VibeBuilders.ai Logo
VibeBuilders.ai

Entrepreneurship

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

From Running a $350M Startup to Failing Big and Rediscovering What Really Matters in Life ❤️
reddit
LLM Vibe Score0
Human Vibe Score1
Disastrous-Airport88This week

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

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

Looking for Feedback on this Idea
reddit
LLM Vibe Score0
Human Vibe Score1
Separate-Employer394This week

Looking for Feedback on this Idea

Hey everyone, I’d love some honest feedback on an idea I’ve been working on (currently just in paper). A little about me: I started in hospitality across South America and Asia, then moved into social entrepreneurship in a rural area, and eventually ecommerce using WordPress. Now, I’m deep into programming here in Europe, which I’ve really come to enjoy. So yes, I understand the perspective of businesses, entrepreneurs and programmers.  Back when I had tons of ideas for businesses and optimizing processes, I always hit the same drama: "You need a developer." But hiring one was too expensive or unreliable or shady business practice, and partnering with a programmer, someone I barely knew often felt too risky (I've learned the hard way that partnerships can feel like marriages). Now, as a programmer, I get a lot of requests from small businesses needing help and sometimes with very simple ideas. And while I can do it, I often don’t have the time, so I have to tell them I can't. And when I do have time, I know the cost can be too much for their budget. This got me thinking: What if I created a course to teach business owners just enough programming to solve their own problems? Not to become full time coders, but to gain enough knowledge to build simple tools or, better yet, understand code enough to ask the right questions whether it's to AI or a future developer. The course would focus on programming but talking business language, starting with building more flexible websites, managing your own content and creating custom tools without the limitations of templates or paid widgets. I’m thinking of creating a supportive community where we learn and grow together (maybe using your business as an example), and I’d be available to help along the way, plus I will be adding tools that you could reuse for your business (mostly because you will be able to read it and understand it → that's the goal). Talking about money, I can only tell you will be way more affordable compared to multiple payments in different places. So, does this resonate with you? I’d really appreciate your honest thoughts. Do you feel you have the time to learn or you still prefer looking for a developer? Feel free to share any frustrations or ideas. And if this sounds interesting, write me a PM, and I’ll keep you updated. Thanks for reading. I'm excited to hear what you think! :)

How I Started Learning Machine Learning
reddit
LLM Vibe Score0
Human Vibe Score1
TechPrimoThis week

How I Started Learning Machine Learning

Hello, everyone. As promised, I'll write a longer post about how I entered the world of ML, hoping it will help someone shape their path. I'll include links to all the useful materials I used alongside the story, which you can use for learning. I like to call myself an AI Research Scientist who enjoys exploring new AI trends, delving deeper into understanding their background, and applying them to real products. This way, I try to connect science and entrepreneurship because I believe everything that starts as scientific research ends up "on the shelves" as a product that solves a specific user problem. I began my journey in ML in 2016 when it wasn't such a popular field. Everyone had heard of it, but few were applying it. I have several years of development experience and want to try my hand at ML. The first problem I encountered was where to start - whether to learn mathematics, statistics, or something else. That's when I came across a name and a course that completely changed my career. Let's start You guessed it. It was Professor Andrew Ng and his globally popular Machine Learning course available on Coursera (I still have the certificate, hehe). This was also my first official online course ever. Since that course no longer exists as it's been replaced by a new one, I recommend you check out: Machine Learning (Stanford CS229) Machine Learning Specialization These two courses start from the basics of ML and all the necessary calculus you need to know. Many always ask questions like whether to learn linear algebra, statistics, or probability, but you don't need to know everything in depth. This knowledge helps if you're a scientist developing a new architecture, but as an engineer, not really. You need to know some basics to understand, such as how the backpropagation algorithm works. I know that Machine Learning (Stanford CS229) is a very long and arduous course, but it's the right start if you want to be really good at ML. In my time, I filled two thick notebooks by hand while taking the course mentioned above. TensorFlow and Keras After the course, I didn't know how to apply my knowledge because I hadn't learned specifically how to code things. Then, I was looking for ways to learn how to code it. That's when I came across a popular framework called Keras, now part of TensorFlow. I started with a new course and acquiring practical knowledge: Deep Learning Specialization Deep Learning by Ian Goodfellow Machine Learning Yearning by Andrew Ng These resources above were my next step. I must admit that I learned the most from that course and from the book Deep Learning by Ian Goodfellow because I like reading books (although this one is quite difficult to read). Learn by coding To avoid just learning, I went through various GitHub repositories that I manually retyped and learned that way. It may be an old-fashioned technique, but it helped me a lot. Now, most of those repositories don't exist, so I'll share some that I found to be good: Really good Jupyter notebooks that can teach you the basics of TensorFlow Another good repo for learning TF and Keras Master the challenge After mastering the basics in terms of programming in TF/Keras, I wanted to try solving some real problems. There's no better place for that challenge than Kaggle and the popular Titanic dataset. Here, you can really find a bunch of materials and simple examples of ML applications. Here are some of my favorites: Titanic - Machine Learning from Disaster Home Credit Default Risk House Prices - Advanced Regression Techniques Two Sigma: Using News to Predict Stock Movements I then decided to further develop my career in the direction of applying ML to the stock market, first using predictions on time series and then using natural language processing. I've remained in this field until today and will defend my doctoral dissertation soon. How to deploy models To continue, before I move on to the topic of specialization, we need to address the topic of deployment. Now that we've learned how to make some basic models in Keras and how to use them, there are many ways and services, but I'll only mention what I use today. For all my ML models, whether simple regression models or complex GPT models, I use FastAPI. It's a straightforward framework, and you can quickly create API endpoints. I'll share a few older and useful tutorials for beginners: AI as an API tutorial series A step-by-step guide Productizing an ML Model with FastAPI and Cloud Run Personally, I've deployed on various cloud providers, of which I would highlight GCP and AWS because they have everything needed for model deployment, and if you know how to use them, they can be quite cheap. Chose your specialization The next step in developing my career, besides choosing finance as the primary area, was my specialization in the field of NLP. This happened in early 2020 when I started working with models based on the Transformer architecture. The first model I worked with was BERT, and the first tasks were related to classifications. My recommendations are to master the Transformer architecture well because 99% of today's LLM models are based on it. Here are some resources: The legendary paper "Attention Is All You Need" Hugging Face Course on Transformers Illustrated Guide to Transformers - Step by Step Explanation Good repository How large language models work, a visual intro to transformers After spending years using encoder-based Transformer models, I started learning GPT models. Good open-source models like Llama 2 then appear. Then, I started fine-tuning these models using the excellent Unsloth library: How to Finetune Llama-3 and Export to Ollama Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth After that, I focused on studying various RAG techniques and developing Agent AI systems. This is now called AI engineering, and, as far as I can see, it has become quite popular. So I'll write more about that in another post, but here I'll leave what I consider to be the three most famous representatives, i.e., their tutorials: LangChain tutorial LangGraph tutorial CrewAI examples Here I am today Thanks to the knowledge I've generated over all these years in the field of ML, I've developed and worked on numerous projects. The most significant publicly available project is developing an agent AI system for well-being support, which I turned into a mobile application. Also, my entire doctoral dissertation is related to applying ML to the stock market in combination with the development of GPT models and reinforcement learning (more on that in a separate post). After long 6 years, I've completed my dissertation, and now I'm just waiting for its defense. I'll share everything I'm working on for the dissertation publicly on the project, and in tutorials I'm preparing to write. If you're interested in these topics, I announce that I'll soon start with activities of publishing content on Medium and a blog, but I'll share all of that here on Reddit as well. Now that I've gathered years of experience and knowledge in this field, I'd like to share it with others and help as much as possible. If you have any questions, feel free to ask them, and I'll try to answer all of them. Thank you for reading.

