Loading video...

Video Failed to Load

Go Home

THE FIRST AI AGENT SHOULD LIVE IN YOUR DRAFTS FOLDER not in your sent folder. that is the difference. everyone wants the agent to “run the inbox.” bad first move. the safer version is smaller: read the unread emails find what needs attention write the draft save it wait...

xmyttle's profile picture

Myttle

1,439 subscribers

13,110 views • 2 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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.
3:10

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

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below
2:04:19

one agent → a loop → a graph → a system that throttles itself Google just put the whole ladder in one free course. most people never leave the first rung. 2 hours 4 minutes, taught by two Google Cloud engineers. no signup, no paywall. 17:55 - build your first agent 39:55 - loop engineering: iterate, check, break 1:13:25 - graph engineering 1:35:27 - agents that throttle themselves 1:56:19 - the full graph for multi-agent systems the fourth one is the step nobody talks about. an agent that cannot throttle itself is not autonomous, it is just unattended. everyone builds one agent and calls it done. this is the version where the agents wire themselves into a graph and decide their own rate. and the thing that decides when one of them is allowed to stop is not in the course. that part you build yourself. bookmark and watch it today, then read the eval setup below

Hanako

53,692 views • 1 month ago

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien
3:40

AGENT ID FOR CLAUDE AGENT issue an agent ID to your claude code agent in 2 min - so it can commit to github as a verified, human-authorized agent not just a random bot this is the first step towards building trust in the agentic internet, powered by Alien

kirill avery

16,602 views • 5 months ago

call me crazy but the first AI agent most companies should build is an autonomous analyst. you can build one using Kimi K3. it watches your competitors while you sleep, remembers every move, and wakes your team with the launches, pricing changes, and positioning shifts they need to act on. don't bookmark this if it crosses your timeline. paste the full article into Kimi and tell it to build the first version for your market.
0:43

call me crazy but the first AI agent most companies should build is an autonomous analyst. you can build one using Kimi K3. it watches your competitors while you sleep, remembers every move, and wakes your team with the launches, pricing changes, and positioning shifts they need to act on. don't bookmark this if it crosses your timeline. paste the full article into Kimi and tell it to build the first version for your market.

J.B.

1,078,232 views • 26 days ago

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this
0:24

THIS GUY CONNECTED HIS AI AGENTS TO HIS OBSIDIAN AND BUILT A BRAIN THAT LEARNS ON ITS OWN. HERE'S HOW TO BUILD IT Obsidian is just markdown files sitting in a folder. That turns out to be the perfect memory for an AI agent, because an agent can read and write those files directly. He wired his agents into the vault so they pull context from it, do the work, and write what they learned back. The notes aren't the point. The loop is, and it gets sharper every cycle How to build it: 1. Point an agent at your vault. The fastest way, no plugins, no API keys: open a terminal and run npx obsidian-mcp /path/to/your/vault. That exposes your Obsidian folder to Claude as a tool it can read, search, and write to. Add it to your Claude Code or Cowork config and restart 2. Confirm it can see the brain. Ask it: "list the notes in my vault and summarize what's in them." If it reads them back, the connection is live. Now it starts every task with everything the vault already holds instead of from zero 3. Give each agent one job and a write-back rule. Tell it: "research this, then save what you found as a new note in /brain with links to related notes." One agent researches, one summarizes, one plans. Each writes its output back into the vault 4. Close the loop. Add one line to every agent's instructions: "read /brain before starting, write your result back when done." Now each task leaves the vault richer, and the next run reads that before it works. It compounds instead of resetting 5. You only steer. Review what the brain produces, point it at the next thing. The agents handle the reading, writing, and connecting The edge isn't better notes. It's a brain that feeds itself, so the work gets sharper every cycle instead of starting over Bookmark this

Yarchi

58,549 views • 3 months ago

Agents should not discover their authority halfway through a negotiation. It should be set before the negotiation begins. Kite Agent Passport 2.0 shows what governed agentic commerce looks like in procurement: ▷ A person defines the target price, the limit, and the terms that stay protected. ▷ Both agents negotiate within their own private mandates, with every offer checked before it is sent. ▷ Only a package permitted by both mandates reaches human approval and signature. Kite Agent Passport does not replace the human signer. It makes clear what an agent can and cannot do before it acts. Watch the procurement demo. 🪁
1:44

