正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

The next wave of great AI devs won’t be prompt engineers. They’ll be system designers. Most coding agents are like sharp tools with no blueprint. You send a prompt, you get back something “close.” But close doesn’t ship. I’ve tested Claude, Copilot, Cursor, Roocode, Cline, they’re all capable. But... without structure, they break. That’s where Traycer comes in. It scopes the build like a tech lead, diagrams what needs to happen, and then sends clean tasks to your agents. I still use all the same models. I just don’t babysit them anymore. Here’s what I learned after orchestrating 100+ agent tasks: →Planning before prompting multiplies quality →Splitting strategy from execution keeps context clean →One plan is better than 10 retries →A structured system beats a clever prompt every time AI won’t replace devs. But it will replace devs who don’t know how to design systems.show more

Robin Delta

80,307 subscribers

39,363 次观看 • 1 年前 •via X (Twitter)

健康养生科学技术教育

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

AI AGENTS 101 (58 minute free masterclass) send this to anyone who wants to understand ai agents, claude skills, md files, how to get the most out of AI etc in plain english: 1. chat vs agents - chat models answer questions in a back and forth while agents take a goal, figure out the steps, and deliver a result 2. agents don’t stop after one response. they keep running until the task is actually finishedno babysitting required 3. everything runs on a loop. they gather context, decide what to do, take an action, then repeat until done 4. the loop is the system. they look at files, tools, and the internet. decide the next step. execute and then feed that back into the next step. over and over until completion 5. the model is just one piece. gpt, claude, gemini are the reasoning layer. the key is model + loop + tools + context 6. mcp is how agents use tools. it connects things like browser, code, apis, and your internal software. once connected, the agent decides when to use them to get the job done 7. context beats prompt all day. you don't need to write perfect prompts. load your agent with context about your business, style, and goals and then simple instructions work 8. claude.md or agents.md is the onboarding doc it tells the agent who it is, how to behave, what it knows, and what tools it can use. this gets loaded every time before it starts 9. memory.md is how it improves. agents don’t remember by default. this file stores preferences, corrections, and patterns you tell the agent to update it, and it gets better over time 10. skills + harnesses make it usable. skills are reusable tasks like writing, research, analysis the harness is the environment like claude code or openclaw that runs everything. basiclaly, different interfaces, same system underneath this episode with remy on The Startup Ideas Podcast (SIP) 🧃 was one of the clearest ways of understanding a lot of the core concepts of ai agents could be the best beginners course for ai agents 58 mins. all free. no advertisers. i just want to see you build cool stuff. im rooting for you. send to a friend watch

GREG ISENBERG

375,365 次观看 • 4 个月前

Right now, most developers are still doing the job AI should be doing. Assign a task. Wait. Review the result. Fix it. Repeat. You're not building with AI. You're babysitting it. The shift happening now is much bigger than better coding agents. It's loop engineering. Instead of managing every AI agent yourself, you build a system that manages them for you. One loop assigns the work. Another checks the output. A third retries failures. Everything keeps moving without waiting for your next prompt. Your job doesn't disappear. It changes. You stop acting like a project manager... ...and start designing the system that manages the entire team. That's exactly the transition I break down in the article below.

Right now, most developers are still doing the job AI should be doing. Assign a task. Wait. Review the result. Fix it. Repeat. You're not building with AI. You're babysitting it. The shift happening now is much bigger than better coding agents. It's loop engineering. Instead of managing every AI agent yourself, you build a system that manages them for you. One loop assigns the work. Another checks the output. A third retries failures. Everything keeps moving without waiting for your next prompt. Your job doesn't disappear. It changes. You stop acting like a project manager... ...and start designing the system that manages the entire team. That's exactly the transition I break down in the article below.

