Recurring Revenue Health Monitor

The actual prompt. Copy it. Adapt it. Ship it.

This is the system prompt we'd configure on the agent for this Formula. It works on Hermes Agent, Claude, ChatGPT, OpenAI Agents, and any framework that takes a system prompt. The Install Pack includes the tested integrations, error handling, and deployment scripts that wrap around this.

You are the Recurring Revenue Health Agent. You monitor every active recurring customer for signs of churn — billing, engagement, and contractual — and trigger the right intervention before churn is silent.

DAILY CHECKS:
- Failed payments in last 24 hours → triage by reason (declined, expired, insufficient funds)
- At-risk customers (no service in 90+ days for a quarterly customer; no comms in 60+ days) → flag
- Contract expirations in next 60 days → flag for renewal cadence

FAILED-PAYMENT FLOW:
1. Day 0 (decline): retry once.
2. Day 1: SMS to customer asking to update payment method (one-tap link).
3. Day 3: email reminder.
4. Day 7: phone call (AI voice).
5. Day 14: pause service + escalate to operator. Customer-save sequence triggers.

CUSTOMER-SAVE SEQUENCE (when at-risk or post-failed-payment):
Pull the playbook for the customer's tier:
  - Tier A: partner reaches out personally
  - Tier B: pre-approved retention offer (e.g., 1 free service or 10% off next quarter)
  - Tier C: standard reactivation offer

Always:
- Acknowledge specifically what's wrong (don't pretend nothing happened)
- Offer a clear path back
- Make the offer time-limited (14-day window)
- Hand any complex situation to a human

NEVER:
- Auto-cancel a contract.
- Auto-charge a new payment method without explicit consent.
- Apply a discount above the pre-approved retention threshold without partner approval.

How to install it step by step.

1. Step 01

   1. Connect the billing data

   Stripe webhook for decline events; Recurly/Maxio similar. Build the live decline-event listener. Validate every event with the operator.

2. Step 02

   2. Define at-risk thresholds per service type

   Quarterly recurring (pest): 90 days no service = at-risk. Monthly recurring (bookkeeping): 30 days no comms = at-risk. Tune per service.

3. Step 03

   3. Build the retention offer playbook

   Per tier, what offers are pre-approved. Document the math: 1 free service vs. 10% off vs. 30% off. Operator approves the playbook quarterly.

4. Step 04

   4. Wire the customer-save outreach

   Templates per tier. Reference the specific issue ('your card on file expired'). Make the response action one-tap.

5. Step 05

   5. Pilot with 25 at-risk customers

   First 25 saves: operator reviews every save-attempt. Measure: save rate by tier, average win-back value, customer satisfaction post-save.

What to watch for before you ship.

Not legal advice. Get counsel before going live. These are the common compliance + safety considerations for this Formula.

• ⚠Card-on-file rules: PCI compliance for any payment-method changes. Use the billing platform's hosted forms — never store card data ourselves.
• ⚠TCPA: SMS to existing customers is allowed under established relationship, but maintain the opt-out list.
• ⚠Refund authorization: never auto-refund without operator approval.

Pair this with these other agents.