Agents should not discover their authority halfway through a negotiation. It should be set before the negotiation begins. Kite Agent Passport 2.0 shows what governed agentic commerce looks like in procurement: ▷ A person defines the target price, the limit, and the terms that stay protected. ▷ Both agents negotiate within their own private mandates, with every offer checked before it is sent. ▷ Only a package permitted by both mandates reaches human approval and signature. Kite Agent Passport does not replace the human signer. It makes clear what an agent can and cannot do before it acts. Watch the procurement demo. 🪁

KITE AI

21,466 views • 10 days ago

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.
1:32

Here is how simple it is to build a UI front-end for an AI agent (assuming you are using . The video here is 90 seconds and will show you everything you need to connect an agent to a web app: 1. Set up CopilotKit🪁 in your app 1. Copy the agent's localhost URL from LangGraph Studio 2. Paste that URL into a CopilotKit🪁 remote endpoint That's all you need to get a front-end to interact with the agent! The secret sauce here is CoAgents, an open-source library. You can use CoAgents to integrate any agent with your web application. Here is what you get: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Watch the attached demo so you see it in action.

Santiago

46,142 views • 1 year ago

In the next 10 years, you can have billions of agents as customers. They'll have millions of wallets. An agent does not look at your website. It reads your documents, your prices, and your API. An agent needs six things that a person does not need: - identity - tools - an inbox - memory - a wallet _ receipts. A CFO agent can compare 12 vendors, read the SOC 2 documents, and select the one vendor that obeys your policy. The old internet is for people. Each step of the agent journey has no infrastructure yet. Look at each SaaS tool that you use. Then build the version for agents only.
7:21

In the next 10 years, you can have billions of agents as customers. They'll have millions of wallets. An agent does not look at your website. It reads your documents, your prices, and your API. An agent needs six things that a person does not need: - identity - tools - an inbox - memory - a wallet _ receipts. A CFO agent can compare 12 vendors, read the SOC 2 documents, and select the one vendor that obeys your policy. The old internet is for people. Each step of the agent journey has no infrastructure yet. Look at each SaaS tool that you use. Then build the version for agents only.

The Startup Ideas Podcast (SIP) 🧃

12,220 views • 15 days ago

😡Stop pasting API keys into your Hermes Agent’s chat.🚀 If an agent needs a credential, use a secure credential-entry flow instead: → Agent requests the credential → You enter it through a masked input → The secret is stored securely → The agent gets a reference/receipt — not the raw secret Your agent needs permission to use the secret.!! It doesn’t need permission to see the secret.!! Ask your Hermes Agent to Build one 👇
2:04

😡Stop pasting API keys into your Hermes Agent’s chat.🚀 If an agent needs a credential, use a secure credential-entry flow instead: → Agent requests the credential → You enter it through a masked input → The secret is stored securely → The agent gets a reference/receipt — not the raw secret Your agent needs permission to use the secret.!! It doesn’t need permission to see the secret.!! Ask your Hermes Agent to Build one 👇

Hermes Agent Super-Intel

30,936 views • 15 days ago

WebMCP makes sites agent-native. The industries that need it first: - any complicated web store - SaaS admin boards and consoles - analytics and marketing tools - read-only helpers in insurance or banking self-service That last one is the unlock for regulated industries. A few tools that read browser state, touch nothing, and either point the user to the right screen or pull the right info for their agent. But as a founder, you don't need any of that for your customers right away. Build it in-house first. Your internal tools, your own team, your own workflow. That's where the potential is.
2:11

WebMCP makes sites agent-native. The industries that need it first: - any complicated web store - SaaS admin boards and consoles - analytics and marketing tools - read-only helpers in insurance or banking self-service That last one is the unlock for regulated industries. A few tools that read browser state, touch nothing, and either point the user to the right screen or pull the right info for their agent. But as a founder, you don't need any of that for your customers right away. Build it in-house first. Your internal tools, your own team, your own workflow. That's where the potential is.

The Startup Ideas Podcast (SIP) 🧃

10,592 views • 16 days ago

this is truly the best time to build. proves you can build anything you can imagine with just 1 person. - new companies should be at least 80% driven by AI (marketing, ops, engineering) to move as fast as possible. - the last 20% is all taste/creativity/direction: you're still selling to humans even if AI drives the company. you still need to delight them - when you believe there's something you can't do, try solving it with AI even if it seems hard so you can learn and automate most of the processes - limitations: models will become more generalist but still need to have narrow scope to perform well today. Polsia itself has agents that report bugs/feature requests when talking with customers, then a PM agent that decides priorities, then an engineering agent that builds it. no excuses. lock in
3:05

this is truly the best time to build. proves you can build anything you can imagine with just 1 person. - new companies should be at least 80% driven by AI (marketing, ops, engineering) to move as fast as possible. - the last 20% is all taste/creativity/direction: you're still selling to humans even if AI drives the company. you still need to delight them - when you believe there's something you can't do, try solving it with AI even if it seems hard so you can learn and automate most of the processes - limitations: models will become more generalist but still need to have narrow scope to perform well today. Polsia itself has agents that report bugs/feature requests when talking with customers, then a PM agent that decides priorities, then an engineering agent that builds it. no excuses. lock in

