Most broken RAG deployments are not model failures. They are upstream failures the model is forced to ventriloquize. The fix is a data pipeline that does the judgment work before retrieval — staleness gates, canonical resolution, business rules as first-class content.
The primary consumer of your documentation is no longer a human. It is an agent making code changes, retrieving context, executing workflows. Treat docs as infrastructure — versioned, tested, owned — or ship guesses every time the model runs.
Meeting transcripts produce decisions. The decisions vanish into a Notion graveyard within thirty days. A two-agent Cowork workflow extracts structured records and attaches review triggers that fire when conditions actually change — not on a calendar.
Senior engineers carry the runbooks nobody wrote. Then they retire. "Document everything" is the ask that produces nothing. A structured-interview pipeline that turns one hour into searchable institutional memory before the bus-factor goes to zero.
New hires don't lack capability. They lack context. Three onboarding agents — orientation, historical reasoning, starter-ticket matching — index the institutional knowledge that already exists in PRs, ADRs, and post-mortems. Ramp compresses.
Most enterprise AI failures are not model failures. They are retrieval failures. Chunking, embeddings, vector stores, knowledge graphs, and the context budget — what actually breaks at scale and how to build the memory layer that holds.
Modernizations die in the comprehension gap, not the rewrite. The gap has no owner, so it stays open. Five extraction patterns bind every rule to a source line, build the lineage map, and force a behavioral test suite to go green before the new system ships.