How I Started Learning Machine Learning
reddit
LLM Vibe Score0
Human Vibe Score1
TechPrimoThis week

How I Started Learning Machine Learning

Hello, everyone. As promised, I'll write a longer post about how I entered the world of ML, hoping it will help someone shape their path. I'll include links to all the useful materials I used alongside the story, which you can use for learning. I like to call myself an AI Research Scientist who enjoys exploring new AI trends, delving deeper into understanding their background, and applying them to real products. This way, I try to connect science and entrepreneurship because I believe everything that starts as scientific research ends up "on the shelves" as a product that solves a specific user problem. I began my journey in ML in 2016 when it wasn't such a popular field. Everyone had heard of it, but few were applying it. I have several years of development experience and want to try my hand at ML. The first problem I encountered was where to start - whether to learn mathematics, statistics, or something else. That's when I came across a name and a course that completely changed my career. Let's start You guessed it. It was Professor Andrew Ng and his globally popular Machine Learning course available on Coursera (I still have the certificate, hehe). This was also my first official online course ever. Since that course no longer exists as it's been replaced by a new one, I recommend you check out: Machine Learning (Stanford CS229) Machine Learning Specialization These two courses start from the basics of ML and all the necessary calculus you need to know. Many always ask questions like whether to learn linear algebra, statistics, or probability, but you don't need to know everything in depth. This knowledge helps if you're a scientist developing a new architecture, but as an engineer, not really. You need to know some basics to understand, such as how the backpropagation algorithm works. I know that Machine Learning (Stanford CS229) is a very long and arduous course, but it's the right start if you want to be really good at ML. In my time, I filled two thick notebooks by hand while taking the course mentioned above. TensorFlow and Keras After the course, I didn't know how to apply my knowledge because I hadn't learned specifically how to code things. Then, I was looking for ways to learn how to code it. That's when I came across a popular framework called Keras, now part of TensorFlow. I started with a new course and acquiring practical knowledge: Deep Learning Specialization Deep Learning by Ian Goodfellow Machine Learning Yearning by Andrew Ng These resources above were my next step. I must admit that I learned the most from that course and from the book Deep Learning by Ian Goodfellow because I like reading books (although this one is quite difficult to read). Learn by coding To avoid just learning, I went through various GitHub repositories that I manually retyped and learned that way. It may be an old-fashioned technique, but it helped me a lot. Now, most of those repositories don't exist, so I'll share some that I found to be good: Really good Jupyter notebooks that can teach you the basics of TensorFlow Another good repo for learning TF and Keras Master the challenge After mastering the basics in terms of programming in TF/Keras, I wanted to try solving some real problems. There's no better place for that challenge than Kaggle and the popular Titanic dataset. Here, you can really find a bunch of materials and simple examples of ML applications. Here are some of my favorites: Titanic - Machine Learning from Disaster Home Credit Default Risk House Prices - Advanced Regression Techniques Two Sigma: Using News to Predict Stock Movements I then decided to further develop my career in the direction of applying ML to the stock market, first using predictions on time series and then using natural language processing. I've remained in this field until today and will defend my doctoral dissertation soon. How to deploy models To continue, before I move on to the topic of specialization, we need to address the topic of deployment. Now that we've learned how to make some basic models in Keras and how to use them, there are many ways and services, but I'll only mention what I use today. For all my ML models, whether simple regression models or complex GPT models, I use FastAPI. It's a straightforward framework, and you can quickly create API endpoints. I'll share a few older and useful tutorials for beginners: AI as an API tutorial series A step-by-step guide Productizing an ML Model with FastAPI and Cloud Run Personally, I've deployed on various cloud providers, of which I would highlight GCP and AWS because they have everything needed for model deployment, and if you know how to use them, they can be quite cheap. Chose your specialization The next step in developing my career, besides choosing finance as the primary area, was my specialization in the field of NLP. This happened in early 2020 when I started working with models based on the Transformer architecture. The first model I worked with was BERT, and the first tasks were related to classifications. My recommendations are to master the Transformer architecture well because 99% of today's LLM models are based on it. Here are some resources: The legendary paper "Attention Is All You Need" Hugging Face Course on Transformers Illustrated Guide to Transformers - Step by Step Explanation Good repository How large language models work, a visual intro to transformers After spending years using encoder-based Transformer models, I started learning GPT models. Good open-source models like Llama 2 then appear. Then, I started fine-tuning these models using the excellent Unsloth library: How to Finetune Llama-3 and Export to Ollama Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth After that, I focused on studying various RAG techniques and developing Agent AI systems. This is now called AI engineering, and, as far as I can see, it has become quite popular. So I'll write more about that in another post, but here I'll leave what I consider to be the three most famous representatives, i.e., their tutorials: LangChain tutorial LangGraph tutorial CrewAI examples Here I am today Thanks to the knowledge I've generated over all these years in the field of ML, I've developed and worked on numerous projects. The most significant publicly available project is developing an agent AI system for well-being support, which I turned into a mobile application. Also, my entire doctoral dissertation is related to applying ML to the stock market in combination with the development of GPT models and reinforcement learning (more on that in a separate post). After long 6 years, I've completed my dissertation, and now I'm just waiting for its defense. I'll share everything I'm working on for the dissertation publicly on the project, and in tutorials I'm preparing to write. If you're interested in these topics, I announce that I'll soon start with activities of publishing content on Medium and a blog, but I'll share all of that here on Reddit as well. Now that I've gathered years of experience and knowledge in this field, I'd like to share it with others and help as much as possible. If you have any questions, feel free to ask them, and I'll try to answer all of them. Thank you for reading.

