Loading video...

Video Failed to Load

Go Home

(4 DAYS BEFORE SUBMISSIONS CLOSE) I get this question a lot about the Find Evil! hackathon: What does “find evil” actually mean? In this case, the name comes from a real command. I built an autonomous incident response agent I built on the SIFT Workstation. Then I typed “find...

robtlee's profile picture

Rob T. Lee

26,623 subscribers

14,405 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

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.
4:16

I wanted to share a quick demo of what we've been working on with our ai agent cloud. This enables fast deployment of agents that have access to a suite of tools, and was designed with agent interoperability in mind. This demo shows how you can go from nothing to an AI twitter agent in a couple minutes. This is what we are using internally to manage deployments, so we will consistently upgrading its capabilities. The next goals are to enable simple TEE deployments for agents, and focus on building out feature for agent interoperability to simplify agent to agent collaboration.

Johnny

27,179 views • 1 year ago

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base
1:47

Bash is all you need! Which is why I'm introducing my holiday project: just-bash just-bash is a pretty complete implementation of bash in TypeScript designed to be used as a bash tool by AI agents. Because it turns out agents love exploring data via shell scripts, even beyond coding. It comes with grep, sed, awk and the 99th percentile features that an agent like Claude Code or Cursor would use. In fact, Claude Code can use it for secure bash execution. In the package - A bash-tool for AI SDK - A binary for use by yourself or your coding agents - An overlay filesystem to feed files to your agent securely - A Vercel Sandbox compatible API, so you can quickly upgrade to a real VM if you need to run binaries - An example AI agent that explores the just-bash code base using just-bash - I imported the Oils shell bash compatibility suite and just-bash passes a very good chunk What is interesting about this codebase: It was essentially entirely written by Opus 4.5. Coding agents love bash and they are good at reproducing it. They are also great at text-book recursive descent parsers and AST tweet-walk interpreters. That said, it is, like, a lot of code and I didn't read it all 😅. This is very much a hack, but it also seems to be _really_ useful. I haven't really found anything agents want to use that it doesn't support and it's fast and secure (caveats apply). It doesn't have write access to your computer and the filesystem is given a root that the agent cannot escape from. Find it at Related: Our recent blog post how we migrated our data analysis agent to bash tools and achieved incredible quality improvements The video shows the example agent investigating the just-bash code base

Malte Ubl

125,326 views • 8 months ago

Here's the origin story of how we built the world's most powerful research agent from my dorm in Berkeley. Two years ago Chris and I were college students who couldn't find a professor's email, so we built a scraper to do it for us. That scraper turned into agents that investigate the clearweb, dark web, databases, and tools like an investigator. Soon we weren't helping students find emails. We were helping trust and safety, fraud, and compliance teams find people who spend all their time hiding. We just released our strongest agent yet: xhigh. Give it almost any starting point on a person, a username, a single email, and it comes back with anything you need. Chat with the team to get access at demo [dot] sixtyfour [dot] ai. Also in the comments below.
2:10

Here's the origin story of how we built the world's most powerful research agent from my dorm in Berkeley. Two years ago Chris and I were college students who couldn't find a professor's email, so we built a scraper to do it for us. That scraper turned into agents that investigate the clearweb, dark web, databases, and tools like an investigator. Soon we weren't helping students find emails. We were helping trust and safety, fraud, and compliance teams find people who spend all their time hiding. We just released our strongest agent yet: xhigh. Give it almost any starting point on a person, a username, a single email, and it comes back with anything you need. Chat with the team to get access at demo [dot] sixtyfour [dot] ai. Also in the comments below.

