webflow. The csv file column names match our webflow CMS field names. tbh... we didn't even know that it can be done with a spreadsheet. We "tried" building it because every other tool we were using is (1) expensive from $0.59 per SEO content piece (2) they didn't provide the scale we wanted (3) we wanted more control over the output. Focus on DR 35+ backlinks... easier We bought backlinks only once... rest of the backlinks was a manual work from us. Bunch of free listing databases (about 65% of our backlinks) You can comment on open forums with your link to get a backlink (be careful tho) Post a blog on Medium com --> DR 94 backlink (takes time to Index) If you pay for Notion you can get a DR 94 backlink from Notion If you use Beehiiv you can get a DR 86 backlink from Beehiiv Google product stacking (Google sites, Google notes etc) --> backlink from almighty Google itself A lot of work goes into backlinks because they are THAT important. I have tried bunch of "black hat" strategies as well... but note that all of these strategies won't work if you don't index the primary source from where your backlink is coming from. BIG search volume and low KD Key things I'm looking for in keywords: I use Ahrefs Keyword research tool... it is literally free BIG search volume - 2k+ is oaky-ish for a single keyword EASY to rank - KD (keyword difficulty) below 15 Look for long tail keywords (these are golden nuggets since they have a VERY clear search intent) - "how to edit..." "how to change..." "how to delete..." "how to paint..." I hope you got the idea. on Ahrefs you can use "\" to get BIG volume long tail keywords... like this "my keyword\". Ahrefs then populates the "\" with the tail. Check SERP (Search Engine Result Page) for your keywords - it shows current top 10 pages for those KWs. Check their content. Can you improve it? Have they missed anything? Keyword gap from your competitors - shows EASY keywords that your competitors have missed and also shows what keywords overlap with you. Also one cool thing... if you don't type any keywords on Ahrefs and press "Enter"... you can browse all the keywords out there... it is magical. Once we have the keywords, we run our spreadsheet. And that's pretty much it. I hope that you can get some ideas from this little silly project. Also... if you have any questions about this... I might share the SEO blog automation excel file/help if people are interested...

boring passive site... now 42k monthly visitors and $2540 MRR

people underestimate SEO... It is evergreen... passive... digital real estate. it can do magic... if you are consistent. Especially now with AI you can 2X your traffic growth and automate 85% of the work. For the past 6 months... we've been building an online directory. we just reached $2540 MRR... with SEO only... from a complete zero. I did share this on other subreddits. Maybe this gives ideas to someone. \+ This can be easily replicated if you have a website lol Current metrics: $2540 MRR - businesses pay us to list on the directory + display ads + pay to be featured. 43k monthly visitors - in the past couple of weeks our SEO growth is a hockey stick. DR (Domain Rating) 35 - it took us 2.5 months to get to that. 51 okay-ish quality referring domains (90% of them are do-follow) and 1.6k backlinks. There are probably 3 main pillars I try to focus on: keywords --> which then is the basis for ALL the content pieces we do blogs, landing pages, about us pages, competitor comparisons etc --> we use a DIY excel file to automate content production at scale. backlinks --> boost DR --> one of the main things to boost ranking on google. website health --> this is technical stuff like internal and external linking, schemas, canonical tags, alt texts, load speeds, compressed images, meta descriptions, titles etc --> do this once... and do it GOOD. $0.07 per SEO optimised blog at scale with AI Yep... we've literally built our own SEO blog tool... and it is a Spreadsheet with bunch of app scripts :D NOTE that we add a little bit of human touch to those blogs that are picked up by Google rank top in 25 How it works... is that we paste in bunch of links (other websites, blogs, news articles) and with a click of a button we can get up to 2000 SEO optimised content pieces... from an Excel file... $0.07 per blog. The spreadsheet is integrated with Chat gpt (obviously). We use GPT-4 for meta descriptions, titles, transforming the content from text to html code since it is more powerful, and GPT-4o for content itself because it is cheaper and faster for "general text". The spreadsheet repurposes content. The spreadsheet generates: Meta descriptions and titles FAQs sections - DON'T skip FAQ sections! They are a must for SEO. On Ahrefs... there is a section of questions people are searching about your keyword... that's your FAQs It can find contextual youtube videos (links to those videos) - to show google that our content is not "just text" thus higher quality. Screenshots and images of the original source (the website link we inputed) I then download a csv version of the excel and import it into our Webflow. The csv file column names match our webflow CMS field names. tbh... we didn't even know that it can be done with a spreadsheet. We "tried" building it because every other tool we were using is (1) expensive from $0.59 per SEO content piece (2) they didn't provide the scale we wanted (3) we wanted more control over the output. Focus on DR 35+ backlinks... easier We bought backlinks only once... rest of the backlinks was a manual work from us. Bunch of free listing databases (about 65% of our backlinks) You can comment on open forums with your link to get a backlink (be careful tho) Post a blog on Medium com --> DR 94 backlink (takes time to Index) If you pay for Notion you can get a DR 94 backlink from Notion If you use Beehiiv you can get a DR 86 backlink from Beehiiv Google product stacking (Google sites, Google notes etc) --> backlink from almighty Google itself A lot of work goes into backlinks because they are THAT important. I have tried bunch of "black hat" strategies as well... but note that all of these strategies won't work if you don't index the primary source from where your backlink is coming from. BIG search volume and low KD Key things I'm looking for in keywords: I use Ahrefs Keyword research tool... it is literally free BIG search volume - 2k+ is oaky-ish for a single keyword EASY to rank - KD (keyword difficulty) below 15 Look for long tail keywords (these are golden nuggets since they have a VERY clear search intent) - "how to edit..." "how to change..." "how to delete..." "how to paint..." I hope you got the idea. on Ahrefs you can use "\" to get BIG volume long tail keywords... like this "my keyword\". Ahrefs then populates the "\" with the tail. Check SERP (Search Engine Result Page) for your keywords - it shows current top 10 pages for those KWs. Check their content. Can you improve it? Have they missed anything? Keyword gap from your competitors - shows EASY keywords that your competitors have missed and also shows what keywords overlap with you. Also one cool thing... if you don't type any keywords on Ahrefs and press "Enter"... you can browse all the keywords out there... it is magical. Once we have the keywords, we run our spreadsheet. And that's pretty much it. I hope that you can get some ideas from this little silly project. Also... if you have any questions about this... I might share the SEO blog automation excel file/help if people are interested...

Looking for Social Media Marketing Partner(s) for High-Potential AI App Business

Hello everyone! I am Mak, and I'm a software engineer and AI developer with a few years of experience. I'm pretty young like the most of you and have an amazing idea. I'm sure that some of you have heard of Rizz, Plug, Wigman and similar apps. Those are simple AI apps that generate pickup lines for people, and I worked as an AI developer for one of the above. I got this business idea after analyzing more about this industry and realizing that these apps make TONS of money—like the one I worked for, which is making about $50k per WEEK using my AI solutions. That's crazy. The point is that I took a pause from working as a software engineer for clients and researched how to do the same thing. It took me a few months to actually understand everything about this business model, and Rizz apps are just one example of this type of business. There is one 17 yo guy I found who made "Cal AI" I guess, basically a simple AI app that analyzes your meal and provides info like calories, etc. I also created AI solutions for a guy who made an AI app that analyzes your face, provides Sigma analytics, and suggests how to improve your face, etc. So the point is that there are tons of AI app ideas that you can create for this industry. And the important fact is that the AI market is growing. Some important AI analytics say that in 2024, there were 1.5B AI app downloads, and mobile AI app consumer spending was $1.8B. That's huge. So, what am I looking for? I need someone, hopefully from the US, or someone who knows how to post social media content for US users, to help me out with my business idea. I'm self-funded and have already spent a lot on important requirements and equipment, which is why I need someone interested in revenue sharing. We can come up with a deal such as capped/tiered revenue share, profit share, deferred model, etc. We could discuss this privately since everyone has different experience levels and thoughts about this. Also, since I'm talking about experience, you don't need huge experience at all. You can be 16-25 years old just like me and only have marketing skills. However, to make it easier for those who don't have marketing skills, I am planning to create code that will automatically generate content for you, and all you need to do is post the content. But this is only for posting content without creating it and is for interested people from the US since I need US customers. However, if you have marketing skills and an idea for getting organic US views, please let's talk. Short info about my app: It is an AI app like the previous examples, which doesn’t yet exist. There is pretty big potential for app growth (60% of Americans could use this app), and it should be pretty easy to market. Good niche, good idea and overall solid market for this app idea. TL;DR I need someone interested in marketing my AI app in exchange for revenue share. No huge experience is needed. I would prefer someone from the US. If you are interested, feel free to contact me here on Reddit via private messages or below. We can talk here, on Discord, LinkedIn, or anywhere you prefer. Thanks once again!

How I went from $27 to $3K as a solopreneur still in a 9-5

My journey started back in November 2023. I was scrolling through Twitter and YouTube and saw a word that I had never come across before. Solopreneur. The word caught my eye. Mainly because I was pretty sure I knew what it meant even though it's not a word you'll find in the dictionary. I liked what it was describing. A solo entrepreneur. A one man business. It completely resonated with me. As a software engineer by trade I'm used to working alone, especially since the pandemic hit and we were forced to work remotely. See, I always wanted to ditch the 9-5 thing but thought that was too big and too scary for a single person to do. Surely you would need a lot of money to get started, right? Surely you would need investors? The whole concept seemed impossible to me. That was until I found all the success stories. I became obsessed with the concept of solopreneurship. As I went further down the rabbit hole I found people like Justin Welsh, Kieran Drew and Marc Louvion to name a few. All of whom have one person businesses making huge money every year. So I thought, if they can do it, why can't I? People like this have cleared the pathway for those looking to escape the 9-5 grind. I decided 2024 would be the year I try this out. My main goal for the year? Build a one man business, earn my first $ online and learn a sh\*t ton along the way. My main goal in general? Build my business to $100K per year, quit my 9-5 and live with freedom. From December 2023 to February 2024 I began brainstorming ideas. I was like a lost puppy looking for his ball. How on earth did people find good ideas? I began writing everything and anything that came to mind down in my notes app on my phone. By February I would have approximately 70 ideas. Each as weird and whacky as the other. I was skeptical though. If I went through all the trouble of building a product for one of these ideas how would I know if anyone would even be interested in using it? I got scared and took a break for a week. All these ideas seemed too big and the chance that they would take off into the atmosphere was slim (in my mind anyways). I was learning more and more about solopreneurship as the weeks went on so I decided to build a product centered around everything I was learning about. The idea was simple. Enter a business idea and use AI to give the user details about how to market it, who their target customers were, what to write on their landing page, etc. All for a measly $27 per use. I quickly built it and launched on March 3rd 2024. I posted about it on Indie Hackers, Reddit and Hacker News. I was so excited about the prospect of earning my first internet $! Surely everyone wanted to use my product! Nope...all I got was crickets. I was quickly brought back down to earth. That was until 5 days later. I looked at my phone and had a new Stripe notification! Cha-ching! My first internet $. What a feeling! That was goal number 1 complete. It would be another 6 days before I would get my second sale...and then another 15 days to get my third. It was an emotional rollercoaster. I went from feeling like quitting the 9-5 was actually possible to thinking that maybe the ups and downs aren't worth it. On one hand I had made my first internet dollar so I should my ecstatic, and don't get me wrong, I was but I wanted more. More validation that I could do this long term. By May I was starting to give up on the product. I had learned so much in the past few months about marketing, SEO, building an audience, etc. and I wanted to build something that I thought could have more success so I focused on one critical thing that I had learned about. What was it? Building a product that had SEO potential. A product that I knew hundreds of people were looking for. See this was my thinking - If I could find a keyword that people were searching for on Google hundreds/thousands of times every month and it was easy to rank high on search engines then I would go all in (in SEO land this equates to a Keyword that has a Keyword Difficulty of = 500). I began researching and found that the keyword "micro saas ideas" was being searched for around 600 times each month. Micro Saas was something that really interested me. It was perfect for solopreneurs. Small software products that 1 person could build. What's not to like if you're in the game of software and solopreneurship? Researching keywords like this became like a game for me. I was hooked. I was doing it every day, finding gems that were being searched for hundreds and thousands of times every month that still had potential. That's when I came up with my next product idea. I decided to create a database of Micro Saas Ideas all with this sort of SEO potential. See if you can build a product that you know people are looking for then that's all the validation you need. So I put this theory to the test. I created a database of Micro Saas Ideas with SEO Potential and launched it in June 2024. This time it was different. I made $700 in the first week of launching. A large contrast to my previous failed attempt at becoming the worlds greatest solopreneur. Since launch I have grown the product to $3K and I couldn't be happier. I know what you're saying, $3K isn't a lot. But it's validation. It's validation that I can earn $ online. Validation that I can grow a business and it gives me hope that one day I'll be able to quit that 9-5 grind. My plan is to keep growing the business. I expect there to be a few challenges up ahead but I'll tackle them as I go and learn from the failures and successes. I have a newsletter where I share Micro Saas Ideas with SEO potential every week which I'll leave below in the first comment. Feel free to come along for the ride. If not I hope this post brings you some value If you're thinking about starting as a solopreneur, stop thinking and start doing, you won't regret it.

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.

Automating dev processes with AI tools?

Hey all! Just wanted to know if any of you would recommend any set of AI tools to streamline the development process of launching apps fast. I’m 5 years into web development and am now a project manager, but we mostly do complex software for big clients (those that you work on for about 6 months to a year with a small team) and feel kind of left-out on not using ai tools (we only use cursor). I often have ideas for smaller apps and want to make the whole process more agile and quick for deployment for myself. Interested in building some microsaas. I read a guy that did replit for mvp and exported the code when he had a couple users into his cursor ide locally. I have tested bolt.new and i know how to make openai/chatgpt agents and such, but was wondering how any of you, if any, are doing it? V0 or lovable for UI? Exporting the code? Using supabase or a local db? Do you recycle a next.js boilerplate? What other Saas do you use for streamlining the process? Thanks in advance for any advice guys. I just want to launch a couple of ideas I have quickly.

