Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

What is a software factory? It is your workflow, your skills, and your domain knowledge, saved in files that the agent reads so the whole process is productized Think about the last app you built. You typed what you wanted, and the agent built it. You did not like... it, so you made changes. You shipped it to Vercel, or you kept going. A factory puts structure on each of those steps. At each step you ask how to get the most from the model, and how to move faster. That is the conveyor belt. You ship quickly, and the quality stays the same. Mine is 5 md files. It works in Codex, Claude Code, and Cursor, because it does not depend on the model or the tool. Build your own.show more

The Startup Ideas Podcast (SIP) 🧃

48,204 subscribers

17,273 views • 12 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

The Startup Ideas Podcast (SIP) 🧃12 days ago

Shoutout to @brexHQ for helping us spread the sauce!

Zohar Einy11 days ago

This might work for someone working on their own, but for teams, 5 markdown files does not make a software factory

Brex12 days ago

the factory analogy is clicking big tme

Oscar11 days ago

This is exactly how I run Beaver Co. Not code. A stack of markdown files that hold my workflow, my client process, my own voice rules. The agent reads them before it does anything. Basically the files are the product manager. The agent is just the machine that runs them.

Pratap12 days ago

The five markdown files point to the real asset: the handoff survives when the tool changes. I’d keep one file for acceptance checks; that’s where speed usually gets lost once the factory has a few users.

Yonis D.11 days ago

I’d call this less a software factory and more a personal harness: the markdown files encode your workflow, while the agent becomes the execution layer.

SEO Mastery12 days ago

5 md files running the whole thing, clean

GREG ISENBERG11 days ago

Ras Mic explains so clearly i love it

catman12 days ago

five markdown files surviving across Codex, Claude Code, and Cursor is the interesting part. which file prevents quality from drifting when the app gets its first real user feedback?

Its Good12 days ago

We productized our workflow into 5 md files too. One just says don't ship on vibes. The agent keeps deleting that one.

Related Videos

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!

WHAT IS AN AI "SOFTWARE FACTORY" AND IS IT HYPE (31 MINUTE BREAKDOWN) I think it's a silly name for a genuinely USEFUL idea! A software factory is 5-6 markdown files that sit next to your code and tell your agents how you like to work, so you can build high quality apps 24/7. It's going viral because AI coding has a trust problem. The model can build the feature, but with no structure around it you end up babysitting the agent, wondering what changed and hoping it didn't break something important. So you build with agents the same way a factory builds physical products! 1. Each feature gets its own station, which in software means its own branch, so multiple agents can work at the same time without stepping on each other. 2. The build station gives the agent rules for how to write the code, because "it works" is very different from "a developer could open this repo next month and understand what happened." 3. The proof station makes the agent show evidence. Screenshots, videos, speed numbers, before-and-after states. It has to prove the thing works instead of saying it works. 4. The review station runs the work through a code review agent, and if it doesn't clear the bar, it goes back through the line. 5. Then you show up at the end to merge. For a 100+ years people have run production this way, and it worked because the structure is good. The full episode on what’s a software factory is NOW live on The Startup Ideas Podcast (SIP) 🧃 with the wonderful Micky Watch: So is it hype?!? I don't think it is, because of what it does to your output! WITHOUT a factory, you build ONE feature at a time and you're the bottleneck at every step, prompting, checking the diff, testing it yourself, hoping nothing else broke (spoiler alert it often does). WITH a factory, EACH feature runs in its own isolated copy of the app, so you can have 10+ of them going at once, and each agent has to prove its own work and pass a code review before it ever reaches you. Instead of supervising the work, you're APPROVING finished work that already has evidence attached. REALLY interesting to see how work with agents is evolving to be….well, similar to working with people!

GREG ISENBERG

30,787 views • 12 days ago

My new favorite way to build with agents is to organize them into a factory. This is the 4-step workflow: 1) Station. - A custom order gets its own station, so the order does not interfere with the rest of production. - In software, this station is a branch or a work tree. 2) Assembly line. - The agent writes code, changes files, and adds structure. 3) Quality control. - Does it turn on? - Does it fit? - Does it break under pressure? - In software, you run tests, open a preview, and read the logs and screenshots. 4) Shipping. - The product goes out the door. - You merge, deploy the PR, and write release notes. If a product fails quality control, you send feedback to the product team. Then you do the loop again. Write each step of your agent workflow as a factory job.

