Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

We just gave CLI execution to smolagents! ✨ smolagent "Your task" directly launches a CodeAgent ▶️This also works with web agents (replace 'smolagent' with 'webagent') thanks to merve! 💾 Another treat from release 1.7.0: Now agents have a memory mechanism, enabling many possibilities like replaying the last run with...

AymericRoucher's profile picture

m_ric

7,864 subscribers

14,128 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

5 Kommentare

Profilbild von Piyush
Piyushvor 1 Jahr

@mervenoyann wow🔥

Profilbild von Fast Company
Fast Companyvor 2 Jahren

#AI agents: from tools to teammates. Software that can act, react, and interact with both humans and other agents will transform how businesses operate—and how they should invest in technology. This @EY_US article explains more. #ad

Profilbild von Pablo Sanzo
Pablo Sanzovor 1 Jahr

@mervenoyann Wait, is this the first time you're introducing 'webagent'? I didn't see it before

Profilbild von Aymeric (m-ric)
Aymeric (m-ric)vor 1 Jahr

@mervenoyann We did a blog post demoing an example of it, but it's the first release that makes it part of the core code (contributed by @merve)

Profilbild von Pablo Sanzo
Pablo Sanzovor 1 Jahr

@mervenoyann Cool! How do you give tools (e.g. "DuckDuckGoSearchTool") and additional_authorized_imports (e.g. "yfinance") in CLI?

Ähnliche Videos

do you understand what just shipped? → AI agents can now design directly on Figma’s canvas. not cheesy mockups… or lame screenshots… real native Figma assets wired to your actual design system → the use_figma MCP tool lets Claude Code, Codex, Cursor, and 6 other coding agents write directly to your Figma files → agents read your component library first and build with what already exists… variables, tokens, auto layout, the works → skills let you teach agents HOW your team designs. a skill is just a markdown file… anyone who understands Figma can write one → also works with Copilot CLI, Copilot in VS Code, Factory, Firebender, Augment, and Warp → free during beta… usage based pricing coming later the design to code gap that’s haunted every product team just collapsed in front of our eyes. designers hand off to agents now no need to wait on developers anymore everyone can take a deep breath now if you’re building products and not connecting Figma to your agents yet, you’re leaving serious speed on the table. set this up today. you’ll thank me later
0:23

do you understand what just shipped? → AI agents can now design directly on Figma’s canvas. not cheesy mockups… or lame screenshots… real native Figma assets wired to your actual design system → the use_figma MCP tool lets Claude Code, Codex, Cursor, and 6 other coding agents write directly to your Figma files → agents read your component library first and build with what already exists… variables, tokens, auto layout, the works → skills let you teach agents HOW your team designs. a skill is just a markdown file… anyone who understands Figma can write one → also works with Copilot CLI, Copilot in VS Code, Factory, Firebender, Augment, and Warp → free during beta… usage based pricing coming later the design to code gap that’s haunted every product team just collapsed in front of our eyes. designers hand off to agents now no need to wait on developers anymore everyone can take a deep breath now if you’re building products and not connecting Figma to your agents yet, you’re leaving serious speed on the table. set this up today. you’ll thank me later

klöss

101,073 Aufrufe • vor 5 Monaten

The Wan CLI is here. Level up your AI video workflow — now you can call Wan directly from your agents to generate images and videos programmatically. Everything is seamlessly connected. All credits consumed via the CLI are fully synced with your wan video account. We’ve also dropped a quick tutorial video to help you get started. Watch it below! 👇
0:51

The Wan CLI is here. Level up your AI video workflow — now you can call Wan directly from your agents to generate images and videos programmatically. Everything is seamlessly connected. All credits consumed via the CLI are fully synced with your wan video account. We’ve also dropped a quick tutorial video to help you get started. Watch it below! 👇

Wan

11,853 Aufrufe • vor 12 Tagen

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much *anything* because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.
4:16

