Robots with AI Agents + Copilot

From the creator

Welcome back to Cozy AI Kitchen, where we explore the latest in AI through fun, hands-on demos. In this episode, we’re joined by robotics expert Griffin Norris from General Robotics, who shows how AI agents and Microsoft Copilot can dramatically simplify programming and controlling robots. Instead of writing complex code from scratch, you’ll see how natural language, MCP servers, and AI models make it possible to: - Generate robot control scripts instantly - Connect robots to cloud-based AI models - Use vision AI for real-world understanding - Build reusable “skills” for robotic systems - Control robots interactively with feedback loops From making a quadruped robot stand and walk to identifying objects like a toaster using vision models, this episode highlights how fast robotics development is evolving in the AI era. If you’ve ever been curious about robotics but didn’t know where to start, this is the perfect introduction. ⏱️ Chapters 00:01 - Robots + AI: The Big Challenge 00:15 - Meet Griffin Norris (General Robotics) 01:25 - Using Copilot + MCP for Code Generation 01:59 - From Docs to Working Robot Code 05:00 - Live Demo: Robot Stands and Walks 05:49 - Adding Vision AI + Scene Understanding 08:20 - Multi-Agent Systems & Faster Development 09:06 - Prebuilt Skills vs Raw Code Generation 11:05 - Controlling Robot with Natural Language 12:12 - Demo: Finding a Toaster with Vision AI 13:52 - Feedback Loops and Iteration 14:55 - Why Now Is the Best Time for Robotics 🎯 What Y

Published 2026-06-16 · Watch on YouTube ↗
Availability and playback restrictions are controlled by the original channel.