Designing Reliable Multi‑Agent Apps with Azure Cosmos DB | OD820
Azure cosmos db Multi Agent systems Ai agents Vector search Semantic search Agentic memory Rag Multi Tenant architecture Microsoft build 2026 Cloud architecture Agent coordination Retrieval augmented generation
This advanced session from Microsoft Build 2026 demonstrates how to build production-ready multi-agent applications using Azure Cosmos DB for agent memory, retrieval, and coordination. The video covers implementing vector and full-text search, semantic reranking, and intelligent memory management including conflict resolution across different memory types. Targeted at experienced developers and architects working on AI agent systems who need to move beyond prototyping to reliable, low-latency production deployments.
Related videos
Boost AI context with hybrid search in Spanner
The Burrito Bot - AI-Powered Search in SQL Server 2025 | MVP Unplugged
From Queries to Agents: The Next Era of Data Retrieval on PostgreSQL | POSETTE 2026
From rows to reasoning: Designing databases for AI apps and agents | BRK223
Build AI-powered collaboration on a visual canvas | ODSP904
Resolve support cases with multi-agent workflows | ODSP915
Build automated agents using optimized AI Foundry models on Snapdragon | DEMSP380
Give your app search superpowers: Agent Retrieval (Vector Search 2.0)
Context engineering explained: What every AI developer should know
Claude Opus 4 + RAG: Build an AI App with Embeddings & Knowledge Graphs | MVP Unplugged
AI Agents For Beginners – OpenClaw Case Study
