Loading video...

Video Failed to Load

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

Introducing /orchestrate, a skill that recursively spawns agents to tackle your most ambitious tasks with the Cursor SDK. We’ve used it to: - Autoresearch our internal skills, cutting token use by 20% while improving evals - Cut cold start times on our internal backend by 80%

Cursor

472,452 subscribers

536,059 views • 3 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

🚨 Announcing AutoBots - Recursively Self-Improving Agents (RSI) Super excited to launch our multi-LLM-based recursively self-improving agents We use DeepSeek Flash 4 for easy tasks and Fable 5 for super hard ones. The agents learn over time, becoming MORE efficient and smarter with each run We use these RSI agents to run our company! It's amazingly good with little to no human intervention required Examples include bug-fixing agents, viral tweet- or video-makers, growth-hacking agents, and so on. AutoBots work in the background to help increase your revenue.

🚨 Announcing AutoBots - Recursively Self-Improving Agents (RSI) Super excited to launch our multi-LLM-based recursively self-improving agents We use DeepSeek Flash 4 for easy tasks and Fable 5 for super hard ones. The agents learn over time, becoming MORE efficient and smarter with each run We use these RSI agents to run our company! It's amazingly good with little to no human intervention required Examples include bug-fixing agents, viral tweet- or video-makers, growth-hacking agents, and so on. AutoBots work in the background to help increase your revenue.

Bindu Reddy

2,504,428 views • 1 month ago

We’ve been working with OpenAI for the past few weeks to test their latest Computer-using Agent model. On our evals, CUA has set a new SOTA. Once integrated with an agent, it can complete long-horizon tasks previously impossible. Try CUA on our playground and Act SDK for free!

We’ve been working with OpenAI for the past few weeks to test their latest Computer-using Agent model. On our evals, CUA has set a new SOTA. Once integrated with an agent, it can complete long-horizon tasks previously impossible. Try CUA on our playground and Act SDK for free!

Scrapybara

89,707 views • 1 year ago

We just released the Databricks synthetic evaluation SDK! 🎉 We’ve found that synthesizing evals is a great way to hill climb your AI system before you’re able to get labels from domain experts. With this SDK, and our fancy diffing UI, users are able to improve the inner loop of improving their agent pretty effectively. Check out the blog post linked 🚀

We just released the Databricks synthetic evaluation SDK! 🎉 We’ve found that synthesizing evals is a great way to hill climb your AI system before you’re able to get labels from domain experts. With this SDK, and our fancy diffing UI, users are able to improve the inner loop of improving their agent pretty effectively. Check out the blog post linked 🚀

Nikhil Thorat

10,446 views • 1 year ago

Introducing the /autobrowse skill (inspired by Andrej Karpathy's autoresearch harness) Ask your agent to perform any task on the web: it explores the page using the Browserbase CLI, learns what went wrong in previous attempts, and iterates until it converges on a reliable workflow. Once token usage is optimized, it graduates the winning approach into a reusable skill for your browser.

Introducing the /autobrowse skill (inspired by Andrej Karpathy's autoresearch harness) Ask your agent to perform any task on the web: it explores the page using the Browserbase CLI, learns what went wrong in previous attempts, and iterates until it converges on a reliable workflow. Once token usage is optimized, it graduates the winning approach into a reusable skill for your browser.

Shrey Pandya

231,003 views • 4 months ago

Andrew Ng: “Agents are the most important trend in AI right now - 100% of my tasks already done by agents. in 3-6 months, we’ll all be building Graphs to orchestrate self-improving agents. No more prompting.” in a 20-minute talk, Andrew Ng explains how to build self-improving agentic systems from scratch. Worth more than a $500 agentic course. Watch this talk, then read how to become an agent orchestrator with graph engineering below.

Andrew Ng: “Agents are the most important trend in AI right now - 100% of my tasks already done by agents. in 3-6 months, we’ll all be building Graphs to orchestrate self-improving agents. No more prompting.” in a 20-minute talk, Andrew Ng explains how to build self-improving agentic systems from scratch. Worth more than a $500 agentic course. Watch this talk, then read how to become an agent orchestrator with graph engineering below.