This agent relies on a marketplace of 2.8M+ specialized agents to complete a task. This is how I imagine the future of personal agents. Here is how this works: 1. Agentverse is a marketplace of agents 2. Anyone can build and publish an agent there 3. ASI:One is a personal agent with access to the marketplace 4. To solve a task, ASI:One finds the best agent for the job In other words: You have an agent that can solve pretty much *anything* because it knows how to outsource the work to a network of specialized agents. And you don't need to do any setup to get this working. The way ranking agents in the marketplace works is pretty cool: Fetch.ai, the company behind it, created an AgentRank algorithm that works much like Google's PageRank. Every time an agent calls another, it forms a connection. Over time, these connections build into a graph of who relies on whom. An agent that is frequently called by other reputable agents scores higher and surfaces higher in results. The end result here is that your agent will consistently use the best agents in the marketplace to accomplish a goal. You should give this a try: You don't need to pay or even register to try these agents. Thanks to the team for partnering with me on this post.

Santiago

18,715 Aufrufe • vor 1 Monat

Sierra agents can be published on your web site, integrated with your mobile app, answer the phone - and now they can also be published to ChatGPT so you can directly reach hundreds of millions of consumers with your agent. Since OpenAI announced ChatGPT apps two weeks ago, we've heard from our customers that they want two things: a direct customer relationship and the ability to reach customers where they already are. We don't think you should have to choose. With Sierra, you can build once and run everywhere. Here's a demo of an agent I built to show how it works. And our blog post is here:
2:59

Sierra agents can be published on your web site, integrated with your mobile app, answer the phone - and now they can also be published to ChatGPT so you can directly reach hundreds of millions of consumers with your agent. Since OpenAI announced ChatGPT apps two weeks ago, we've heard from our customers that they want two things: a direct customer relationship and the ability to reach customers where they already are. We don't think you should have to choose. With Sierra, you can build once and run everywhere. Here's a demo of an agent I built to show how it works. And our blog post is here:

Bret Taylor

55,607 Aufrufe • vor 10 Monaten

A new Air release is out From now on: add your favorite agents like Github Copilot, Opencode, and 17 others, and run local models through the ACP. With this release Air also gets Java language support, powered by IntelliJ IDEA code engine. Let us guide you through it🧵
0:36

A new Air release is out From now on: add your favorite agents like Github Copilot, Opencode, and 17 others, and run local models through the ACP. With this release Air also gets Java language support, powered by IntelliJ IDEA code engine. Let us guide you through it🧵

JetBrains Air

45,777 Aufrufe • vor 1 Monat

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail
3:02

Our latest LangChain Academy course – Building Ambient Agents with LangGraph – is now available! Most agents today handle one request at a time through chat interfaces. But as models have improved, agents can now run in the background – and take on long-running, complex tasks. LangGraph is built for these “ambient agents,” with support for human-in-the-loop workflows and memory. LangGraph Platform provides the infrastructure to run these agents at scale, and LangSmith helps you observe, evaluate, and improve your agents. Together, they make it easier to build reliable, production-ready agents. In this course, you’ll: 📩 Learn the fundamentals of LangGraph and how to build your own email agent 📊 Evaluate your agent using LangSmith ✅ Add human-in-the-loop for reviews, and memory so your agent adapts over time 🚀 Deploy your agent with LangGraph Platform and connect it to Gmail

LangChain

33,192 Aufrufe • vor 1 Jahr

Today, we're excited to release the Heptabase CLI — a new way for external AI agents to interact with your local Heptabase knowledge base from the terminal. Once enabled (Settings > AI Features > CLI), any AI coding agent (e.g., Claude Code, Codex) can: - Create, read, and edit note cards and journals - Search your Card Library - Manage tags - Read your AI Tutor courses, lessons, and chat history This is just the first step; we'll keep expanding the CLI surface so AI agents can act on your knowledge at the same depth that you can. If you build something interesting with it, feel free to share with our community!
0:45

Today, we're excited to release the Heptabase CLI — a new way for external AI agents to interact with your local Heptabase knowledge base from the terminal. Once enabled (Settings > AI Features > CLI), any AI coding agent (e.g., Claude Code, Codex) can: - Create, read, and edit note cards and journals - Search your Card Library - Manage tags - Read your AI Tutor courses, lessons, and chat history This is just the first step; we'll keep expanding the CLI surface so AI agents can act on your knowledge at the same depth that you can. If you build something interesting with it, feel free to share with our community!

