Building AI Agents and Multi-Agent Systems with Azure AI
summary
Shows how to build agents with Semantic Kernel and host/orchestrate them in Azure AI Foundry using Python, plugins and Logic Apps; demos call a Playwright MCP server for browser automation and create/delete real Outlook calendar events. Describes agent patterns (concurrent, sequential, group chat, handoff), threads persisted in the cloud, streaming responses, and a multi-agent app factory that autonomously builds and QA-tests a 5x5 Battleship web app with Playwright-driven tests and iterative developer/reviewer turns.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 4:19Agentic AI for modern apps
- 7:53Semantic Kernel orchestration
- 15:20Adding tools to agents
- 26:59Hosting in Azure AI Foundry
- 34:37Multi-agent group chats
- 45:14Live demo: autonomous app factory
- 54:11Closing
related talks
36mBuilding AI Agents in .NET with Azure AI Foundry
46mAI Agents for the Rest of Us
26mAI powered automation & multi-agent orchestration
39mEvolving Intelligence: Designing Autonomous AI Agents
05h 17mBuilding AI Applications
01h 54mBuilding Code First AI Agents with Azure AI Agent Service
01h 02mDevelop AI agents with Semantic Kernel
58mAdvanced Autonomous AI Agents: Memory, Collaboration and Evolution in Action