AI Coding Agents and how to code them
summary
Claims that agents can run tools, edit files, run builds and coordinate teams get shown end to end: an MCP server exposes tools, MCP model context protocol plus LangChain and LGraph coordinate a supervisor plus three worker agents (front end, back end, devops), the demo creates files (including hello.txt), runs npm installs and spins up a React app that mostly renders but sometimes stalls, discovers conference dates 27–28 February 2025, needs OpenAI and Anthropic API keys, and warns about loops up to 100 iterations and cost/security tradeoffs.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 7:52Coding assistants' limits
- 12:39Basic AI coding agent
- 23:38MCP for tool integration
- 30:12Agents with MCP servers
- 39:44Multi-agent demo
- 56:28Future of developers
- 1:07:18Zenoder live demo
- 1:15:30Q&A
related talks
01h 03mAI Coding Agents and how to code them
48mAI Coding Agents and how to code them
48mAI Coding Agents and How to Code Them
01h 28mAI Coding Agents and How to Code Them
40mAI Coding Agents and how to code them
01h 01mAI Agents In-Depth – Function Calling, MCP and Tool Use Under the Hood
36mPutting AI Agents to Work: A New Era of Open Source Connectivity with MCP
40mAgents in Action: Advancing Open Source AI Missions