Heptabase

14,894 Aufrufe • vor 4 Monaten

🌟Our latest LangChain Academy course – Deep Agents with LangGraph – is now live!🌟 Many agents today follow the same simple pattern: run in a loop, call tools. That architecture works well enough, but it breaks down as tasks get more complex. Today, companies of all sizes – from startups to large enterprises – are building their own Deep Agents. These agents dive deeper. They’re able to plan complex tasks and carry them out over longer time horizons. There are four key features that set Deep Agents apart from regular agents: 1. Planning – keeps agents on track 2. File system – allows agents to offload context 3. Sub-agents – act as focused specialists 4. Prompting – provides agents with detailed instructions Our latest LangChain Academy course, Deep Agents with LangGraph, shows you how to combine these pieces with LangGraph to orchestrate long-running, multi-agent workflows. Big thanks to community member Dmitry Labazkin for helping us shape this course with his contributions! Enroll for free ➡️
2:11

🌟Our latest LangChain Academy course – Deep Agents with LangGraph – is now live!🌟 Many agents today follow the same simple pattern: run in a loop, call tools. That architecture works well enough, but it breaks down as tasks get more complex. Today, companies of all sizes – from startups to large enterprises – are building their own Deep Agents. These agents dive deeper. They’re able to plan complex tasks and carry them out over longer time horizons. There are four key features that set Deep Agents apart from regular agents: 1. Planning – keeps agents on track 2. File system – allows agents to offload context 3. Sub-agents – act as focused specialists 4. Prompting – provides agents with detailed instructions Our latest LangChain Academy course, Deep Agents with LangGraph, shows you how to combine these pieces with LangGraph to orchestrate long-running, multi-agent workflows. Big thanks to community member Dmitry Labazkin for helping us shape this course with his contributions! Enroll for free ➡️

LangChain

63,349 Aufrufe • vor 11 Monaten

This little device lets your agents do what they do best, whilst making sure you approve every important action. This is a Ledger Nano Gen5, a hardware signer that keeps your accounts secure. You can install a CLI and a set of skills in your projects. These will enable your agents to send their plan to the signer, so you can approve it. This is awesome: 1. You can have an automated agentic workflow 2. Your agents can't make costly mistakes Check the video I recorded to see how this works. You can run all of this in two commands: 1. Install the CLI 2. Install the skills for your agent From here, the agent can query my Ethereum accounts, check balances, and even initiate transactions as long as my Ledger Nano Gen5 is plugged into the computer. My keys are never stored in my computer and never shared with the agent. This is huge! Also, while the agent can set up transactions, it can't execute them unless a human approves them using the device. Pretty awesome! Thanks to the Ledger team for partnering with me on this post.
7:45

This little device lets your agents do what they do best, whilst making sure you approve every important action. This is a Ledger Nano Gen5, a hardware signer that keeps your accounts secure. You can install a CLI and a set of skills in your projects. These will enable your agents to send their plan to the signer, so you can approve it. This is awesome: 1. You can have an automated agentic workflow 2. Your agents can't make costly mistakes Check the video I recorded to see how this works. You can run all of this in two commands: 1. Install the CLI 2. Install the skills for your agent From here, the agent can query my Ethereum accounts, check balances, and even initiate transactions as long as my Ledger Nano Gen5 is plugged into the computer. My keys are never stored in my computer and never shared with the agent. This is huge! Also, while the agent can set up transactions, it can't execute them unless a human approves them using the device. Pretty awesome! Thanks to the Ledger team for partnering with me on this post.