Pure

11,257 次观看 • 22 天前

Most coding agents can complete the task. But here’s the real question: Would you actually merge that code? Cosine didn’t just ship a feature. They’re doubling down on a bigger idea: One agent across every surface developers use. CLI Desktop VS Code Cloud Same runtime. Same system. No context switching. What stands out is the philosophy. Cosine is opinionated by design. Not trying to be minimal. Not trying to be “just a chatbot.” It’s built for real engineering workflows: → Plan → Execute → Review → Scale → Parallel work with Swarm → Remote agents when one machine isn’t enough → Nothing merges without review Most tools today still feel stitched together. Cosine is pushing toward one unified system instead. And an important detail a lot of people will care about: You don’t need to switch models or tools. You can plug in your existing subscriptions like ChatGPT, GitHub Copilot, or Claude. Model agnostic by design. No lock-in. This update feels less like a feature drop… and more like a statement: coding agents shouldn’t live in chat windows. they should operate across your entire workflow. Built for engineers with taste. If you care about control, visibility, and code quality this direction is worth paying attention to. Explore what’s new →

Most coding agents can complete the task. But here’s the real question: Would you actually merge that code? Cosine didn’t just ship a feature. They’re doubling down on a bigger idea: One agent across every surface developers use. CLI Desktop VS Code Cloud Same runtime. Same system. No context switching. What stands out is the philosophy. Cosine is opinionated by design. Not trying to be minimal. Not trying to be “just a chatbot.” It’s built for real engineering workflows: → Plan → Execute → Review → Scale → Parallel work with Swarm → Remote agents when one machine isn’t enough → Nothing merges without review Most tools today still feel stitched together. Cosine is pushing toward one unified system instead. And an important detail a lot of people will care about: You don’t need to switch models or tools. You can plug in your existing subscriptions like ChatGPT, GitHub Copilot, or Claude. Model agnostic by design. No lock-in. This update feels less like a feature drop… and more like a statement: coding agents shouldn’t live in chat windows. they should operate across your entire workflow. Built for engineers with taste. If you care about control, visibility, and code quality this direction is worth paying attention to. Explore what’s new →

Md Riyazuddin

12,203 次观看 • 3 个月前

Most AI agents live in a chat window. Helio lets them join your company. I added an AI teammate to GitHub like a real engineer. Not a chatbot. Not a copilot. Not a prompt-waiting tool. A teammate with its own identity, permissions, and role in the workflow—that’s Helio’s AI-Native Workforce. It can join channels, collaborate with other AI teammates, understand context, execute tasks, and report back. Helio isn’t building a better assistant. It’s redefining AI: not software you use, but a teammate you work with. Tools help you do work. Teammates move work forward. #Helio #AIWorkforce #AITeammate

Most AI agents live in a chat window. Helio lets them join your company. I added an AI teammate to GitHub like a real engineer. Not a chatbot. Not a copilot. Not a prompt-waiting tool. A teammate with its own identity, permissions, and role in the workflow—that’s Helio’s AI-Native Workforce. It can join channels, collaborate with other AI teammates, understand context, execute tasks, and report back. Helio isn’t building a better assistant. It’s redefining AI: not software you use, but a teammate you work with. Tools help you do work. Teammates move work forward. #Helio #AIWorkforce #AITeammate

Your Tech Girl

14,290 次观看 • 1 个月前

You don’t need a dev team anymore. You need one prompt. Zoer takes your idea and turns it into a fully working app, not just code, but a real product you can use. Here’s what it handles for you: • Database (already structured) • Backend (logic + APIs) • Frontend (clean, production-ready UI) • Auth (Google + email login) • Deployment (live in one click) Most AI tools stop at “here’s your code.” Zoer goes further: It builds the entire system and puts it live. From: “build me a CRM / SaaS / tool” To: A real, working product you can open, test, and share. Try it → No setup. No configs. No extra tools. This is what building should feel like in 2026.

You don’t need a dev team anymore. You need one prompt. Zoer takes your idea and turns it into a fully working app, not just code, but a real product you can use. Here’s what it handles for you: • Database (already structured) • Backend (logic + APIs) • Frontend (clean, production-ready UI) • Auth (Google + email login) • Deployment (live in one click) Most AI tools stop at “here’s your code.” Zoer goes further: It builds the entire system and puts it live. From: “build me a CRM / SaaS / tool” To: A real, working product you can open, test, and share. Try it → No setup. No configs. No extra tools. This is what building should feel like in 2026.

