Skip to main content

RAG Playbooks

Playbooks · RAG overview · RAG retrieval →

Implementation guides for G.A.I.N RAG. The RAG Blueprint is the reference design. These playbooks are the how: who starts retrieve, which corpus is in scope, and how the pack is audited.

PEP still gates every retrieve. Enforcement lives in Runtime. This series owns the retrieval store and the pack, not the verdict engine.

THE CLAIM

Retrieval is a governed action, not a database query. The route declares retrieval. The app fetches. The LLM does not pick the corpus.

Playbooks

PlaybookOne-line purpose
RAG retrievalPrefetch vs tool mode, scope, PEP pack, validation, worked example
  1. G.A.I.N RAG: principles
  2. RAG Blueprint: reference design
  3. RAG retrieval: implement mode, scope, and the pack
  4. Eval Plane ③ Context: recall, scope leaks, abstention
  5. Runtime: PEP/PDP on the retrieve action

Who should read what

RoleStart withThen
RAG / knowledge teamsRAG retrievalG.A.I.N RAG, Eval Context
AI platformRAG retrievalRoute contract, PEP enforcement
GovernanceRuntimeRetrieval scope scenarios in policy tests

RAG retrieval →