Randomly asked ChatGPT and Claude for a 4 year roadmap for an ML Engineer
reddit
LLM Vibe Score0
Human Vibe Score1
Brilliant_Fishing110This week

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

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

Randomly asked ChatGPT and Claude for a 4 year roadmap for an ML Engineer
reddit
LLM Vibe Score0
Human Vibe Score1
Brilliant_Fishing110This week

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

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

Running and selling multiple side projects alongside a 9-5
reddit
LLM Vibe Score0
Human Vibe Score1
leanpreneur1This week

Running and selling multiple side projects alongside a 9-5

My current side project started 56 days ago when I started writing 1,000 words per day. My core businesses are an agency and job board, and I just needed a creative outlet. The likes of Chris Guillebeau and Nathan Barry attribute their progression to writing so I thought I’d see if it might do the same for me. At first I was just vomiting words onto the screen, I made a blog and wrote mainly technical guides related to my skills. Over time I realised I was writing more and more about running a business as a solopreneur, or lean operator. There is tons of content out there giving you the Birds Eye of going from 0 to £10m. Inspiring stuff, but I think there is a void in real content, explaining the nuts and bolts of the how.  What is the day-to-day like for the solopreneurs who make a good living and have plenty of free time? That’s what I’m striving for anyway. I’m not talking about the 7-figure outliers. Or the ones teaching you to make content so you can have a business teaching others how to make content, and so on. I’m also sick of the ‘I made $X in 5 minutes and how you can too’  So, I started chatting to people in my network who run lean businesses and/or side hustles. I ask them a bit about their journey and ask them to teach something - how they operate, or a skill/process/system/tool that other people like you/me will find useful. One of my first chats was with Sam Dickie, who runs multiple side projects so thought I’d share here, see if others find it useful and get some feedback. I’ve removed all links as I’ve never posted on Reddit before so conscious of not being promotional, I’m posting this stuff to a tiny email list of friends with no upsells. Just finding my feet on whether others find it useful or not: — Sam is a serial entrepreneur who builds projects in his spare time whilst working a 9-5. He’s scaled and sold multiple ventures and currently runs one of the best newsletters out there for builders and entrepreneurs. Building audience through newsletters has always been a cornerstone strategy for him, so, along with sharing his advice on solopreneurism, he’s also generously shared his lean newsletter writing process. About Sam Sam is a Senior Product Manager who has spent the last 15 years working in the tech sector after starting his career as a town planner. In addition to his job he spends some of his spare time building side projects. These have included a 3D printing startup, a tech directory, a newsletter, a beta product directory, and consultancy. Sam is the epitome of making a success out of following your interest and curiosity. It’s clear he enjoys his business ventures and builds in a risk-free way.   It’s often touted by business gurus to avoid building around your interests, but Sam bucks the trend successfully. I think he’s someone who has already found his 1,000 true fans.  Descending rabbit holes, Sam’s journey of invention and curation 3D printing Sam’s first foray into launching a startup was with Fiilo, a 3D printing business. This was at the height of the 3D printing craze and he self-admits that he used the launch as an excuse to buy a 3D printer. He ended up with two and launching a product called GrowGo. GrowGo is a sustainable 3D-printed product that turns any bottle into somewhere that you can grow plants and herbs. He eventually sold this business and the printers, making around £10k. Along the way, he was exposed to various business tasks, including building a website in Weebly, the biggest nocode website builder of the time, and built an API that enabled print on demand for his product. NoCode.Tech The experiences of building as someone non-technical led to numerous friends asking how he built all of this tech. Back then, nocode wasn’t popular, and it had almost zero search volume, so Sam created a basic directory. A quick landing page on Weebly with a basic value prop, a short explanation and a list of the tools he had used before. It hit the top spot on Product Hunt, and he landed 2,000 subscribers in the first 48 hours. But, he hadn’t built it at this point, so he set about getting to work. He built the directory and list to 30,000 subs and monetised the site through advertising. At its peak with Sam, it was receiving about £2,000 per month in ad revenue. He was still working his 9-5 at this point, so thought it might be a good time to exit. The site was still growing, but it was becoming anxiety inducing whilst he was still working full-time. So, he ended up selling the site and making friend’s with the buyer. Fast forwarding a bit, Nocode.tech was eventually acquired by Stackr, a nocode app. Sam was working for their competitor at the time and ended up being offered a job by his friend who acquired the site. All of this from a side project in his area of passion. Creator Club After selling the directory, Sam lost his outlet for sharing his tools and learnings.  Being fascinated with curation and loving sifting through for nuggets, he invested more time into his personal website and launched Creator Club newsletter. Sam writes monthly and currently has over 8,000 subs. It’s one of the few newsletters that I let bypass my email filters and land in my main inbox. Life as a Part-Time Multipreneur Side Hustler If it’s not obvious already Sam is a curiosity led business creator. He’s found that the products without a revenue focus or intention have ironically outperformed those created for the sole purpose of creating money. He enjoys working on his side hustles. He could have run the Nocode.Tech for 10 more years and wouldn’t have tired of it as it’s a byproduct of his interest. For this reason, he has also created the Beta Directory, simply because he loves unearthing early-stage products. He admits he gets the fear when he thinks about quitting his 9-5, although he suspects if he devoted the same energy to one of his projects it could replace his income (no doubts from me here). This same fear means that he can run his ventures with less fear. This way, he can experiment with freedom and isn’t risking the ranch with a young family to consider. For example, recently he stopped paid sponsors on his newsletter as it was more stress than the value of the income to him. Sam divides his time on evenings and weekends (unequally) between the following: Creator Club Validation Co Beta directory Consultancy The pure side hustle status magnifies the need to run lean, let’s jump into his process…. Sam’s lean newsletter curation and creation process Starting out publishing his personal newsletter Going against his expertise, Sam originally over-engineered his process.  He curated with Feedly and tried to automate the full writing process with Zapier. The trouble is that there are too many points of failure which can lead the whole  chain to break down, and you spend more time fixing the system. For a 200 subscriber newsletter, he needed to pare things back. His set-up now Sam scaled back and now simple builds automations when he needs them. He keeps the process simple, right down to the design and any welcome automations. Keeping things real We touched on the trend that keeping things raw is better. Content has come full circle with the advent of AI. Everything looks too perfect and consequently, people’s tastes are changing. Sam mentioned watermarks that show content isn’t AI written, and we referenced content such as Greg Isenberg’s sketches, and Chris Donnelly’s image posts. \\Step by Step Process:\\ Using Stoop Inbox to manage sources Curation with Pocket Managing content with Airtable and Zapier Using Bearly to summarise Substack for writing Monitoring content sources Sam uses Stoop Inbox, an RSS curation tool, to manage his content sources. It gives him a dedicated email address for newsletters and he follows an Inbox Zero methodology. He checks in daily in Stoop, and on X, Reddit and IndieHackers. With X, he just uses the standard interface but has been careful to curate his feed, sometimes adding in extra notifications to hear from interesting people. Highlighting content When curating links, Sam uses Arc browser and the Pocket extension to save links. It’s super simple and lightweight. He creates tags which trigger an automation that curates the link to Airtable. If you watch the video, here’s a shoutout to Alice, the AI interface I use which has recently featured on Product Hunt. It’s a fantastic tool with bags of potential to enhance a solopreneur’s life. Ranking and sorting content He sends the links indexed using Pocket to a basic Airtable base via Zapier. From there, he grades the content and sets aside some time to read it in more depth. Pocket pulls through the title, metadata, and URL link. Review Sam does this manually but has used a tool as a shortcut for digesting long form content — Bearly.ai. Bearly.ai was created by Trung Phan and linking back to raw content, Trung is 1/3 of the hosts on the Not Investment Advice podcast. Its irreverent style and thumbnail are an example of a successful podcast that doesn’t over polish. Writing it all up Being a huge Notion fan (check out the free templates on his site), Sam originally used Notion for writing and linked it into Revue. When Elon sunsetted Revue, he switched to Substack. He loves the Substack interface so drafts in Substack based on a duplication of last month’s edition. Before publishing, Sam runs through a 10-point Notion checklist, which he shared with me. Parting Advice Keep your tool stack as lean as possible. Avoid tool switching to the shiny new object. Getting launched quickly is key. Don’t think that you have to be everywhere for distribution, Sam sticks with what he knows on X and LinkedIn. Overall, he advises just keeping things simple and therefore minimising risk. Resources He says they’re cliche, but I don’t agree; they’re timeless. Paul Graham of Y Combinator is someone Sam recommends following. He doesn’t write much, which is great as Sam gets anxiety when someone good often writes and he can’t keep up with the writing. His content is well thought out and distills complex concepts in entrepreneurship and startups. In addition, Sam loves Naval Ravikant’s approach. He mentions checking out the Almanac of Naval Ravikant for collected wisdom. Follow Sam’s Journey Again, not going to link here but you can find Sam’s stuff easily enough if you want to. His personal website is beautiful and contains loads of free downloads. He has also curated personal websites he admires if you need some inspiration. Sam is a super nice guy so reach out to him, I did before I started my personal blog recently, and he gave me some great advice. Also, worth keeping an eye on Validation Co, where he aims to help early-stage makers and creators validate their ideas. He’s building super slow — trying to enjoy the process without unachievable deadlines. Maintaining his stamina and passion. Amazing, I hope he writes more about that soon! -- That’s my second shot at an interview, hope you enjoyed it and found something useful in it. I’m talking to a marketplace founder who spends 2–3 hours per month his project, a multiple job board owner with a 9-5 and a leading book designer next. As this is my side project, should I keep going?