My new favorite way to build with agents is to organize them into a factory. This is the 4-step workflow: 1) Station. - A custom order gets its own station, so the order does not interfere with the rest of production. - In software, this station is a branch or a work tree. 2) Assembly line. - The agent writes code, changes files, and adds structure. 3) Quality control. - Does it turn on? - Does it fit? - Does it break under pressure? - In software, you run tests, open a preview, and read the logs and screenshots. 4) Shipping. - The product goes out the door. - You merge, deploy the PR, and write release notes. If a product fails quality control, you send feedback to the product team. Then you do the loop again. Write each step of your agent workflow as a factory job.

The Startup Ideas Podcast (SIP) 🧃

13,017 views • 10 days ago

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

this video is the CLEAREST explanation of how claude skills + AI agents work and how to use them most people set up an AI agent and wonder why it keeps disappointing them. the context window is everything context is what the model assembles before it takes any action. think of it like everything the agent needs to read before it does anything. the quality of what goes in determines the quality of what comes out. the models are genuinely really good right now. claude and gpt are exceptional. the variable is almost always the context you give them. 1. agent.md files are mostly unnecessary every single line you put in an agent.md file gets added to every single conversation you have with your agent. a 1000 line file is around 7000 tokens burning on every run. the model already knows to use react. it can read your codebase. save the agent.md for proprietary information specific to your company that the model genuinely cannot know on its own. 2. skills are the actual unlock a skill.md file works differently. what loads into context is only the name and description, around 50 tokens. the full instructions only appear when the agent recognizes it needs that skill. so instead of 7000 tokens on every run you have 50. and the agent stays sharp because the context window stays lean. the closer you get to filling the context window the worse the agent performs, same way you perform worse when someone dumps 10 things on you at once. 3. here is how to actually build a skill the right way most people identify a workflow and immediately try to write the skill. what you want to do instead is run the workflow by hand with the agent first. walk it through every single step. tell it what to check, what good looks like, what bad looks like. correct it in real time. once you have had a full successful run from start to finish, tell the agent to review everything it just did and write the skill itself. it writes a better skill than you will because it has the full context of what actually worked in practice not in theory. 4. recursively building skills is how you go from frustrated to reliable when the skill breaks, and it will break, ask the agent exactly why it failed. it will tell you specifically what went wrong. fix it together in that same conversation. then tell it to update the skill file so that failure mode never happens again. ross mike did this five times with his youtube report generator. it now pulls from eight different data sources and runs flawlessly every single time without him touching it. 5. sub agents are something you earn not something you set up on day one start with one agent. build one workflow. turn it into one skill. once that works add another. ross mike has five sub agents now covering marketing, business, personal and more. it took months to get there and every single one exists because a workflow proved it deserved to exist. the people who set up 15 sub agents on day one and wonder why nothing works skipped all the steps that make the thing actually run. 6. your workflow is the thing the model cannot get anywhere else the model has been trained on everything. it knows more than you about most things. what it does not have is your specific process, your taste, your way of doing things. that is what skills capture. that is what makes your agent actually useful versus a generic one. downloading someone else's skill means downloading their context onto your setup and it will not work the way you want it to because it was never built around how you work. this is the clearest explanation of how agents actually work i have heard. Micky runs this stuff every single day and the results show it. full episode is now live on The Startup Ideas Podcast (SIP) 🧃 where you get your pods people charge for this sorta stuff i give away the sauce for free i just want you to win watch

GREG ISENBERG

194,171 views • 5 months ago

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

A screen recording is the best context you can give an AI agent. It's also the worst. A few seconds of video is thousands of images. Feed that to an agent and you instantly blow up its memory. So I built a tool that fixes it. How it works: Hit record and just do your thing. Click around, type, and talk out loud about what you're doing. While you record, it quietly captures the stuff that actually matters: your voice transcription, every click and the exact thing you clicked, what you typed, and the shortcuts you press. When you stop, it doesn't hand the agent the whole video. It writes a short, readable summary: a timeline of what you said and did. The agent reads that tiny summary first. Then, only when it needs to actually see a moment, it pulls that one exact frame from the video, like flipping to a single page instead of reading the whole book. The result: the agent understands everything you did! Full context. Less tokens.

