Build A Knowledge Base For Agents (with Sanity) - Workshop Recording

This workshop covers building knowledge-backed agents with Mastra and Sanity Context, using organized topic entries, Jev-powered retrieval, and scoped MCP endpoints. When company facts are scattered across websites, files, and a CMS, a managed knowledge layer helps agents find answers faster, resolve conflicting information, and access only the sources intended for them. Hosted by: Brandon Barros, Founding Product Advocate @ Mastra Anne Prins, Tech Partnerships Lead @ Sanity John Siciliano, Senior Technical Product Marketing Manager @ Sanity CHAPTERS 00:00 Welcome and introductions 05:19 Why agents need knowledge governance 07:11 Demo: a fast documentation agent built with Mastra and Sanity 12:09 Using Jev to prefetch relevant knowledge as users type 13:29 When to use structured queries vs. knowledge retrieval 15:42 Building topic entries and selecting context with Jev 19:25 Finding conflicting facts and tracing them back to their sources 26:52 Why custom agents need control over user context and behavior 29:02 Scoping knowledge access through MCP and maintaining it over time 35:50 Q&A: retrieval visualization, importing PDFs, and crawling websites WHAT IS MASTRA Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development, from prototype to production. 📚 MASTRA RESOURCES Website: https://mastra.ai X: https://x.com/mastra_ai Discord: https://mastra.ai/community/discord GitHub: https://github.com/mastra-ai Learn Mastra: https://mastra.ai/learn Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of... Patterns for Building AI Agents (Book): https://mastra.ai/books/patterns-of-b...