How I Built a $6k/mo Business with Cold Email
reddit
LLM Vibe Score0
Human Vibe Score1
Afraid-Astronomer130This week

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

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

I Quit My Tech Job 6 Months Ago. Built 10+ Products. Made $0. Here's Everything I Learned.
reddit
LLM Vibe Score0
Human Vibe Score1
WaynedevvvThis week

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.

Started a content marketing agency 8 years ago - $0 to $7,863,052 (2025 update)
reddit
LLM Vibe Score0
Human Vibe Score0.882
mr_t_forhireThis week

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

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

10 Side Projects in 10 Years: Lessons from Failures and a $700 Exit
reddit
LLM Vibe Score0
Human Vibe Score1
TheValueProviderThis week

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.

Why the value of writing code and other digital services is going to zero
reddit
LLM Vibe Score0
Human Vibe Score1
BalloonWheelieThis week

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

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

how I built a $6k/mo business with cold email
reddit
LLM Vibe Score0
Human Vibe Score1
Afraid-Astronomer130This week

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

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

I Quit My Tech Job 6 Months Ago. Built 10+ Products. Made $0. Here's Everything I Learned.
reddit
LLM Vibe Score0
Human Vibe Score1
WaynedevvvThis week

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.

Why the value of writing code and other digital services is going to zero
reddit
LLM Vibe Score0
Human Vibe Score1
BalloonWheelieThis week

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

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

How to get that big idea for your next business? Use trends!
reddit
LLM Vibe Score0
Human Vibe Score1
IRemember123This week

How to get that big idea for your next business? Use trends!