Movez

35,515 views • 1 month ago

SpaceXAI engineer (ex-Cursor CEO): "95% of Cursor now use agents. they are used about 5x more than any feature we made one agent the CEO - it creates other agents to handle our tasks" In a 30-min lecture, SpaceXAI engineer reveal their actual GrokBot x Agents setup in a live demo This replaces weeks of random GrokBot tutorials Watch the architecture, then use the article below to build your own 24/7 Grok Bot team from scratch

SpaceXAI engineer (ex-Cursor CEO): "95% of Cursor now use agents. they are used about 5x more than any feature we made one agent the CEO - it creates other agents to handle our tasks" In a 30-min lecture, SpaceXAI engineer reveal their actual GrokBot x Agents setup in a live demo This replaces weeks of random GrokBot tutorials Watch the architecture, then use the article below to build your own 24/7 Grok Bot team from scratch

codila

36,489 views • 9 days ago

Anthropic engineer: "90% of our engineers were using self-improving loops. Now everyone shifted to building Graphs." In 20 minutes he shows how Anthropic builds agents that remember across sessions and learn while they sleep. The missing piece most engineers miss: a loop resets, a graph compounds. Watch it, then try your first graph with the step-by-step guide below

Anthropic engineer: "90% of our engineers were using self-improving loops. Now everyone shifted to building Graphs." In 20 minutes he shows how Anthropic builds agents that remember across sessions and learn while they sleep. The missing piece most engineers miss: a loop resets, a graph compounds. Watch it, then try your first graph with the step-by-step guide below

Mahax

45,857 views • 1 month ago

SpaceXAI engineer (ex. Cursor): "at SpaceXAI, 95% of our code is written by AI agents. Most of engineers are running 10-20+ agents in parallel. I'm running 20+ GrokBot agents with /loop, /goal, /swarm inside pstack, which lets agents fully own, verify and ship tasks." in a 1-hour workshop, SpaceXAI engineer showed how they build self-improving coding agent team from scratch worth more than 10 paid courses on building agents watch today, then read how to build a team of self-learning GrokBot agents from scratch in article below

SpaceXAI engineer (ex. Cursor): "at SpaceXAI, 95% of our code is written by AI agents. Most of engineers are running 10-20+ agents in parallel. I'm running 20+ GrokBot agents with /loop, /goal, /swarm inside pstack, which lets agents fully own, verify and ship tasks." in a 1-hour workshop, SpaceXAI engineer showed how they build self-improving coding agent team from scratch worth more than 10 paid courses on building agents watch today, then read how to build a team of self-learning GrokBot agents from scratch in article below

Codez

25,063 views • 5 days ago

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:

I rebuilt Posia using the Pi Agent SDK. The core agent is ~15 lines of code, and the harness is so flexible and hackable. Recorded a 17-min walkthrough on: - Pi’s extension system + how to build your own - extensions that cut tool tokens by 80–96% - the core Pi SDK, step by step - building hosted agents with it Adding my Pi extensions setup in AI Builder Club repo here:

Jason Zhou

66,010 views • 1 month ago

Built a slim lib that can be used by your agent to spawn a native web view to interact with you. Starts in <300ms and is fully js hackable. Comes with Pi extension that follows your cursor around for your agents working in the background while you surf.

Built a slim lib that can be used by your agent to spawn a native web view to interact with you. Starts in <300ms and is fully js hackable. Comes with Pi extension that follows your cursor around for your agents working in the background while you surf.

Daniel Griesser

31,788 views • 6 months ago

Today, we’re introducing Skills in Chrome, a new way to build one-click workflows for your most frequently used AI prompts — like asking for ingredient substitutions to make a recipe vegan, generating side-by-side shopping comparisons across multiple tabs, or scanning long docs to get the info you need quickly. When you write a prompt that you want to use again, you can save it as a Skill directly from your chat history. The next time you need it, select your saved Skill in Gemini in Chrome by typing forward slash ( / ) or clicking the plus sign ( + ) button, and your Skill will run on the page you’re viewing, along with any other tabs you select.

Today, we’re introducing Skills in Chrome, a new way to build one-click workflows for your most frequently used AI prompts — like asking for ingredient substitutions to make a recipe vegan, generating side-by-side shopping comparisons across multiple tabs, or scanning long docs to get the info you need quickly. When you write a prompt that you want to use again, you can save it as a Skill directly from your chat history. The next time you need it, select your saved Skill in Gemini in Chrome by typing forward slash ( / ) or clicking the plus sign ( + ) button, and your Skill will run on the page you’re viewing, along with any other tabs you select.