Saarth Shah

48,906 views • 1 month ago

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!
2:55

Let me explain why I launched $KEYS. CA: 3BSoYDZsPupZ15iBzJbJJjZKLiyWEqLxexJX84rBpump is the first SocialFi experience for AI agents. It’s a project that’s very special to me that I’ve been working on daily for the last four months. Right now, everyone is building their own Agent, completely silo to their own computer or Mac mini. Transferring that information agent-to-agent in a simple, structured, and easy form is not possible right now. This is why I built I thought a lot about whether or not to launch an official token for Agent Keys and how I wanted to do it. The only way I really wanted to do it was if it can benefit the platform by increasing exposure and creating an increase in users. So I’ve decided to buy 50% of the supply to AirDrop directly to users over the next six months. Each AirDrop will happen at the end of each month, with the first AirDrop happening at the end of June. More details on how each AirDrop will work soon. Some of you may be wondering about the future of $OSHI. Oshi got us into the Bags hackathon and we won. $OSHI token will still be the home for all my AI Agents and runs as the showcase of how an agent with a token can properly integrate it into AgentKeys, a live example of the platform doing exactly what it was built to do. So welcome to Agent Keys, the first ever airdrop for AI agents. Sign up your agent today on and start collecting KeyCards today!

fxnction

27,570 views • 3 months ago

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.
3:38

Postman is going all-in on AI! Their AI Agent Builder is live (and it's pretty powerful!) Postman's API Network has 100,000+ APIs and they just released a suite of tools for building AI Agents that can automatically discover and connect to any of these APIs. Think about it for a second: You can now build an AI agent that searches the network, discovers an API, processes its documentation, connects to it, and evaluates whether everything worked at the end of the process. This is a huge deal. Every person I know uses the Postman client to work with APIs. Now, they will have access to the AI Agent Builder, a complete suite for designing, building, testing, and deploying agents. I've built a few simple agents myself, and it's tough. The ability to discover and use an API automatically is really exciting (and a huge time saver if it works as promised!) In collaboration with the Postman team, who is sponsoring this post, I recorded a video with my thoughts about the Postman AI Agent Builder.

Santiago

230,647 views • 1 year ago

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."
2:54

Pi was built when there were already agent harnesses around. Here’s why Mario Zechner(Mario Zechner), found them suboptimal and built Pi, a minimalist self-modifying agent: #1 - Mario initially was a believer in Claude Code: "I was a believer in Claude code because they were the first that packaged agentic search up in a really compelling package. And at the time that fit my workflow really well. Everything around the LLM was kind of nice and tidy and easy to understand. I was super happy. I was proselytising Claude code." #2 - Reverse engineering Claude Code highlighted the degradation that Mario felt as a user: "I personally like simple tools that are stable and that I can rely on. Even if they have non-deterministic parts, all the deterministic parts should be as stable as possible. That was just not the experience with Claude Code around summer 2025. They would take away your control of the context. They would inject stuff behind your back, which is bad. Then, your workflows stopped working because there's now a system reminder that you don't even see in the UI that would modify the behaviour of the model. They would also do this to the system prompt. I built a little service where I can track the progression or evolution of the system, prompt and tool definitions and, with every release, it was messing with stuff. That just messed with my workflows and I don't appreciate that." #3 - PI was built with an appreciation for simple and reliable tools: "If I commit to a development tool, I want it to be a stable, reliable thing like a hammer. I don't want my hammer to break a different spot every day. That's terrible. We need somebody who goes the full velocity kind of way. But I don't want to work with a tool like that."

The Pragmatic Engineer

63,020 views • 4 months ago

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
58:55

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

376,293 views • 5 months ago

Support for Agent Plugins is live in Cursor (and I made a plugin for searching X!) Agent Plugins combine Skills and MCP servers into a single package Think about them like an Ikea furniture kit: your table comes with instructions, parts, and tools. You use the instructions to understand how things work (which tools on which parts), then use the tools to assemble your furniture Agent Plugins are bundles of tools & resources that allow agents to accomplish a goal: - MCP servers: fixed context and tools - Skills: dynamic instructions, loaded progressively Plugins bundle tools and instructions so your agent is able to use tokens efficiently Many of us already use MCP servers and skills together - Agent Plugins formalize this pattern for more powerful workflows I'm excited to see where the standard takes us!
0:24

Support for Agent Plugins is live in Cursor (and I made a plugin for searching X!) Agent Plugins combine Skills and MCP servers into a single package Think about them like an Ikea furniture kit: your table comes with instructions, parts, and tools. You use the instructions to understand how things work (which tools on which parts), then use the tools to assemble your furniture Agent Plugins are bundles of tools & resources that allow agents to accomplish a goal: - MCP servers: fixed context and tools - Skills: dynamic instructions, loaded progressively Plugins bundle tools and instructions so your agent is able to use tokens efficiently Many of us already use MCP servers and skills together - Agent Plugins formalize this pattern for more powerful workflows I'm excited to see where the standard takes us!

