Stream #35: Production-grade AI agents with SurrealDB & Pydantic AI

Explore the practical challenges of taking Graph-RAG agents from experiment to production with SurrealDB and PydanticAI. Unlike simple RAGs, these agents need durable, queryable memory, checked rules for agent requests and responses, and observability that surfaces retrieval and validation drift. In this session SurrealDB and PydanticAI show a compact, reproducible pattern - build a KG, run a typed pai-memory agent via the Gateway, and use Logfire/OTel to trace and diagnose failures.