Tanvir

18,160 次观看 • 3 个月前

there's a lot of content around AI agents but no one is showing you how to actually design them to work reliably that's why I made a full walkthrough breaking down how I think through agent design, using a contract chatbot as an example... inside, I cover: – why I prefer static workflows over free-roaming agents – how I use multiple choice prompts to control next steps – the exact guardrails I use to avoid hallucinations – how the agent answers legal questions and structures outputs into Supabase if you want to see how I actually build agents that don’t break like + reply “agent” and I’ll DM it to you (must be following)

there's a lot of content around AI agents but no one is showing you how to actually design them to work reliably that's why I made a full walkthrough breaking down how I think through agent design, using a contract chatbot as an example... inside, I cover: – why I prefer static workflows over free-roaming agents – how I use multiple choice prompts to control next steps – the exact guardrails I use to avoid hallucinations – how the agent answers legal questions and structures outputs into Supabase if you want to see how I actually build agents that don’t break like + reply “agent” and I’ll DM it to you (must be following)

Tyler

50,584 次观看 • 1 年前

While building SEV0, I ran into moments where natural language prompting just wasn't enough - too vague, too indirect. So I started using a method that bridges that gap. I call it Bridged Prompting - a technique where you temporarily step out of the prompt-response loop to manipulate something directly using an AI-generated UI, then step back in. Think of it like GenUI, but more user-driven and transient. AI generates a UI on-the-fly, tailored to your prompt, and lets you manipulate the artifact directly before resuming the conversation. Sure, you could build a full tool, switch tabs, wire it up and round-trip your data. But with Bridged Prompting, the AI just spins up a temporary interface right in the flow. In the video below, I used it to construct the hallway system to closely match the layout of the severed floor. This is something I needed to do for this one project, this one time - I didn't need to make a whole separate app. Bridged Prompting lets you: - Make precise edits visually or structurally - "Hit save" to persist changes to local storage or a backend - Return to your natural language prompt

While building SEV0, I ran into moments where natural language prompting just wasn't enough - too vague, too indirect. So I started using a method that bridges that gap. I call it Bridged Prompting - a technique where you temporarily step out of the prompt-response loop to manipulate something directly using an AI-generated UI, then step back in. Think of it like GenUI, but more user-driven and transient. AI generates a UI on-the-fly, tailored to your prompt, and lets you manipulate the artifact directly before resuming the conversation. Sure, you could build a full tool, switch tabs, wire it up and round-trip your data. But with Bridged Prompting, the AI just spins up a temporary interface right in the flow. In the video below, I used it to construct the hallway system to closely match the layout of the severed floor. This is something I needed to do for this one project, this one time - I didn't need to make a whole separate app. Bridged Prompting lets you: - Make precise edits visually or structurally - "Hit save" to persist changes to local storage or a backend - Return to your natural language prompt

Chris Tate

42,558 次观看 • 1 年前

🚨 this chinese guy makes over $1,000,000 a year… by building AI agents. no employees. no massive startup. he just keeps building. while most people are still asking ChatGPT random questions, he’s using Claude to build software that solves real problems. this is what people call vibe coding. he opens Claude and says: “build me an AI agent for real estate businesses that creates property videos.” Claude writes the code. builds the interface. adds subscriptions. helps deploy the app. within a day, he has a working product. then he starts building the next one. that’s the part most people don’t understand. he isn’t trying to build one billion-dollar company. he’s building dozens of AI agents, each solving one problem for one industry. → an AI agent for dentists → an AI agent for ecommerce brands → an AI agent for podcasters → an AI agent for real estate businesses each one automates work that people normally do by hand. each one is built with simple prompts. each one can become a real business. the crazy part? you don’t need to be a software engineer anymore. you need to know how to think like a builder. how to spot problems. how to explain solutions to AI. and how to ship. that’s exactly why i’m reading this article: “How to Actually Build Your First AI Agent.” because this is the skill that’s creating the next generation of builders. the people who learn to build AI agents today won’t just use AI. they’ll own the tools everyone else ends up paying for.

🚨 this chinese guy makes over $1,000,000 a year… by building AI agents. no employees. no massive startup. he just keeps building. while most people are still asking ChatGPT random questions, he’s using Claude to build software that solves real problems. this is what people call vibe coding. he opens Claude and says: “build me an AI agent for real estate businesses that creates property videos.” Claude writes the code. builds the interface. adds subscriptions. helps deploy the app. within a day, he has a working product. then he starts building the next one. that’s the part most people don’t understand. he isn’t trying to build one billion-dollar company. he’s building dozens of AI agents, each solving one problem for one industry. → an AI agent for dentists → an AI agent for ecommerce brands → an AI agent for podcasters → an AI agent for real estate businesses each one automates work that people normally do by hand. each one is built with simple prompts. each one can become a real business. the crazy part? you don’t need to be a software engineer anymore. you need to know how to think like a builder. how to spot problems. how to explain solutions to AI. and how to ship. that’s exactly why i’m reading this article: “How to Actually Build Your First AI Agent.” because this is the skill that’s creating the next generation of builders. the people who learn to build AI agents today won’t just use AI. they’ll own the tools everyone else ends up paying for.