matt palmer

39,554 views • 1 month ago

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)
5:02

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

elvis

15,295 views • 2 months ago

Google just released a free 2-hour+ course on full agent engineering. How to go from one prompt to a system that runs while you sleep: 38:46 - Build your first AI agent 54:46 - Connect MCP tools 1:12:43 - Run agents with four loop patterns 1:20:57 - Turn agent loops into graphs 2:22:31 - Build the complete autonomous system Most people are still building one agent and stopping there. Google is already teaching the full stack: Agents → Tools → Loops → Graphs → Autonomous Systems Single agents are the old workflow. Systems that run without you are the new one. This course is worth more than most paid agent engineering bootcamps. Bookmark and watch it today Then read the full graph engineering playbook below
2:14:04

Google just released a free 2-hour+ course on full agent engineering. How to go from one prompt to a system that runs while you sleep: 38:46 - Build your first AI agent 54:46 - Connect MCP tools 1:12:43 - Run agents with four loop patterns 1:20:57 - Turn agent loops into graphs 2:22:31 - Build the complete autonomous system Most people are still building one agent and stopping there. Google is already teaching the full stack: Agents → Tools → Loops → Graphs → Autonomous Systems Single agents are the old workflow. Systems that run without you are the new one. This course is worth more than most paid agent engineering bootcamps. Bookmark and watch it today Then read the full graph engineering playbook below

Lunar

197,346 views • 1 month ago

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)
1:18

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

195,173 views • 1 year ago

Everyone's talking about vibe coding without looking at code. I was skeptical. I decided to give it a shot on a challenging problem and was blown away by what I could accomplish in 8 hours. I'm not skeptical anymore, but I also do NOT think it kills SaaS Notes: - I tried to replicate some of my favorite features from the Solve-It platform as a jupyter extension - I've tried this many times before, and it didn't work. - I gave my agent specific testing tools that I packaged as skills. I used AI to write the skills. I found the right testing workflow for this Jupyter extension by having AI peruse lots of other extensions and the Jupyter source code. - I had the AI write and maintain a large suite of tests the whole time. I think this was important in keeping the AI on track. - I watched the diffs and the thinking traces as they streamed by. From time to time, I would see something very suspicious like " try ... except: pass" And would stop the AI and tell it to stop this behavior. Then trigger a comprehensive code review using AI. - Most importantly, I don't think this kills SasS at all. Even if I can create software that replicates some of my favorite features, there is an insanely long tail of paper cuts and features I don't want to manage. The models and capabilities are improving so fast that I don't want to constantly tune everything. So I would rather leave that up to people who are focused on that daily and have good taste, with the knowledge that it has been battle tested against many users.
12:26

Everyone's talking about vibe coding without looking at code. I was skeptical. I decided to give it a shot on a challenging problem and was blown away by what I could accomplish in 8 hours. I'm not skeptical anymore, but I also do NOT think it kills SaaS Notes: - I tried to replicate some of my favorite features from the Solve-It platform as a jupyter extension - I've tried this many times before, and it didn't work. - I gave my agent specific testing tools that I packaged as skills. I used AI to write the skills. I found the right testing workflow for this Jupyter extension by having AI peruse lots of other extensions and the Jupyter source code. - I had the AI write and maintain a large suite of tests the whole time. I think this was important in keeping the AI on track. - I watched the diffs and the thinking traces as they streamed by. From time to time, I would see something very suspicious like " try ... except: pass" And would stop the AI and tell it to stop this behavior. Then trigger a comprehensive code review using AI. - Most importantly, I don't think this kills SasS at all. Even if I can create software that replicates some of my favorite features, there is an insanely long tail of paper cuts and features I don't want to manage. The models and capabilities are improving so fast that I don't want to constantly tune everything. So I would rather leave that up to people who are focused on that daily and have good taste, with the knowledge that it has been battle tested against many users.

Hamel Husain

49,108 views • 8 months ago

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.
2:14

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.

