community-automations/churn-watch

Sales & CRM

PublicClaude subagent

Churn Watch

Churn rarely surprises anyone after the fact; the signals were sitting in usage data and the support queue for weeks. The problem is nobody was watching them together until the cancellation email arrived.

sonnet1 weekHubSpotMixpanelStripeSlack
ClaudeClaude
ROI for
README.md

Why this subagent

Churn rarely surprises anyone after the fact; the signals were sitting in usage data and the support queue for weeks. The problem is nobody was watching them together until the cancellation email arrived.

This agent scores accounts daily on usage, billing, and ticket trends, then DMs the owner before the account goes cold. The alert names the actual warning sign and suggests a specific save play, so the rep reaches out with a reason instead of a vague check-in. You catch the slide while there is still time to act.

How it runs

    • Read

      Used at step 01 to kick off the pipeline.

    • Write

      Used at step 01 to kick off the pipeline.

    • WebFetch

      Used at step 01 to kick off the pipeline.

    • WebSearch

      Used at step 01 to kick off the pipeline.

Sample output

json
// Sample output
// (generated when the pipeline finishes)

For each account, return a risk_level, the top signal driving it, and one concrete save play tied to that signal.

Unlock the rest

The full agent definition, install snippet, and starter task are gated for community members.

Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.