AI Coding Agents and how to code them
summary
Demo shows concrete claims and working code: an agent loop using GPT4.1 plus a REACT thought‑action loop calls tools exposed via MCP servers (bash, file system, Brave web search), spawns a multi-agent supervisor system with frontend/backend/DevOps agents, creates files (hello.txt), installs packages, generates a React + FastAPI scaffold, and even makes git branches and commits — the multi‑agent pipeline executes end‑to‑end on a local repo rather than remaining a high‑level promise.
AI-written summary · about
chapters (10)
- 0:00Introduction and Speaker Background
- 0:12The Rise of AI in Software Development
- 2:27Understanding AI Agents
- 8:31Live Coding Session: Building a Basic AI Agent
- 12:24Enhancing AI Agents with Tool Use
- 20:20Introducing MCP for Advanced Tool Integration
- 31:01Multi-Agent Collaboration
- 40:30Z Coder: AI Agents in Your IDE
- 44:41Future of Software Development with AI
- 47:18Conclusion and Contact Information
related talks
48mAI Coding Agents and How to Code Them
40mAI Coding Agents and how to code them
01h 28mAI Coding Agents and How to Code Them
01h 03mAI Coding Agents and how to code them
01h 28mAI Coding Agents and how to code them
01h 01mAI Agents In-Depth – Function Calling, MCP and Tool Use Under the Hood
41mGoing beyond copilot with AI Agents
30mBeyond the Hype: Using AI Coding Agents Today