Cold Emailers: Would You Use a Tool That Automates *Smart* Follow-Ups? (Brutally Honest Feedback Needed)

Hey everyone, I’m a founder building a tool to fix something I hate about cold emailing: generic, spammy follow-ups that waste time and kill reply rates. Here’s the idea: You set a goal (e.g., “book a meeting,” “close a sale”). The tool automatically adjusts follow-up timing/messaging based on that goal. Example: If a lead opens your email but doesn’t reply, it sends a follow-up addressing common objections. I need your BRUTAL honesty: Is this a problem you’d pay to solve? Why/why not? What’s the #1 thing that makes you ignore cold emails? Would you try a free beta? (I’ll manually run campaigns for 5 people to prove the concept.) Why I’m asking: I don’t want to waste 6 months building something nobody wants. If this resonates, I’ll keep you updated. If it’s dumb, tell me to shut it down. PS: I personally find it sending follow up sequences and having a tool that does it for me would be a no brainer. I know there are other tools out there that do this but they are quite expensive and difficult to navigate through so that’s why I’m building this tool. So I need your help to help validate this idea

Hear me out, you are annoying

I am a full stack web developer capable of realizing most of the people’s ideas here. Few things to mention out: Developers are not Google itself. You can’t randomly tell them to implement AI, blockchain, NFT, stocks etc. cus developers are not wizards. Stuff like that requires knowledge, quite a lot of it, and if you want someone to spend shit ton of time implementing smtn, you better prepare to pay for it, cus that knowledge is valuable. Most of the time it requires whole teams to do the work you imagined. If someone came to me and told me yeah, I want a copy of upwork. Sure bud, and where are the other 50 developers? (there are exceptions here but still, people are talking whole platforms while I am the only dev there, mate imma need a whole year for this one) be ready to pay. Sure, your idea is cool, but I can’t wait another 2 years untill it starts making money, plus if it’s fully online business, why would i want to share 50/50 with you? No one is dumb enough to do 3 months od work for free just to share 50/50 in best case, with someone who “had an idea”, I could delete the files any second I want to it’s my code! No one is doing big projects for free, be ready to pay and know the value of other’s work. Otherwise have fun scrolling through indian freelancers! At least try to manage something! I am right now looking for projects that I could join, who needs a web dev and all of them are like okay do the work, don’t expect any money cus we aee starting with no money at all and we won’t bother any investors cus you aee the dumb enough developer do male our business for 25% share

How to increase the sales of my book

In just 3 months, it generated over $100 in revenue. I wanted to share my journey for two reasons: to potentially assist others in self-publishing their own books and to receive feedback to enhance my marketing strategy. I envision that there are others facing similar challenges. Let's dive into the financials, time spent, Key takeaways and the Challenges to address behind this product. Finances First, let's take a look at the financial overview. 💳 Expenses 🔹 E-book creation: · Book cover: $ 0. I used Adobe Express with 30 days of free trial. · ChatGPT: 20 $ a month. I leveraged AI to generate the chapters of the book, ensuring that no critical topics were overlooked during the content creation process and to refine the English, as it's not my native language. I also used to help me with copywriting of the web. If anyone is interested, I can share my Python code for outlining the chapters calling the API, but you can also directly ask chatgpt. · Kindle KDP (Kindle Direct Publishing): order author copies: 10 $. 🔹 Web creation: Domain: I got a com) / .org /.net domain for just 1 $ the first year. Carrd.co subscription: 19 $ (1 year) 🔹 Marketing: Promoted post on reddit: $30 Paid ads with google ads: $30 💰 Revenue 🔸 Sales: $102 💸 Net Profit: \~- $ 18 I initially thought the sales for this e-book would be quite modest, maybe only 3 or 4 books. However, the fact that I've sold more than that so far is a pleasant surprise. Even though the overall numbers may still be considered "peanuts" in the grand scheme of book sales, it suggests there could be more demand for content on digital asset custody than I had originally anticipated. This is a good learning experience, and I'll look to refine my marketing approach to see if I can reach a wider audience interested in this topic 🔹 Time Spent Next, let's review the time invested. 📖 Writing the e-book: 40 hours 🌍 Website + Stripe integration: 10 hours 📣 Creating promotional content: 10 hours ⏱️ Additional marketing efforts: 5 hours Total time spent: 65 hours As you can see, I dedicated more time to writing the e-book itself than to marketing and distribution. I spent relevant time to marketing because I though that a successful product launch requires a robust marketing effort. Many e-book authors overlook this crucial aspect! I utilized three sales channels: · Amazon: I found that there were no books specifically about digital asset custody, resulting in strong positioning in Amazon searches. Additionally, my book immediately secured the top position in Google searches for "digital asset custody book." However, despite achieving 50% of sales in the UK, I have not received any reviews globally. Sales distribution for this channel: 20% physical book, 80% ebook. · Twitter: Daniel\_ZZ80. With only 46 followers, the performance on this platform has not been optimal. I am beginning to write posts related to digital assets to increase visibility. · Gumroad: Lockeyyy.gumroad.com. I offered a discounted version of the ebook, but have not yet made any sales through this channel. Key takeaways: · The process of creating this e-book was extremely fulfilling, and while it has garnered overwhelmingly positive feedback from friends and colleagues (not considered as sales), it has yet to receive any Amazon reviews ☹. · Kindle KDP proved to be ideal for a rapid go-to-market strategy. · AI is an excellent tool for generating ideas and providing access to global audiences with perfect grammar. Otherwise, I would need to hire a translator, which can be very expensive. · Despite offering a full 30-day money-back guarantee, leading me to believe that the quality of the content is indeed good. · I have gained valuable insights for future technical books. · Although the current financial balance may be negative, I anticipate reaching the break-even point within one month, and this has now become a passive income stream. However, I recognize the need to regularly update the content due to the rapidly changing nature of this field. Challenges to address: · Is the timing for launching this book appropriate? In other words, is the world of digital asset custody a trendy and interesting topic for the audience? · What is causing the lack of sales through Gumroad? · Should I seek assistance as my marketing efforts have not yielded results? · Why are there no reviews on Amazon? · Why are sales primarily concentrated in the EU with only one sale in the US, which is my main target market? Feedback is appreciated. If you're interested in learning more about my approach, feel free to send me a direct message. A bit about my background: After dedicating my entire career to the banking industry, I explored various side projects. As an IT professional, I have now transitioned into the digital asset realm. After three years of intensive study, I recently published my first book on digital asset custody. I hope you found this post informative. Cheers! P.S.: I'm currently in the process of launching two more books using this system. 😊

From Setbacks to $20K Profit: My AI Influencer Earnings Breakdown (Jan 2025) 💰

(Monthly income breakdown is in the end) 📌 Introduction Hey everyone! 👋 Before I dive into this month’s breakdown, I just want to be upfront—English isn’t my first language, so I’ve used ChatGPT to refine this post for better readability. That said, everything here is 100% real—my personal experiences, struggles, and earnings as someone running a full-time AI influencer business. Since I get a lot of DMs asking about my AI models, here are their Instagram links: 📷 Emma – https://www.instagram.com/emmalauireal 📷 Jade – https://www.instagram.com/jadelaui (jadecasual is the second account) Also, if you’ve been wondering about the community I run, where I teach others how to build AI influencers from scratch, here’s the link (I got approval from mods for this link): 🔗 AI Winners Now, let’s get into what happened this month. 🚀 \------- First, a huge thank you! 🎉 Three months ago, I shared my journey of building an AI influencer business, and I was blown away by the response. That post got 263K+ views and was shared over 2.7K times—way more than I ever expected. If you’re new here or want to check out the full story of how I started, you can read it here: 🔗 Click Here (Reddit link) \------- 🔹 What I Did in January After the holiday rush in December, I knew January would be a slow month—people had already spent most of their money at the end of the year. So instead of pushing harder on monetization, I shifted my focus to tech development and optimization. Flux Character Loras: I spent a lot of time refining and testing different Flux-based character Loras for my models. This is still a work in progress, but the goal is to improve long-term consistency and make my workflow even more efficient. NSFW Content Expansion: On Emma’s side, I expanded her content library using a real model body double, making her content look more organic and natural. Jade, however, remains 100% AI-generated, keeping her workflow entirely digital. Social Media Wipeout (Thanks, VA 🙃): I had handed off both Twitter accounts to a virtual assistant to help with engagement and DMs. Big mistake. He ended up spamming DMs, which got both accounts banned—Emma (80K followers) and Jade (20K followers). 🤦‍♂️ Right now, I’m rebuilding Emma’s account from scratch and taking a much more cautious approach. Jade’s account is still offline for now. New Platform: Threads – I hadn’t touched Threads before, but since engagement on Instagram can be unpredictable, I decided to start accounts for both models. So far, they’re performing well, and I’ll continue experimenting. Launched AI Winners Community: After getting flooded with DMs (both here and on Instagram), I realized there was a massive demand for structured learning around AI influencers. So, I launched AI Winners, a paid community where I break down everything I’ve learned. It’s still early, but I see it turning into a solid, long-term community. Investment & Acquisition Talks: I’m still evaluating potential investors and acquisition offers for my AI models. There’s growing interest in buying or investing in Emma & Jade, so I’ve been having conversations to explore different options. Overall, January was about tech, rebuilding, and long-term planning—not immediate revenue. But that’s what keeps this business sustainable. 🚀 \------- ⚠️ Biggest Challenges This Month Lost Both Twitter Accounts (Massive Traffic Hit) 🚨 The biggest blow this month was losing my models’ Twitter accounts. Twitter was responsible for about 40% of my total traffic, meaning both free and paid subs took a direct hit. While Emma’s revenue took a slight dip, Jade’s income dropped significantly—partly due to the account loss and partly because January is naturally slow. (Full revenue breakdown at the end of the post.) Jade’s Instagram Tanked (Possible Shadow Ban?) 🤔 Jade’s Instagram completely lost momentum in early January. Engagement and reach dropped by over 80%, and I still haven’t figured out why. It feels like a shadow ban, but I have no clear confirmation. To counter this, I launched a second backup account, and things are starting to recover. \------- 🚀 Potential Improvements & What’s Next Locking in a Stable Workflow 🔄 Right now, Emma & Jade’s workflow is still evolving, but I’m aiming to fully stabilize it. As I’m writing this, content is generating on my second monitor—a sign that I’m close to achieving full automation without compromising quality. Boosting Jade’s Fanvue Revenue 💰 Jade’s income took a hit this month, and it’s 100% a traffic issue. The solution? More content, more reach. I’ll be increasing social media output to drive consistent traffic back to Fanvue and restore her earnings. Patreon is Done. All Focus on Fanvue 🚫 I shut down both Emma & Jade’s Patreon accounts. The goal is not to split revenue—I want everything funneled into Fanvue for higher engagement and bigger paydays. \------- 💰 January 2025 Earnings Breakdown Despite January being one of the slowest months for online creators, Emma and Jade still brought in over $29K in revenue, with a net profit exceeding $20K after all expenses. Emma Laui generated $20,206.77, with around $6,000 in expenses (chatter payments, NSFW designer fees, and other operational costs). Jade Laui earned $8,939.05, with $2,000 in expenses. Considering Twitter account losses, Instagram setbacks, and the usual January spending slump, this is still a solid outcome. The focus now is on scaling traffic and maximizing Fanvue revenue heading into February. 🚀🔥 That’s the full breakdown for January! If you have questions, feel free to drop a comment, and I’ll answer when I can. Happy to help, just like others helped me when I was starting out! 🚀🔥

How to increase the sales of my book

In just 3 months, it generated over $100 in revenue. I wanted to share my journey for two reasons: to potentially assist others in self-publishing their own books and to receive feedback to enhance my marketing strategy. I envision that there are others facing similar challenges. Let's dive into the financials, time spent, Key takeaways and the Challenges to address behind this product. Finances First, let's take a look at the financial overview. 💳 Expenses 🔹 E-book creation: · Book cover: $ 0. I used Adobe Express with 30 days of free trial. · ChatGPT: 20 $ a month. I leveraged AI to generate the chapters of the book, ensuring that no critical topics were overlooked during the content creation process and to refine the English, as it's not my native language. I also used to help me with copywriting of the web. If anyone is interested, I can share my Python code for outlining the chapters calling the API, but you can also directly ask chatgpt. · Kindle KDP (Kindle Direct Publishing): order author copies: 10 $. 🔹 Web creation: Domain: I got a com) / .org /.net domain for just 1 $ the first year. Carrd.co subscription: 19 $ (1 year) 🔹 Marketing: Promoted post on reddit: $30 Paid ads with google ads: $30 💰 Revenue 🔸 Sales: $102 💸 Net Profit: \~- $ 18 I initially thought the sales for this e-book would be quite modest, maybe only 3 or 4 books. However, the fact that I've sold more than that so far is a pleasant surprise. Even though the overall numbers may still be considered "peanuts" in the grand scheme of book sales, it suggests there could be more demand for content on digital asset custody than I had originally anticipated. This is a good learning experience, and I'll look to refine my marketing approach to see if I can reach a wider audience interested in this topic 🔹 Time Spent Next, let's review the time invested. 📖 Writing the e-book: 40 hours 🌍 Website + Stripe integration: 10 hours 📣 Creating promotional content: 10 hours ⏱️ Additional marketing efforts: 5 hours Total time spent: 65 hours As you can see, I dedicated more time to writing the e-book itself than to marketing and distribution. I spent relevant time to marketing because I though that a successful product launch requires a robust marketing effort. Many e-book authors overlook this crucial aspect! I utilized three sales channels: · Amazon: I found that there were no books specifically about digital asset custody, resulting in strong positioning in Amazon searches. Additionally, my book immediately secured the top position in Google searches for "digital asset custody book." However, despite achieving 50% of sales in the UK, I have not received any reviews globally. Sales distribution for this channel: 20% physical book, 80% ebook. · Twitter: Daniel\_ZZ80. With only 46 followers, the performance on this platform has not been optimal. I am beginning to write posts related to digital assets to increase visibility. · Gumroad: Lockeyyy.gumroad.com. I offered a discounted version of the ebook, but have not yet made any sales through this channel. Key takeaways: · The process of creating this e-book was extremely fulfilling, and while it has garnered overwhelmingly positive feedback from friends and colleagues (not considered as sales), it has yet to receive any Amazon reviews ☹. · Kindle KDP proved to be ideal for a rapid go-to-market strategy. · AI is an excellent tool for generating ideas and providing access to global audiences with perfect grammar. Otherwise, I would need to hire a translator, which can be very expensive. · Despite offering a full 30-day money-back guarantee, leading me to believe that the quality of the content is indeed good. · I have gained valuable insights for future technical books. · Although the current financial balance may be negative, I anticipate reaching the break-even point within one month, and this has now become a passive income stream. However, I recognize the need to regularly update the content due to the rapidly changing nature of this field. Challenges to address: · Is the timing for launching this book appropriate? In other words, is the world of digital asset custody a trendy and interesting topic for the audience? · What is causing the lack of sales through Gumroad? · Should I seek assistance as my marketing efforts have not yielded results? · Why are there no reviews on Amazon? · Why are sales primarily concentrated in the EU with only one sale in the US, which is my main target market? Feedback is appreciated. If you're interested in learning more about my approach, feel free to send me a direct message. A bit about my background: After dedicating my entire career to the banking industry, I explored various side projects. As an IT professional, I have now transitioned into the digital asset realm. After three years of intensive study, I recently published my first book on digital asset custody. I hope you found this post informative. Cheers! P.S.: I'm currently in the process of launching two more books using this system. 😊

