RBAC and audit trails show up as bullet points on every RAG vendor's website — but almost none show the actual enforcement. This post walks through what permission-aware retrieval really looks like at the database layer, using PostgreSQL and pgvector, and gives security teams a concrete checklist for verifying any vendor's claims before signing.

This post walks through exactly how: the diagnosis process, the specific architecture changes we made, the tradeoffs we accepted along the way, and the results that followed. If you're running a RAG system where "it mostly works" isn't good enough — because your users are lawyers, auditors, or anyone else who can't afford a confidently wrong answer — this is the playbook we used, and the one we'd use again.