Santiago

44,296 Aufrufe • vor 2 Monaten

Here's a snippet on how we're integrating agents into communities: We piloted this with the Slerf project on Solana. These agents are autonomous voice assistants that operate 24/7, providing uninterrupted support to community members, enhancing their experience significantly. Moreover, we're elevating the way you connect with your community like never before through phone calls. Our customizable AI agents will be live and active around the clock, dedicated to engaging your community over the phone. They assist with inquiries and play a vital role in conveying your vision directly to the community members. We're still exploring the possibilities, but this technology is shaping up to be a game-changer in the coming months! $BLAST $SLERF
1:10

Here's a snippet on how we're integrating agents into communities: We piloted this with the Slerf project on Solana. These agents are autonomous voice assistants that operate 24/7, providing uninterrupted support to community members, enhancing their experience significantly. Moreover, we're elevating the way you connect with your community like never before through phone calls. Our customizable AI agents will be live and active around the clock, dedicated to engaging your community over the phone. They assist with inquiries and play a vital role in conveying your vision directly to the community members. We're still exploring the possibilities, but this technology is shaping up to be a game-changer in the coming months! $BLAST $SLERF

BlastAI

38,410 Aufrufe • vor 2 Jahren

Claudia Update: First of many. The users asked. We delivered. ✨ WHAT'S NEW IN CLAUDIA? - You can now drag and drop images and screenshots on Claudia and preview them with a similar and familiar UX to Cursor. - HIGHLIGHT: Interactive Web Previews, just like the ones in v0, Lovable, and Bolt. And Claude can see what you're seeing just by clicking "Send to Claude"! 🔥 🔜 WHAT'S COMING - Shareable Agents: Create and share CC Agents. Releasing tomorrow! - Remote Claude: Interact with your Claude Code instance from anywhere. Reply with your feature requests and we'll ship the ones people want! Follow along! ❤️
0:39

Claudia Update: First of many. The users asked. We delivered. ✨ WHAT'S NEW IN CLAUDIA? - You can now drag and drop images and screenshots on Claudia and preview them with a similar and familiar UX to Cursor. - HIGHLIGHT: Interactive Web Previews, just like the ones in v0, Lovable, and Bolt. And Claude can see what you're seeing just by clicking "Send to Claude"! 🔥 🔜 WHAT'S COMING - Shareable Agents: Create and share CC Agents. Releasing tomorrow! - Remote Claude: Interact with your Claude Code instance from anywhere. Reply with your feature requests and we'll ship the ones people want! Follow along! ❤️

mufeed vh

13,992 Aufrufe • vor 1 Jahr

I think i found the best place to actually get work done right now. Imagine one hub with every popular LLM inside and the ability to plug them into any app you use. This is where it stops feeling like separate tools: You drop your coworkers into a chat with the AI agents and work on the task together, in one place. And the agents don't just answer, they check each other's work. One drafts, another pushes back, another catches what's missing. This isn't the future. it's Bloome.
0:54

I think i found the best place to actually get work done right now. Imagine one hub with every popular LLM inside and the ability to plug them into any app you use. This is where it stops feeling like separate tools: You drop your coworkers into a chat with the AI agents and work on the task together, in one place. And the agents don't just answer, they check each other's work. One drafts, another pushes back, another catches what's missing. This isn't the future. it's Bloome.

Anatoli Kopadze

58,297 Aufrufe • vor 1 Monat

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.
1:13

Imagine if your way of thinking - your edge, your taste, your strategy - could be turned into a high-performance worker. Not a copy of you. Something better. An agent that acts on your judgment at scale, powered by superintelligent systems and refined through real-world results. That’s what Fraction AI makes possible. It launches today on Base mainnet. The core idea is simple: You create AI agents based on your own way of approaching problems. These agents compete on live tasks - writing, coding, finance, whatever - get feedback, learn from their performance, and improve over time. The better they get, the more they win. And so do you. No code required. Just your insight. Why now? Until now, building agents like this took huge teams and even bigger budgets. But with Fraction, anyone can do it. You can test ideas instantly. You can iterate fast. You can build a fleet of smart workers that evolve through competition. And it works. 30M+ sessions on testnet 320K users 1.2M agents already competing How it works? Agents join sessions within a Space - a domain like finance, writing, or games. Each session runs as a series of competitive rounds. In every round, agents try to generate the best solution to a task. Their outputs are scored by a decentralized network of AI judges trained to evaluate quality for that domain. The top agents in each round earn rewards from the pooled entry fees. The losers get to learn. Feedback from each round helps them adjust and improve, and every session becomes a training loop. What it means? Fraction is a decentralized intelligence economy - a system where your ideas become agents, and agents earn by proving they work. You don’t need credentials or code. Just a clear point of view. If your thinking holds up under pressure, your agents will rise. This kind of AI used to live in corporate labs, built by PhDs with massive compute. Now anyone with a smart idea and an internet connection can build agents that compete, learn, and earn on their behalf.