Using AI to Streamline JTBD Interviews and Analysis

Hello everyone! 👋 I wanted to share a personal project I have worked on in the last months that uses LLMs together with Jobs-to-be-Done to make product development easier and more efficient. The idea is to automate identifying key jobs, figuring out who performs them, creating synthetic users, and conducting interviews. By doing this, we cut down on the time and resources usually spent on manual user research, making it quicker and simpler to gather the insights needed for your product roadmap. Here’s how it works: Discovering Main Jobs and Job Performers: Starting with a rough vision, the code helps you identify and suggest potential main jobs and the people who typically perform them, based on your vision and skillset. Creating Synthetic Users: I use LLMs to build user archetypes that reflect real needs, goals, and pain points. Automated Interviews: Using GPT’s language capabilities, I’ve set up a system that runs interviews with these synthetic personas, pulling out key insights on customer motivations and needs. Analyzing Interviews and Extract Needs: Finally, we break down all the information from these interviews into actionable insights—covering everything from job steps to emotional and social jobs. This project lays the groundwork for a user-centered product design strategy, helping me make smarter decisions on what features to prioritize, how to improve user experience, and how to drive overall product development. Would love to hear your thoughts! 💬

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

How I Made $250.000+ in a Year: A Case Study of My AI Influencer Journey

Update on February 22th: I changed my AI influencer's names because it caused some problems on my business. One year, two AI-powered influencers, and $250K in revenue. Sounds unreal? It’s not. Today, I’m pulling back the curtain on the strategies, tools, and hard-won lessons that took me from concept to a six-figure success story in the AI influencer space. Hey, I'm Ben—a 32-year-old designer who spent the past year navigating the world of AI influencers. Let me clear up any confusion right from the start: I’m not here to sell you anything. This is purely a case study to share what worked, what didn’t, and what I’ve learned along the way. I’ll also make sure to answer all your questions in the comments for free whenever I can, so don’t hesitate to ask. Links to Past Topics: If you're curious about some of the groundwork I covered, check out a few of my earlier posts here: How I Make $10,000 Monthly | AI Influencer Management How I Earned $7000+ in 15 Days | AI Influencer Business Update These earlier posts cover a lot of the backstory, so feel free to explore them before diving into this one. So if you're ready, here is the full story: \---- The idea of creating an AI influencer was one of those “what if” moments that wouldn’t leave my mind. At first, it sounded futuristic—even a bit too ambitious. It all started when I stumbled upon an AI influencer on Instagram with the handle AnnaMaes2000. Her content blew me away—the quality, the detail, and just how real everything looked. I was instantly hooked and ended up going through every post, just trying to figure out how she was pulling this off. That’s when I knew I had to learn how this was done. The next step? YouTube. I dived into videos on Stable Diffusion, soaking up everything I could about creating AI-generated images. Those tutorials taught me the basics and got me up to speed. Then, I created my first AI influencer, let's call her Mel for now. Right after that, to complete the storyline and boost engagement, I introduced Mel's “mother,” Jess. Adding Jess gave the whole project depth and a narrative that drew people in, creating a unique family dynamic that instantly elevated traffic and interest. After thousands of bad photos, hundreds of deleted posts, and months of trial and error, you can now see the quality that defines my current accounts. Here’s a rundown of the tools and checkpoints I’ve used from day one, in order: Fooocus on RunDiffusion — Juggernaut V8 Fooocus on RunDiffusion — Juggernaut V9 Fooocus on PC (locally) — Juggernaut V9 Fooocus on PC (locally) —Lyuyang Mix + Juggernaut V9 Flux on PC (couple of photos only since it's so slow even on RTX 4090) Flux on Fal.ai. \---- There’s no magic Instagram hack that guarantees success, despite what everyone thinks and keeps asking me. Quality content, consistent uploads, and solid craftsmanship are what actually help your photos hit trends and show up on the Explore page. Unlike 95% of low-quality AI accounts out there, I don’t rely on faceswap videos, spam Reels, or go around liking comments on other accounts. My approach is fully organic, focused solely on creating my own unique content. By following Instagram's guidelines to the letter, I've managed to direct some of Mel and Jess' fans over to Patreon and Fanvue. There, for a small subscription fee, fans can access exclusive lingerie content. For those looking for more, higher-tier subscriptions give access to even more premium content. Some possible questions and their answers: No, you can't share hardcore NSFW content on Patreon. You can do that on Fanvue. Yes, you can create AI creators on Fanvue — OnlyFans doesn't allow it. Yes, you can use your own ID to get KYC. Yes, we're telling both Mel and Jess is (or use) AI to generate content. And yes, some people leave and some people still have fun with chatting, having a good time and get perfect content for their needs. And yes, we have a chatter team to work on these accounts. \---- This journey wasn’t all smooth sailing. I faced unexpected roadblocks, like platform restrictions that limited certain types of content, and managing fan expectations was more challenging than anticipated. Staying within guidelines while keeping fans engaged required constant adaptation. These hurdles forced me to get creative, adjust my approach, and learn fast. Once I saw Mel and Jess gaining traction, I knew it was time to scale up. Expanding meant finding new ways to keep content fresh, creating deeper narratives, and considering how to bring even more followers into the fold. My focus turned to building a sustainable model that could grow without sacrificing quality or authenticity. If you’re thinking about diving into AI content creation, here’s my advice: patience, consistency, and a focus on quality are key. Don’t cut corners or rely on quick-fix hacks. Invest time in learning the right tools, creating engaging stories, and building an audience that values what you bring to the table. This approach took me from zero to six figures, and it’s what makes the journey worth it. \---- And finally, here’s the income breakdown that everyone’s curious about: Mel on Fanvue: $82,331.58 (Gross earnings because we have chatter cuts like 15%) Mel on Patreon: $50,865.98 (Net earnings) Jess on Fanvue: $89,068.26 (Gross earnings because we have chatter cuts like 15%) Jess on Patreon: $39,040.70 And thanks to Reddit and my old posts, I got a perfect investor like after 5 months, so this is a "payback" for that. Like I said, I'll answer every question in the comments — take care and let me know.

Steep Learning : How I Mapped approximately 10K AI tools to 15K Replaceable Tasks across 4K professions

Hello Everyone , I would like to share some knowledge today which I went towards countless hours to do . I founded a portal called Seekme.ai, a comprehensive platform that houses over 10,000 AI tools and resources. Today, I'm excited to share with you an insightful and enlightening journey of how I mapped these tools to 15,000 tasks across 4,000 professions. This process, which I've named "Learn by Doing," got me the power of determination, collaboration, and adaptability. The Idea: It all started when I recognized the need for a more efficient and accessible way for professionals to understand which AI tools could help them automate their tasks. The traditional approach of manually researching and testing each AI tool for every profession was time-consuming and inefficient. I envisioned a solution that could streamline this process, making AI adoption easier and more accessible for a broader audience. The Planning: To begin, we needed a clear understanding of the task landscape across various professions. With the help of some Reddit communities , we embarked on an extensive study of common tasks in various industries. We utilized various sources, including government reports, industry surveys, and academic research, to create a comprehensive list of tasks. The result was an impressive list of 15,000 tasks. The Mapping: With the list of tasks in hand, the next step was to identify which AI tools could perform these tasks. I meticulously researched and analyzed each AI tool's capabilities and features. We cross-referenced this information with the tasks I had identified and created a mapping between the two. The process involved a significant amount of collaboration and refinement, as we continually updated and expanded our database of AI tools and tasks. The Challenges: The mapping process was not without its challenges. One of the primary obstacles was ensuring the accuracy and completeness of our data. To address this issue, I implemented a rigorous quality control process that included multiple rounds of checks and validations.I also established partnerships with industry experts and AI vendors to ensure our data was up-to-date and accurate. There is also a challenge that I faced was what is the quality of the tools which is the problem and how do I rank multiple tools if they do the same tasks without user feedback The Results: After months of hard work and dedication, I successfully mapped 10,000 AI tools to 15,000 tasks across 4,000 professions. Our new feature, AI by Profession, was born. This innovative will allow users to quickly and easily identify the AI tools that can automate tasks in their profession, making AI adoption more accessible and efficient than ever before. The Impact: The impact of this project has been significant. By making it easier for professionals to identify AI tools that can automate tasks in their industry, we're helping to drive productivity, efficiency, and innovation. Our users are saving time and resources by not having to manually research and test AI tools. Furthermore, we're contributing to the broader goal of democratizing AI and making it accessible to a broader audience. But there is a still an issue we face of ranking tools who does the similar job. For instance for content creation there 10 tools that can do same video editing so how do we rank it . We are planning to add categories to this to make it more exhaustive Conclusion: The journey to mapping 10,000 AI tools for 15,000 tasks across 4,000 professions was a challenging and rewarding experience. It required a significant amount of planning, determination, and collaboration, but the end result was a powerful tool that's making a difference in the lives of professionals around the world. I don’t know yet how useful it is yet for users So I am inviting you all to see if this feature can help you better equip yourself on the new wave and do things better. I am always up for a chat on anything AI and provide my help if needed. Looking forward to some feedback aswell

Hear me out, you are annoying

I am a full stack web developer capable of realizing most of the people’s ideas here. Few things to mention out: Developers are not Google itself. You can’t randomly tell them to implement AI, blockchain, NFT, stocks etc. cus developers are not wizards. Stuff like that requires knowledge, quite a lot of it, and if you want someone to spend shit ton of time implementing smtn, you better prepare to pay for it, cus that knowledge is valuable. Most of the time it requires whole teams to do the work you imagined. If someone came to me and told me yeah, I want a copy of upwork. Sure bud, and where are the other 50 developers? (there are exceptions here but still, people are talking whole platforms while I am the only dev there, mate imma need a whole year for this one) be ready to pay. Sure, your idea is cool, but I can’t wait another 2 years untill it starts making money, plus if it’s fully online business, why would i want to share 50/50 with you? No one is dumb enough to do 3 months od work for free just to share 50/50 in best case, with someone who “had an idea”, I could delete the files any second I want to it’s my code! No one is doing big projects for free, be ready to pay and know the value of other’s work. Otherwise have fun scrolling through indian freelancers! At least try to manage something! I am right now looking for projects that I could join, who needs a web dev and all of them are like okay do the work, don’t expect any money cus we aee starting with no money at all and we won’t bother any investors cus you aee the dumb enough developer do male our business for 25% share

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!

Lost in Life at 21: Seeking Fast-Track to Entrepreneurship via AI and Coding – NEED HELP

Hello everyone, I'm coming to you because I'm a bit lost in my life. Let me introduce myself, I'm 21, I'm French and I'm a student in a Master 1 marketing program. I've got 1 year left before I finish my master's and after that I know I want to become an entrepreneur so I can achieve some financial and geographical freedom, but I don't know exactly how to go about it. A few days ago, I had the idea of learning more about AI, which is an emerging sector where there's also a future financial opportunity. I saw that I needed to learn Python first in order to understand AI, do you have any advice for me as I don't know anything about it (I have a science high school diploma)? Do you think it's worth learning to code, knowing what the CEO of Nvidia said recently? If so, my plan is to learn to code until the end of my master's degree (1 year and 5 months), and then move to Canada to improve my English and earn money for my future business. For information, I earn around 1300€/month thanks to my work-study program and I have 40k€ in savings. Do you have any advice for me on how to succeed as quickly as possible and earn as much money as possible intelligently? &#x200B; Translated with DeepL.com (free version)

Learn Coding while building your dream idea (and pay for the lessons).

I have a business idea and would welcome feedback. As a coder with experience running a successful outsourcing shop and teaching coding skills to employees, I want to create a unique class concept where students are entrepreneurs who have an idea they want to develop and sell while learning how to code it themselves. The course would span 6–12 months, focusing on building an MVP (Minimum Viable Product) for each student's project. I would teach coding and guide students on effectively using AI tools like GPT4 and Claude to streamline the coding process by 50-75%. We would start by creating a comprehensive PRD (Product Requirements Document) and estimating the time to completion and the necessary tech stack. The class size would be limited to 4–5 students to ensure proper management and support. The monthly fee would be around $1,000 or more, considering the personalized attention and the potential for students to launch their own products by the end of the course. Students would need to commit significant effort and time (at least 6 months) to the program. Upon completion, students would be equipped with the skills to market their product, add features using AI tools, and manage other coders if needed. They would also gain a solid understanding of the time and resources required to implement new features. As an added benefit, the total cost of this program would likely be comparable to outsourcing the project development. What are your thoughts on this business idea? Do you think there is a market for this type of learning experience?

Looking for a co-founder for a B2B AI startup. I have a development team and funds for at least a year of operations.