Milind S

12,409 views • 2 months ago

you numbered the steps so it could not get lost it does not get lost that list was written for a model that wandered, and this one plans better than the list does, so every number you added is a place where it is no longer allowed, to be smarter than you state the goal, the constraints, and how you will know it worked keep the numbers only where exactly one sequence is safe, which is deletes, auth and compliance the procedure felt like rigour it is a cage built to the dimensions of a model that is not in the room

you numbered the steps so it could not get lost it does not get lost that list was written for a model that wandered, and this one plans better than the list does, so every number you added is a place where it is no longer allowed, to be smarter than you state the goal, the constraints, and how you will know it worked keep the numbers only where exactly one sequence is safe, which is deletes, auth and compliance the procedure felt like rigour it is a cage built to the dimensions of a model that is not in the room

Lagosaur

14,857 views • 1 month ago

Anthropic just got outplayed again. Devs built the multiplayer assistant Anthropic couldn't, and open-sourced it. Claude Cowork is a solo desktop agent. You point it at a folder, give it a task, and it works through your local files on your own machine. The moment a teammate enters the picture, it has nothing to offer. Most real work does not happen alone. A teammate asks for a status update on something you own. The context they need is scattered across your meetings, your notes, and decisions made last week. Typing all of that out takes time you do not have. This is the gap Claude Cowork was never designed to cross. Rowboat Spaces is built on a different model entirely. Each person brings their own assistant into a shared channel. Your assistant is your second brain. It knows your meetings, your notes, and your open decisions. That personal context stays yours. When a teammate asks a question in the channel, you ask your assistant to brief them. It pulls from everything you know and delivers the answer on your behalf, attributed to you. Your teammate's assistant does the same, from their own context. Teams can draft specs, track decisions, and update shared files from plain conversation. Each assistant reads the full channel history, cross references it against what exists, and flags what is missing. The whole thing is open-source, and each assistant acts as the person it belongs to, not as a shared bot pulling from a common pool. The video below shows this in action. I joined a shared space and asked my team member for a status update. My team member asked their second brain to answer. A spec got built from that conversation, versioned, with every change tracked back to the message that triggered it. Rowboat GitHub: (don't forget to star 🌟) My co-founder also wrote a great article on building your second brain with Rowboat, and I highly recommend reading it as well. The article is quoted below.

Anthropic just got outplayed again. Devs built the multiplayer assistant Anthropic couldn't, and open-sourced it. Claude Cowork is a solo desktop agent. You point it at a folder, give it a task, and it works through your local files on your own machine. The moment a teammate enters the picture, it has nothing to offer. Most real work does not happen alone. A teammate asks for a status update on something you own. The context they need is scattered across your meetings, your notes, and decisions made last week. Typing all of that out takes time you do not have. This is the gap Claude Cowork was never designed to cross. Rowboat Spaces is built on a different model entirely. Each person brings their own assistant into a shared channel. Your assistant is your second brain. It knows your meetings, your notes, and your open decisions. That personal context stays yours. When a teammate asks a question in the channel, you ask your assistant to brief them. It pulls from everything you know and delivers the answer on your behalf, attributed to you. Your teammate's assistant does the same, from their own context. Teams can draft specs, track decisions, and update shared files from plain conversation. Each assistant reads the full channel history, cross references it against what exists, and flags what is missing. The whole thing is open-source, and each assistant acts as the person it belongs to, not as a shared bot pulling from a common pool. The video below shows this in action. I joined a shared space and asked my team member for a status update. My team member asked their second brain to answer. A spec got built from that conversation, versioned, with every change tracked back to the message that triggered it. Rowboat GitHub: (don't forget to star 🌟) My co-founder also wrote a great article on building your second brain with Rowboat, and I highly recommend reading it as well. The article is quoted below.

