Build your own AI Agent
summary
Explains how to assemble agent chains that reflect on answers, call tools, and iterate without a human in the loop; demos show a workflow that ingests hundreds of Jira/Google Drive tasks, groups and summarizes them, builds a 3–5 page PowerPoint draft, and computes completion stats (example: estimated 25 points, completed 15.5 → 62%). Uses GPT-3.5 and GPT‑4, LangChain, GitHub/Azure Boards/Teams integrations and a custom UI (NAAI/Nancy); reflection on 3.5 surprisingly outperforms zero‑shot GPT‑4 in benchmarks and the demos run end‑to‑end.
AI-written summary · about
chapters (8)
- 0:00AI agents introduction
- 4:18Reflection improves AI responses
- 9:52AI agents in business
- 23:13Multi-agent workflows deep dive
- 37:32Data privacy with local models
- 47:38Chatbots with AI agents
- 1:00:13Customizing AI agents
- 1:15:06Key takeaways
related talks
25mBuilding AI Agents
52mCut the Hype and Build Your Own AI Agents
25mNo Code, No Problem: Building Powerful AI Agents with Just Your Words
30mBuilding Reliable AI Agents: An Open Source Approach To Evaluation and Observability
01h 29mBuild Your Own Data Science AI Agents
38mGenerative AI Agents: How they Work and How to Build One
01h 01mAI Agents In-Depth – Function Calling, MCP and Tool Use Under the Hood
16mBuilding Applications with AI Agents