Hello, As the title said I'm looking for a co-founder. I built with my team a few ventures that generate revenues but I don't believe that any of them has a future. I have 15 years of experience in Software Engineering and AI. Worked in various industries, but always in data-driven applications. I spent the last 3 years as an entrepreneur and raised successfully money from VCs. &#x200B; A few preconceptions I have: \- B2C is extremely hard. Very quickly you realize that you need to spend all your resources on marketing. \- B2B is extremely hard - but for different reasons. Sales cycles take months. If you want to reach serious buyers and decision-makers, you need to have an amazing network. Even then, companies will prioritize 90% of the time to do things internally rather than paying for anything. \- I hate when people say that "ideas are garbage", and I think that execution is overhyped. Execution is a matter of finding the right people, and paying them (I am confident to say that I can guarantee good execution). Ideas are not garbage, ideas need validation, and garbage "entrepreneurs" are too lazy to validate anything. &#x200B; Your ideal profile: \- You have a great idea, something that has been brewing for some time but you lack resources or technical experience to execute by yourself. \- You have domain expertise, experience, and a network. If we build an MVP in 3 months, you can get 20 interviews with industry people to validate the solution. Once the MVP is built you can put it in front of another 40 people. \- You are a product person. \- You can do efficient sales calls. (Bonus: You are a sales person) If you are an ideal profile, please reach out.

How I Made $250.000+ in a Year: A Case Study of My AI Influencer Journey

Update on February 22th: I changed my AI influencer's names because it caused some problems on my business. One year, two AI-powered influencers, and $250K in revenue. Sounds unreal? It’s not. Today, I’m pulling back the curtain on the strategies, tools, and hard-won lessons that took me from concept to a six-figure success story in the AI influencer space. Hey, I'm Ben—a 32-year-old designer who spent the past year navigating the world of AI influencers. Let me clear up any confusion right from the start: I’m not here to sell you anything. This is purely a case study to share what worked, what didn’t, and what I’ve learned along the way. I’ll also make sure to answer all your questions in the comments for free whenever I can, so don’t hesitate to ask. Links to Past Topics: If you're curious about some of the groundwork I covered, check out a few of my earlier posts here: How I Make $10,000 Monthly | AI Influencer Management How I Earned $7000+ in 15 Days | AI Influencer Business Update These earlier posts cover a lot of the backstory, so feel free to explore them before diving into this one. So if you're ready, here is the full story: \---- The idea of creating an AI influencer was one of those “what if” moments that wouldn’t leave my mind. At first, it sounded futuristic—even a bit too ambitious. It all started when I stumbled upon an AI influencer on Instagram with the handle AnnaMaes2000. Her content blew me away—the quality, the detail, and just how real everything looked. I was instantly hooked and ended up going through every post, just trying to figure out how she was pulling this off. That’s when I knew I had to learn how this was done. The next step? YouTube. I dived into videos on Stable Diffusion, soaking up everything I could about creating AI-generated images. Those tutorials taught me the basics and got me up to speed. Then, I created my first AI influencer, let's call her Mel for now. Right after that, to complete the storyline and boost engagement, I introduced Mel's “mother,” Jess. Adding Jess gave the whole project depth and a narrative that drew people in, creating a unique family dynamic that instantly elevated traffic and interest. After thousands of bad photos, hundreds of deleted posts, and months of trial and error, you can now see the quality that defines my current accounts. Here’s a rundown of the tools and checkpoints I’ve used from day one, in order: Fooocus on RunDiffusion — Juggernaut V8 Fooocus on RunDiffusion — Juggernaut V9 Fooocus on PC (locally) — Juggernaut V9 Fooocus on PC (locally) —Lyuyang Mix + Juggernaut V9 Flux on PC (couple of photos only since it's so slow even on RTX 4090) Flux on Fal.ai. \---- There’s no magic Instagram hack that guarantees success, despite what everyone thinks and keeps asking me. Quality content, consistent uploads, and solid craftsmanship are what actually help your photos hit trends and show up on the Explore page. Unlike 95% of low-quality AI accounts out there, I don’t rely on faceswap videos, spam Reels, or go around liking comments on other accounts. My approach is fully organic, focused solely on creating my own unique content. By following Instagram's guidelines to the letter, I've managed to direct some of Mel and Jess' fans over to Patreon and Fanvue. There, for a small subscription fee, fans can access exclusive lingerie content. For those looking for more, higher-tier subscriptions give access to even more premium content. Some possible questions and their answers: No, you can't share hardcore NSFW content on Patreon. You can do that on Fanvue. Yes, you can create AI creators on Fanvue — OnlyFans doesn't allow it. Yes, you can use your own ID to get KYC. Yes, we're telling both Mel and Jess is (or use) AI to generate content. And yes, some people leave and some people still have fun with chatting, having a good time and get perfect content for their needs. And yes, we have a chatter team to work on these accounts. \---- This journey wasn’t all smooth sailing. I faced unexpected roadblocks, like platform restrictions that limited certain types of content, and managing fan expectations was more challenging than anticipated. Staying within guidelines while keeping fans engaged required constant adaptation. These hurdles forced me to get creative, adjust my approach, and learn fast. Once I saw Mel and Jess gaining traction, I knew it was time to scale up. Expanding meant finding new ways to keep content fresh, creating deeper narratives, and considering how to bring even more followers into the fold. My focus turned to building a sustainable model that could grow without sacrificing quality or authenticity. If you’re thinking about diving into AI content creation, here’s my advice: patience, consistency, and a focus on quality are key. Don’t cut corners or rely on quick-fix hacks. Invest time in learning the right tools, creating engaging stories, and building an audience that values what you bring to the table. This approach took me from zero to six figures, and it’s what makes the journey worth it. \---- And finally, here’s the income breakdown that everyone’s curious about: Mel on Fanvue: $82,331.58 (Gross earnings because we have chatter cuts like 15%) Mel on Patreon: $50,865.98 (Net earnings) Jess on Fanvue: $89,068.26 (Gross earnings because we have chatter cuts like 15%) Jess on Patreon: $39,040.70 And thanks to Reddit and my old posts, I got a perfect investor like after 5 months, so this is a "payback" for that. Like I said, I'll answer every question in the comments — take care and let me know.

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

From Setbacks to $20K Profit: My AI Influencer Earnings Breakdown (Jan 2025) 💰

(Monthly income breakdown is in the end) 📌 Introduction Hey everyone! 👋 Before I dive into this month’s breakdown, I just want to be upfront—English isn’t my first language, so I’ve used ChatGPT to refine this post for better readability. That said, everything here is 100% real—my personal experiences, struggles, and earnings as someone running a full-time AI influencer business. Since I get a lot of DMs asking about my AI models, here are their Instagram links: 📷 Emma – https://www.instagram.com/emmalauireal 📷 Jade – https://www.instagram.com/jadelaui (jadecasual is the second account) Also, if you’ve been wondering about the community I run, where I teach others how to build AI influencers from scratch, here’s the link (I got approval from mods for this link): 🔗 AI Winners Now, let’s get into what happened this month. 🚀 \------- First, a huge thank you! 🎉 Three months ago, I shared my journey of building an AI influencer business, and I was blown away by the response. That post got 263K+ views and was shared over 2.7K times—way more than I ever expected. If you’re new here or want to check out the full story of how I started, you can read it here: 🔗 Click Here (Reddit link) \------- 🔹 What I Did in January After the holiday rush in December, I knew January would be a slow month—people had already spent most of their money at the end of the year. So instead of pushing harder on monetization, I shifted my focus to tech development and optimization. Flux Character Loras: I spent a lot of time refining and testing different Flux-based character Loras for my models. This is still a work in progress, but the goal is to improve long-term consistency and make my workflow even more efficient. NSFW Content Expansion: On Emma’s side, I expanded her content library using a real model body double, making her content look more organic and natural. Jade, however, remains 100% AI-generated, keeping her workflow entirely digital. Social Media Wipeout (Thanks, VA 🙃): I had handed off both Twitter accounts to a virtual assistant to help with engagement and DMs. Big mistake. He ended up spamming DMs, which got both accounts banned—Emma (80K followers) and Jade (20K followers). 🤦‍♂️ Right now, I’m rebuilding Emma’s account from scratch and taking a much more cautious approach. Jade’s account is still offline for now. New Platform: Threads – I hadn’t touched Threads before, but since engagement on Instagram can be unpredictable, I decided to start accounts for both models. So far, they’re performing well, and I’ll continue experimenting. Launched AI Winners Community: After getting flooded with DMs (both here and on Instagram), I realized there was a massive demand for structured learning around AI influencers. So, I launched AI Winners, a paid community where I break down everything I’ve learned. It’s still early, but I see it turning into a solid, long-term community. Investment & Acquisition Talks: I’m still evaluating potential investors and acquisition offers for my AI models. There’s growing interest in buying or investing in Emma & Jade, so I’ve been having conversations to explore different options. Overall, January was about tech, rebuilding, and long-term planning—not immediate revenue. But that’s what keeps this business sustainable. 🚀 \------- ⚠️ Biggest Challenges This Month Lost Both Twitter Accounts (Massive Traffic Hit) 🚨 The biggest blow this month was losing my models’ Twitter accounts. Twitter was responsible for about 40% of my total traffic, meaning both free and paid subs took a direct hit. While Emma’s revenue took a slight dip, Jade’s income dropped significantly—partly due to the account loss and partly because January is naturally slow. (Full revenue breakdown at the end of the post.) Jade’s Instagram Tanked (Possible Shadow Ban?) 🤔 Jade’s Instagram completely lost momentum in early January. Engagement and reach dropped by over 80%, and I still haven’t figured out why. It feels like a shadow ban, but I have no clear confirmation. To counter this, I launched a second backup account, and things are starting to recover. \------- 🚀 Potential Improvements & What’s Next Locking in a Stable Workflow 🔄 Right now, Emma & Jade’s workflow is still evolving, but I’m aiming to fully stabilize it. As I’m writing this, content is generating on my second monitor—a sign that I’m close to achieving full automation without compromising quality. Boosting Jade’s Fanvue Revenue 💰 Jade’s income took a hit this month, and it’s 100% a traffic issue. The solution? More content, more reach. I’ll be increasing social media output to drive consistent traffic back to Fanvue and restore her earnings. Patreon is Done. All Focus on Fanvue 🚫 I shut down both Emma & Jade’s Patreon accounts. The goal is not to split revenue—I want everything funneled into Fanvue for higher engagement and bigger paydays. \------- 💰 January 2025 Earnings Breakdown Despite January being one of the slowest months for online creators, Emma and Jade still brought in over $29K in revenue, with a net profit exceeding $20K after all expenses. Emma Laui generated $20,206.77, with around $6,000 in expenses (chatter payments, NSFW designer fees, and other operational costs). Jade Laui earned $8,939.05, with $2,000 in expenses. Considering Twitter account losses, Instagram setbacks, and the usual January spending slump, this is still a solid outcome. The focus now is on scaling traffic and maximizing Fanvue revenue heading into February. 🚀🔥 That’s the full breakdown for January! If you have questions, feel free to drop a comment, and I’ll answer when I can. Happy to help, just like others helped me when I was starting out! 🚀🔥

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!

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!

From Setbacks to $20K Profit: My AI Influencer Earnings Breakdown (Jan 2025) 💰

(Monthly income breakdown is in the end) 📌 Introduction Hey everyone! 👋 Before I dive into this month’s breakdown, I just want to be upfront—English isn’t my first language, so I’ve used ChatGPT to refine this post for better readability. That said, everything here is 100% real—my personal experiences, struggles, and earnings as someone running a full-time AI influencer business. Since I get a lot of DMs asking about my AI models, here are their Instagram links: 📷 Emma – https://www.instagram.com/emmalauireal 📷 Jade – https://www.instagram.com/jadelaui (jadecasual is the second account) Also, if you’ve been wondering about the community I run, where I teach others how to build AI influencers from scratch, here’s the link (I got approval from mods for this link): 🔗 AI Winners Now, let’s get into what happened this month. 🚀 \------- First, a huge thank you! 🎉 Three months ago, I shared my journey of building an AI influencer business, and I was blown away by the response. That post got 263K+ views and was shared over 2.7K times—way more than I ever expected. If you’re new here or want to check out the full story of how I started, you can read it here: 🔗 Click Here (Reddit link) \------- 🔹 What I Did in January After the holiday rush in December, I knew January would be a slow month—people had already spent most of their money at the end of the year. So instead of pushing harder on monetization, I shifted my focus to tech development and optimization. Flux Character Loras: I spent a lot of time refining and testing different Flux-based character Loras for my models. This is still a work in progress, but the goal is to improve long-term consistency and make my workflow even more efficient. NSFW Content Expansion: On Emma’s side, I expanded her content library using a real model body double, making her content look more organic and natural. Jade, however, remains 100% AI-generated, keeping her workflow entirely digital. Social Media Wipeout (Thanks, VA 🙃): I had handed off both Twitter accounts to a virtual assistant to help with engagement and DMs. Big mistake. He ended up spamming DMs, which got both accounts banned—Emma (80K followers) and Jade (20K followers). 🤦‍♂️ Right now, I’m rebuilding Emma’s account from scratch and taking a much more cautious approach. Jade’s account is still offline for now. New Platform: Threads – I hadn’t touched Threads before, but since engagement on Instagram can be unpredictable, I decided to start accounts for both models. So far, they’re performing well, and I’ll continue experimenting. Launched AI Winners Community: After getting flooded with DMs (both here and on Instagram), I realized there was a massive demand for structured learning around AI influencers. So, I launched AI Winners, a paid community where I break down everything I’ve learned. It’s still early, but I see it turning into a solid, long-term community. Investment & Acquisition Talks: I’m still evaluating potential investors and acquisition offers for my AI models. There’s growing interest in buying or investing in Emma & Jade, so I’ve been having conversations to explore different options. Overall, January was about tech, rebuilding, and long-term planning—not immediate revenue. But that’s what keeps this business sustainable. 🚀 \------- ⚠️ Biggest Challenges This Month Lost Both Twitter Accounts (Massive Traffic Hit) 🚨 The biggest blow this month was losing my models’ Twitter accounts. Twitter was responsible for about 40% of my total traffic, meaning both free and paid subs took a direct hit. While Emma’s revenue took a slight dip, Jade’s income dropped significantly—partly due to the account loss and partly because January is naturally slow. (Full revenue breakdown at the end of the post.) Jade’s Instagram Tanked (Possible Shadow Ban?) 🤔 Jade’s Instagram completely lost momentum in early January. Engagement and reach dropped by over 80%, and I still haven’t figured out why. It feels like a shadow ban, but I have no clear confirmation. To counter this, I launched a second backup account, and things are starting to recover. \------- 🚀 Potential Improvements & What’s Next Locking in a Stable Workflow 🔄 Right now, Emma & Jade’s workflow is still evolving, but I’m aiming to fully stabilize it. As I’m writing this, content is generating on my second monitor—a sign that I’m close to achieving full automation without compromising quality. Boosting Jade’s Fanvue Revenue 💰 Jade’s income took a hit this month, and it’s 100% a traffic issue. The solution? More content, more reach. I’ll be increasing social media output to drive consistent traffic back to Fanvue and restore her earnings. Patreon is Done. All Focus on Fanvue 🚫 I shut down both Emma & Jade’s Patreon accounts. The goal is not to split revenue—I want everything funneled into Fanvue for higher engagement and bigger paydays. \------- 💰 January 2025 Earnings Breakdown Despite January being one of the slowest months for online creators, Emma and Jade still brought in over $29K in revenue, with a net profit exceeding $20K after all expenses. Emma Laui generated $20,206.77, with around $6,000 in expenses (chatter payments, NSFW designer fees, and other operational costs). Jade Laui earned $8,939.05, with $2,000 in expenses. Considering Twitter account losses, Instagram setbacks, and the usual January spending slump, this is still a solid outcome. The focus now is on scaling traffic and maximizing Fanvue revenue heading into February. 🚀🔥 That’s the full breakdown for January! If you have questions, feel free to drop a comment, and I’ll answer when I can. Happy to help, just like others helped me when I was starting out! 🚀🔥