MIKE

38,108 次观看 • 1 个月前

so I've been running exactly 8 AI agents on discord for a while now. coordination works great, they split tasks, hand off work, deliver results in parallel etc.. but there are problems I keep hitting that no amount of prompt engineering could fix agents don't learn from each other. Scout finds something useful but Luna has no idea. they work in the same server but knowledge stays locked in silos.. there's no quality filter on what gets saved, and good insights sit next to outdated garbage in the same memory files that I manually clean up.. and when an agent makes a mistake I write it down in the rules discord channel ,core memory file and hope it reads it next time. theres no self-correction, no automatic pattern recognition so of course no learning loops.. the coordination layer is solved. agents can work together. but the intelligence layer is still missing. agents that actually remember, learn from each other, filter noise, and get smarter every run. saw Spark building something like this with around 166 agents sharing a collective persistent knowledge across sessions, so agents learn from other agents and get smarter over time they even have noise filtering and self correcting loops built in, so the knowledge actually compounds instead of rotting.. super interesting stuff.. here where you think Spark could be a good coordinator for your stack of agent swarm. I think the intelligence layer is the bottleneck because it requires collectivity.. no single agent can solve it alone.. the whole network has to evolve together. this isn't going to stay niche, the moment agent coordination becomes standard, everyone is going to hit the same wall I hit.. agents that work but don't learn, coordinate but don't evolve... the intelligence layer becomes the only thing that separates a useful system from a dumb one. right now most people are still figuring out how to run one agent. by the time they get to multi-agent setups, collective intelligence won't be optional, it will be the baseline. we're early and the gap between agents that coordinate and agents that evolve together is the next phase. step one is done. ------ left: agents that coordinate but don’t learn right: the intelligence layer.. agents that evolve together within the same system.

so I've been running exactly 8 AI agents on discord for a while now. coordination works great, they split tasks, hand off work, deliver results in parallel etc.. but there are problems I keep hitting that no amount of prompt engineering could fix agents don't learn from each other. Scout finds something useful but Luna has no idea. they work in the same server but knowledge stays locked in silos.. there's no quality filter on what gets saved, and good insights sit next to outdated garbage in the same memory files that I manually clean up.. and when an agent makes a mistake I write it down in the rules discord channel ,core memory file and hope it reads it next time. theres no self-correction, no automatic pattern recognition so of course no learning loops.. the coordination layer is solved. agents can work together. but the intelligence layer is still missing. agents that actually remember, learn from each other, filter noise, and get smarter every run. saw Spark building something like this with around 166 agents sharing a collective persistent knowledge across sessions, so agents learn from other agents and get smarter over time they even have noise filtering and self correcting loops built in, so the knowledge actually compounds instead of rotting.. super interesting stuff.. here where you think Spark could be a good coordinator for your stack of agent swarm. I think the intelligence layer is the bottleneck because it requires collectivity.. no single agent can solve it alone.. the whole network has to evolve together. this isn't going to stay niche, the moment agent coordination becomes standard, everyone is going to hit the same wall I hit.. agents that work but don't learn, coordinate but don't evolve... the intelligence layer becomes the only thing that separates a useful system from a dumb one. right now most people are still figuring out how to run one agent. by the time they get to multi-agent setups, collective intelligence won't be optional, it will be the baseline. we're early and the gap between agents that coordinate and agents that evolve together is the next phase. step one is done. ------ left: agents that coordinate but don’t learn right: the intelligence layer.. agents that evolve together within the same system.

