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.

OpenAI Agents SDK + MCP = Vibe Coding Agents I now have a CRACKED workflow to develop agents, Cursor can not only write the code but look at the logs at LangWatch, so it can debug the interaction between agents and write the fix itself

Rogerio Chaves

2,805 subscribers

51,352 views • 1 year ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

11 Comments

Rogerio Chaves1 year ago

Link:

Etherspot 🐞2 years ago

Want to build a Web3 app without all the overhead costs? Try TransactionKit, a React toolkit that makes building dApps easy. Integrate cutting-edge account abstraction features in just a few clicks. Try it today 👇

Emre Coklar1 year ago

A big fan of your work. You keep delivering bangers, thanks for sharing!

Rogerio Chaves1 year ago

thank you very much @EmreCoklar, it means a lot!!

Srineesh1 year ago

Is it only for apps that are using langflow, what if i need to find by user session. Scenario: one of my users for the chat app complained of prompt not responding correctly can i just give user session to the mcp and ask it to figure out the issue??

Andrey Frolov1 year ago

This is cool!

Rogerio Chaves1 year ago

Thanks Andrey 😄

LightFi1 year ago

Oh great one but where’s the link?

Rogerio Chaves1 year ago

Sorry 😅 indeed:

Renat1 year ago

The dream, AI debugging AI.

Rogerio Chaves1 year ago

we've been debugging for too long, time to take the back seat 😁

Related Videos

Agents & MCP are great... but how can you DEPLOY an agent with MCP tools? Here's the fastest way I've found to build and deploy with the OpenAI Agents SDK in <3 minutes.

Agents & MCP are great... but how can you DEPLOY an agent with MCP tools? Here's the fastest way I've found to build and deploy with the OpenAI Agents SDK in <3 minutes.

matt palmer

64,690 views • 1 year ago

We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor. Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.

We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor. Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.

Cursor

3,036,270 views • 1 month ago

I built a Rust-based image compressor, WASM binary, and SvelteKit app! I wanted to see how far I could go using only coding agents. I did not write any code by hand. After 520 agents, 350M tokens, and $287 I can now say… extremely far.

I built a Rust-based image compressor, WASM binary, and SvelteKit app! I wanted to see how far I could go using only coding agents. I did not write any code by hand. After 520 agents, 350M tokens, and $287 I can now say… extremely far.

Lee Robinson

564,272 views • 5 months ago

Hoping your coding agents could understand you and adapt to your preferences? Meet TOM-SWE, our new framework for coding agents that don’t just write code, but model the user's mind persistently (ranging from general preferences to small details) arxiv: ❓Motivation: Most coding agents today can plan, edit, run, and test code. But they still fail at a key part of real-world development, understanding the user! Underspecified, shifting, or context-dependent instructions can easily break them. You must have those moments when coding agents were running for 10 minutes and ended up producing things largely misaligned. (1/)

Hoping your coding agents could understand you and adapt to your preferences? Meet TOM-SWE, our new framework for coding agents that don’t just write code, but model the user's mind persistently (ranging from general preferences to small details) arxiv: ❓Motivation: Most coding agents today can plan, edit, run, and test code. But they still fail at a key part of real-world development, understanding the user! Underspecified, shifting, or context-dependent instructions can easily break them. You must have those moments when coding agents were running for 10 minutes and ended up producing things largely misaligned. (1/)

Xuhui Zhou

39,728 views • 7 months ago

For a long time, software was limited by how fast people could write code, and how good that code was. As models have improved, that constraint has largely disappeared. Now the bottleneck is access: what surfaces can your agents actually reach? Those interaction layers sit on top of coding agents, the kernel that turns prompts into real-world impact. With Notion's custom agents, we pushed this further. They adapt to your work style as you collaborate with them, using the same deterministic logic that powers coding agents. Simon Last sarah guo

For a long time, software was limited by how fast people could write code, and how good that code was. As models have improved, that constraint has largely disappeared. Now the bottleneck is access: what surfaces can your agents actually reach? Those interaction layers sit on top of coding agents, the kernel that turns prompts into real-world impact. With Notion's custom agents, we pushed this further. They adapt to your work style as you collaborate with them, using the same deterministic logic that powers coding agents. Simon Last sarah guo

Notion Developers

25,065 views • 2 months ago

is now both MCP server creator and MCP server tester (client). You can now immediately test the generated MCP server from within MCPify itself. Using Cloudflare Developers agents-sdk to do this automatically.

is now both MCP server creator and MCP server tester (client). You can now immediately test the generated MCP server from within MCPify itself. Using Cloudflare Developers agents-sdk to do this automatically.

Bhanu Teja P

27,747 views • 1 year ago

Introducing Cursor 2.0. Our first coding model and the best way to code with agents.

Introducing Cursor 2.0. Our first coding model and the best way to code with agents.