Hello entrepreneurs and aspiring business owners, I am Mikael and I want to share a post about how to spot business ideas. If you're wondering who the owl is, it's Agent O, my sidekick (please bear with him... or me, if you can). Let's get on to it. So, there are basically two ways of getting ideas for your new business: Find a service, product or experience that's already working. Identify and ride a trend. 🦉 : Third, have a rich relative pass you their business and sip margaritas by the sea while scrolling Reddit for the rest of your life! 🕵️ : Refrain yourself, I just got started ffs, I don't want to get banned! So, what are trends? Trends are patterns of adoption of a product, service or experience by people who want to satisfy a common need. Cool, huh? How trends start Trends emerge and evolve as temporary or permanent solutions to human needs. All products, services and experiences are the expression of human needs manifested through a perceived lack, which we humans interpret as problems. Let me make this more clear. Humans have needs: from basic (food, shelter, safety) to advanced (community, knowledge) to evolved (self actualization, spirituality) and everything in between. Don’t see this as a hierarchy, as it’s usually depicted with Maslow’s pyramid. See it as cycles with different degrees of impact on humans that vary in time and intensity. 🦉 : WHAT!?? 🕵️ : Hear me out… How Trends Affect Society Human needs are physical, emotional, intellectual and spiritual. Every day we feel the impact of those needs with different degrees of required fulfillment. You can’t go on without air for more than a few minutes. You can’t live without food and water for more than a few days. So, when it comes to the needs of the body, these have a shorter timeframe in which they need to be addressed. 🦉 : Ahh, I see what you did there… \\🕵️ \\: Thanks! But you can also live with an unfulfilled need for love or friends for a long time. You can live with a decaying health as well. And you also can live your entire life without finding out if there is a God or not. Humans perceive needs as something they lack within, which in turn is expressed as a problem on the outside. I lack food or water, this will create a problem for my survival. So I need to find food and water in my environment. This lack creates a behavior seeking a product, service or experience to fulfill that need. Makes sense? 🦉 : I just went out and got me a “Mice à la Forest” dinner! 🕵️: Bon appétit! See, Agent O fulfilled a bodily need. That’s what animals do, as they’re driven by instinct and are governed by natural laws (survive, reproduce, sleep, repeat). Humans are driven by more complex needs, as our intellect and emotions allow us to override those basic primary instincts. Why Trends Are Important What an entrepreneur does is to shift the perspective: instead of seeing a lack, he/she sees an opportunity by asking the question: how can I fulfill this need? Or, even better put: how can I help people by solving their problem? That’s the first step to solving a problem: asking a question. That is why the best products are actually problems solved by entrepreneurs who work to solve their own need for a product, service or experience. They then provide it to other people for a cost. Easy, right? That’s what entrepreneurship is: solving a problem. The bigger the problem, the bigger the impact. The bigger the impact, the higher the revenue. It’s easier to understand trends now, isn’t it? You can see that trends are nothing more than the initial adoption of a product, service or experience by a group of people who are looking for a solution to their common need. 🦉 : Did you get that from a book? 🕵️ : You snore when you sleep… ¯\\(\ツ)/\¯ 🦉 : $@#&\*! Hooman! Needs are the foundation on which the modern world is built. Once you understand needs, you fundamentally change your perception of problems into opportunities. This mental shift is the entrepreneurial mindset: where others see problems, you see solutions. Where Do Trends Start So, to recap: human needs are translated into problems. Founders understand the root of the problem (the need) and create products, services, experiences as solutions to those needs. They offer the solution to the public through startups and companies, which belong to a specific niche in a particular industry. 🦉 : Aaah, so that’s why it’s called venture capital? 🕵️ : Yeah, because you’re venturing into a new endeavor to let people know about your solution to their (and ideally your) problem. 🦉 : So if you use ads to market your venture, it’s an adventure? 🕵️ : I see what you did there… If the need behind the adoption is strong and real enough, that trend will translate into a niche within an industry. If the adoption isn’t driven by strong fundamental needs, it will turn into a fad and disappear from the perception of the public, no matter how much marketing money is thrown at it. This happens because the solution (product/service/experience) to the need didn’t create the physical, intellectual or emotional response required to create a recurring behavior around it. Remember this: Problem (why) -> Behavior (how) -> Solution (what) Understand this: there are multiple types of trends. There are product or service trends. There are industry driven trends. There are tendency driven trends, like the emergence of a new paradigm that improves a lot of industries (yes, I’m looking at you, AI). Where Do Trends Come From So now you can see that trends are patterns of adoption related to a specific human need that is addressed through one or multiple products or services. This is a bottom up direction coming from evolution. Multiple trends in different industries also emerge from a theme, which is a bigger vision of a human effort to address a high level problem. This is a top down direction, coming from implementation (by governments, different organizations or other interested parties with the power to influence changes at mass level). Conclusion Now you have a better understanding of trends by looking at them through the lens of human needs. Also, you might also understand time better because you realize that human needs have different degrees of impact in time and intensity. So you now see that trends don’t only relate to individuals, but also to groups of people, from the smallest community to countries and even global needs. That is the reason you’ll sometimes hear some say that time is a flat circle: because clothes change, but humans are quite the same. Needs don’t change a lot in time, just the way we address and solve them. Here’s an interesting game for you: take a look at some behaviors in your life. Which of them are driven by a bodily need, which by an intellectual or emotional one? Which ones are completely automated and you had no idea you were doing? How are these behaviors controlling parts of your life that you were unaware of until now? If you made it this far, thank you for taking the time to read this. I hope you enjoyed it, found it useful and entertaining. Ofc, I value your opinion and welcome it in the comments. Thank you!

How to get that big idea for your next business? Use trends!
reddit
LLM Vibe Score0
Human Vibe Score1
IRemember123This week

How to get that big idea for your next business? Use trends!