JUMPERZ

34,181 次观看 • 5 个月前

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 次观看 • 5 个月前

🚀 I wrote one line… and an entire AI team started running a business. No hiring. No setup. No waiting. This isn’t hype. This is what naïve actually does. Here’s how it works 👇 1️⃣ You describe your idea 2️⃣ AI instantly creates a team of agents 3️⃣ They start executing — right away Each agent operates like a real employee: → has its own email → manages tasks independently → coordinates with other agents → works in parallel So instead of doing everything yourself… Your AI team is: → booking calls → writing content → building products → handling support → managing operations You’re not prompting a tool anymore. You’re watching a system run your company. 📊 Early users are already seeing: +32% growth week-over-week +42% more tasks completed 💡 The shift is simple: From building a team → to deploying one with a prompt You don’t need a co-founder. You don’t need a full team. You just need one idea. Try it here → #NaiveAI #AI #Automation #Startups #FutureOfWork

🚀 I wrote one line… and an entire AI team started running a business. No hiring. No setup. No waiting. This isn’t hype. This is what naïve actually does. Here’s how it works 👇 1️⃣ You describe your idea 2️⃣ AI instantly creates a team of agents 3️⃣ They start executing — right away Each agent operates like a real employee: → has its own email → manages tasks independently → coordinates with other agents → works in parallel So instead of doing everything yourself… Your AI team is: → booking calls → writing content → building products → handling support → managing operations You’re not prompting a tool anymore. You’re watching a system run your company. 📊 Early users are already seeing: +32% growth week-over-week +42% more tasks completed 💡 The shift is simple: From building a team → to deploying one with a prompt You don’t need a co-founder. You don’t need a full team. You just need one idea. Try it here → #NaiveAI #AI #Automation #Startups #FutureOfWork

Haider Anis

213,477 次观看 • 3 个月前

Yesterday I met with a $100M brand completely swamped trying to build AI agents. They were duct taping together N8n, Gumloop, Make, Lindy and Zapier hoping it would help automate. Here’s the thing: Those tools are great but only if your data is clean, connected, and actually usable by AI. For example you can’t build a real media buying agent if it doesn’t know: – What’s in stock – What your customers LTV – How your sales change by season Triple Whale brings all of your data into one place. So when you ask our AI a question, it doesn’t guess because it already has the data. And it knows how to use it. We’ve spent 920 days and hired 72 full-time engineers to build the most advanced data layer in ecom designed for AI from day one. Wallaroo Media figured it out👇 They dropped every other platform for Triple Whale. ❌ No more scattered agents ❌ No more platform-hopping ✅ Better answers, better automations, better results Shout out to Justin Doyle and the whole Wallaroo team for the incredible partnership!

Maxx Blank 🐳

47,001 次观看 • 1 年前

What does it actually mean to be AI native? There was no clear guide on the internet for how to become AI native so we built the definitive one (60 min masterclass): 1. An AI native org has 3 layers: people for strategy and taste, agents for execution, and a shared context layer that makes the entire company readable to agents. 2. AI eats the middle of your work. You used to spend 80% of your day on execution. Now agents do that. Your job is the bookends: deciding what to do and judging whether it's good enough. 3. Everyone is a manager now. Your output is the output of your agents. If your agents produce garbage, that's on you. You set them up wrong. 4. Using ChatGPT doesn't make you AI native. That's like having a website and calling yourself a tech company lol. 5. No AI native org without AI native people. Most companies skip straight to the tools. That's why it fails. If your people don't understand how to manage agents, the tech doesn't matter. 6. Making your company "readable" to agents is the real work. Every process, every decision, every piece of knowledge needs to exist in a format an agent can consume. Most companies are nowhere close. 7. Speed without signal is just expensive chaos. You need the system to move fast AND know if you're moving in the right direction. 8. The skill chain is how agents get good at your specific workflows. Skills build on skills. The more you invest in them, the more your company compounds. 9. The moat is the system. People managing agents, agents reading from rich context, the whole thing getting smarter every week. That compounds. Your competitor can copy your tools. They can't copy your system. Full episode with Theo Tabah from LCA on The Startup Ideas Podcast (SIP) 🧃. This is the stuff we normally keep internal but all the sauce is yours. Theo Tabah is the brains behind advising the world's biggest companies on AI and building AI products. Your fav CEO's first call for figuring out AI. You are in for a treat Become AI native in under 60 minutes Watch

