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.
App Store reviews, NPS verbatims, Zendesk tickets, interview notes, community mentions — five inputs, five biases, five cadences. Treat them equal and the loudest channel wins. The fix is a normalization and weighting layer that produces one weekly brief.
Seven patterns for moving DB2, IMS, and VSAM data into RAG: nightly EBCDIC export, CDC, federation, event sourcing, dual-write, schema-on-read, and RAG over the COBOL itself. Pick by freshness budget, not preference.
Most enterprise AI lives between pilot and replacement. Five patterns for the 12-18 months it actually takes — strangler fig, sidecar, parallel run, dual-write, eval-based rollback — with the rollback signals that catch silent quality drift.
GMV is the scoreboard, not the game. Marketplace teams that wait for revenue to confirm a category is dying have already lost the merchants whose absence caused it. Four signals, one weekly brief, three to six weeks of warning before the line bends.