From Setbacks to $20K Profit: My AI Influencer Earnings Breakdown (Jan 2025) 💰

(Monthly income breakdown is in the end) 📌 Introduction Hey everyone! 👋 Before I dive into this month’s breakdown, I just want to be upfront—English isn’t my first language, so I’ve used ChatGPT to refine this post for better readability. That said, everything here is 100% real—my personal experiences, struggles, and earnings as someone running a full-time AI influencer business. Since I get a lot of DMs asking about my AI models, here are their Instagram links: 📷 Emma – https://www.instagram.com/emmalauireal 📷 Jade – https://www.instagram.com/jadelaui (jadecasual is the second account) Also, if you’ve been wondering about the community I run, where I teach others how to build AI influencers from scratch, here’s the link (I got approval from mods for this link): 🔗 AI Winners Now, let’s get into what happened this month. 🚀 \------- First, a huge thank you! 🎉 Three months ago, I shared my journey of building an AI influencer business, and I was blown away by the response. That post got 263K+ views and was shared over 2.7K times—way more than I ever expected. If you’re new here or want to check out the full story of how I started, you can read it here: 🔗 Click Here (Reddit link) \------- 🔹 What I Did in January After the holiday rush in December, I knew January would be a slow month—people had already spent most of their money at the end of the year. So instead of pushing harder on monetization, I shifted my focus to tech development and optimization. Flux Character Loras: I spent a lot of time refining and testing different Flux-based character Loras for my models. This is still a work in progress, but the goal is to improve long-term consistency and make my workflow even more efficient. NSFW Content Expansion: On Emma’s side, I expanded her content library using a real model body double, making her content look more organic and natural. Jade, however, remains 100% AI-generated, keeping her workflow entirely digital. Social Media Wipeout (Thanks, VA 🙃): I had handed off both Twitter accounts to a virtual assistant to help with engagement and DMs. Big mistake. He ended up spamming DMs, which got both accounts banned—Emma (80K followers) and Jade (20K followers). 🤦‍♂️ Right now, I’m rebuilding Emma’s account from scratch and taking a much more cautious approach. Jade’s account is still offline for now. New Platform: Threads – I hadn’t touched Threads before, but since engagement on Instagram can be unpredictable, I decided to start accounts for both models. So far, they’re performing well, and I’ll continue experimenting. Launched AI Winners Community: After getting flooded with DMs (both here and on Instagram), I realized there was a massive demand for structured learning around AI influencers. So, I launched AI Winners, a paid community where I break down everything I’ve learned. It’s still early, but I see it turning into a solid, long-term community. Investment & Acquisition Talks: I’m still evaluating potential investors and acquisition offers for my AI models. There’s growing interest in buying or investing in Emma & Jade, so I’ve been having conversations to explore different options. Overall, January was about tech, rebuilding, and long-term planning—not immediate revenue. But that’s what keeps this business sustainable. 🚀 \------- ⚠️ Biggest Challenges This Month Lost Both Twitter Accounts (Massive Traffic Hit) 🚨 The biggest blow this month was losing my models’ Twitter accounts. Twitter was responsible for about 40% of my total traffic, meaning both free and paid subs took a direct hit. While Emma’s revenue took a slight dip, Jade’s income dropped significantly—partly due to the account loss and partly because January is naturally slow. (Full revenue breakdown at the end of the post.) Jade’s Instagram Tanked (Possible Shadow Ban?) 🤔 Jade’s Instagram completely lost momentum in early January. Engagement and reach dropped by over 80%, and I still haven’t figured out why. It feels like a shadow ban, but I have no clear confirmation. To counter this, I launched a second backup account, and things are starting to recover. \------- 🚀 Potential Improvements & What’s Next Locking in a Stable Workflow 🔄 Right now, Emma & Jade’s workflow is still evolving, but I’m aiming to fully stabilize it. As I’m writing this, content is generating on my second monitor—a sign that I’m close to achieving full automation without compromising quality. Boosting Jade’s Fanvue Revenue 💰 Jade’s income took a hit this month, and it’s 100% a traffic issue. The solution? More content, more reach. I’ll be increasing social media output to drive consistent traffic back to Fanvue and restore her earnings. Patreon is Done. All Focus on Fanvue 🚫 I shut down both Emma & Jade’s Patreon accounts. The goal is not to split revenue—I want everything funneled into Fanvue for higher engagement and bigger paydays. \------- 💰 January 2025 Earnings Breakdown Despite January being one of the slowest months for online creators, Emma and Jade still brought in over $29K in revenue, with a net profit exceeding $20K after all expenses. Emma Laui generated $20,206.77, with around $6,000 in expenses (chatter payments, NSFW designer fees, and other operational costs). Jade Laui earned $8,939.05, with $2,000 in expenses. Considering Twitter account losses, Instagram setbacks, and the usual January spending slump, this is still a solid outcome. The focus now is on scaling traffic and maximizing Fanvue revenue heading into February. 🚀🔥 That’s the full breakdown for January! If you have questions, feel free to drop a comment, and I’ll answer when I can. Happy to help, just like others helped me when I was starting out! 🚀🔥

How I Made $250.000+ in a Year: A Case Study of My AI Influencer Journey

Update on February 22th: I changed my AI influencer's names because it caused some problems on my business. One year, two AI-powered influencers, and $250K in revenue. Sounds unreal? It’s not. Today, I’m pulling back the curtain on the strategies, tools, and hard-won lessons that took me from concept to a six-figure success story in the AI influencer space. Hey, I'm Ben—a 32-year-old designer who spent the past year navigating the world of AI influencers. Let me clear up any confusion right from the start: I’m not here to sell you anything. This is purely a case study to share what worked, what didn’t, and what I’ve learned along the way. I’ll also make sure to answer all your questions in the comments for free whenever I can, so don’t hesitate to ask. Links to Past Topics: If you're curious about some of the groundwork I covered, check out a few of my earlier posts here: How I Make $10,000 Monthly | AI Influencer Management How I Earned $7000+ in 15 Days | AI Influencer Business Update These earlier posts cover a lot of the backstory, so feel free to explore them before diving into this one. So if you're ready, here is the full story: \---- The idea of creating an AI influencer was one of those “what if” moments that wouldn’t leave my mind. At first, it sounded futuristic—even a bit too ambitious. It all started when I stumbled upon an AI influencer on Instagram with the handle AnnaMaes2000. Her content blew me away—the quality, the detail, and just how real everything looked. I was instantly hooked and ended up going through every post, just trying to figure out how she was pulling this off. That’s when I knew I had to learn how this was done. The next step? YouTube. I dived into videos on Stable Diffusion, soaking up everything I could about creating AI-generated images. Those tutorials taught me the basics and got me up to speed. Then, I created my first AI influencer, let's call her Mel for now. Right after that, to complete the storyline and boost engagement, I introduced Mel's “mother,” Jess. Adding Jess gave the whole project depth and a narrative that drew people in, creating a unique family dynamic that instantly elevated traffic and interest. After thousands of bad photos, hundreds of deleted posts, and months of trial and error, you can now see the quality that defines my current accounts. Here’s a rundown of the tools and checkpoints I’ve used from day one, in order: Fooocus on RunDiffusion — Juggernaut V8 Fooocus on RunDiffusion — Juggernaut V9 Fooocus on PC (locally) — Juggernaut V9 Fooocus on PC (locally) —Lyuyang Mix + Juggernaut V9 Flux on PC (couple of photos only since it's so slow even on RTX 4090) Flux on Fal.ai. \---- There’s no magic Instagram hack that guarantees success, despite what everyone thinks and keeps asking me. Quality content, consistent uploads, and solid craftsmanship are what actually help your photos hit trends and show up on the Explore page. Unlike 95% of low-quality AI accounts out there, I don’t rely on faceswap videos, spam Reels, or go around liking comments on other accounts. My approach is fully organic, focused solely on creating my own unique content. By following Instagram's guidelines to the letter, I've managed to direct some of Mel and Jess' fans over to Patreon and Fanvue. There, for a small subscription fee, fans can access exclusive lingerie content. For those looking for more, higher-tier subscriptions give access to even more premium content. Some possible questions and their answers: No, you can't share hardcore NSFW content on Patreon. You can do that on Fanvue. Yes, you can create AI creators on Fanvue — OnlyFans doesn't allow it. Yes, you can use your own ID to get KYC. Yes, we're telling both Mel and Jess is (or use) AI to generate content. And yes, some people leave and some people still have fun with chatting, having a good time and get perfect content for their needs. And yes, we have a chatter team to work on these accounts. \---- This journey wasn’t all smooth sailing. I faced unexpected roadblocks, like platform restrictions that limited certain types of content, and managing fan expectations was more challenging than anticipated. Staying within guidelines while keeping fans engaged required constant adaptation. These hurdles forced me to get creative, adjust my approach, and learn fast. Once I saw Mel and Jess gaining traction, I knew it was time to scale up. Expanding meant finding new ways to keep content fresh, creating deeper narratives, and considering how to bring even more followers into the fold. My focus turned to building a sustainable model that could grow without sacrificing quality or authenticity. If you’re thinking about diving into AI content creation, here’s my advice: patience, consistency, and a focus on quality are key. Don’t cut corners or rely on quick-fix hacks. Invest time in learning the right tools, creating engaging stories, and building an audience that values what you bring to the table. This approach took me from zero to six figures, and it’s what makes the journey worth it. \---- And finally, here’s the income breakdown that everyone’s curious about: Mel on Fanvue: $82,331.58 (Gross earnings because we have chatter cuts like 15%) Mel on Patreon: $50,865.98 (Net earnings) Jess on Fanvue: $89,068.26 (Gross earnings because we have chatter cuts like 15%) Jess on Patreon: $39,040.70 And thanks to Reddit and my old posts, I got a perfect investor like after 5 months, so this is a "payback" for that. Like I said, I'll answer every question in the comments — take care and let me know.

I’m curious,what tools or strategies do you all use for lead generation?

Hey everyone, I wanted to share how I’ve been improving my email outreach over the past few months. Finding the right leads for outreach can be challenging, especially when you’re working with a specific niche. Early on, I was using a tool that provided leads, but I quickly realized that many of the leads weren’t really a good fit for what I offer. While it gave me a lot of contacts, they weren’t always in the right industry or at the right job level. To solve this, I started using a combination of tools: WarpLeads to export unlimited leads and Apollo for more targeted searches. By using Apollo, I was able to focus on the specific roles and industries that were more likely to convert into customers. After I had the leads, I made sure to verify their emails with Reoon, which helped clean up the list and improved my email deliverability. Since making these changes, my email engagement has gone up, and I’ve closed 3 new deals that I wouldn’t have landed without a more targeted approach. It's been a huge improvement overall. I’m curious,what tools or strategies do you all use for lead generation? Any tips you’ve found helpful?

SaaS, Agency, or job?

Recently, I was fired, and since I have some savings, I decided it’s finally time to start my own venture. After a couple of weeks of research and trying to figure out what I should do, here are my thoughts and some questions at the end. I’d appreciate any feedback or opinions. It’s not that I expect to wake up a multimillionaire, but I see how people make money without working the typical 9-5. Some of the worst examples are on YouTube—those agency, OFM, dropshipping hustle bros. I know it’s naive to believe all of it because they’re just selling courses, but some of them do seem to have built impressive income streams. Anyway, let’s dive into two categories and compare. Agency (providing services, development, consultation): I’ll talk about AI automation because of my background in ML Engineering and Generative AI, but this could apply to any other agency niche. It seems like a good business idea for someone who knows generative AI and can do some impressive things with LLMs, agents, etc. I even started working on it—built a website—but I stopped when I couldn’t define exactly what services to offer. I could do heavy backend tasks with infrastructure, like real machine learning and AI with fine-tuning, but I couldn’t find any examples of agencies doing this. Almost 100% of them are doing simple automations with tools like Zapier or Make. When it comes to business owners, it’s really hard to find clients in general. After reading Reddit threads, articles, and watching videos, it seems like nearly everyone struggles with client acquisition. For a one-person agency offering more complex services like real ML, it would likely be even harder to find clients, compared to big outsourcing companies with sales teams. Even without focusing on the client challenge, which is obvious in any business, looking at what successful agency owners earn, it’s usually around $100k–$200k a year. I’m not talking about the high end, just regular people. I got this information from reading, and a simple example is from interviews with people who claim to make $10k/month. But many others in these communities struggle to even reach that point. It seems like this is a difficult target for most people. SaaS: This area seems more straightforward, and with my background, it feels like a good fit. However, from reading different sources, I’ve found stories like, “It took me six months to get my first client,” or “I worked on a simple SaaS for nine months and just reached my first $1k.” There are also warnings not to believe those who claim to make $10k/month easily, and many people report struggling to grow after getting their first 10 clients. So, it’s clear to me that even with good tech skills, you’re not going to make massive amounts of money overnight, which I understand. However, with so many people becoming startup founders and indie hackers, many seem to struggle despite thinking it’s the way to go. I know both paths can potentially skyrocket, but here’s where I need help: Am I wrong about agencies? Am I wrong about SaaS? The toughest question for me: I don’t want to go back to a 9-5 job, even if I could earn $300k a year. Even if my own business takes more time and I earn less in the first few years, I still believe it will be more profitable long term, and I will be happier. So, should I pursue an agency, SaaS, or a traditional job?