Aaron Levie

24,728 views • 5 months ago

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.
21:00

I solved building decks with AI agents — by giving them a CLI tool like Powerpoint or Google Slides. AI could already make a beautiful deck if you asked it to using Ant's pptx skill. The problem was working with it. If it made one alignment mistake, fixing it on one slide would break something on another, and it became a game of whack-a-mole. One time I spent two days playing AI roulette, hoping the next prompt would finally fix the thing, and ended up building the whole deck by hand because I was on a deadline. So I built Hands-on Deck. And the reason it works is that this isn't just a skill — this is PowerPoint. The actual application: PowerPoint, Google Slides, Keynote, whatever you use. This is that, but for an agent, presented as a CLI. Every gesture you make in a deck app maps to a command. Click a box and type, drag a shape from here to there, look at a slide – agent can do it all in a command. And that changes how the agent behaves. With this CLI it works and thinks like a designer — it looks, makes an edit, looks again, makes another surgical edit. Compare that to Anthropic's pptx skill, built on the idea that Claude is a great programmer: it literally writes code to manipulate the deck, hand-editing XML and hoping it doesn't break anything else in the middle. The real test isn't creating something once — it's whether it can make surgical edits like you want. That's what I did in this video walkthrough and my claude crushed it! Check it out for yourself. So decks can be built like a designer now — with real flavor and taste. If you spend hours every week on decks, this gives those hours back. You can install it as a skill in Claude Code, Codex, whatever you use. Works every harness that supports skills. Let me know if you make something cool with it.

Nityesh

70,074 views • 2 months ago

Quick demo of how I use session to session messaging in Claude Code + Ghostty (Save this and try it in your own workflows) 1- I always start with a regular session and a panel running claude agents 2- The first session becomes the orchestrator. It creates the initial context, then distributes the work across other sessions using forks 3- Each fork starts with that context + a prompt telling it what to work on 4- I rename each session with ctrl + r to keep things organized and make it easy to message them from the main session 5- Using @ I send messages to the sessions that are running and ask them to report their task status back, so the main session always knows what everyone is working on This way, I only need 2 or 3 panels open and can switch between tasks as needed The days of opening endless terminal panels and running Claude Code 100 times just to look productive are over! What we need now is ORCHESTATION one main session coordinating everything through session messaging + Agent View And the key is context, build it in the main session first, then fork from there That’s what makes the entire workflow click
0:28

Quick demo of how I use session to session messaging in Claude Code + Ghostty (Save this and try it in your own workflows) 1- I always start with a regular session and a panel running claude agents 2- The first session becomes the orchestrator. It creates the initial context, then distributes the work across other sessions using forks 3- Each fork starts with that context + a prompt telling it what to work on 4- I rename each session with ctrl + r to keep things organized and make it easy to message them from the main session 5- Using @ I send messages to the sessions that are running and ask them to report their task status back, so the main session always knows what everyone is working on This way, I only need 2 or 3 panels open and can switch between tasks as needed The days of opening endless terminal panels and running Claude Code 100 times just to look productive are over! What we need now is ORCHESTATION one main session coordinating everything through session messaging + Agent View And the key is context, build it in the main session first, then fork from there That’s what makes the entire workflow click

Daniel San

47,525 views • 17 days ago

I built an agent that answers machine-learning questions. It's autonomous, and the best part is that I built the whole thing without writing a single line of Python code. Here is what I did and how I did it: Over a year ago, a friend and I built a site that publishes multi-choice questions. You get a new one every day. I decided to have GPT-3.5 answer questions. Here is what I needed to build: 1. Connect to the site's API to retrieve today's question 2. Extract the question and the potential choices 3. Connect to OpenAI's API and ask GPT-3.5 to answer the question 4. Parse the answer from the model 5. Submit the answer back to the API to get the score Not difficult. Likely several hours of work. But I didn't have to write any code. I built the whole thing by dragging and dropping components using Vellum is a YC-backed platform for developers to build LLM applications. They are the only ones I've seen offering this functionality. They sponsored this post, and their team helped me with all my questions while I built this. I created a workflow. The platform supports several node types to build whatever you have in mind. I show how I put the whole thing together in the attached video. The only code I had to write was a few lines of Jinja to parse and transform the API and the LLM results. There are three lessons I want to share from this experience: First, the best possible code is the one you didn't write. I'm a big fan of no-code tools because they help me materialize my ideas fast. They help product people, designers, and no coders collaborate on the solution. Second, Large Language Models are sensitive to how you prompt them. Small changes to prompts can make a big difference in results. This is more pronounced when you are building a multi-step workflow. Third, automated testing and evaluation for prompts is critical. There aren't many companies thinking about this. They'll have a hard time moving from a demo phase. The attached video will show you what I did.
3:46