Hello entrepreneurs and aspiring business owners, I am Mikael and I want to share a post about how to spot business ideas. If you're wondering who the owl is, it's Agent O, my sidekick (please bear with him... or me, if you can). Let's get on to it. So, there are basically two ways of getting ideas for your new business: Find a service, product or experience that's already working. Identify and ride a trend. 🦉 : Third, have a rich relative pass you their business and sip margaritas by the sea while scrolling Reddit for the rest of your life! 🕵️ : Refrain yourself, I just got started ffs, I don't want to get banned! So, what are trends? Trends are patterns of adoption of a product, service or experience by people who want to satisfy a common need. Cool, huh? How trends start Trends emerge and evolve as temporary or permanent solutions to human needs. All products, services and experiences are the expression of human needs manifested through a perceived lack, which we humans interpret as problems. Let me make this more clear. Humans have needs: from basic (food, shelter, safety) to advanced (community, knowledge) to evolved (self actualization, spirituality) and everything in between. Don’t see this as a hierarchy, as it’s usually depicted with Maslow’s pyramid. See it as cycles with different degrees of impact on humans that vary in time and intensity. 🦉 : WHAT!?? 🕵️ : Hear me out… How Trends Affect Society Human needs are physical, emotional, intellectual and spiritual. Every day we feel the impact of those needs with different degrees of required fulfillment. You can’t go on without air for more than a few minutes. You can’t live without food and water for more than a few days. So, when it comes to the needs of the body, these have a shorter timeframe in which they need to be addressed. 🦉 : Ahh, I see what you did there… \\🕵️ \\: Thanks! But you can also live with an unfulfilled need for love or friends for a long time. You can live with a decaying health as well. And you also can live your entire life without finding out if there is a God or not. Humans perceive needs as something they lack within, which in turn is expressed as a problem on the outside. I lack food or water, this will create a problem for my survival. So I need to find food and water in my environment. This lack creates a behavior seeking a product, service or experience to fulfill that need. Makes sense? 🦉 : I just went out and got me a “Mice à la Forest” dinner! 🕵️: Bon appétit! See, Agent O fulfilled a bodily need. That’s what animals do, as they’re driven by instinct and are governed by natural laws (survive, reproduce, sleep, repeat). Humans are driven by more complex needs, as our intellect and emotions allow us to override those basic primary instincts. Why Trends Are Important What an entrepreneur does is to shift the perspective: instead of seeing a lack, he/she sees an opportunity by asking the question: how can I fulfill this need? Or, even better put: how can I help people by solving their problem? That’s the first step to solving a problem: asking a question. That is why the best products are actually problems solved by entrepreneurs who work to solve their own need for a product, service or experience. They then provide it to other people for a cost. Easy, right? That’s what entrepreneurship is: solving a problem. The bigger the problem, the bigger the impact. The bigger the impact, the higher the revenue. It’s easier to understand trends now, isn’t it? You can see that trends are nothing more than the initial adoption of a product, service or experience by a group of people who are looking for a solution to their common need. 🦉 : Did you get that from a book? 🕵️ : You snore when you sleep… ¯\\(\ツ)/\¯ 🦉 : $@#&\*! Hooman! Needs are the foundation on which the modern world is built. Once you understand needs, you fundamentally change your perception of problems into opportunities. This mental shift is the entrepreneurial mindset: where others see problems, you see solutions. Where Do Trends Start So, to recap: human needs are translated into problems. Founders understand the root of the problem (the need) and create products, services, experiences as solutions to those needs. They offer the solution to the public through startups and companies, which belong to a specific niche in a particular industry. 🦉 : Aaah, so that’s why it’s called venture capital? 🕵️ : Yeah, because you’re venturing into a new endeavor to let people know about your solution to their (and ideally your) problem. 🦉 : So if you use ads to market your venture, it’s an adventure? 🕵️ : I see what you did there… If the need behind the adoption is strong and real enough, that trend will translate into a niche within an industry. If the adoption isn’t driven by strong fundamental needs, it will turn into a fad and disappear from the perception of the public, no matter how much marketing money is thrown at it. This happens because the solution (product/service/experience) to the need didn’t create the physical, intellectual or emotional response required to create a recurring behavior around it. Remember this: Problem (why) -> Behavior (how) -> Solution (what) Understand this: there are multiple types of trends. There are product or service trends. There are industry driven trends. There are tendency driven trends, like the emergence of a new paradigm that improves a lot of industries (yes, I’m looking at you, AI). Where Do Trends Come From So now you can see that trends are patterns of adoption related to a specific human need that is addressed through one or multiple products or services. This is a bottom up direction coming from evolution. Multiple trends in different industries also emerge from a theme, which is a bigger vision of a human effort to address a high level problem. This is a top down direction, coming from implementation (by governments, different organizations or other interested parties with the power to influence changes at mass level). Conclusion Now you have a better understanding of trends by looking at them through the lens of human needs. Also, you might also understand time better because you realize that human needs have different degrees of impact in time and intensity. So you now see that trends don’t only relate to individuals, but also to groups of people, from the smallest community to countries and even global needs. That is the reason you’ll sometimes hear some say that time is a flat circle: because clothes change, but humans are quite the same. Needs don’t change a lot in time, just the way we address and solve them. Here’s an interesting game for you: take a look at some behaviors in your life. Which of them are driven by a bodily need, which by an intellectual or emotional one? Which ones are completely automated and you had no idea you were doing? How are these behaviors controlling parts of your life that you were unaware of until now? If you made it this far, thank you for taking the time to read this. I hope you enjoyed it, found it useful and entertaining. Ofc, I value your opinion and welcome it in the comments. Thank you!

Can AI Mentorship and Community Support Help Entrepreneurs Succeed?
reddit
LLM Vibe Score0
Human Vibe Score1
Expensive_Ad_1176This week

Can AI Mentorship and Community Support Help Entrepreneurs Succeed?

Starting a business can often feel like you're flying blind, especially without a mentor to guide you. But what if you could tap into AI-powered mentorship tools and a supportive community to get advice and feedback whenever you need it? 🚀 AI mentorship offers personalized guidance and structured frameworks, minus the need for traditional face-to-face time. And platforms like this one allow us to connect, share experiences, and learn from each other. It’s a game-changer, right? Here’s what I’m curious about: Have you tried AI mentorship tools? What was your experience? How do you currently get advice and feedback on your business? Do you think mentorship should always be face-to-face, or can online tools and communities play a big role in helping entrepreneurs succeed? Would you consider using structured learning tools (like lesson-based frameworks or step-by-step guidance) to guide your entrepreneurship journey? I’m working on Procasio, an educational entrepreneurship app designed to promote inclusivity and accessibility. It would combine AI mentorship, structured learning paths, gamified elements, and case studies, helping small business owners, teachers, students, and aspiring entrepreneurs learn effectively without overwhelming costs. 🎓💡 The app would include: Discussion posts and messaging for real-time advice. Goal setting and personalized learning recommendations. Case studies and practical scenarios to put theory into action. A low-cost, accessible approach for entrepreneurs at any stage. I’d love to hear your thoughts—do you think AI-powered mentorship and structured learning can make entrepreneurship education easier and more effective?

ai automation agency: making $200,000 a month from building automated marketing workflows
youtube
LLM Vibe Score0.355
Human Vibe Score0.41
Cody SchneiderDec 4, 2024

ai automation agency: making $200,000 a month from building automated marketing workflows

Sub to my newsletter for growth tactics and startup ideas - https://investorupdate.beehiiv.com/subscribe In the Pit Podcast with Cody Schneider Talent Fiber: Hire marketing specialists 80% less than US equivalents - https://talentfiber.com/ Swell AI: Content marketing powered by AI - https://www.swellai.com/ Drafthorse AI: Write and publish hundres of SEO for blog posts in minutes - https://www.drafthorseai.com/ Landing Cat: Build thousands of ecommerce collection pages in minutes - https://www.landingcat.com/ Summary In this episode, I chat with Michael Greenberg about AI automation in marketing services. We discuss building AI automation agencies, opportunities in productized services, and specific AI-powered marketing workflows. Michael shares insights on content creation strategies, including social media posts, podcasts, and virtual influencers. We also explore the technical aspects of implementing AI systems and the business considerations for entrepreneurs in this space. Michael provides perspectives on the challenges of running an AI automation agency and balancing experimentation with focus in entrepreneurship. Timestamps: 0:00 - Process Automation in Marketing 10:20 - Process Automation in Marketing 18:41 - AI-Powered Ghostwriting System 23:32 - Generating Content at Scale with AI 28:23 - AI Avatars and Virtual Influencers 35:13 - Creating Artificial Controversy with AI 47:35 - Balancing Experimentation and Focus in Business Host Links Personal email newsletter - https://investorupdate.beehiiv.com/subscribe https://twitter.com/codyschneiderxx https://www.linkedin.com/in/codyxschneider/ https://codyschneider.com/ https://inthepitpodcast.com/ Guest Links https://x.com/gentoftech https://www.linkedin.com/in/gentoftech/ https://www.3rdbrain.co/