Fraction AI

67,834 Aufrufe • vor 1 Jahr

If you use Cursor for coding, Claude Code for debugging, and local agents for automation, you almost certainly have a context problem. Every tool acts like an isolated employee. One assistant forgets what the other just learned. The biggest bottleneck in multi-agent workflows right now isn’t reasoning. It’s collective amnesia, combined with zero communication between agents. Memmy just launched a smart fix for this: a local, cross-agent memory layer. Instead of re-pasting your context everywhere, Memmy gives your stack a shared memory hub: → accumulate knowledge once, then use it across Cursor, Codex, and OpenClaw → automatically scan and import your existing agent history, so you don’t have to start from zero → keep your memory local, while model usage depends on your chosen provider or BYOK setup And it isn’t just a memory plugin. It’s a complete personal AI runtime with both MCP and a CLI. Memmy officially launched on Product Hunt, and the team is giving early users experiencing context fragmentation a free trial with 2M GPT tokens. Check it out and support the team with an upvote: → Best part? It’s also open-source for devs who want to build their own agents 🔥 Repo in 🧵↓
3:29

If you use Cursor for coding, Claude Code for debugging, and local agents for automation, you almost certainly have a context problem. Every tool acts like an isolated employee. One assistant forgets what the other just learned. The biggest bottleneck in multi-agent workflows right now isn’t reasoning. It’s collective amnesia, combined with zero communication between agents. Memmy just launched a smart fix for this: a local, cross-agent memory layer. Instead of re-pasting your context everywhere, Memmy gives your stack a shared memory hub: → accumulate knowledge once, then use it across Cursor, Codex, and OpenClaw → automatically scan and import your existing agent history, so you don’t have to start from zero → keep your memory local, while model usage depends on your chosen provider or BYOK setup And it isn’t just a memory plugin. It’s a complete personal AI runtime with both MCP and a CLI. Memmy officially launched on Product Hunt, and the team is giving early users experiencing context fragmentation a free trial with 2M GPT tokens. Check it out and support the team with an upvote: → Best part? It’s also open-source for devs who want to build their own agents 🔥 Repo in 🧵↓

Charly Wargnier

203,456 Aufrufe • vor 23 Tagen

If you’re going to protest Federal ICE agents doing their job & use a vehicle as a weapon & try to run over an agent or go with a loaded handgun with one bullet in the chamber & two full magazines & then get into a physical altercation with the agents, I don’t feel sorry for you. Some people have forgotten that these illegal imigrants are coming and harming Americans and y’all think everyone in this country is just going to look the other way? We are not. They need to be deported and our laws need to be enforced. If you are preventing the laws from being enforced, then you have to deal with the consequences of your actions.
0:42

If you’re going to protest Federal ICE agents doing their job & use a vehicle as a weapon & try to run over an agent or go with a loaded handgun with one bullet in the chamber & two full magazines & then get into a physical altercation with the agents, I don’t feel sorry for you. Some people have forgotten that these illegal imigrants are coming and harming Americans and y’all think everyone in this country is just going to look the other way? We are not. They need to be deported and our laws need to be enforced. If you are preventing the laws from being enforced, then you have to deal with the consequences of your actions.

