Churn Risk Identifier

Analyze the following customer data and identify accounts at risk of churning:

**Product/Service**: [YOUR PRODUCT OR SERVICE NAME]
**Customer Segment**: [SEGMENT BEING ANALYZED, e.g., "All Pro plan customers", "Enterprise accounts", "Customers in their first 90 days"]
**Analysis Period**: [TIME WINDOW, e.g., "Last 30 days", "Q1 2026"]

**Customer Data**:
```
[PASTE AVAILABLE CUSTOMER DATA. Include as much as you have for each account. Useful data points include:

Account: [COMPANY OR CUSTOMER NAME]
- Plan: [Plan type and monthly value]
- Account age: [How long they have been a customer]
- Recent tickets: [Number and brief summary of recent support interactions]
- Sentiment trend: [Any CSAT or NPS scores, or general tone of recent interactions]
- Usage: [Login frequency, feature adoption, or any usage metrics you track]
- Contract status: [Renewal date, month-to-month vs annual, etc.]
- Notable events: [Recent complaints, escalations, failed implementations, contact from competitors]

Repeat for each account. You can include 5-50 accounts.]
```

**Known Churn Reasons** (optional):
```
[LIST THE TOP REASONS CUSTOMERS HAVE CHURNED IN THE PAST, e.g.,
- "Too expensive for the value received"
- "Missing key integration with Salesforce"
- "Switched to Competitor X after poor support experience"
- "Internal champion left the company"]
```

Produce the following:

### 1. Risk Scorecard
For each account, assign a churn risk score and categorize:

| Account | Risk Score (1-10) | Risk Level | Primary Risk Signal | Days to Estimated Action |
Where Risk Level is:
- **Critical (8-10)**: Likely to churn within 30 days without intervention
- **High (6-7)**: Showing multiple warning signs, intervention needed within 2 weeks
- **Moderate (4-5)**: Early signals present, monitor closely and engage proactively
- **Low (1-3)**: Healthy account, no immediate concern

### 2. Signal Analysis
For each at-risk account (score 4 or higher), detail:
- **Account**: Name and key context
- **Risk Signals Detected**: Specific data points that indicate risk (not assumptions, only evidence from the provided data)
- **Risk Pattern**: Which known churn pattern this matches (e.g., "declining engagement", "unresolved escalation", "champion departure", "price sensitivity")
- **What We Do Not Know**: Information gaps that would improve the assessment (e.g., "No usage data available; login frequency would clarify whether they are still active")

### 3. Retention Playbooks
For each risk pattern identified, provide a specific intervention:

**Pattern: [Risk Pattern Name]**
- **Immediate Action** (this week): What to do right now (specific outreach, conversation, offer)
- **Message Template**: A ready-to-send email or call script tailored to this pattern
- **Escalation Trigger**: What response (or non-response) means this needs to escalate to a manager or executive
- **Success Metric**: How to measure whether the intervention worked
- **Timeline**: When to follow up and when to consider the account stabilized or lost

### 4. Portfolio Summary
- Total accounts analyzed: [count]
- Accounts at critical risk: [count and combined revenue at risk]
- Accounts at high risk: [count and combined revenue at risk]
- Most common risk pattern: [pattern]
- Recommended priority order for outreach: [ranked list of accounts to contact first]

### 5. Systemic Issues
Patterns that affect multiple accounts and suggest a product, process, or service problem rather than individual account issues. These require fixes at the team or company level, not just individual retention efforts.