AI assisted pipeline hygiene checklist (L1)
Before every forecast call, RevOps runs a shared prompt over the exported pipeline to list the records failing basic hygiene: no next step, stale close date, missing contact roles, value that changed without a note.
The steps
- 01
Define hygiene in five rules
Tool: Manual
Five checks maximum, each objectively verifiable from the export. Twenty rules produce a list nobody works. Owner: RevOps lead. DoD: five rules written and agreed with sales leadership.
- 02
Export and check
Tool: Salesforce
Weekly export of open pipeline with the fields the rules need. At L1 this is a report export, not an integration. Owner: RevOps. DoD: export scheduled before the forecast call.
- 03
Produce an owner grouped list
Tool: ChatGPT
Output grouped by rep with the specific failing field per record. A total count changes nothing, a named list does. Pitfall: sending the whole list to everyone. DoD: each rep receives only their records.
- 04
Fix before the call, not during
Tool: Slack
Reps have until the morning of the call. Forecast meetings stop being data cleanup sessions, which is the actual return here. Owner: frontline managers. DoD: hygiene fail rate reported weekly.
Tools in this playbook
- Manual
- Salesforce
- ChatGPT
- Slack
Next playbooks
Unfamiliar terms are defined in the AI and Revenue Dictionary. Related frameworks live in the framework library.