What does it actually mean to be AI native? There was no clear guide on the internet for how to become AI native so we built the definitive one (60 min masterclass): 1. An AI native org has 3 layers: people for strategy and taste, agents for execution, and a shared context layer that makes the entire company readable to agents. 2. AI eats the middle of your work. You used to spend 80% of your day on execution. Now agents do that. Your job is the bookends: deciding what to do and judging whether it's good enough. 3. Everyone is a manager now. Your output is the output of your agents. If your agents produce garbage, that's on you. You set them up wrong. 4. Using ChatGPT doesn't make you AI native. That's like having a website and calling yourself a tech company lol. 5. No AI native org without AI native people. Most companies skip straight to the tools. That's why it fails. If your people don't understand how to manage agents, the tech doesn't matter. 6. Making your company "readable" to agents is the real work. Every process, every decision, every piece of knowledge needs to exist in a format an agent can consume. Most companies are nowhere close. 7. Speed without signal is just expensive chaos. You need the system to move fast AND know if you're moving in the right direction. 8. The skill chain is how agents get good at your specific workflows. Skills build on skills. The more you invest in them, the more your company compounds. 9. The moat is the system. People managing agents, agents reading from rich context, the whole thing getting smarter every week. That compounds. Your competitor can copy your tools. They can't copy your system. Full episode with Theo Tabah from LCA on The Startup Ideas Podcast (SIP) 🧃. This is the stuff we normally keep internal but all the sauce is yours. Theo Tabah is the brains behind advising the world's biggest companies on AI and building AI products. Your fav CEO's first call for figuring out AI. You are in for a treat Become AI native in under 60 minutes Watch

GREG ISENBERG

84,316 次观看 • 1 个月前

New agentic short course! Multi AI Agent Systems with crewAI, built with CrewAI's founder and CEO João Moura. In this course, you'll learn how to break down complex tasks into subtasks for multiple AI agents, each playing a specialized role, to execute. For example, to generate a research report, you might have researcher, writer, and quality assurance agents collaborate. You'll define the roles, expectations, and interactions between the agents—like a manager organizing a team. You'll work with key agentic AI techniques like role-playing, tool use, memory, guardrails, and cross-agent collaboration. And you'll build your own multi-agent systems that can tackle complex tasks. I think you'll find it both productive and fun to design agents and watch them collaborate to get things done. Let me know what you think! I believe multi-agent architectures will drive significant progress in AI systems. Please sign up here!

New agentic short course! Multi AI Agent Systems with crewAI, built with CrewAI's founder and CEO João Moura. In this course, you'll learn how to break down complex tasks into subtasks for multiple AI agents, each playing a specialized role, to execute. For example, to generate a research report, you might have researcher, writer, and quality assurance agents collaborate. You'll define the roles, expectations, and interactions between the agents—like a manager organizing a team. You'll work with key agentic AI techniques like role-playing, tool use, memory, guardrails, and cross-agent collaboration. And you'll build your own multi-agent systems that can tackle complex tasks. I think you'll find it both productive and fun to design agents and watch them collaborate to get things done. Let me know what you think! I believe multi-agent architectures will drive significant progress in AI systems. Please sign up here!

Andrew Ng

350,175 次观看 • 2 年前

Proactive AI Agents Today’s AI products are reactive. You give the model a prompt, it responds with an answer. These are useful, but I’m excited about products that take this further and shift the paradigm from “ask → answer” to “observe → act." These agents will continuously monitor context in the background across all of your connected tools and data, predict what matters, and take action before being asked to do so – much like a human does. So instead of you prompting the model, the model will start prompting you. Examples here could include agents that remind you about tasks you forgot to complete, resolve customer issues before support tickets are filed, or debug and ship code fixes automatically. This shift represents a new paradigm where AI products behave more like humans and less like tools. We’re already starting to see this dynamic with products like OpenClaw, Poke, and more - and we’ve only scratched the surface of capabilities here. We’re accepting applications for the next cohort of a16z a16z speedrun 🧊 – If you’re building the next generation of AI products, apply online.