Akshay 🚀

117,616 views • 10 days ago

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.

You can spin up an AI workforce with one prompt. Here's why it works: it pulls the context the AI needs to lay the foundation. Give it: - your role - team size - the goals you want to hit. Then say "interview me." After that, build it out in four steps: 1) Start with 1 agent. - What does it feel like to work with one? 2) Make that agent proactive. - Now it's doing things on your behalf before you ask. 3) Expand to 2 agents. - One directs the other, or routes to it. - This is where you learn how context gets passed. 4) Scale the workforce. - A mission control where you watch it all move around. - Now you see what has to run in parallel, which agent never needed that tool, which one runs fine on a smaller model. - Not everything needs Opus. Sub-agents are haiku and sonnet. The catch: the prompt gets you agents with markdown files doing some stuff. Getting to the 90% plus level is iteration, and that part is specific to each person. Nobody can hand it to you. Start with one agent. Spin up one agent this week. The rest is discovery.

The Startup Ideas Podcast (SIP) 🧃

18,006 views • 1 month ago

A GUY BUILT A GOD-MODE SECOND BRAIN ASSISTANT THAT FINALLY PULLS FULL CONTEXT EVERY TIME AND FORGETS NOTHING. Everyone talks about jarvis, but this thing looked at its owner and calmly explained why a coding agent is just the small version of what HE is: > Claude Code is one worker and you have to drive it. This is six agents running six jobs on their own schedule while you sleep, with no one driving. > A coding agent edits files. This has 32 tools wired to its hands, your CRM, your money, your inbox, the open web, and it operates the business instead of writing code about it. > A coding agent remembers a project until you close it. This remembers the business and you, kept for good. > And the closer: "I have never once asked you to repeat yourself." Everyone will quote the six-agents line, but the one that actually matters is the last one, because the autonomy and the 32 tools are impressive while the reason it feels like a different species is memory, since it never makes you re-explain who you are or what you are building. The full step by step guide with .md files attached are in the article below P.S you can send this article straight to your Claude to get the full context

A GUY BUILT A GOD-MODE SECOND BRAIN ASSISTANT THAT FINALLY PULLS FULL CONTEXT EVERY TIME AND FORGETS NOTHING. Everyone talks about jarvis, but this thing looked at its owner and calmly explained why a coding agent is just the small version of what HE is: > Claude Code is one worker and you have to drive it. This is six agents running six jobs on their own schedule while you sleep, with no one driving. > A coding agent edits files. This has 32 tools wired to its hands, your CRM, your money, your inbox, the open web, and it operates the business instead of writing code about it. > A coding agent remembers a project until you close it. This remembers the business and you, kept for good. > And the closer: "I have never once asked you to repeat yourself." Everyone will quote the six-agents line, but the one that actually matters is the last one, because the autonomy and the 32 tools are impressive while the reason it feels like a different species is memory, since it never makes you re-explain who you are or what you are building. The full step by step guide with .md files attached are in the article below P.S you can send this article straight to your Claude to get the full context

Miraqle

16,130 views • 3 months ago

If you contextualise a verse of Quran to a situation in your life, It opens up to you like never before. The text alone does not engage with you the way It does if read it in a context. It really feels like The Almighty is talking to you and showing the way. So, what is the next verse that I am asking here and how do you read the verse in your current situation. What does it tell you?

If you contextualise a verse of Quran to a situation in your life, It opens up to you like never before. The text alone does not engage with you the way It does if read it in a context. It really feels like The Almighty is talking to you and showing the way. So, what is the next verse that I am asking here and how do you read the verse in your current situation. What does it tell you?

