Campaign landing

Production RAG applications

Retrieval quality can look excellent until users stop asking clean demo questions.

Retrieval quality looks excellent on demo questions and collapses when users ask messy, multi-hop, or stale-data questions. Hallucinations often start as retrieval misses, not model creativity.

Why common approaches fail

Teams optimize embedding similarity on clean corpora and skip chunking contracts, citation paths, ACL-aware retrieval, freshness, and evals that mirror production query distribution.

Related failure modes

RAG evaluation metrics that matter
How to detect retrieval drift
How to productionize a RAG application

Evidence

Production RAG for enterprise knowledge: why demos fail and what to measure instead
Tenant isolation for multi-tenant RAG: ACLs that survive multi-hop retrieval

Full capability write-up: Production RAG applications.