crm-hygienelisted

# CRM Hygiene ## Purpose Take a set of CRM deals and find where the record has drifted from reality — stale fields, impossible dates, stages that outrun the evidence — then hand back concrete, approve-able corrections so the pipeline you forecast on is the pipeline you actually have. ## Inputs - The deals to check (a single deal, an owner's open pipeline, or one stage) - Current CRM field values: stage, amount, close date, next step, owner, last activity - Evidence of what's really happening: recent meetings, commitments, stakeholders ## Method Run three passes. Each produces flags; the output is a ranked list of write-back proposals. **1. Field-by-field staleness check.** For every deal, test each field against a rule: - **Next step** — is one set, and is it dated and in the future? A blank or past-dated next step means the deal has no defined motion. Flag. - **Close date** — is it in the past? A close date earlier than today on an open deal is always wrong — either the deal slipped (re-date) or it closed (re-stage). Flag. - **Stage** — does it match the last real interaction? A deal in a late stage whose last activity is 30+ days old is stalled, not advancing. Flag. - **Amount** — is it set and non-zero past early stages? An unvalued deal in mid/late stage can't be forecast. Flag. - **Owner / last activity** — is there activity in the last 14 days on an open deal? No touch = at risk of going dark. Flag. **2. Contradiction detection.** Cross-field logic the AE