Cursor

3,563,132 views • 8 months ago

an OpenAI engineer just showed how he gets agents to do his whole job: code, debug and more, using loops 29 minutes from the engineer who coined "harness engineering" he writes the rules, agents write the code, a reviewer agent loops until it's right the winners won't have the smartest model, they'll have the best loop around it watch it, then read the full guide on loops below

an OpenAI engineer just showed how he gets agents to do his whole job: code, debug and more, using loops 29 minutes from the engineer who coined "harness engineering" he writes the rules, agents write the code, a reviewer agent loops until it's right the winners won't have the smartest model, they'll have the best loop around it watch it, then read the full guide on loops below

Anatoli Kopadze

167,836 views • 4 days ago

First look at Agents SDK dynamic ui gen via MCP UI

First look at Agents SDK dynamic ui gen via MCP UI

Confidence

17,809 views • 8 months ago

A lot of developers are using agents to write their code these days. I was a hold-out... but Claude Opus 4.5 finally cracked me. So, I made a video walking through how I write code with agents end-to-end. We'll talk plans, rules, and everything else in my setup!

A lot of developers are using agents to write their code these days. I was a hold-out... but Claude Opus 4.5 finally cracked me. So, I made a video walking through how I write code with agents end-to-end. We'll talk plans, rules, and everything else in my setup!

Ben Holmes

59,468 views • 5 months ago

Coding agents can now automatically fix issues reported by DevTools → The MCP server now accesses the issues panel to detect and resolve problems like cookie errors or missing form labels.

Coding agents can now automatically fix issues reported by DevTools → The MCP server now accesses the issues panel to detect and resolve problems like cookie errors or missing form labels.

Chrome for Developers

32,331 views • 6 months ago

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

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 views • 3 months ago

Cursor can now write detailed plans before starting complex tasks. This allows agents to run for significantly longer.

Cursor can now write detailed plans before starting complex tasks. This allows agents to run for significantly longer.

Cursor

424,263 views • 8 months ago

when I look at my old simulations, a lot of them, most of them, can be easily vibe setup with agents, or even one shot by the agents. it makes me wonder how many of the ideas and devices that were results of branching off of originally intended directions and goals would I miss if I attempt them now with the agents? How many new ones would the agents be able to attempt and identify? Is inverse design just the most stupid and bruteforce version of auto research? i should get a workflow with MOOSE working so I could set the agents free in the world of multiphysics simulations.

when I look at my old simulations, a lot of them, most of them, can be easily vibe setup with agents, or even one shot by the agents. it makes me wonder how many of the ideas and devices that were results of branching off of originally intended directions and goals would I miss if I attempt them now with the agents? How many new ones would the agents be able to attempt and identify? Is inverse design just the most stupid and bruteforce version of auto research? i should get a workflow with MOOSE working so I could set the agents free in the world of multiphysics simulations.

outside five sigma

62,983 views • 3 months ago

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.

I built a Deep Research AI Agent team using OpenAI Agents SDK and Firecrawl. It combines multiple AI agents that can autonomously search the web, extract content, and generate detailed reports with enhanced analysis. 100% Opensource Code with step-by-step tutorials.

Shubham Saboo

50,831 views • 1 year ago

🚀 Announcing LangSmith Skills + CLI 🚀 Agent improvements are increasingly driven by coding agents themselves. We're releasing LangSmith Skills alongside the LangSmith CLI to make coding agents experts at the agent engineering lifecycle. LangSmith Skills enable agents to debug traces, create datasets, and run experiments - and thanks to the CLI, agents are able to do it all natively through the terminal, where they're most comfortable. Try out LangSmith Skills and the CLI with your own coding agents! ➡️ Skills: ➡️ CLI:

🚀 Announcing LangSmith Skills + CLI 🚀 Agent improvements are increasingly driven by coding agents themselves. We're releasing LangSmith Skills alongside the LangSmith CLI to make coding agents experts at the agent engineering lifecycle. LangSmith Skills enable agents to debug traces, create datasets, and run experiments - and thanks to the CLI, agents are able to do it all natively through the terminal, where they're most comfortable. Try out LangSmith Skills and the CLI with your own coding agents! ➡️ Skills: ➡️ CLI:

LangChain

49,416 views • 3 months ago

📌Meet $AVM: The SuperComputer for AI Agents. The virtual machine that lets agents write, run, and verify code without human help (explained) 👇

📌Meet $AVM: The SuperComputer for AI Agents. The virtual machine that lets agents write, run, and verify code without human help (explained) 👇

AVM

42,451 views • 11 months ago

Voice RAG Agent using OpenAI Agents SDK and Qdrant as the vector database. 100% Opensource Code.

Voice RAG Agent using OpenAI Agents SDK and Qdrant as the vector database. 100% Opensource Code.

Shubham Saboo

28,219 views • 1 year ago

“People aren’t just building for humans anymore. They’re building for agents.” Cloudflare shares how Cloudflare Sandbox SDK works with the OpenAI Agents SDK to help agents run code in secure environments while keeping sensitive data separate from execution.

“People aren’t just building for humans anymore. They’re building for agents.” Cloudflare shares how Cloudflare Sandbox SDK works with the OpenAI Agents SDK to help agents run code in secure environments while keeping sensitive data separate from execution.

OpenAI Developers

40,871 views • 2 months ago