AI Agents for the Rest of Us
summary
Shows concrete code using Semantic Kernel and Azure AI Agent Service to build multiagent workflows (a medical demo with about five to six agents: patient history, radiology, pathology, etc.) and demonstrates selection and termination strategies, a facilitator pattern, and A2A agent cards. Includes query planning with Azure Search/vector retrieval and reports a ~40% relevancy and ~30% answer improvement. Covers MCP discovery at runtime and practical eval and memory considerations.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 5:20AI agent adoption phases
- 7:08AI agent definition and components
- 12:43AI agent capabilities and limits
- 15:11AI agents in industries
- 19:01Why multiple agents
- 21:05Multi-agent patterns
- 26:18RAG with query planning
- 31:12Model Context Protocol
- 37:50Agent-to-agent protocol
- 41:41Evaluating agent performance
- 43:27Key takeaways
related talks
56mBuilding AI Agents and Multi-Agent Systems with Azure AI
07h 25mAI Agents Conference 2026 - Day 2
36mBuilding AI Agents in .NET with Azure AI Foundry
26mAI powered automation & multi-agent orchestration
01h 00mBuilding your own AI Agent using Semantic Kernel
01h 02mDevelop AI agents with Semantic Kernel
58mAdvanced Autonomous AI Agents: Memory, Collaboration and Evolution in Action
01h 54mBuilding Code First AI Agents with Azure AI Agent Service