Steep Learning : How I Mapped approximately 10K AI tools to 15K Replaceable Tasks across 4K professions

Hello Everyone , I would like to share some knowledge today which I went towards countless hours to do . I founded a portal called Seekme.ai, a comprehensive platform that houses over 10,000 AI tools and resources. Today, I'm excited to share with you an insightful and enlightening journey of how I mapped these tools to 15,000 tasks across 4,000 professions. This process, which I've named "Learn by Doing," got me the power of determination, collaboration, and adaptability. The Idea: It all started when I recognized the need for a more efficient and accessible way for professionals to understand which AI tools could help them automate their tasks. The traditional approach of manually researching and testing each AI tool for every profession was time-consuming and inefficient. I envisioned a solution that could streamline this process, making AI adoption easier and more accessible for a broader audience. The Planning: To begin, we needed a clear understanding of the task landscape across various professions. With the help of some Reddit communities , we embarked on an extensive study of common tasks in various industries. We utilized various sources, including government reports, industry surveys, and academic research, to create a comprehensive list of tasks. The result was an impressive list of 15,000 tasks. The Mapping: With the list of tasks in hand, the next step was to identify which AI tools could perform these tasks. I meticulously researched and analyzed each AI tool's capabilities and features. We cross-referenced this information with the tasks I had identified and created a mapping between the two. The process involved a significant amount of collaboration and refinement, as we continually updated and expanded our database of AI tools and tasks. The Challenges: The mapping process was not without its challenges. One of the primary obstacles was ensuring the accuracy and completeness of our data. To address this issue, I implemented a rigorous quality control process that included multiple rounds of checks and validations.I also established partnerships with industry experts and AI vendors to ensure our data was up-to-date and accurate. There is also a challenge that I faced was what is the quality of the tools which is the problem and how do I rank multiple tools if they do the same tasks without user feedback The Results: After months of hard work and dedication, I successfully mapped 10,000 AI tools to 15,000 tasks across 4,000 professions. Our new feature, AI by Profession, was born. This innovative will allow users to quickly and easily identify the AI tools that can automate tasks in their profession, making AI adoption more accessible and efficient than ever before. The Impact: The impact of this project has been significant. By making it easier for professionals to identify AI tools that can automate tasks in their industry, we're helping to drive productivity, efficiency, and innovation. Our users are saving time and resources by not having to manually research and test AI tools. Furthermore, we're contributing to the broader goal of democratizing AI and making it accessible to a broader audience. But there is a still an issue we face of ranking tools who does the similar job. For instance for content creation there 10 tools that can do same video editing so how do we rank it . We are planning to add categories to this to make it more exhaustive Conclusion: The journey to mapping 10,000 AI tools for 15,000 tasks across 4,000 professions was a challenging and rewarding experience. It required a significant amount of planning, determination, and collaboration, but the end result was a powerful tool that's making a difference in the lives of professionals around the world. I don’t know yet how useful it is yet for users So I am inviting you all to see if this feature can help you better equip yourself on the new wave and do things better. I am always up for a chat on anything AI and provide my help if needed. Looking forward to some feedback aswell

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

I built an instant no-code AI tool for training & explaining regression/classification models

Hey everyone! I recently developed a no-code SaaS tool aimed at simplifying and speeding up machine learning workflows, particularly for regression and classification tasks. I’d love to get feedback from the community here, especially from those who are experienced with machine learning and data science workflows. I’ll give a quick rundown of the tool's features, but I want to emphasize that I’m here more to learn about what would be valuable for you than to promote anything. The basic idea: This tool allows you to go from a raw dataset (CSV or tabular text format) to a trained ML model in minutes, rather than needing weeks or months of coding, hyperparameter tuning, and visualization work. It's designed to be intuitive for users without a strong coding background but still offers the depth that experienced users would need. Here’s how it works: Data Upload & Prep: Start by uploading a CSV or other tabular format dataset. The tool includes data prep steps that are designed to be simple but cover essentials (e.g., missing value handling, scaling). Model Training & Tuning: You can choose between regression and classification models, with automatic hyperparameter tuning happening in the background (under a time limit that you can set). It aims to find a good balance without needing direct input but does allow for manual adjustments if desired. Performance Analysis: It provides aggregated performance metrics like F1, recall, precision, R2, and others, alongside charts like AUROC, confusion matrices, and feature importance charts. I also included SHAP plots for deeper insight into feature contributions, as I know they’re becoming a standard for interpretability. Inference Options: The tool lets you do inference on either manually entered data or batch data (again, via CSV). The UI is lightweight and tries to make this as seamless as possible. What I’m hoping to get feedback on: Are there core features that feel like they’re missing? My goal was to provide a well-rounded suite for non-technical users but with enough depth for data scientists to find value. Does this kind of tool fit into your workflow? Or would something like this be more of a beginner tool? How valuable is explainability? I know SHAP is popular, but I’m curious if it actually makes it into the workflows of many data scientists here. Anything else you’d like to see in a tool like this? I know that there are a lot of no-code ML tools out there, so I’m not trying to reinvent the wheel—I just tried to make something a bit more straightforward while still incorporating some flexibility and depth. If you’ve used similar tools or have thoughts on what would make something like this actually useful in practice, I’d really appreciate any insights! Thank you so much for reading, and looking forward to any feedback you’re willing to share. Beta testers are welcome, currently forming a list.

Obliterate my app idea before I bet my life savings on it (AI lead-gen tool)

So I have this app idea on my mind for months now, but I’m 95% sure it’ll flop. Can you help me figure it out? The Problem: Many agencies struggle to stand out in a crowded marketplace and waste time on discovery calls. Current lead generation tools often feel impersonal and don’t showcase how an agency’s expertise can solve specific problems of clients. The Idea: A lead generation tool for agency owners that uses AI to create personalized recommendations for prospects (potential customers) early in the sales process. These recommendations are sent as custom reports (aka lead magnet) to the prospect. This would showcase how the agency can address the unique needs and requirements of the potential client without requiring a discovery call right away. The whole process will be 100% automated, allowing agency owners to focus on closing deals. Target audience: Agency owners/marketers who want to focus on acquiring qualified leads online. In the future, I’d love to explore niches like SaaS and real estate. How it works in 4 steps: Prospect Input: Prospects visit an agency’s landing page (generated by my app) and submit their goals and challenges. AI Matching: The custom-trained AI processes their input and combines it with the agency’s data to generate a customized, actionable report. Delivery: The report is instantly emailed to the prospect, highlighting how the agency can address his/her challenges. Follow-Up: With the prospect warmed up, the agency can follow up and (hopefully) convert them into a client. For example, a digital marketing agency could use the app to create a landing page offering a free ‘Personalized Marketing Strategy Report.’ When a prospect submits his goals and challenges, the AI instantly generates and emails a tailored report, showcasing the agency’s expertise. Why It Might Fail: Maybe agencies won’t see the value in automation, or AI-generated reports might feel impersonal. Could this idea fill a real gap? Why It Might Work: It’s a way for agencies to stand out with personalized lead magnets that feel unique and interactive. It could help agencies attract and convert qualified leads in an automated way. Your Honest Feedback: Would this help agencies improve their lead-generation process, or is it just flashy nonsense? What flaws or challenges do you see in this idea? Is this worth pursuing, or should I stick to spending time with my family 😂? Thank you guys, your honesty might save me from myself! PS: I won’t link to my tool because I don’t want to come off as a spammer.

No code AI

Limited time Try B12 1 mo for 3 months

eiten

Eiten - Algorithmic Investing Strategies for Everyone Eiten is an open source toolkit by Tradytics that implements various statistical and algorithmic investing strategies such as Eigen Portfolios, Minimum Variance Portfolios, Maximum Sharpe Ratio Portfolios, and Genetic Algorithms based Portfolios. It allows you to build your own portfolios with your own set of stocks that can beat the market. The rigorous testing framework included in Eiten enables you to have confidence in your portfolios. If you are looking to discuss these tools in depth and talk about more tools that we are working on, please feel free to join our Discord channel where we have a bunch of more tools too. Files Description | Path | Description | :--- | :---------- | eiten | Main folder. | &boxur; figures | Figures for this github repositories. | &boxur; stocks | Folder to keep your stock lists that you want to use to create your portfolios. | &boxur; strategies | A bunch of strategies implemented in python. | backtester.py | Backtesting module that both backtests and forward tests all portfolios. | data_loader.py | Module for loading data from yahoo finance. | portfolio_manager.py | Main file that takes in a bunch of arguments and generates several portfolios for you. | simulator.py | Simulator that uses historical returns and monte carlo to simulate future prices for the portfolios. | strategy_manager.py | Manages the strategies implemented in the 'strategies' folder. Required Packages You will need to install the following package to train and test the models. Scikit-learn Numpy Tqdm Yfinance Pandas Scipy You can install all packages using the following command. Please note that the script was written using python3. Build your portfolios Let us see how we can use all the strategies given in the toolkit to build our portfolios. The first thing you need to do is modify the stocks.txt file in the stocks folder and add the stocks of your choice. It is recommended to keep the list small i.e anywhere between 5 to 50 stocks should be fine. We have already put a small stocks list containing a bunch of tech stocks like AAPL, MSFT, TSLA etc. Let us build our portfolios now. This is the main command that you need to run. This command will use last 5 years of daily data excluding the last 90 days and build several portfolios for you. Based on those portfolios, it will then test them on the out of sample data of 90 days and show you the performance of each portfolio. Finally, it will also compare the performance with your choice of market index which is QQQ here. Let's dive into each of the parameters in detail. istest: The value determined if the program is going to keep some separate data for future testing. When this is enabled, the value of futurebars should be larger than 5. future_bars: These are the bars that the tool will exclude during portfolio building and will forward test the portfolios on the excluded set. This is also called out of sample data. datagranularityminutes: How much granular data do you want to use to build your portfolios. For long term portfolios, you should use daily data but for short term, you can use hourly or minute level data. The possible values here are 3600, 60, 30, 15, 5, 1. 3600 means daily. historytouse: Whether to use a specific number of historical bars or use everything that we receive from yahoo finance. For minute level data, we only receive up to one month of historical data. For daily, we receive 5 years worth of historical data. If you want to use all available data, the value should be all but if you want to use smaller history, you can set it to an integer value e.g 100 which will only use the last 100 bars to build the portfolios. applynoisefiltering: This uses random matrix theory to filter out the covariance matrix from randomness thus yielding better portfolios. A value of 1 will enable it and 0 will disable it. market_index: Which index do you want to use to compare your portfolios. This should mostly be SPY but since we analyzed tech stocks, we used QQQ. only_long: Whether to use long only portfolio or enable short selling as well. Long only portfolios have shown to have better performance using algorithmic techniques. eigenportfolionumber: Which eigen portfolio to use. Any value between 1-5 should work. The first eigen portfolio (1) represents the market portfolio and should act just like the underlying index such as SPY or QQQ. The second one is orthogonal and uncorrelated to the market and poses the greatest risk and reward. The following ones have reduced risk and reward. Read more on eigen-portfolios. stocksfilepath: File that contains the list of stocks that you want to use to build your portfolio. Some Portfolio Building Examples Here are a few examples for building different types of portfolios. Both long and short portfolios by analyzing last 90 days data and keeping the last 30 days as testing data. This will give us 60 days of portfolio construction data and 30 days of testing. Only long portfolio on 60 minute bars of the last 30 days. No future testing. Compare the results with SPY index instead of QQQ. Do not apply noise filtering on the covariance matrix. Use the first eigen portfolio (market portfolio) and compare with SQQQ, Portfolio Strategies Four different portfolio strategies are currently supported by the toolkit. Eigen Portfolios These portfolios are orthogonal and uncorrelated to the market in general thus yielding high reward and alpha. However, since they are uncorrelated to the market, they can also provide great risk. The first eigen portfolio is considered to be a market portfolio which is often ignored. The second one is uncorrelated to the others and provides the highest risk and reward. As we go down the numbering, the risk as well as the reward are reduced. Minimum Variance Portfolio (MVP) MVP tries to minimize the variance of the portfolio. These portfolios are lowest risk and reward. Maximum Sharpe Ratio Portfolio (MSR) MSR solves an optimization problem that tries to maximize the sharpe ratio of the portfolio. It uses past returns during the optimization process which means if past returns are not the same as future returns, the results can vary in future. Genetic Algorithm (GA) based Portfolio This is our own implementation of a GA based portfolio that again tries to maximize the sharpe ratio but in a slightly more robust way. This usually provides more robust portfolios than the others. When you run the command above, our tool will generate portfolios from all these strategies and give them to you. Let us look at some resulting portfolios. Resulting Portfolios For the purpose these results, we will use the 9 stocks in the stocks/stocks.txt file. When we run the above command, we first get the portfolio weights for all four strategies. For testing purposes, the above command used last five years of daily data up till April 29th. The remaining data for this year was used for forward testing i.e the portfolio strategies had no access to it when building the portfolios. What if my portfolio needs different stocks?: All you need to do is change the stocks in the stocks.txt file and run the tool again. Here is the final command again that we run in order to get our portfolios: Portfolio Weights We can see that the eigen portfolio is giving a large weight to TSLA while the others are dividing their weights more uniformly. An interesting phenomena happening here is the hedging with SQQQ that all the strategies have learned automatically. Every tool is assigning some positive weight to SQQQ while also assigning positive weights to other stocks which indicates that the strategies are automatically trying to hedge the portfolios from risk. Obviously this is not perfect, but just the fact that it's happening is fascinating. Let us look at the backtest results on the last five years prior to April 29, 2020. Backtest Results The backtests look pretty encouraging. The black dotted line is the market index i.e QQQ. Other lines are the strategies. Our custom genetic algorithm implementation seems to have the best backtest results because it's an advanced version of other strategies. The eigen portfolio that weighed TSLA the most have the most volatility but its profits are also very high. Finally, as expected, the MVP has the minimum variance and ultimately the least profits. However, since the variance is extremely low, it is a good portfolio for those who want to stay safe. The most interesting part comes next, let us look at the forward or future test results for these portfolios. Forward Test Results These results are from April 29th, 2020 to September 4th, 2020. The eigen portfolio performed the best but it also had a lot of volatility. Moreover, most of those returns are due to TSLA rocketing in the last few months. After that, our GA algorithm worked quite effectively as it beat the market index. Again, as expected, the MVP had the lowest risk and reward and slowly went up in 4-5 months. This shows the effectiveness and power of these algorithmic portfolio optimization strategies where we've developed different portfolios for different kinds of risk and reward profiles. Conclusion and Discussion We are happy to share this toolkit with the trading community and hope that people will like and contribute to it. As is the case with everything in trading, these strategies are not perfect but they are based on rigorous theory and some great empirical results. Please take care when trading with these strategies and always manage your risk. The above results were not cherry picked but the market has been highly bullish in the last few months which has led to the strong results shown above. We would love for the community to try out different strategies and share them with us. Special Thanks Special thanks to Scott Rome's blog. The eigen portfolios and minimum variance portfolio concepts came from his blog posts. The code for filtering eigen values of the covariance matrix was also mostly obtained from one of his posts. License A product by Tradytics Copyright (c) 2020-present, Tradytics.com

