Example prompts
› Which intent signals in our product predict churn?
› Run the Warning Signals skill and show me accounts that viewed the cancel page this week
What this Skill does
Detects intent events in your product data (cancel_viewed, downgrade_viewed, pricing_viewed, billing_viewed, delete_account) and measures how much more often accounts that fire them go on to churn. Terminal events like cancel_completed are excluded, because they are the outcome itself.
When it fires
- An account fires an intent event (cancel, downgrade, pricing, billing views)
- Optionally: at least N times within 7 days
- Completed cancellations and payments are excluded as signals
Inputs
- Brazebee MCP: connected to Claude or ChatGPT with your Brazebee API key
- Product usage: Amplitude, PostHog, or Mixpanel connected in Brazebee
- Billing and CRM: Stripe and HubSpot for ARR, plan, renewal date, and account owner
How it works
- 01 / Finds intent events by name (cancel, downgrade, pricing, billing, delete)
- 02 / Builds a cohort per event and per count (at least 1x, 2x, 3x)
- 03 / Compares each cohort's churn rate against the rest
- 04 / Keeps the signals that separate churners clearly
Output
Warning Signals: "cancel_viewed" at least 3x in 7 days
Cohort: 64 accounts · $410k ARR
Churn: 31% in cohort vs 4% in the rest (7.8x)
Act on: 6 accounts fired this signal in the last 7 days
Route: CSM · Slack #cs-alerts · "Immediate save call"Example numbers. Your thresholds and rates come from your own data.
Tips
- Repeated views beat a single view: test at least 2x and 3x in 7 days
- Pricing page views can also mean expansion intent. Check the upsell rate too
- Speed matters most here. Route to Slack, not a weekly report