Meet The AI Entrepreneur Who Used LinkedIn To Raise $13.8 Million
youtube
LLM Vibe Score0.436
Human Vibe Score0.64
ForbesApr 19, 2024

Meet The AI Entrepreneur Who Used LinkedIn To Raise $13.8 Million

Benjamin Harvey, the CEO of AI Squared, says he’s added investors including former TIAA CEO Roger Ferguson. Harvey joined Forbes senior writer, Jabari Young, at the Nasdaq MarketSite to discuss the startup’s Series A raise. Read the full story on Forbes: https://www.forbes.com/sites/jabariyoung/2024/04/17/meet-the-ai-entrepreneur-who-used-linkedin-to-raise-138-million/?sh=60958bea5837 0:00 Introduction 2:16 Benjamin Gives Biggest Tip On Learning Profit Loss 5:00 Benjamin Harvey On The State Of AI 8:25 How Will AI Evolve And Change In The Future? 14:04 What Is It Like To Be CEO Of AI Squared? 17:04 How Benjamin's Upbringing And Love Of Cartoons Helps Put Ideas Together In Business 23:02 Benjamin On Getting Investors For AI Squared 25:56 Benjamin's Take On ChatGPT And How Its Used 29:48 Artificial Intelligence: Benjamin's Take On What's Next 34:49 A Good AI Platform vs. A Great One Subscribe to FORBES: https://www.youtube.com/user/Forbes?sub_confirmation=1 Fuel your success with Forbes. Gain unlimited access to premium journalism, including breaking news, groundbreaking in-depth reported stories, daily digests and more. Plus, members get a front-row seat at members-only events with leading thinkers and doers, access to premium video that can help you get ahead, an ad-light experience, early access to select products including NFT drops and more: https://account.forbes.com/membership/?utmsource=youtube&utmmedium=display&utmcampaign=growthnon-subpaidsubscribe_ytdescript Stay Connected Forbes newsletters: https://newsletters.editorial.forbes.com Forbes on Facebook: http://fb.com/forbes Forbes Video on Twitter: http://www.twitter.com/forbes Forbes Video on Instagram: http://instagram.com/forbes More From Forbes: http://forbes.com Forbes covers the intersection of entrepreneurship, wealth, technology, business and lifestyle with a focus on people and success.

How to Start an AI Business in 2025 - STEP BY STEP
youtube
LLM Vibe Score0.45
Human Vibe Score0.72
Liam OttleyMar 3, 2024

How to Start an AI Business in 2025 - STEP BY STEP

📚 Join the #1 community for AI entrepreneurs and connect with 100,000+ members: https://bit.ly/3uRIRB3 📈 We help industry experts, entrepreneurs & developers build and scale their AI Agency: https://b.link/9kmmllts 🤝 Need AI Solutions Built? Work with me: https://b.link/qv62vqy6 ⚒️ Build AI Agents Without Coding: https://agentivehub.com/ 🚀 Apply to Join My Team at Morningside AI: https://tally.so/r/wbYr52 NOTE ON AI LIAM: AI Liam has been shut down and replaced with a free course that is updated frequently on my Free Skool community. At Morningside we no longer had the bandwidth to continue updating AI Liam with the features and info it needed, so have opted for a free course instead: https://bit.ly/3uRIRB3 I also do weekly Q&As so you can ask me questions directly! I'll see you inside, Liam 💪🏼 Learn How to Start an Online AI Business as a Beginner in 2024 with my complete, step by step guide. Making money with AI and making money with ChatGPT are huge opportunities in the online business space, but knowing whether to start an AI education business, AI Automation Agency, AI consulting business, AI SaaS or become an AI freelancer can be difficult as a beginner. If you're interested in becoming an AI entrepreneur in 2024 and starting your own AI business, this video is the one for you! I cover five different types of AI business ideas that you can start to make money online with AI, and how to get started with each. Other Resources/Links Mentioned 🔗 GPTs Complete Guide: https://youtu.be/Hh2zqaf0Fvg?si=oq5Emaf-co3nXzID Prompt Engineering Beginners Guide: https://youtu.be/ydjRYmM19DY?si=adwasE8fULHzcUYh Prompt Engineering Advanced Guide: https://youtu.be/-XivIt5oSw?si=dmhA1doWEjPI5ni Custom Tooling w/ Relevance AI: https://youtu.be/_sNGuQz-LyY?si=AJAnexuw9kDU30fF Dave's Channel (FOR AI FREELANCERS): https://www.youtube.com/@daveebbelaar Timestamps: 0:00 - Intro 3:06 - Why Listen to Me? 6:43 - Chapter 1: Is AI Business Right For You? 7:30 - Is Entrepreneurship Right For You? 11:01 - Do I Need to be a Developer? 12:01 - How Much Time do I Need to Invest? 13:57 - Why Start an AI Business? 19:58 - Chapter 2: 5 Types of AI Businesses 20:32 - AI Business #1 25:17 - AI Business #2 30:33 - AI Business #3 36:37 - AI Business #4 39:27 - AI Business #5 41:34 - How AI Businesses Are Connected 52:52 - Chapter 3: AI Business Core Skills 53:21 - Skill #1 59:52 - Skill #2 1:10:25 - Skill #3 1:22:41 - Skill #4 1:24:50 - Skill #5 1:27:49 - Skill #6 1:29:18 - Chapter 4: Step-by-Step Launch Guide

How I'd Learn AI in 2025 (if I could start over)
youtube
LLM Vibe Score0.406
Human Vibe Score0.92
Dave EbbelaarAug 4, 2023

How I'd Learn AI in 2025 (if I could start over)