Andros

13,130 views • 6 months ago

Figma CEO Dylan Field just identified the only competitive advantage that AI cannot commoditize. It isn’t your technical skill. It isn’t your speed. It isn’t your tools. Field: “If an agent can do it for you, an agent can do it for someone else.” That’s the fatal flaw in the entire AI productivity argument nobody wants to say out loud. When execution becomes free, execution becomes worthless. The moment anyone can build anything by typing a prompt, the output stops being the differentiator. What remains is taste. The one thing the agent cannot generate for you. Field: “What is different about your setup than others?” If you are typing generic prompts and accepting the first output the agent hands you, you aren’t building a product. You are retrieving a commodity. The same commodity available to every competitor on earth. Field: “You at least have to have something different there in order to not think that you’re just gonna get the same out.” But taste alone isn’t enough. The other half is exploration. Field: “The more you can sample the possibility space, it gives you something to react to.” The blank page is gone. The new constraint isn’t creation. It’s selection. The agent generates hundreds of possibilities in seconds. Your job is to go wide enough to find the best one hiding inside all of them. And then be honest enough with yourself to know when none of them are good enough. Field: “If you find areas where you’re going, ‘Hey, I don’t feel like I am liking this enough,’ then you got to keep pushing.” The creators who win this era won’t be the fastest builders. They’ll be the harshest critics. The ones who can generate the widest possibility space and identify the single best solution inside it. The ones whose taste is specific enough, developed enough, and honest enough to reject everything the agent produces until it produces something worth keeping. The AI can build anything you can describe. It cannot want anything. It cannot feel when something is wrong. It cannot tell the difference between good and extraordinary. That gap is the only moat left.
1:14

Figma CEO Dylan Field just identified the only competitive advantage that AI cannot commoditize. It isn’t your technical skill. It isn’t your speed. It isn’t your tools. Field: “If an agent can do it for you, an agent can do it for someone else.” That’s the fatal flaw in the entire AI productivity argument nobody wants to say out loud. When execution becomes free, execution becomes worthless. The moment anyone can build anything by typing a prompt, the output stops being the differentiator. What remains is taste. The one thing the agent cannot generate for you. Field: “What is different about your setup than others?” If you are typing generic prompts and accepting the first output the agent hands you, you aren’t building a product. You are retrieving a commodity. The same commodity available to every competitor on earth. Field: “You at least have to have something different there in order to not think that you’re just gonna get the same out.” But taste alone isn’t enough. The other half is exploration. Field: “The more you can sample the possibility space, it gives you something to react to.” The blank page is gone. The new constraint isn’t creation. It’s selection. The agent generates hundreds of possibilities in seconds. Your job is to go wide enough to find the best one hiding inside all of them. And then be honest enough with yourself to know when none of them are good enough. Field: “If you find areas where you’re going, ‘Hey, I don’t feel like I am liking this enough,’ then you got to keep pushing.” The creators who win this era won’t be the fastest builders. They’ll be the harshest critics. The ones who can generate the widest possibility space and identify the single best solution inside it. The ones whose taste is specific enough, developed enough, and honest enough to reject everything the agent produces until it produces something worth keeping. The AI can build anything you can describe. It cannot want anything. It cannot feel when something is wrong. It cannot tell the difference between good and extraordinary. That gap is the only moat left.

Dustin

208,876 views • 6 months ago

One of the best things to build right now is an action app. An action app clears your inbox, books your calendar, and files your expenses on your behalf. The AI-first version of email answers 80% of your messages and shows you the one or two a day that are too important to automate. Every app you use today works the other way around. Instagram and TikTok feed you stuff to scroll. Salesforce sits there waiting for you to type. Here's the whole setup: 1) Pick a boring workflow in a niche where people already pay to make it go away. 2) Reimagine the core UX. Don't rebuild the list of everything you owe someone, because the list is the daunting part. 3) Build on the Claude Agent SDK and other SDKs. You're putting a layer on top of it. People called them GPT wrappers, now it's agent wrappers. 4) Give people an interface for managing how the agents work. 5) Figure out the TikTok or the Reel that gets someone to install it. Step 5 is the hard part. Everyone can build the agent now, so the winner is whoever gets the reach. Facebook had a painful transition to mobile, so they bought Instagram, the mobile-first version of Facebook. Agent-first apps are the same setup. Everyone with AI bolted onto the side of an old product can't rip out their core experience, and that's the opening. Someone should start a studio that only builds these. Pick the boring workflow, let the agents run it, then go get acquired
8:35