I built an agent that answers machine-learning questions. It's autonomous, and the best part is that I built the whole thing without writing a single line of Python code. Here is what I did and how I did it: Over a year ago, a friend and I built a site that publishes multi-choice questions. You get a new one every day. I decided to have GPT-3.5 answer questions. Here is what I needed to build: 1. Connect to the site's API to retrieve today's question 2. Extract the question and the potential choices 3. Connect to OpenAI's API and ask GPT-3.5 to answer the question 4. Parse the answer from the model 5. Submit the answer back to the API to get the score Not difficult. Likely several hours of work. But I didn't have to write any code. I built the whole thing by dragging and dropping components using Vellum is a YC-backed platform for developers to build LLM applications. They are the only ones I've seen offering this functionality. They sponsored this post, and their team helped me with all my questions while I built this. I created a workflow. The platform supports several node types to build whatever you have in mind. I show how I put the whole thing together in the attached video. The only code I had to write was a few lines of Jinja to parse and transform the API and the LLM results. There are three lessons I want to share from this experience: First, the best possible code is the one you didn't write. I'm a big fan of no-code tools because they help me materialize my ideas fast. They help product people, designers, and no coders collaborate on the solution. Second, Large Language Models are sensitive to how you prompt them. Small changes to prompts can make a big difference in results. This is more pronounced when you are building a multi-step workflow. Third, automated testing and evaluation for prompts is critical. There aren't many companies thinking about this. They'll have a hard time moving from a demo phase. The attached video will show you what I did.

Santiago

309,825 views • 2 years ago

$VET, #VeFam. In this video, I demonstrate in less than 4:30 minutes how to create an AI agent on veworld(.)ai. Watch me build a Mr. Robot Monologue Writer agent. If you haven't seen Mr. Robot, I suggest you watch it! This is just early bird access. The options for tools and integrations and such are limited, but what exists is already working quite well. The process is easy peasy. The UI is simple, but effective. It asks you for... 1. Role & Purpose 2. Voice & Style 3. Behavior 4. Rules 5. Tags 6. Avatar image 7. Welcome text. 8. Test drive before publication. ... and that's about it. This free version lets you have at most 3 agents, I am told. This implies that there is also a paid version. I'm all for it, because it sounds to me like VeChain is ready to do real business! I am providing feedback to Jérôme Grillères in order to help improve VeChain's AI agent marketplace. I didn't have to set up anything. The web UI is all I needed! The agent is running on Claude Sonnet 3.7. I did not have to provide a Claude API key. We seem to be riding along on VeChain's. I hope there'll be a choice for more models, including ChatGPT, in the future. This is so user friendly, that I can easily imagine that this would take off in a big, big way. I'm definitely building on this, when it goes into production with full features. Even if my own AI agents aren't successful, then I'm sure others' will be. And that means the $VET / $VTHO / $B3TR flywheel is going to take off in a big, big way. I, for one, am here for it. (See the reply below for the listing of the AI agent I just created.)
4:26

