Pipeline Hygiene Rules

Step 1 — Pull every open deal (read-only)

Pull all open deals: current stage, amount, close date, next step field, and how long the deal has sat in its current stage (time-in-stage). Read-only — no field on the deal is changed in this step.

Step 2 — Pull activities per deal (read-only)

Pull logged calls, emails, meetings, and notes per deal, with timestamps. This is the basis for the staleness check in Step 4.

Step 3 — Pull tasks per deal (read-only)

Pull open tasks tied to each deal, with due dates. A task past its due date with no completion is overdue.

Step 4 — Apply the four hygiene rules

Evaluate every open deal against all four independently — a deal can trip more than one:

Step 5 — Write the hygiene flag (the only write)

For every deal that trips at least one rule, write the internal hygiene-flag field on the deal noting which rule(s) tripped and the date. This is the only field the agent ever writes — never the stage, the owner, or the amount. Deals that trip no rule get their flag cleared if previously set.

Step 6 — Nudge the owning rep in Slack

For each flagged deal, send the owning rep a Slack nudge naming the deal, which rule(s) tripped, and the concrete action needed:

Group multiple flagged deals for the same rep into one message rather than one message per deal.

Step 7 — Escalate the day's worst to {{escalation_channel}}

After all rep nudges are sent, rank flagged deals by:

1. Number of rules tripped at once (most rules first).
2. Deal amount at risk (largest first, as a tiebreaker).
3. Days since last activity (longest first, as a second tiebreaker).

Post the top offenders to {{escalation_channel}} in one message: deal name, owning rep, amount, which rules tripped, and days since last activity. Post exactly once per run.