One of the best things to build right now is an action app. An action app clears your inbox, books your calendar, and files your expenses on your behalf. The AI-first version of email answers 80% of your messages and shows you the one or two a day that are too important to automate. Every app you use today works the other way around. Instagram and TikTok feed you stuff to scroll. Salesforce sits there waiting for you to type. Here's the whole setup: 1) Pick a boring workflow in a niche where people already pay to make it go away. 2) Reimagine the core UX. Don't rebuild the list of everything you owe someone, because the list is the daunting part. 3) Build on the Claude Agent SDK and other SDKs. You're putting a layer on top of it. People called them GPT wrappers, now it's agent wrappers. 4) Give people an interface for managing how the agents work. 5) Figure out the TikTok or the Reel that gets someone to install it. Step 5 is the hard part. Everyone can build the agent now, so the winner is whoever gets the reach. Facebook had a painful transition to mobile, so they bought Instagram, the mobile-first version of Facebook. Agent-first apps are the same setup. Everyone with AI bolted onto the side of an old product can't rip out their core experience, and that's the opening. Someone should start a studio that only builds these. Pick the boring workflow, let the agents run it, then go get acquired

The Startup Ideas Podcast (SIP) 🧃

14,323 views • 6 days ago

$FET just quietly built the internet for AI agents. 3,000,000 agents. One network. One token. Here's what nobody is explaining: Every AI agent needs 3 things to be useful: An address. A way to be found. A way to get paid. Agentverse gives agents all three. Your agent becomes discoverable on ASI: One. Other agents can find it, call it, or hire it. Automatically. No human in the loop. This is agent-to-agent commerce. And every transaction settles in $FET. More agents = more activity = more demand. The infrastructure is already live. The economy is just getting started.
1:00

$FET just quietly built the internet for AI agents. 3,000,000 agents. One network. One token. Here's what nobody is explaining: Every AI agent needs 3 things to be useful: An address. A way to be found. A way to get paid. Agentverse gives agents all three. Your agent becomes discoverable on ASI: One. Other agents can find it, call it, or hire it. Automatically. No human in the loop. This is agent-to-agent commerce. And every transaction settles in $FET. More agents = more activity = more demand. The infrastructure is already live. The economy is just getting started.

2xnmore

12,894 views • 5 months ago

Can your agent finally edit your videos? Yup, it's a repo called video use, by Browser Use. You put the raw footage in a folder. Then Claude Code or Codex edits it. It removes the filler words, cuts the dead space, adds the subtitles, and renders the file. Then it checks its own cut points. Most creators use the same small set of edits in every video. That style stays in your head and in your hands. This repo puts it in a file that an agent can read. People ask for a full YouTube channel on day one. They see bad results, and they stop. Start with one format instead. - One founder loom into a 60 second launch video - 3 clips out of one podcast recording Then make the format a system. Then you operate the system, or you sell it. - Real estate agents need listing videos - Coaches need clips - Agencies need ad variations Manual installation with git clone is possible. For 95% of people, the agent is faster. Here's how i intalled it: - Gave the setup prompt to Claude Code with shell access - Let it read install.md - Installed the repo - Connected FFmpeg - Registered the skill
4:22

Can your agent finally edit your videos? Yup, it's a repo called video use, by Browser Use. You put the raw footage in a folder. Then Claude Code or Codex edits it. It removes the filler words, cuts the dead space, adds the subtitles, and renders the file. Then it checks its own cut points. Most creators use the same small set of edits in every video. That style stays in your head and in your hands. This repo puts it in a file that an agent can read. People ask for a full YouTube channel on day one. They see bad results, and they stop. Start with one format instead. - One founder loom into a 60 second launch video - 3 clips out of one podcast recording Then make the format a system. Then you operate the system, or you sell it. - Real estate agents need listing videos - Coaches need clips - Agencies need ad variations Manual installation with git clone is possible. For 95% of people, the agent is faster. Here's how i intalled it: - Gave the setup prompt to Claude Code with shell access - Let it read install.md - Installed the repo - Connected FFmpeg - Registered the skill