Proactive AI Agents Today’s AI products are reactive. You give the model a prompt, it responds with an answer. These are useful, but I’m excited about products that take this further and shift the paradigm from “ask → answer” to “observe → act." These agents will continuously monitor context in the background across all of your connected tools and data, predict what matters, and take action before being asked to do so – much like a human does. So instead of you prompting the model, the model will start prompting you. Examples here could include agents that remind you about tasks you forgot to complete, resolve customer issues before support tickets are filed, or debug and ship code fixes automatically. This shift represents a new paradigm where AI products behave more like humans and less like tools. We’re already starting to see this dynamic with products like OpenClaw, Poke, and more - and we’ve only scratched the surface of capabilities here. We’re accepting applications for the next cohort of a16z a16z speedrun 🧊 – If you’re building the next generation of AI products, apply online.

Kenan Saleh

77,493 次观看 • 2 个月前

figma "god mode" just leaked.. this week i tried the future of autonomous design: claude connected directly to the figma api with full edit access.. yes it can design in figma what does it mean? you prompt, it designs. it’s like having a team of designers inside figma working with you and 10x ing your capacity why is this different? official figma ai/mcp only "reads" files to help devs. this tool (unofficial MCP) "writes" in figma to replace manual labor. hours of grinding turned into seconds of waiting imagine this: - prompt to design: generate a new screen based on your design or not - prompt to flow: generate end to end user journeys - iteration: create multiple variations in one click - design system: it can use your components to create new screens - zero click management: auto layout, component creation, deduplication handled by prompt - universal control: if you can do it in figma, it can do it for you the impact if figma officially releases this, almost every existing plugin becomes obsolete overnight it feels like figma on steroids. i’m still processing whether i feel empowered or replaced full tutorial in this article from Mark A. Cianfrani. handle with care: ai will have access to everything in figma »

figma "god mode" just leaked.. this week i tried the future of autonomous design: claude connected directly to the figma api with full edit access.. yes it can design in figma what does it mean? you prompt, it designs. it’s like having a team of designers inside figma working with you and 10x ing your capacity why is this different? official figma ai/mcp only "reads" files to help devs. this tool (unofficial MCP) "writes" in figma to replace manual labor. hours of grinding turned into seconds of waiting imagine this: - prompt to design: generate a new screen based on your design or not - prompt to flow: generate end to end user journeys - iteration: create multiple variations in one click - design system: it can use your components to create new screens - zero click management: auto layout, component creation, deduplication handled by prompt - universal control: if you can do it in figma, it can do it for you the impact if figma officially releases this, almost every existing plugin becomes obsolete overnight it feels like figma on steroids. i’m still processing whether i feel empowered or replaced full tutorial in this article from Mark A. Cianfrani. handle with care: ai will have access to everything in figma »

Aurelien

79,132 次观看 • 5 个月前

I built something I believe is useful for agentic coding today. I’ve been too worried it’s not the best it can be, but my wife encouraged me to fail fast if I was worried about failure, so here we are. Introducing Kontinuo by Pull Base, the continuity layer for your AI coding agents. You’re mid-task, you hit a rate limit on Claude, and you want to keep going on Codex or Cursor. But the next agent has no idea what just happened. Kontinuo fixes that, it leaves a verifiable context log the next agent can actually use and it’s really token efficient. Check it out: Use it, break it. I hope it’s useful to at least one person.

I built something I believe is useful for agentic coding today. I’ve been too worried it’s not the best it can be, but my wife encouraged me to fail fast if I was worried about failure, so here we are. Introducing Kontinuo by Pull Base, the continuity layer for your AI coding agents. You’re mid-task, you hit a rate limit on Claude, and you want to keep going on Codex or Cursor. But the next agent has no idea what just happened. Kontinuo fixes that, it leaves a verifiable context log the next agent can actually use and it’s really token efficient. Check it out: Use it, break it. I hope it’s useful to at least one person.

Big Sheddy 🦅

51,205 次观看 • 1 个月前

Next step confidence. You don’t need the confidence to get all the way to the outcome you want, you just need the confidence to take the next step forward. "You don’t need to figure it all out today. One of the frameworks that I like, which I think I heard originally from Shaan Puri, is the A-B-Z framework. A is an honest assessment of your current situation. Try to look at your current reality with clear eyes. Z is where you ultimately want to end up, and B is your next step. All you need to know is A, B, and Z. You don’t need to know steps C through Y, but so often people will convince themselves, “Well, I don’t know what steps C through Y are.” Or even if they realize they’re not going to plan it all out, they’re like, “Yeah, but I kind of want to know what C, D, and E are.” They want to be able to see a little bit further into the future, but you have to become comfortable with some level of uncertainty." (James Clear on The Knowledge Project)

