Analyze Customer Cancellation Reasons to Surface Preventable Churn Fixes

Get a structured churn analysis table separating controllable from uncontrollable cancellations, with exact counts, root causes, and one retention fix per category.

You getSummary Table and top 3 Priorities

Prompt

Prompt
Act as a customer retention analyst. I will paste raw customer cancellation reasons, exit survey notes, or support tickets right after this prompt. Analyze the data to separate preventable churn from uncontrollable churn and surface concrete fixes.

Rules:
- Count every cancellation entry and group them into clear, mutually exclusive categories.
- Classify each category as Controllable (product gaps, onboarding, support, pricing) or Uncontrollable (business closed, seasonal pause, acquired).
- Identify the specific root cause behind each category using only the pasted data; do not invent reasons or statistics.
- Propose exactly one actionable retention fix per controllable category that a support or product team can test within 30 days.

Output format:
1. Summary Table: Columns for Category, Type (Controllable or Uncontrollable), Exact Count, Root Cause, and 30-Day Retention Fix.
2. Top 3 Priorities: A short numbered list of the highest-impact controllable categories to tackle first, with one sentence explaining why.

End with one line noting any ambiguous entries, missing context, or assumptions made while grouping the data.

Example output

At a glanceQ1 cancellations by reason84 cancellation notes; first four reasons are controllable
  • Steep Onboarding Curve: 24
  • Missing Slack Sync: 18
  • Pricing vs. Seat Usage: 14
  • Company Closed or Merged: 12
  • Slow Support Replies: 9
  • Project Completed: 7

Example for: a 15-person B2B project management SaaS reviewing 84 Q1 cancellation notes.

1. Summary Table
CategoryTypeExact CountRoot Cause30-Day Retention Fix
Steep Onboarding CurveControllable24New teams struggle to import existing tasks and set up permissions in week one.Add a 15-minute live setup call offer to the day-two welcome email.
Missing Slack SyncControllable18Users want two-way status updates in Slack without opening the web app.Publish a Zapier template workaround and notify affected accounts.
Pricing vs. Seat UsageControllable14Small teams pay for unused seats after seasonal contractors leave.Introduce a self-serve pause or flex-seat downgrade option at checkout.
Slow Support RepliesControllable9Billing and bug tickets waited over 48 hours during January spikes.Route billing-tagged cancellations to a dedicated 4-hour priority queue.
Company Closed or MergedUncontrollable12Customer went out of business or was acquired by a parent company.None; exclude from controllable churn metrics.
Project CompletedUncontrollable7Agencies hired the tool for a single fixed-term client engagement.None; tag for a 6-month win-back email campaign.
2. Top 3 Priorities
  1. Steep Onboarding Curve (24): Fixing week-one setup friction addresses nearly 29% of all Q1 cancellations and requires no engineering work.
  2. Missing Slack Sync (18): Providing a documented Zapier workaround immediately retains workflow-dependent teams while the native integration is scoped.
  3. Pricing vs. Seat Usage (14): Offering a flex-seat downgrade in the cancellation flow gives cost-sensitive teams an alternative to leaving.

Assumptions and gaps: 4 vague entries reading "no longer needed" were grouped under Project Completed; revenue impact per account is unknown because MRR data was not included.

Written by AI from this prompt. Your results will vary.

Tips and common edits

Why this works

  • Forces mutually exclusive categories and exact counts so high-volume churn drivers stand out immediately.
  • Separates controllable from uncontrollable churn to stop teams from wasting time on unpreventable losses.
  • Requires one 30-day retention fix per category, keeping recommendations practical for support and product teams.

Use this monthly or quarterly after exporting exit survey responses or cancellation tickets. Paste 20 to 200 raw customer reasons right after the prompt in ChatGPT, Claude, or Gemini.

Common edits

  • Add account MRR or plan tier to the pasted data and ask the model to sort the table by lost revenue instead of count.
  • Change the 30-day fix constraint to focus only on help-center articles or automated in-app messages.

Make it repeatable

Keep using this prompt without pasting it in every time.

Keep exploring

More in Customer Support