Use when building secure corporate RAG: chunking with overlap, hybrid literal-vs-semantic search, ACL filtering before the model, Spring AI or LangChain stacks. Triggers on "corporate RAG", "hybrid search", "RAG ACL", "secure retrieval". Non-triggers: plain code search with no access control (use graphify). Outcome: a RAG pipeline that cites sources, filters by profile, and states that RAG does not remove hallucination.
