Use this when the pipeline report and reality disagree. It produces a ranked list of data problems, a cleanup plan and the rules that keep data clean afterwards.
Inputs
- Exports of accounts, contacts and opportunities (or read access).
- The fields and stages the business relies on.
- The reports leadership uses, so impact can be judged.
The play
1. Inventory issues
| Area | Check |
|---|---|
| Duplicates | Accounts by domain; contacts by email; similar names |
| Completeness | Required fields empty: industry, size, owner, lifecycle stage, source |
| Opportunities | Past close dates, no next step, no activity in 30 days, amount empty or zero, stage without required fields |
| Ownership | Records owned by former employees or unassigned |
| Lifecycle | Customers without closed-won deals; leads with won deals |
| Picklists | Free-text values where picklists should be; outdated values |
| Relationships | Contacts not linked to accounts; deals without contacts |
| Compliance | Opted-out contacts still in active sequences |
2. Quantify and rank
Count each issue and score impact: does it break forecasting, routing, outreach or compliance? Compliance and forecast issues come first.
3. Plan the cleanup
For each issue: the fix, who decides (some merges need a human), whether it can be done in bulk safely, and the order. Merges and deletions are proposed with a sample for approval, then run in batches with a backup export first.
4. Prevent recurrence
Required fields at stage changes, validation rules, duplicate checks on create, ownership reassignment when people leave, a monthly hygiene report.
Output format
Health score: X/100
Issues (ranked): <issue - count - % of records - impact - fix - bulk-safe? - owner>
Cleanup plan: <week by week, with approval points>
Prevention: <rules to add>
Monthly report: <metrics to track>
What good looks like
- Every issue has a count and an impact, not just "data is messy".
- Opt-out compliance issues are fixed first.
- The prevention rules are light enough that reps follow them.
- The common mistake is a one-time cleanup sprint with no rules, so the data is dirty again in a quarter.
Rules
- MUST export a backup before any bulk change.
- MUST get approval with a sample before merges, deletions or bulk updates.
- MUST fix opted-out contacts in active sequences immediately.
- NEVER permanently delete records without explicit approval.
Example prompts
- "Audit these CRM exports and tell me what's wrong, ranked by impact."
- "Our forecast is off every month. Check our opportunity data."
- "Write the hygiene rules and monthly report for our CRM."