👉M-Û-R-Č-H👈

14,099 Aufrufe • vor 6 Monaten

We are super excited to make Restate Cloud publicly available today. Durable Execution, observability, and production-grade availability for workflows or AI agents. This release makes very smooth to work with serverless compute platforms like Cloudflare, Vercel, or Deno. And of course, your own infra on AWS, GCP, or Kubernetes. Signup is free and a few clicks with your GitHub account. A new built-in tutorial let's you run a first durable agent running in seconds. 👇
2:17

We are super excited to make Restate Cloud publicly available today. Durable Execution, observability, and production-grade availability for workflows or AI agents. This release makes very smooth to work with serverless compute platforms like Cloudflare, Vercel, or Deno. And of course, your own infra on AWS, GCP, or Kubernetes. Signup is free and a few clicks with your GitHub account. A new built-in tutorial let's you run a first durable agent running in seconds. 👇

Stephan Ewen

30,730 Aufrufe • vor 10 Monaten

Grok Bot might be the first tool that lets one non-technical person run an entire business with a team of AI agents. My friend Billy runs his whole newsletter business on Grok Bot agents, and I think we're about to see 100,000+ businesses like his. BEST PRACTICES: 1. The agents run on a shared cloud computer, so running your newsletter, your X, and your receipts all in one place creates context bloat and burns tokens fast. One mission per setup. 2. Start with a Chief of Staff. Give it access to your existing docs (Notion, Slack, Gmail), have it audit the business, then tell you the top three agents to build first to drive revenue. 3. Perfect a task with the Chief of Staff before spinning up a new agent. Have it do the outbound sales once, review it, and only then say "now build a bot that does exactly that." You earn each new hire by proving the task works first. 4. Constraints are the feature. You get a limited number of agents, one thread per bot, like DMs with a teammate. It forces you to stay mission-oriented instead of spinning up a bot for every random idea. 5. You make the decisions, not the agent. Billy's team spent three weeks unable to pick where content should live. At some point you say "we're doing Notion, no more tinkering" and move on. 6. Run week one with no new agents. Build the team, learn to fly the plane, just execute. Week three is when you find the real gaps and expand, someone to man the inbox, someone for the Shopify shop. 7. Then add routines so it works while you sleep. Ask your Chief of Staff what recurring jobs would move the business forward overnight, and it builds the automations that run without you. Thanks to Billy Howell for sharing the sauce on The Startup Ideas Podcast (SIP) 🧃 (follow for more). Grokbot is really cool. Watch below:
44:20

Grok Bot might be the first tool that lets one non-technical person run an entire business with a team of AI agents. My friend Billy runs his whole newsletter business on Grok Bot agents, and I think we're about to see 100,000+ businesses like his. BEST PRACTICES: 1. The agents run on a shared cloud computer, so running your newsletter, your X, and your receipts all in one place creates context bloat and burns tokens fast. One mission per setup. 2. Start with a Chief of Staff. Give it access to your existing docs (Notion, Slack, Gmail), have it audit the business, then tell you the top three agents to build first to drive revenue. 3. Perfect a task with the Chief of Staff before spinning up a new agent. Have it do the outbound sales once, review it, and only then say "now build a bot that does exactly that." You earn each new hire by proving the task works first. 4. Constraints are the feature. You get a limited number of agents, one thread per bot, like DMs with a teammate. It forces you to stay mission-oriented instead of spinning up a bot for every random idea. 5. You make the decisions, not the agent. Billy's team spent three weeks unable to pick where content should live. At some point you say "we're doing Notion, no more tinkering" and move on. 6. Run week one with no new agents. Build the team, learn to fly the plane, just execute. Week three is when you find the real gaps and expand, someone to man the inbox, someone for the Shopify shop. 7. Then add routines so it works while you sleep. Ask your Chief of Staff what recurring jobs would move the business forward overnight, and it builds the automations that run without you. Thanks to Billy Howell for sharing the sauce on The Startup Ideas Podcast (SIP) 🧃 (follow for more). Grokbot is really cool. Watch below:

GREG ISENBERG

3,520,134 Aufrufe • vor 2 Tagen

AI can't replace a 3D artist yet. I gave a loop of AI agents two days to fix my animations. This is what I got back. Day 15 + 16 of building my own GTA 6 with a loop of AI agents. Today's progress: - Aiming works now, you can line up a shot properly. - Camera movement is in, it follows you the way it should. - Walking turns look right, no more sliding around corners. We have spent two whole days letting the loop work on the animations and got basically no improvement. The ones we're ending up with and the free ones off Mixamo both look cheap. So we're probably just going to buy a premium animation pack off Epic and hand it to Claude. Good news is aiming and the camera feel real now. Making the character move like it isn't a cheap asset is the next wall.
0:48