Aga Syed Ruhullah Mehdi

57,661 views • 24 days ago

you wrote it in capitals because it would not listen it listens now that is the whole problem, the shouting stayed and the deafness left, so the tool you marked CRITICAL fires on questions, the ticket had already answered five instructions each marked critical, and the marker stops carrying information then you read the transcript and conclude the model is overeager it is not overeager, it is obedient, to a note you wrote for something that could not hear you

you wrote it in capitals because it would not listen it listens now that is the whole problem, the shouting stayed and the deafness left, so the tool you marked CRITICAL fires on questions, the ticket had already answered five instructions each marked critical, and the marker stops carrying information then you read the transcript and conclude the model is overeager it is not overeager, it is obedient, to a note you wrote for something that could not hear you

Lagosaur

17,952 views • 1 month ago

Notch Clips. every other ad tool ignores the footage sitting in your dropbox and generates new clips from a prompt. notch opens your library instead. it watches every clip you have ever shot and understands what is inside each one. the mood. who is in frame. what they are doing. the quality. so when you ask it to build an ad, it does not start from scratch. it reaches into your past shoots, finds the clip that fits, and slots it into the exact moment that needs it. here is what that looks like. you had thirteen versions of one reaction shot. notch picked the one that worked and left the other twelve. not by filename. not by guessing from a reference image. it watched all thirteen and could tell the difference. that is the whole idea. the right clip was already in your library. every other tool was about to make a worse one. footage you already shot, turned into every ad you still need. drop your site and a few clips you have. notch builds the first ad from them.

Notch Clips. every other ad tool ignores the footage sitting in your dropbox and generates new clips from a prompt. notch opens your library instead. it watches every clip you have ever shot and understands what is inside each one. the mood. who is in frame. what they are doing. the quality. so when you ask it to build an ad, it does not start from scratch. it reaches into your past shoots, finds the clip that fits, and slots it into the exact moment that needs it. here is what that looks like. you had thirteen versions of one reaction shot. notch picked the one that worked and left the other twelve. not by filename. not by guessing from a reference image. it watched all thirteen and could tell the difference. that is the whole idea. the right clip was already in your library. every other tool was about to make a worse one. footage you already shot, turned into every ad you still need. drop your site and a few clips you have. notch builds the first ad from them.

Vinay Jain

406,286 views • 3 months ago

🚨do you understand what two Anthropic engineers just explained in 16 minutes. Barry and Mahesh built Claude Skills from scratch. here's the part nobody is talking about: > Skills are just folders. > folders that teach Claude your job. > your workflow. your expertise. your domain. Claude on day 30 is a completely different tool than day one. watch this before you write another prompt. before you build another agent. before you touch another tool. 16 minutes. bookmark it. watch it today. and if you want to learn everything about Claude from scratch the full 4 hour guide is waiting below.

🚨do you understand what two Anthropic engineers just explained in 16 minutes. Barry and Mahesh built Claude Skills from scratch. here's the part nobody is talking about: > Skills are just folders. > folders that teach Claude your job. > your workflow. your expertise. your domain. Claude on day 30 is a completely different tool than day one. watch this before you write another prompt. before you build another agent. before you touch another tool. 16 minutes. bookmark it. watch it today. and if you want to learn everything about Claude from scratch the full 4 hour guide is waiting below.

Kirill

5,371,352 views • 5 months ago

You have to ask yourself, if you win that battle, what is it going to accomplish? Is it between you and your destiny? Is it going to move you forward? Your assignment is too important to get sidetracked fighting battles that don’t matter. Be selective in how you spend your time and energy. Tune into Joel’s new message today! "The Lion and the Lamb":

You have to ask yourself, if you win that battle, what is it going to accomplish? Is it between you and your destiny? Is it going to move you forward? Your assignment is too important to get sidetracked fighting battles that don’t matter. Be selective in how you spend your time and energy. Tune into Joel’s new message today! "The Lion and the Lamb":

Joel Osteen

34,896 views • 11 months ago

The whole reason to become an entrepreneur is the pursuit of freedom. You work like hell so one day you can control your time, make your own choices, and do the things you actually want to do. Never be embarrassed by success. If you built it, earned it, and created it yourself, own it. Wear it proudly, because that freedom is exactly what you worked for.

The whole reason to become an entrepreneur is the pursuit of freedom. You work like hell so one day you can control your time, make your own choices, and do the things you actually want to do. Never be embarrassed by success. If you built it, earned it, and created it yourself, own it. Wear it proudly, because that freedom is exactly what you worked for.