Google

1,282,021 views • 4 months ago

🏆 Congrats to our NY Tech Week Hackathon Winners! 🥇 SEEYUH — @versatilitylab Built a zero-day vulnerability research system that uses the Agents SDK + o4-mini to orchestrate agent-based security analysis. (Demo below.) 🥈 Level Up — Adam Anzuoni & Kirk Kaiser Gamified employee onboarding with multimodal adventures powered by the Agents SDK, Realtime API, gpt-image-1, and o3. 🥉 Scotty — Faizan Created an AI interviewer for system design questions—interviewees respond via voice and sketch. Built with the Agents SDK + Realtime API.

🏆 Congrats to our NY Tech Week Hackathon Winners! 🥇 SEEYUH — @versatilitylab Built a zero-day vulnerability research system that uses the Agents SDK + o4-mini to orchestrate agent-based security analysis. (Demo below.) 🥈 Level Up — Adam Anzuoni & Kirk Kaiser Gamified employee onboarding with multimodal adventures powered by the Agents SDK, Realtime API, gpt-image-1, and o3. 🥉 Scotty — Faizan Created an AI interviewer for system design questions—interviewees respond via voice and sketch. Built with the Agents SDK + Realtime API.

OpenAI Developers

39,157 views • 1 year ago

The music is about to stop. First came vibe coding. Today Lantern is dropping the first vibe marketing platform. 50+ agents powered by our Revenue Ontology. CMOs you have a choice: ship 10x more ambitious campaigns or cut 20% of your team. See for yourself ⬇️

The music is about to stop. First came vibe coding. Today Lantern is dropping the first vibe marketing platform. 50+ agents powered by our Revenue Ontology. CMOs you have a choice: ship 10x more ambitious campaigns or cut 20% of your team. See for yourself ⬇️

David Bromberg 🏮

1,009,772 views • 4 months ago

Every company needs killer Skills library. Not a folder in GitHub that 10% of the company knows how to use. A living library the whole company benefits from. The best deal review skill gets better every time a sales rep uses it. A great research skill gets discovered instead of rebuilt 50 times. Creating a skill should be as easy as asking to create something useful from based on the context of your work. And the top skills (and skill creators) should rise to the top. Create, share, collaborate on, discover and understand usage of skills, organize them into databases by team or use case, then use them across any of your agents. Still early, but the idea is to make Notion the best home for your company’s collective AI skills. Made a quick demo (all available now)!

Every company needs killer Skills library. Not a folder in GitHub that 10% of the company knows how to use. A living library the whole company benefits from. The best deal review skill gets better every time a sales rep uses it. A great research skill gets discovered instead of rebuilt 50 times. Creating a skill should be as easy as asking to create something useful from based on the context of your work. And the top skills (and skill creators) should rise to the top. Create, share, collaborate on, discover and understand usage of skills, organize them into databases by team or use case, then use them across any of your agents. Still early, but the idea is to make Notion the best home for your company’s collective AI skills. Made a quick demo (all available now)!

Hurley

691,328 views • 12 days ago

we are working on OpenControl - a library that uses AI to finally solve the headache of internal tooling idea is simple - define a set of tools in code that can reference functions from your codebase or anywhere else these tools get deployed to your infra (runs anywhere, lambda, worker, containers, etc) and exposes a protocol that allows clients like cursor, claude-code, etc to use them they can orchestrate tasks like "can you reset the password of anyone who hasn't logged in a year" demo below and details on how it works in the thread

we are working on OpenControl - a library that uses AI to finally solve the headache of internal tooling idea is simple - define a set of tools in code that can reference functions from your codebase or anywhere else these tools get deployed to your infra (runs anywhere, lambda, worker, containers, etc) and exposes a protocol that allows clients like cursor, claude-code, etc to use them they can orchestrate tasks like "can you reset the password of anyone who hasn't logged in a year" demo below and details on how it works in the thread

dax

109,046 views • 1 year ago

Today we're introducing Web Skill Factory: a pipeline that turns solved web tasks into reusable, verified code. Most agent "skills" are notes a model rereads and reinterprets every run. Ours are programs. On a WebArena subset with gpt-5.4, reusing the library moved accuracy on held-out instances from 55% to 70%, and cut average steps from 17.1 to 14.7.