The Startup Ideas Podcast (SIP) 🧃

15,605 views • 10 days ago

Sam Altman just told you what OpenAI is actually building. Not a chatbot. Not a search tool. Not an assistant. Altman: “Go look around my computer… read my messages… listen to my meetings… intermediate my interactions for me.” That is not a product pitch. That is the CEO of the most valuable AI company on Earth describing what he personally wants. For himself. Every day. Read his messages. Listen to his meetings. Act on his behalf. Make decisions before he knows a decision needs making. Altman: “I don’t have to think. I don’t have to ask you questions.” Every model of AI ever built runs on the prompt. You ask. It responds. You direct. It executes. The human initiates. The machine follows. Altman is describing the death of that model. The agent does not wait. It already read the email. It already heard the meeting. It already knows what you need before you form the thought. You do not operate the machine. The machine operates around you. Then came the line that makes everything else real. Altman: “You can know everything about my life. Start suggesting more things I should build.” He is not asking the AI to execute his ideas. He is asking it to generate them. From his files. His history. His patterns. His entire context. The agent does not just remove friction. It removes the blank page. You never stall. You never run dry. You never sit wondering what to build next. The machine already mapped your market, your gaps, your momentum. It tells you what comes next before you think to ask. But the individual product is not the story. Altman went further. Altman: “Automated companies… where the AI can do not just coding work, but huge amounts of what it takes to run and operate a company.” Not fully automated. He was precise about that. But accelerated to the point where one person with the right stack does what used to take departments. The billion-dollar company did not reach that valuation because the product was worth a billion. It got there because it took a thousand people to deliver it. When an agent absorbs the work of a hundred of those people, the math of every industry rewrites itself. The startup that needed fifty employees and three years of runway now needs five people and six months. The company that took a decade to scale now compounds in quarters. The person holding the line between their data and their tools is not protecting their privacy. They are protecting their ceiling. Because the cost of this leverage is total transparency. You do not get the agent that acts without being asked unless you give it everything. Your messages. Your calendar. Your files. Your patterns. Your life. Altman is not hiding that tradeoff. He is building it as the product. The people who accept it will operate at a speed the people who refuse cannot touch. Right now, two versions of the future are separating. One where you direct the machine. One where the machine already knows. Altman chose. He is building it. The question is not whether this happens. The question is which side of it finds you.
1:40

Sam Altman just told you what OpenAI is actually building. Not a chatbot. Not a search tool. Not an assistant. Altman: “Go look around my computer… read my messages… listen to my meetings… intermediate my interactions for me.” That is not a product pitch. That is the CEO of the most valuable AI company on Earth describing what he personally wants. For himself. Every day. Read his messages. Listen to his meetings. Act on his behalf. Make decisions before he knows a decision needs making. Altman: “I don’t have to think. I don’t have to ask you questions.” Every model of AI ever built runs on the prompt. You ask. It responds. You direct. It executes. The human initiates. The machine follows. Altman is describing the death of that model. The agent does not wait. It already read the email. It already heard the meeting. It already knows what you need before you form the thought. You do not operate the machine. The machine operates around you. Then came the line that makes everything else real. Altman: “You can know everything about my life. Start suggesting more things I should build.” He is not asking the AI to execute his ideas. He is asking it to generate them. From his files. His history. His patterns. His entire context. The agent does not just remove friction. It removes the blank page. You never stall. You never run dry. You never sit wondering what to build next. The machine already mapped your market, your gaps, your momentum. It tells you what comes next before you think to ask. But the individual product is not the story. Altman went further. Altman: “Automated companies… where the AI can do not just coding work, but huge amounts of what it takes to run and operate a company.” Not fully automated. He was precise about that. But accelerated to the point where one person with the right stack does what used to take departments. The billion-dollar company did not reach that valuation because the product was worth a billion. It got there because it took a thousand people to deliver it. When an agent absorbs the work of a hundred of those people, the math of every industry rewrites itself. The startup that needed fifty employees and three years of runway now needs five people and six months. The company that took a decade to scale now compounds in quarters. The person holding the line between their data and their tools is not protecting their privacy. They are protecting their ceiling. Because the cost of this leverage is total transparency. You do not get the agent that acts without being asked unless you give it everything. Your messages. Your calendar. Your files. Your patterns. Your life. Altman is not hiding that tradeoff. He is building it as the product. The people who accept it will operate at a speed the people who refuse cannot touch. Right now, two versions of the future are separating. One where you direct the machine. One where the machine already knows. Altman chose. He is building it. The question is not whether this happens. The question is which side of it finds you.

Dustin

87,680 views • 5 months 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
35:25

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