Beyond RAG: Build a Relational Context Engine from Scratch — Peter Werry, Unblocked

Why watch

A technical workshop demonstrating how to build a Relational Context Engine that surpasses RAG limitations by converting natural language into actual database queries rather than semantic similarity search. Covers four key components: schema discovery, identity resolution, query planning, and validation, applied to GitHub repository data including PRs, tickets, wikis, and chat. Designed for AI engineers building developer tools who need structured, temporal context retrieval.