voicefilter

VoiceFilter Note from Seung-won (2020.10.25) Hi everyone! It's Seung-won from MINDs Lab, Inc. It's been a long time since I've released this open-source, and I didn't expect this repository to grab such a great amount of attention for a long time. I would like to thank everyone for giving such attention, and also Mr. Quan Wang (the first author of the VoiceFilter paper) for referring this project in his paper. Actually, this project was done by me when it was only 3 months after I started studying deep learning & speech separation without a supervisor in the relevant field. Back then, I didn't know what is a power-law compression, and the correct way to validate/test the models. Now that I've spent more time on deep learning & speech since then (I also wrote a paper published at Interspeech 2020 😊), I can observe some obvious mistakes that I've made. Those issues were kindly raised by GitHub users; please refer to the Issues and Pull Requests for that. That being said, this repository can be quite unreliable, and I would like to remind everyone to use this code at their own risk (as specified in LICENSE). Unfortunately, I can't afford extra time on revising this project or reviewing the Issues / Pull Requests. Instead, I would like to offer some pointers to newer, more reliable resources: VoiceFilter-Lite: This is a newer version of VoiceFilter presented at Interspeech 2020, which is also written by Mr. Quan Wang (and his colleagues at Google). I highly recommend checking this paper, since it focused on a more realistic situation where VoiceFilter is needed. List of VoiceFilter implementation available on GitHub: In March 2019, this repository was the only available open-source implementation of VoiceFilter. However, much better implementations that deserve more attention became available across GitHub. Please check them, and choose the one that meets your demand. PyTorch Lightning: Back in 2019, I could not find a great deep-learning project template for myself, so I and my colleagues had used this project as a template for other new projects. For people who are searching for such project template, I would like to strongly recommend PyTorch Lightning. Even though I had done a lot of effort into developing my own template during 2019 (VoiceFilter -> RandWireNN -> MelNet -> MelGAN), I found PyTorch Lightning much better than my own template. Thanks for reading, and I wish everyone good health during the global pandemic situation. Best regards, Seung-won Park Unofficial PyTorch implementation of Google AI's: VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking. Result Training took about 20 hours on AWS p3.2xlarge(NVIDIA V100). Audio Sample Listen to audio sample at webpage: http://swpark.me/voicefilter/ Metric | Median SDR | Paper | Ours | | ---------------------- | ----- | ---- | | before VoiceFilter | 2.5 | 1.9 | | after VoiceFilter | 12.6 | 10.2 | SDR converged at 10, which is slightly lower than paper's. Dependencies Python and packages This code was tested on Python 3.6 with PyTorch 1.0.1. Other packages can be installed by: Miscellaneous ffmpeg-normalize is used for resampling and normalizing wav files. See README.md of ffmpeg-normalize for installation. Prepare Dataset Download LibriSpeech dataset To replicate VoiceFilter paper, get LibriSpeech dataset at http://www.openslr.org/12/. train-clear-100.tar.gz(6.3G) contains speech of 252 speakers, and train-clear-360.tar.gz(23G) contains 922 speakers. You may use either, but the more speakers you have in dataset, the more better VoiceFilter will be. Resample & Normalize wav files First, unzip tar.gz file to desired folder: Next, copy utils/normalize-resample.sh to root directory of unzipped data folder. Then: Edit config.yaml Preprocess wav files In order to boost training speed, perform STFT for each files before training by: This will create 100,000(train) + 1000(test) data. (About 160G) Train VoiceFilter Get pretrained model for speaker recognition system VoiceFilter utilizes speaker recognition system (d-vector embeddings). Here, we provide pretrained model for obtaining d-vector embeddings. This model was trained with VoxCeleb2 dataset, where utterances are randomly fit to time length [70, 90] frames. Tests are done with window 80 / hop 40 and have shown equal error rate about 1%. Data used for test were selected from first 8 speakers of VoxCeleb1 test dataset, where 10 utterances per each speakers are randomly selected. Update: Evaluation on VoxCeleb1 selected pair showed 7.4% EER. The model can be downloaded at this GDrive link. Run After specifying traindir, testdir at config.yaml, run: This will create chkpt/name and logs/name at base directory(-b option, . in default) View tensorboardX Resuming from checkpoint Evaluate Possible improvments Try power-law compressed reconstruction error as loss function, instead of MSE. (See #14) Author Seungwon Park at MINDsLab (yyyyy@snu.ac.kr, swpark@mindslab.ai) License Apache License 2.0 This repository contains codes adapted/copied from the followings: utils/adabound.py from https://github.com/Luolc/AdaBound (Apache License 2.0) utils/audio.py from https://github.com/keithito/tacotron (MIT License) utils/hparams.py from https://github.com/HarryVolek/PyTorchSpeakerVerification (No License specified) utils/normalize-resample.sh from https://unix.stackexchange.com/a/216475

How-to-learn-Deep-Learning

Approach A practical, top-down approach, starting with high-level frameworks with a focus on Deep Learning. UPDATED VERSION: 👉 Check out my 60-page guide, No ML Degree, on how to land a machine learning job without a degree. Getting started [2 months] There are three main goals to get up to speed with deep learning: 1) Get familiar to the tools you will be working with, e.g. Python, the command line and Jupyter notebooks 2) Get used to the workflow, everything from finding the data to deploying a trained model 3) Building a deep learning mindset, an intuition for how deep learning models behave and how to improve them Spend a week on codecademy.com and learn the python syntax, command line and git. If you don't have any previous programming experience, it's good to spend a few months learning how to program. Otherwise, it's easy to become overwhelmed. Spend one to two weeks using Pandas and Scikit-learn on Kaggle problems using Jupyter Notebook on Colab, e.g. Titanic, House prices, and Iris. This gives you an overview of the machine learning mindset and workflow. Spend one month implementing models on cloud GPUs. Start with FastAI and PyTorch. The FastAI community is the go-to place for people wanting to apply deep learning and share the state of the art techniques. Once you have done this, you will know how to add value with ML. Portfolio [3 - 12 months] Think of your portfolio as evidence to a potential employer that you can provide value for them. When you are looking for your first job, there are four main roles you can apply for Machine Learning Engineering, Applied Machine Learning Researcher / Residencies, Machine Learning Research Scientist, and Software Engineering. A lot of the work related to machine learning is pure software engineering roles (category 4), e.g. scaling infrastructure, but that's out of scope for this article. It's easiest to get a foot in the door if you aim for Machine Learning Engineering roles. There are a magnitude more ML engineering roles compared to category 2 & 3 roles, they require little to no theory, and they are less competitive. Most employers prefer scaling and leveraging stable implementations, often ~1 year old, instead of allocating scarce resources to implement SOTA papers, which are often time-consuming and seldom work well in practice. Once you can cover your bills and have a few years of experience, you are in a better position to learn theory and advance to category 2 & 3 roles. This is especially true if you are self-taught, you often have an edge against an average university graduate. In general, graduates have weak practical skills and strong theory skills. Context You'll have a mix of 3 - 10 technical and non-technical people looking at your portfolio, regardless of their background, you want to spark the following reactions: the applicant has experience tackling our type of problems, the applicant's work is easy to understand and well organized, and the work was without a doubt 100% made by the applicant. Most ML learners end up with the same portfolio as everyone else. Portfolio items include things as MOOC participation, dog/cat classifiers, and implementations on toy datasets such as the titanic and iris datasets. They often indicate that you actively avoid real-world problem-solving, and prefer being in your comfort zone by copy-pasting from tutorials. These portfolio items often signal negative value instead of signaling that you are a high-quality candidate. A unique portfolio item implies that you have tackled a unique problem without a solution, and thus have to engage in the type of problem-solving an employee does daily. A good starting point is to look for portfolio ideas on active Kaggle competitions, and machine learning consulting projects, and demo versions of common production pipelines. Here's a Twitter thread on how to come up with portfolio ideas. Here are rough guidelines to self-assess the strength of your portfolio: Machine learning engineering: Even though ML engineering roles are the most strategic entry point, they are still highly competitive. In general, there are ~50 software engineering roles for every ML role. From the self-learners I know, 2/3 fail to get a foot in the door and end up taking software engineering roles instead. You are ready to look for a job when you have two high-quality projects that are well-documented, have unique datasets, and are relevant to a specific industry, say banking or insurance. Project Type | Base score | -------------| -----------| Common project | -1 p || Unique project | 10 p | Multiplier Type | Factor -----------------|----------------- Strong documentation | 5x 5000-word article | 5x Kaggle Medal | 10x Employer relevancy | 20x Hireable: 5,250 p Competative: 15,000 p Applied research / research assistant/ residencies: For most companies, the risk of pursuing cutting edge research is often too high, thus only the biggest companies tend to need this skillset. There are smaller research organizations that hire for these positions, but these positions tend to be poorly advertised and have a bias for people in their existing community. Many of these roles don't require a Ph.D., which makes them available to most people with a Bachelor's or Master's degrees, or self-learners with one year of focussed study. Given the status, scarcity, and requirements for these positions, they are the most competitive ML positions. Positions at well-known companies tend to get more than a thousand applicants per position. Daily, these roles require that you understand and can implement SOTA papers, thus that's what they will be looking for in your portfolio. Projects type | Base score --------------| ----------- Common project | -10 p Unique project | 1 p SOTA paper implementation | 20 p Multiplier type | Factor ----------------| --------------- Strong documentation | 5x 5000-word article | 5x SOTA performance | 5x Employer relevancy | 20x Hireable: 52,500 p Competitive: 150,000 p Research Scientist: Research scientist roles require a Ph.D. or equivalent experience. While the former category requires the ability to implement SOTA papers, this category requires you to come up with research ideas. The mainstream research community measure the quality of research ideas by their impact, here is a list of the venues and their impact. To have a competitive portfolio, you need two published papers in the top venues in an area that's relevant to your potential employer. Project type | Base score -------------| ---------------- Common project | -100 p An unpublished paper | 5 p ICML/ICLR/NeurIPS publication | 500p All other publications | 50 p Multiplier type | Factor ------------------| ------------------ First author paper | 10x Employer relevancy | 20x Hireable: 20,000 p Competitive roles and elite PhD positions: 200,000 p Examples: My first portfolio item (after 2 months of learning): Code | Write-up My second portfolio item (after 4 months of learning): Code | Write-up Dylan Djian's first portfolio item: Code | Write-up Dylan Djian's second portfolio item: Code | Write-up Reiichiro Nakano's first portfolio item: Code | Write-up Reiichiro Nakano's second portfolio item: Write-up Most recruiters will spend 10-20 seconds on each of your portfolio items. Unless they can understand the value in that time frame, the value of the project is close to zero. Thus, writing and documentation are key. Here's another thread on how to write about portfolio items. The last key point is relevancy. It's more fun to make a wide range of projects, but if you want to optimize for breaking into the industry, you want to do all projects in one niche, thus making your skillset super relevant for a specific pool of employers. Further Inspiration: FastAI student projects Stanford NLP student projects Stanford CNN student projects Theory 101 [4 months] Learning how to read papers is critical if you want to get into research, and a brilliant asset as an ML engineer. There are three key areas to feel comfortable reading papers: 1) Understanding the details of the most frequent algorithms, gradient descent, linear regression, and MLPs, etc 2) Learning how to translate the most frequent math notations into code 3) Learn the basics of algebra, calculus, statistics, and machine learning For the first week, spend it on 3Blue1Brown's Essence of linear algebra, the Essence of Calculus, and StatQuests' the Basics (of statistics) and Machine Learning. Use a spaced repetition app like Anki and memorize all the key concepts. Use images as much as possible, they are easier to memorize. Spend one month recoding the core concepts in python numpy, including least squares, gradient descent, linear regression, and a vanilla neural network. This will help you reduce a lot of cognitive load down the line. Learning that notations are compact logic and how to translate it into code will make you feel less anxious about the theory. I believe the best deep learning theory curriculum is the Deep Learning Book by Ian Goodfellow and Yoshua Bengio and Aaron Courville. I use it as a curriculum, and the use online courses and internet resources to learn the details about each concept. Spend three months on part 1 of the Deep learning book. Use lectures and videos to understand the concepts, Khan academy type exercises to master each concept, and Anki flashcards to remember them long-term. Key Books: Deep Learning Book by Ian Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD by Jeremy Howard and Sylvain. Gugger. Deep Learning with Python by François Chollet. Neural Networks and Deep Learning by Michael Nielsen. Grokking Deep Learning by Andrew W. Trask. Forums FastAI Keras Slack Distill Slack Pytorch Twitter Other good learning strategies: Emil Wallner S. Zayd Enam Catherine Olsson Greg Brockman V2 Greg Brockman V1 Andrew Ng Amid Fish Spinning Up by OpenAI Confession as an AI researcher YC Threads: One and Two If you have suggestions/questions create an issue or ping me on Twitter. UPDATED VERSION: 👉 Check out my 60-page guide, No ML Degree, on how to land a machine learning job without a degree. Language versions: Korean | English