Today we're introducing Web Skill Factory: a pipeline that turns solved web tasks into reusable, verified code. Most agent "skills" are notes a model rereads and reinterprets every run. Ours are programs. On a WebArena subset with gpt-5.4, reusing the library moved accuracy on held-out instances from 55% to 70%, and cut average steps from 17.1 to 14.7.

Microsoft AI Frontiers

15,530 views • 29 days ago

Excited to announce that Sola has raised a $17.5M Series A led by a16z with support from Conviction Y Combinator, bringing total funding to $21M 🚀 From the start, we set out to reimagine human-AI interaction to push the boundaries of process automation. Our agents watch how people do tasks on-screen, then handle those tasks automatically, even in legacy tools.

Excited to announce that Sola has raised a $17.5M Series A led by a16z with support from Conviction Y Combinator, bringing total funding to $21M 🚀 From the start, we set out to reimagine human-AI interaction to push the boundaries of process automation. Our agents watch how people do tasks on-screen, then handle those tasks automatically, even in legacy tools.

Neil Deshmukh

334,569 views • 1 year ago

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:

Claude R Perrin Code SDK is under-rated One cool part with Claude Code SDK is that it supports full features out of box: - Skills - Sub agents - Hooks - ... Which means you can use claude code CLI as a debug tool to build agent, and then import to your Claude code powered agent Here is a quick example of a pptx presentation agent using Claude Code SDK + doc skills Code example from AI Builder Club by Kai:

Jason Zhou

11,981 views • 10 months ago

How will companies build agents that work alongside their employees? I discuss this with Guillermo Rauch, the CEO of Vercel, who’s building V... an internal agent used by almost 1,000 people across Vercel. We talk about: - The Openclaw Movement - How to get started building agents for your team? - Do we build a team of many agents or one GOD agent? - Hard parts of creating agents - Agents that delegate to other agents with different permissions and computer access - Eve The framework for building agents This is Agent Native #4 00:00 Intro 01:21 The State of Agent Adoption 07:26 "V" - Vercel's Internal Company Agent 14:32 Lessons from OpenClaw: Soul & Computer use 22:20 One God Agent OR a Team of Agents 27:11 Build Your Own Agent: Skills, Tools & Permissions 33:52 Proactive Agents, Triggers & Self-Improvement 40:30 Who Will Build Agents & Getting Started 46:22 Open Models - Cheaper, Faster, Better 53:05 Closing Thoughts: Owning Your Own Intelligence

How will companies build agents that work alongside their employees? I discuss this with Guillermo Rauch, the CEO of Vercel, who’s building V... an internal agent used by almost 1,000 people across Vercel. We talk about: - The Openclaw Movement - How to get started building agents for your team? - Do we build a team of many agents or one GOD agent? - Hard parts of creating agents - Agents that delegate to other agents with different permissions and computer access - Eve The framework for building agents This is Agent Native #4 00:00 Intro 01:21 The State of Agent Adoption 07:26 "V" - Vercel's Internal Company Agent 14:32 Lessons from OpenClaw: Soul & Computer use 22:20 One God Agent OR a Team of Agents 27:11 Build Your Own Agent: Skills, Tools & Permissions 33:52 Proactive Agents, Triggers & Self-Improvement 40:30 Who Will Build Agents & Getting Started 46:22 Open Models - Cheaper, Faster, Better 53:05 Closing Thoughts: Owning Your Own Intelligence

Riley Brown

76,198 views • 28 days ago

The Risk On Network is growing. You no longer need to scroll CT for hours to know what's going on in the market. Introducing The Ponzi Times — a daily crypto market roundup, Mon-Sat, straight to your inbox. Brought to you by Risk On, published by our newest contributor Korba with the The Ponzi Times

The Risk On Network is growing. You no longer need to scroll CT for hours to know what's going on in the market. Introducing The Ponzi Times — a daily crypto market roundup, Mon-Sat, straight to your inbox. Brought to you by Risk On, published by our newest contributor Korba with the The Ponzi Times

Risk On

12,854 views • 5 months ago