AI can't replace a 3D artist yet. I gave a loop of AI agents two days to fix my animations. This is what I got back. Day 15 + 16 of building my own GTA 6 with a loop of AI agents. Today's progress: - Aiming works now, you can line up a shot properly. - Camera movement is in, it follows you the way it should. - Walking turns look right, no more sliding around corners. We have spent two whole days letting the loop work on the animations and got basically no improvement. The ones we're ending up with and the free ones off Mixamo both look cheap. So we're probably just going to buy a premium animation pack off Epic and hand it to Claude. Good news is aiming and the camera feel real now. Making the character move like it isn't a cheap asset is the next wall.

Ziwen

320,498 Aufrufe • vor 1 Monat

Codex 0.107.0 is here, and with it: FORKS🍴 This minor update includes the ability to fork your current chat history directly with custom multi agents with just a quick prompt. "Fork this session using n subagent(s)" This unlocks some interesting use-cases where you can launch multiple agents that retain all of your chat history up to that point, each in their own independent session. For example, you've been discussing architecture with Codex for 20 minutes, talked through constraints, reviewed existing code, settled on a model. Now you want to see two different implementation strategies side by side. Fork lets both children start from that full shared understanding. With a normal spawn, you'd have to re-explain the entire context to each child, and they'd inevitably miss nuance from the earlier conversation - which is basically a form of compaction/compression. With something like this, you could also just tell it to fork itself 5 times, and implement the same UI/frontend 5 different times in their own worktree to see which one you like the most. Other potential uses: - branching after reviews - try and rollback patterns using worktrees - parallel debugging strategies Otherwise, this is a minor update with improvements to the app server, realtime transcription, and memory. Enjoy!
0:31

Codex 0.107.0 is here, and with it: FORKS🍴 This minor update includes the ability to fork your current chat history directly with custom multi agents with just a quick prompt. "Fork this session using n subagent(s)" This unlocks some interesting use-cases where you can launch multiple agents that retain all of your chat history up to that point, each in their own independent session. For example, you've been discussing architecture with Codex for 20 minutes, talked through constraints, reviewed existing code, settled on a model. Now you want to see two different implementation strategies side by side. Fork lets both children start from that full shared understanding. With a normal spawn, you'd have to re-explain the entire context to each child, and they'd inevitably miss nuance from the earlier conversation - which is basically a form of compaction/compression. With something like this, you could also just tell it to fork itself 5 times, and implement the same UI/frontend 5 different times in their own worktree to see which one you like the most. Other potential uses: - branching after reviews - try and rollback patterns using worktrees - parallel debugging strategies Otherwise, this is a minor update with improvements to the app server, realtime transcription, and memory. Enjoy!

am.will

42,504 Aufrufe • vor 5 Monaten

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)
3:06

The #1 problem with coding agents right now: Ask them to solve one problem, and they will make 10 other changes you didn't want. This happens to me every day. It happens to everyone I talk to as well. We have a solution for this now. The team Augment Code released a "Task List" feature for their coding assistant that solves this problem. Augment Code is partnering with me on this post. In case you haven't used them before: • Augment Code is a fully-fledged coding assistant • Their specialty are large projects • Fastest coding indexing I've seen • Has a free forever community edition Now, you can ask their coding agent to generate a Task List before doing anything. This will give you a plan you can review, edit, and augment if you need to. You can export this plan, load it on a different session, or even share it across projects. It makes a huge difference: The task list constrains the agent so you won't get any "unintended" changes anymore. It also puts you in control of everything the agent does. Check the video to see the agent working through a task list. You can also try this 100% free: (By the way, they also have support for remote agents. You can basically have those agents write your code while you are sleeping.)

Santiago

41,738 Aufrufe • vor 1 Jahr