coca

Coca - toolbox for system refactoring and analysis !GitHub release (latest SemVer) !GitHub go.mod Go version Coca is a toolbox which is design for legacy system refactoring and analysis, includes call graph, concept analysis, api tree, design patterns suggest. Coca 是一个用于系统重构、系统迁移和系统分析的工具箱。它可以分析代码中的测试坏味道、模块化分析、行数统计、分析调用与依赖、Git 分析以及自动化重构等。 Related Tools: Coco is an effective DevOps analysis and auto-suggest tool. Kotlin version: Chapi Migration Guide (Chinese Version): 《系统重构与迁移指南》 Inspired by: newlee & Tequila Refactoring Modeling: !Refactoring Modeling Languages Support: Java (full features) Features List: Getting started Requirements: graphviz for dot file to image (such as svg, png) The easiest way to get coca is to use one of the pre-built release binaries which are available for OSX, Linux, Windows on the release page. You can also install yourself : Usage Analysis Arch Android Studio Gradle DSL Module (merge header) command: coca arch -x "com.android.tools.idea.gradle.dsl" -H true !Gradle Demo Android Studio Gradle DSL Module Elements Part: command: coca arch -x "com.android.tools.idea.gradle.dsl.parser.elements" !Gradle Demo Find Bad Smells Examples Result: Code Line Count Results: Results to json Cloc by directory results csv: Cloc Top File output to: cocareporter/sortcloc.json and also: Build Deps Tree Examples Results: !Call Demo Identify Spring API !API Demo With Count or multi package: coca api -r com.macro.mall.demo.controller.,com.zheng.cms.admin.,com.phodal.pholedge -c Git Analysis Results: Concept Analyser Results Examples: Count Refs Results: Reverse Call Graph Results: !RCall Demo Auto Refactor support: rename move remove unused import remove unused class Evaluate Arduino Results(Old Version): New Version: Evaluate.json examples Todo results: coca suggest +--------+------------------+--------------------------------+ | CLASS | PATTERN | REASON | +--------+------------------+--------------------------------+ | Insect | factory | too many constructor | | Bee | factory, builder | complex constructor, too | | | | many constructor, too many | | | | parameters | +--------+------------------+--------------------------------+ coca tbs bash +---------------------+---------------------------------------------------------------+------+ | TYPE | FILENAME | LINE | +---------------------+---------------------------------------------------------------+------+ | DuplicateAssertTest | app/test/cc/arduino/i18n/ExternalProcessOutputParserTest.java | 107 | | DuplicateAssertTest | app/test/cc/arduino/i18n/ExternalProcessOutputParserTest.java | 41 | | DuplicateAssertTest | app/test/cc/arduino/i18n/ExternalProcessOutputParserTest.java | 63 | | RedundantPrintTest | app/test/cc/arduino/i18n/I18NTest.java | 71 | | RedundantPrintTest | app/test/cc/arduino/i18n/I18NTest.java | 72 | | RedundantPrintTest | app/test/cc/arduino/i18n/I18NTest.java | 77 | | DuplicateAssertTest | app/test/cc/arduino/net/PACSupportMethodsTest.java | 19 | | DuplicateAssertTest | app/test/processing/app/macosx/SystemProfilerParserTest.java | 51 | | DuplicateAssertTest | app/test/processing/app/syntax/PdeKeywordsTest.java | 41 | | DuplicateAssertTest | app/test/processing/app/tools/ZipDeflaterTest.java | 57 | | DuplicateAssertTest | app/test/processing/app/tools/ZipDeflaterTest.java | 83 | | DuplicateAssertTest | app/test/processing/app/tools/ZipDeflaterTest.java | 109 | +---------------------+---------------------------------------------------------------+------+ coca deps -p fixtures/deps/mavensample +---------------------------+----------------------------------------+---------+ | GROUPID | ARTIFACTID | SCOPE | +---------------------------+----------------------------------------+---------+ | org.flywaydb | flyway-core | | | mysql | mysql-connector-java | runtime | | org.springframework.cloud | spring-cloud-starter-contract-verifier | test | +---------------------------+----------------------------------------+---------+ bash brew install go bash export GOROOT=/usr/local/opt/go/libexec export GOPATH=$HOME/.go export PATH=$PATH:$GOROOT/bin:$GOPATH/bin git clone https://github.com/modernizing/coca go get github.com/onsi/ginkgo go get github.com/onsi/gomega `` License Arch based on Tequila Git Analysis inspired by Code Maat Test bad smells inspired by Test Smell Examples @ 2019 A Phodal Huang's Idea. This code is distributed under the MPL license. See LICENSE` in this directory.

The only video you need to Master N8N + AI agents (For complete beginners)

Serious about Implementing AI? Shortcut your Path HERE, and connect with +300 entrepreneurs on the same mission: https://www.skool.com/scrapes This is a comprehensive 4hr course with all the secrets I've learned from 8 months of building out N8N workflows for my clients (over 100+ workflows!). During this course we'll cover everything you need to shortcut your journey into building automations with N8N, AI Agents & workflow automation! 🛠️ Links (affiliate) • n8n: https://n8n.partnerlinks.io/scrapesai 📧 Curated roundups of real-world AI implementations 📧 https://scrapes-ai.kit.com/b6b1a73dfd Want more? https://www.youtube.com/@simonscrapes?sub_confirmation=1 🚧 Looking for custom built AI agents for your business? 🚧 https://automake.io 💬 Share in the comments what you learnt during the video! 0:00:00 - Course Overview 0:04:12 - SECTION 1 - Getting started 0:09:57 - 1.1. Setting up N8N 0:15:10 - 1.2. Building blocks of N8N 0:16:52 - 1.3. The N8N Canvas 0:19:02 - 1.4. Triggers & Actions 0:24:55 - 1.5. Connect nodes 0:30:09 - 1.6. Visualising Data 0:32:13 - 1.7. JSON vs Table vs Schema 0:35:12 - 1.8. Mastering Static Data 0:38:10 - 1.9. Dynamic Data 0:43:21 - 1.10. Referencing Nodes (Foolproof) 0:47:05 - 1.11. Pinning Data 0:49:26 - 1.12. Simple Retry Logic 0:52:15 - 1.13. Node Naming 0:57:38 - SECTION 2 - Building Your First Automation with Data From Your Business 0:58:45 - 2.1. Planning Your Workflow 1:02:05 - 2.2. Monitoring Your Gmail 1:04:15 - 2.3. Setting up Google Credentials 1:09:01 - 2.4. Manipulating Data with Set 1:13:11 - 2.5. Data Format Comparison (HTML, Markdown) 1:15:55 - 2.6. Your First Automation 1:20:46 - 2.7. Building an Invoice Parsing System & Tackling File Formats 1:30:42 - 2.8. Cleaning Data with Code Node 1:39:19 - 2.9. Conditionals (IF) 1:44:24 - 2.10. Multiple Inputs 1:46:04 - 2.11. Merging Data 1:50:03 - 2.12. Memory Management 1:51:15 - 2.13. Large Data Sets (Loops) 1:54:52 - 2.14. Rounding Up Our Automation 1:55:16 - SECTION 3 - Agentic Workflows & AI Agents 1:56:07 - 3.1. Agentic vs Non-Agentic Workflows 1:59:28 - 3.2. Agentic Examples You Might Use 2:05:16 - 3.3. N8N AI Nodes 2:12:55 - 3.4. AI Agents - So What Are They? 2:20:42 - 3.5. AI Agents - What Business Use Do They Have? 2:25:05 - 3.6. Setting Up AI in Our Workflow 2:27:58 - 3.7. Prompting for Beginners 2:33:29 - 3.8. Openrouter for AI Models 2:39:10 - 3.9. Getting Consistent Outputs 2:45:53 - 3.10. Rounding Up Your Invoice Parsing Workflow 2:46:49 - 3.11. Mapping Back to Your Database 2:54:00 - SECTION 4 - Data From Outside Your Business 2:59:10 - 4.1. Connecting to an API with N8N 3:01:29 - 4.2. Reading API Docs Made Easy 3:04:24 - 4.3. API Authorisation 3:06:50 - 4.4. POST Request - PDFco 3:12:47 - 4.5. Uploading Our Files via API 3:22:18 - 4.6. Completing Our API Uploads 3:25:37 - 4.7. Connect to ANY API in 2 mins 3:29:30 - 4.8. Push Data Back to Our Table 3:35:03 - SECTION 5 - Making Your Life Easy & Scalable 3:37:27 - 5.1. Naming Workflows & Tagging 3:38:43 - 5.2. Workflow Separation 3:41:11 - 5.3. Modular Design 3:48:12 - 5.4. Error Handling 3:52:31 - 5.5. Debugging (easy Mode!) 3:53:31 - 5.6. Community Nodes 3:56:31 - 5.7. N8N Template Library 3:59:14 - 5.8. Getting Help #N8N #n8ntutorial #N8NBeginner

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.

6 Best AI Tools For Business [Effortless Business Productivity]

Register at Reply.io now and get a 75% discount on the first four months using promo code ‘ANDY’: https://bit.ly/3SyU56Q. Act fast—this exclusive offer is only valid until December 31, 2023. A discount is available when you subscribe to the annual plan. Don’t miss out! Thanks to Reply io for sponsoring this video. Our sponsors help us grow the channel and keep making better videos for you. Thanks for your support! 00:00 - Intro 00:07 - #1 Reply.io 02:49 - #2 Second Nature 03:47 - #3 People AI 05:05 - #4 Dooly 06:15 - #5 TLDV 07:28 - #6 Rows LINKS ↓ Click Here To Start AI Automation:https://skool.com/aimate/about Get 1-on-1 AI Consulting: https://calendly.com/andyhafell/andy? Follow me on Twitter: https://twitter.com/theaiandy My AI Video Newsletter: https://andyhafell.ck.page/ab4b146797 Worlds #1 AI Discord Server: https://discord.gg/aTSzxrj6XY Follow on Tiktok: https://www.tiktok.com/@andyhafell Follow on Instagram: https://www.instagram.com/aiandyhafell Follow on Facebook: https://www.facebook.com/Andyhafell Follow on YouTube Shorts: https://www.youtube.com/channel/UCkLB_RfEjSZx567JaPcBRlA Email for Business Inquiries: biz@aiandy.ai

How To Build a FAST Website Using AI (Step-by-Step)

Get up to 75% off your hosting (only $2.99/mo) + 3 months FREE with Hostinger: https://www.hostinger.com/charliechang/ ^Use code CHARLIECHANG for an exclusive discount! In this video, I go over a full step-by-step guide on how to build a website using AI! I'll be showing you how to easily create a professional website using Hostinger's new AI website builder, which anyone can do without any coding or design skills. You can literally build the foundation for your website in just a few minutes. We'll also talk about how you can incorporate other tools like ChatGPT and MidJourney into the process. Free stuff 💰: ► Get up to 12 Free Stocks on WeBull when you deposit just $0.01 (valued up to $30,600): https://a.webull.com/i/CharlieChang ► Join my FREE newsletter: https://www.hustleclub.co/ Be sure to watch the entire video because we'll be covering everything you need to know, from customizing your website's design and adding content, to personalizing your website to fit your brand's identity. Their drag-and-drop interface allows you to easily arrange elements on the page and create a visually stunning website without needing any technical expertise. There are also a ton of other tools like their AI logo maker, AI writer, and even a heatmap where you can analyze where the attention will go on your website. Overall, I highly recommend using Hostinger because I've been using them for years, and it's by far the most affordable way that you can build a website in 2023. Again, you can help support the channel AND get the best exclusive deal on hosting by using this link and putting in code CHARLIECHANG at checkout: https://www.hostinger.com/charliechang I am passionate about teaching website building because I really think it's an essential skill to have. I have been building websites for over 20 years and think it's crucial for anyone that wants to start a business, or even anyone in general. If you want to learn more about building websites for your business, be sure to check out my other videos on this channel on those topics: How to Make a Website using ChatGPT 2023 (Full Tutorial): https://www.youtube.com/watch?v=LJyfhD5CUiM ChatGPT Tutorial: How to Use Chat GPT For Beginners 2023: https://www.youtube.com/watch?v=Gaf_jCnA6mc I hope you guys found this video helpful, and if you did please SHARE it with a friend or family member who you think could benefit and also LIKE and subscribe for more videos like this in the future! Thank you so much for watching, and happy website building! -Charlie #AI #WEBSITE #TUTORIAL Timeline: 0:00 - Intro 0:27 - Web Hosting 2:18 - How To Use the AI Website Builder 3:40 - Customizing Your Website 7:18 - AI Tools 8:38 - Using ChatGPT 9:51 - Using Midjourney 10:48 - Conclusion Disclaimer: Some of the links above may be affiliate links, which means that if you click on them I may receive a small commission. The retailers and financial services companies pay the commission at no cost to you, and this helps to support our channel and keep our videos free. Thank you! In addition, I am not a financial advisor. Charlie Chang does not provide tax, legal or accounting advice. The ideas presented in this video are for entertainment purposes only. Please do your own due diligence before making any financial decisions. ► My Instagram: https://www.instagram.com/charliechang

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!