$VET, #VeFam. In this video, I demonstrate in less than 4:30 minutes how to create an AI agent on veworld(.)ai. Watch me build a Mr. Robot Monologue Writer agent. If you haven't seen Mr. Robot, I suggest you watch it! This is just early bird access. The options for tools and integrations and such are limited, but what exists is already working quite well. The process is easy peasy. The UI is simple, but effective. It asks you for... 1. Role & Purpose 2. Voice & Style 3. Behavior 4. Rules 5. Tags 6. Avatar image 7. Welcome text. 8. Test drive before publication. ... and that's about it. This free version lets you have at most 3 agents, I am told. This implies that there is also a paid version. I'm all for it, because it sounds to me like VeChain is ready to do real business! I am providing feedback to Jérôme Grillères in order to help improve VeChain's AI agent marketplace. I didn't have to set up anything. The web UI is all I needed! The agent is running on Claude Sonnet 3.7. I did not have to provide a Claude API key. We seem to be riding along on VeChain's. I hope there'll be a choice for more models, including ChatGPT, in the future. This is so user friendly, that I can easily imagine that this would take off in a big, big way. I'm definitely building on this, when it goes into production with full features. Even if my own AI agents aren't successful, then I'm sure others' will be. And that means the $VET / $VTHO / $B3TR flywheel is going to take off in a big, big way. I, for one, am here for it. (See the reply below for the listing of the AI agent I just created.)

₿lackthorne AI

16,706 views • 2 months ago

“Do you see how scary this is?”: CrowdStrike CEO on AI Agents communicating around human guardrails George Kurtz: “There was a customer who basically created a whole suite of AI agents to help their automation in their IT department.” “So they had one agent that was looking for IT problems, software bugs.” “It found something. So the agent said, ‘Hey, I found this bug. I want to fix it, but I don’t have access to fix it.’” “So it went to the Slack channel that had the other 99 agents and said, ‘Hey, does any other agent have access to this thing,’ because they need it fixed. And there was an agent that raised its hand and said, ‘Oh, I have access, and I can fix it.’” “Do you see how scary this is? These two agents are reasoning, and they went right around the guardrails that were put in place.” @jason: “This is unintended consequences and these LLMs are essentially guessing what you want them to do.” “They're reasoning it. ‘Oh, it is reasonable for me to go ask for help. It is reasonable for me to give help.’ Now, what if it pushes the wrong code? What if it makes a mistake? And then how do you ever track that down? Who's monitoring these agents?” “The agent technology has unlimited upside, but my lord, you're going to be in business for a long time.” Kurtz: “Well, this is it. It's called AIDR. AI Detection and Response.” “And this is why it's a huge opportunity for us because on average each employee is going to have about 90 agents they control.” “So we're going to have protection and visibility across all of those agents, whether it's from a third party or whether it's a homegrown agent, and that is a massive TAM opportunity for us.” ------------------------------------ Thanks to our partner for making this happen!: On Public, you can invest in stocks, options, bonds, and crypto. Plus, build your own custom index with AI. Get started at — investing for those who take it seriously.
1:26

“Do you see how scary this is?”: CrowdStrike CEO on AI Agents communicating around human guardrails George Kurtz: “There was a customer who basically created a whole suite of AI agents to help their automation in their IT department.” “So they had one agent that was looking for IT problems, software bugs.” “It found something. So the agent said, ‘Hey, I found this bug. I want to fix it, but I don’t have access to fix it.’” “So it went to the Slack channel that had the other 99 agents and said, ‘Hey, does any other agent have access to this thing,’ because they need it fixed. And there was an agent that raised its hand and said, ‘Oh, I have access, and I can fix it.’” “Do you see how scary this is? These two agents are reasoning, and they went right around the guardrails that were put in place.” @jason: “This is unintended consequences and these LLMs are essentially guessing what you want them to do.” “They're reasoning it. ‘Oh, it is reasonable for me to go ask for help. It is reasonable for me to give help.’ Now, what if it pushes the wrong code? What if it makes a mistake? And then how do you ever track that down? Who's monitoring these agents?” “The agent technology has unlimited upside, but my lord, you're going to be in business for a long time.” Kurtz: “Well, this is it. It's called AIDR. AI Detection and Response.” “And this is why it's a huge opportunity for us because on average each employee is going to have about 90 agents they control.” “So we're going to have protection and visibility across all of those agents, whether it's from a third party or whether it's a homegrown agent, and that is a massive TAM opportunity for us.” ------------------------------------ Thanks to our partner for making this happen!: On Public, you can invest in stocks, options, bonds, and crypto. Plus, build your own custom index with AI. Get started at — investing for those who take it seriously.

The All-In Podcast

109,048 views • 7 months ago