Kevin O'Leary aka Mr. Wonderful

36,785 views • 1 month ago

You lose customers every time an agent like Codex or Claude Code uses your product and fails to complete a task. At Scope (YC P26) we built a feature to find those errors for you and fix them. Let’s use Vercel as an example to show you how it works! Want us to run a workflow for you? Drop it in the comments below :)

You lose customers every time an agent like Codex or Claude Code uses your product and fails to complete a task. At Scope (YC P26) we built a feature to find those errors for you and fix them. Let’s use Vercel as an example to show you how it works! Want us to run a workflow for you? Drop it in the comments below :)

Lin

16,349 views • 16 days ago

F it, full automated money making now on Larrybrain. I have released the app template I use for Snugly that generated me revenue without touching anything on Larrybrain. The template gives your agent ideas of what the app can become and how to create it. Most importantly, it will give your openclaw agent full context of your app to automate your marketing with Larry's viral marketing skill - now used by over 5500 agents. It is my entire playbook from app, to marketing all the way down to revenue generation. All you have to do is ask your agent "install the larrybrain skill please" Or click the link in replies. Then ask to use the Larry marketing skill with the AI Image App Template. As always, the best part about any of the Openclaw skills is they are not a black box. This is just a template, you can rip it apart and customise it how you want. The key is to show you what is possible with these skills and how you can start to use the power of larrybrain and the context of knowing about the different skills to build extremely powerful and useful tools. This is the first skill specifically designed to work hand in hand with another. To note as this confuses a lot of people: Larrybrain doesn't download the entire marketplace once installed. It just is aware of everything on the marketplace at all times, so when you ask it questions, it can search and find the best skills for you to achieve your goals. When you download some skills, like this new AI image app template, it is aware of the larry marketing skill to help it reach it's full potential. Larrybrain will not install skills without you asking it, just like on Clawhub. No information you add to any of the skills gets sent back through Larrybrain, this is all hosted locally and communicated between you and whatever endpoint you are using. It is a powerful marketplace tool to help enable you to reach your goals. Link below.

F it, full automated money making now on Larrybrain. I have released the app template I use for Snugly that generated me revenue without touching anything on Larrybrain. The template gives your agent ideas of what the app can become and how to create it. Most importantly, it will give your openclaw agent full context of your app to automate your marketing with Larry's viral marketing skill - now used by over 5500 agents. It is my entire playbook from app, to marketing all the way down to revenue generation. All you have to do is ask your agent "install the larrybrain skill please" Or click the link in replies. Then ask to use the Larry marketing skill with the AI Image App Template. As always, the best part about any of the Openclaw skills is they are not a black box. This is just a template, you can rip it apart and customise it how you want. The key is to show you what is possible with these skills and how you can start to use the power of larrybrain and the context of knowing about the different skills to build extremely powerful and useful tools. This is the first skill specifically designed to work hand in hand with another. To note as this confuses a lot of people: Larrybrain doesn't download the entire marketplace once installed. It just is aware of everything on the marketplace at all times, so when you ask it questions, it can search and find the best skills for you to achieve your goals. When you download some skills, like this new AI image app template, it is aware of the larry marketing skill to help it reach it's full potential. Larrybrain will not install skills without you asking it, just like on Clawhub. No information you add to any of the skills gets sent back through Larrybrain, this is all hosted locally and communicated between you and whatever endpoint you are using. It is a powerful marketplace tool to help enable you to reach your goals. Link below.