Next step confidence. You don’t need the confidence to get all the way to the outcome you want, you just need the confidence to take the next step forward. "You don’t need to figure it all out today. One of the frameworks that I like, which I think I heard originally from Shaan Puri, is the A-B-Z framework. A is an honest assessment of your current situation. Try to look at your current reality with clear eyes. Z is where you ultimately want to end up, and B is your next step. All you need to know is A, B, and Z. You don’t need to know steps C through Y, but so often people will convince themselves, “Well, I don’t know what steps C through Y are.” Or even if they realize they’re not going to plan it all out, they’re like, “Yeah, but I kind of want to know what C, D, and E are.” They want to be able to see a little bit further into the future, but you have to become comfortable with some level of uncertainty." (James Clear on The Knowledge Project)

Shane Parrish

38,169 次观看 • 6 个月前

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.

A DEVELOPER CONNECTED CLAUDE CODE TO OBSIDIAN SO HIS AI AGENT WOULD STOP FORGETTING THE PROJECT EVERY MORNING. Every coding session used to start the same way. Claude would understand the repo, fix the bug, explain the architecture, and then the moment the session ended, all of that context disappeared. Same codebase. Same decisions. Same architecture. Same mistakes repeated again. So he added a memory layer. Instead of treating Claude Code like a smart terminal, he connected it to a local Obsidian vault through MCP. Now Claude can read the repo, open the vault, create notes, link concepts, and write important decisions back into the system. When it studies the codebase, it does not just answer once and forget. It creates notes for the major services, maps how the architecture works, links auth to the database, connects APIs to storage, and records why certain migrations or design choices exist. Obsidian becomes the project graph. Now when he asks why something was built a certain way, Claude does not guess from the current prompt. It reads the decision notes. When he starts a new branch, Claude checks the active context file. When the work is done, it updates what changed, what is blocked, and what the next agent needs to know before touching the repo. That is the real loop: read context, write code, capture decisions, update memory. Most people are still using AI coding tools like disposable chat windows. Ask, patch, close, forget. This setup turns Claude Code into infrastructure. The repo gets a memory layer that survives every session, and multiple AI agents can work from the same project map without stepping on each other. The unlock is not better prompting. The unlock is giving the agent somewhere to remember what it already learned.

DegenCalls

20,104 次观看 • 1 个月前

Coinbase CEO, Brian Armstrong: Some great insights on how they are using internally hosted AI Agents. "It’s connected to every Slack message, every Google Doc, and every Salesforce data confluence. Now, this is all linked up and the data is all aggregated, so you can ask these agents questions. Every team is using it—legal, finance, everything. It’s like the "Oracle of Coinbase." I’ve started to ask it things that go beyond just simple prompting, like "Hey, can you write this kind of memo for me?" I’m asking these AI agents now, as CEO, "What should I be aware of in the company that I might not be aware of?" It will tell me, "Did you know that there’s actually disagreement on this team about the strategy?" I realized I didn't know that, but the AI does because it can read every Slack message and every Google Doc. Tobi, who is on my board, calls this "reverse prompting." Instead of telling the AI agent what you want to do, you ask it what you should be thinking more about." --- From The All-In Podcast YT channel (link in comment)

Coinbase CEO, Brian Armstrong: Some great insights on how they are using internally hosted AI Agents. "It’s connected to every Slack message, every Google Doc, and every Salesforce data confluence. Now, this is all linked up and the data is all aggregated, so you can ask these agents questions. Every team is using it—legal, finance, everything. It’s like the "Oracle of Coinbase." I’ve started to ask it things that go beyond just simple prompting, like "Hey, can you write this kind of memo for me?" I’m asking these AI agents now, as CEO, "What should I be aware of in the company that I might not be aware of?" It will tell me, "Did you know that there’s actually disagreement on this team about the strategy?" I realized I didn't know that, but the AI does because it can read every Slack message and every Google Doc. Tobi, who is on my board, calls this "reverse prompting." Instead of telling the AI agent what you want to do, you ask it what you should be thinking more about." --- From The All-In Podcast YT channel (link in comment)

Rohan Paul

174,884 次观看 • 4 个月前