Here's the roadmap that I would follow to learn artificial intelligence (AI). 📚 Get the FREE roadmap here ➡️ https://bit.ly/data-alchemy Already got tech skills and want to start as a freelancer? 🛠️ Let me show you how: https://www.datalumina.com/data-freelancer?utmsource=youtube&utmmedium=video&utmcampaign=youtubevideotraffic&utmcontent=How%20I%27d%20Learn%20AI%20in%202024%20%28if%20I%20could%20start%20over%29 ⏱️ Timestamps 00:00 Introduction 00:34 Why learn AI? 01:28 Code vs. Low/No-code approach 02:27 Misunderstandings about AI 03:27 Ask yourself this question 04:19 What makes this approach different 05:42 Step 1: Set up your environment 06:54 Step 2: Learn Python and key libraries 08:02 Step 3: Learn Git and GitHub Basics 08:35 Step 4: Work on projects and portfolio 13:12 Step 5: Specialize and share knowledge 14:31 Step 6: Continue to learn and upskill 15:39 Step 7: Monetize your skills 16:53: What is Data Alchemy? 🛠️ Explore ProjectPro https://bit.ly/3q837w8 👋🏻 About Me Hey there! I'm Dave, an AI Engineer and the founder of Datalumina, where our mission is to facilitate entrepreneurial and technological proficiency in professionals and businesses. Through my videos here on this channel, my posts on LinkedIn, and courses on Skool, I share practical strategies and tools to navigate the complexities of data, artificial intelligence, and entrepreneurship. ✔️ How I manage my business and dev projects https://try.web.clickup.com/datalumina 📥 Datalumina's Newsletter https://www.datalumina.com/newsletter #ai #roadmap #datalumina 📌 Video Description In this video, Dave shares a comprehensive and actionable roadmap for anyone looking to start their journey into the exciting world of artificial intelligence (AI) in 2024. Whether you're a complete beginner or someone looking to pivot your career towards AI, this video lays out a step-by-step guide that demystifies the process of learning AI from the ground up. Dave highlights the significance of AI in today's tech landscape and addresses common misconceptions that newcomers might have. With a focus on practical learning, the video emphasizes the importance of choosing between a code-centric or a low/no-code approach, making AI accessible to a broader audience. Dave's unique approach involves asking a critical question that shapes the learning path, ensuring that viewers embark on a journey tailored to their goals and interests. The roadmap detailed in the video covers essential steps such as setting up your learning environment, mastering Python and key libraries crucial for AI, understanding the basics of Git and GitHub, and the importance of working on projects to build a strong portfolio. Dave also talks about the importance of specialization and the continuous process of learning and upskilling in fields like generative AI, large language models, chatbots, and machine learning. Furthermore, Dave shares insights on how to monetize your AI skills, turning your passion into a profession. The video concludes with an introduction to Data Alchemy, a concept that encapsulates the transformative power of AI knowledge. For those eager to dive into the AI world, Dave offers a free roadmap accessible through the link provided in the video description. This invaluable resource serves as a compass for navigating the complexities of AI learning, making it an essential watch for anyone interested in artificial intelligence, machine learning, and related technologies.

I Tried Selling AI Art Prints On Etsy For 30 Days
youtube
LLM Vibe Score0.45
Human Vibe Score0.72
Jensen TungMay 11, 2023

I Tried Selling AI Art Prints On Etsy For 30 Days

🖼️ Sell physical art with Printful: https://www.printful.com/a/jensentung 💰 Use Elevate.Store & save $1600 when starting your business. Insane deals on Canva Pro, Wix, Mailchimp, Vistaprint, .Store Domain Name & many more: https://www.elevate.store/jensentung/1 LEARN MORE 💸 Check out my top 25 business ideas to start: https://stan.store/jensentung 👋 Book a 1:1 consulting call with me: https://stan.store/jensentung/p/call-8bmh6 STOCKS AND CRYPTO 📈 Where I invest in stocks, ETFs, and HISAs: https://interactivebrokers.com/mkt/?src=JensenNPY&url=%2Fen%2Fwhyib%2Foverview.php 💵 Where I buy Bitcoin & Crypto: https://coinbase-consumer.sjv.io/LX7Kba 💰 How I store my Bitcoin & Crypto: https://bit.ly/3NWBKfS ENTREPRENEURSHIP 💻 Shopify (Get FREE trial): https://shopify.pxf.io/PO0gYQ 👕 Printful (Print-On-Demand): https://www.printful.com/a/jensentung 🟢 Fiverr: https://go.fiverr.com/visit/?bta=574619&brand=fiverrcpa 🖼️ Kittl (Use code JENSENYT for 25% off all plans): https://kittl.pxf.io/21AZ2O ETSY 🎨 Etsy (Get 40 FREE listings): https://etsy.me/433Ombp 🐝 Everbee (Etsy Keyword Research): https://everbee.io/?via=jensen FILMMAKING 🎥 All my video gear and equipment: https://kit.co/JensenTung 🎵 Where I get my music: https://fm.pxf.io/jensenfreetrial 📝 How I take notes & manage projects: https://affiliate.notion.so/s7g8vhkbmnjf SOCIALS 🟡 Instagram: https://instagram.com/jensentung ⚪ TikTok: https://tiktok.com/@jensentung 🔵 Facebook: https://facebook.com/JensenTungOfficial 🟣 Twitch: https://twitch.tv/jensentung ⚫ Website: https://jensentung.com/ DISCLAIMER The inclusion of Interactive Brokers’ (IBKR) name, logo or weblinks is present pursuant to an advertising arrangement only. IBKR is not a contributor, reviewer, provider or sponsor of content published on this site, and is not responsible for the accuracy of any products or services discussed. VIDEO SUMMARY In this video, I share with you my experience of trying to sell physical AI art prints through Print On Demand on Etsy for 30 days. I talk about the different strategies I tried, the results I got, and what I learned. STARRING 👤 Jensen Tung: https://www.instagram.com/jensentung WEBSITES & TOOLS MENTIONED 👉 Midjourney: https://www.midjourney.com 👉 NightCafe: https://creator.nightcafe.studio/?code=JENSEN 👉 Stable Diffusion: https://youtu.be/pA-njBq1qmM 👉 Etsy (Get 40 FREE listings): https://etsy.me/433Ombp 👉 Everbee (eRank alternative that I now use): https://www.everbee.io/?via=jensen 👉 Printful: https://www.printful.com/a/jensentung 👉 Gigapixel AI: https://topazlabs.com/ref/1998