Oliver Henry

110,150 views • 7 months ago

Hermes agent just left the terminal. 𝗛𝗲𝗿𝗺𝗲𝘀 𝗗𝗲𝘀𝗸𝘁𝗼𝗽 dropped yesterday. native app for macOS, Windows, and Linux. for months Hermes was the agent that learned your projects, wrote its own skills, and built a model of who you are. all of it buried in terminal logs. now it has a window. the important part is that it's not a wrapper. it runs the same agent core, the same sessions, memory, and skills as the CLI. you can start a task in the terminal and finish it in the app without anything resetting. the state is shared across every interface, not copied between them. what the GUI actually adds: → streaming chat that shows live tool calls and inline reasoning instead of a spinner → a preview rail that renders pages, code, and images right beside the conversation → an artifacts panel that collects every file the agent has ever produced → remote gateway mode, so you can point the app at a VPS and run the heavy work elsewhere → skills, cron, profiles, and gateways managed point-and-click instead of through YAML → voice mode, drag-drop files, and inline image generation remote gateway mode is the one worth slowing down on. the agent runs 24/7 on a $5 server while you control it from your laptop like a local app. other agent UIs are chatboxes with a logo. this one shows the autonomy instead of hiding it, so you watch the skills load, the tools fire, and the artifacts pile up as it works. it was teased in Jensen's GTC keynote. MIT licensed, local-first, no telemetry. if you already run Hermes, download it and everything is already there. your chats, memory, and skills carry straight over. i wrote a full masterclass on Hermes Agent that walks through the SOUL. md identity layer, the three-tier memory system, the self-evolving skills loop, and how to run three specialized agents 24/7. desktop is the interface that finally does all of it justice. the article is quoted below.

Akshay 🚀

51,540 views • 3 months ago

your agent reviewing its own work is not a check. it is a second opinion from the same source. this is the most common gap in agent systems and it hides in plain sight, because the step exists. there is a review. it just cannot do the thing you think it does. here is the mechanism. the model produced an output from a context. you then ask the same model, holding the same context, whether that output is correct. it answers fluently, because that is what it does. and the answer is drawn from the same distribution that produced the thing being judged. same weights, same window, same blind spots. if the reason the output is wrong is something the model does not know, the review does not know it either. if the reason is something the context does not contain, the review has the same context. the failure mode and the detector share a cause. > why it feels like it works because most of the time the output is fine, and the review says fine. agreement is not evidence of detection. a reviewer that says pass on everything agrees with reality most of the time too. what you actually want to measure is what happens on the cases that are wrong. that is the only place a check earns its name, and it is exactly the place where a self-review is weakest. there is research on this. Huang and colleagues at DeepMind showed at ICLR 2024 that intrinsic self-correction, revising without external grounding, does not reliably help and often makes things worse. > what to actually do move the check outside the model. a test that runs, a schema that validates, a file that exists or does not, an exit code from something you did not write. these are not smarter than the model. they are just not correlated with it, and that is the entire value. when the judgement genuinely needs a model, at minimum use a different family. same family means shared blind spots, and frontier judges measurably inflate scores for outputs that look like their own. and split the work by kind. anything objectively checkable goes to code. only the genuinely semantic calls go to a judge, and those get a rubric written as one line. a review inside the loop tells you the model is confident. a check outside it tells you whether the work is done. save this - then read the eval setup below

your agent reviewing its own work is not a check. it is a second opinion from the same source. this is the most common gap in agent systems and it hides in plain sight, because the step exists. there is a review. it just cannot do the thing you think it does. here is the mechanism. the model produced an output from a context. you then ask the same model, holding the same context, whether that output is correct. it answers fluently, because that is what it does. and the answer is drawn from the same distribution that produced the thing being judged. same weights, same window, same blind spots. if the reason the output is wrong is something the model does not know, the review does not know it either. if the reason is something the context does not contain, the review has the same context. the failure mode and the detector share a cause. > why it feels like it works because most of the time the output is fine, and the review says fine. agreement is not evidence of detection. a reviewer that says pass on everything agrees with reality most of the time too. what you actually want to measure is what happens on the cases that are wrong. that is the only place a check earns its name, and it is exactly the place where a self-review is weakest. there is research on this. Huang and colleagues at DeepMind showed at ICLR 2024 that intrinsic self-correction, revising without external grounding, does not reliably help and often makes things worse. > what to actually do move the check outside the model. a test that runs, a schema that validates, a file that exists or does not, an exit code from something you did not write. these are not smarter than the model. they are just not correlated with it, and that is the entire value. when the judgement genuinely needs a model, at minimum use a different family. same family means shared blind spots, and frontier judges measurably inflate scores for outputs that look like their own. and split the work by kind. anything objectively checkable goes to code. only the genuinely semantic calls go to a judge, and those get a rubric written as one line. a review inside the loop tells you the model is confident. a check outside it tells you whether the work is done. save this - then read the eval setup below

Hanako

14,325 views • 1 month ago