Complete procedures with a way back.

Govern source revisions, preserve ACLs through parsing and chunking, pin embeddings, combine lexical and semantic retrieval, validate claim-level citations, evaluate abstention, and release immutable indexes with safe rollback.

Threat-model every untrusted source and sensitive sink, minimize capabilities and context, enforce typed tools and egress, sandbox code, bind approvals, red-team end to end, and rehearse containment.

Evaluate an MCP server as executable supply chain and delegated authority, pin its identity, constrain a local runtime or verify a remote trust endpoint, configure a positive tool allowlist, review OAuth scopes, observe real effects, test prompt injection, set per-tool approvals and rehearse complete removal.

Engineer a production prompt as a versioned, evidence-grounded application contract with explicit instruction hierarchy, safe abstention, representative evals, deterministic gates, controlled rollout, observability, and atomic rollback.