New ResearchCorpBenchSee the results ↗AI models tested on real business tasks.

Retention

On demand

Churn Reason Analyser Agent

Learn why customers leave.

Summarise why customers leave and suggest practical improvements to investigate.

Take it into your workspace

Use Churn Reason Analyser

Choose where you want to use this blueprint, then copy the prompt to get started.

Choose your agent platform

Use Revensi in ChatGPT

Connect once, then paste your prompt below.

Add to ChatGPT

Personalise with Revensi
Churn evidenceIllustrative demo

Classify three October departures.

  1. Read Stripe cohort · 20 Oct

What it does

Turn departure feedback into improvements to investigate.

Summarise why customers leave and suggest practical improvements to investigate. Built for customer success operations and product leaders.

  1. Build the churn cohort

    Choose the cancelled accounts and any feedback explaining their decisions. Exit interviews and account history can reveal more than a single cancellation reason.

  2. Classify supported reasons

    Group stated reasons, keep unknown reasons visible and avoid filling gaps with assumptions.

  3. Propose corrective experiments

    Get a summary of recurring issues and small improvements your team could test.

How it works

Summarise why customers leave and suggest practical improvements to investigate. Built for customer success operations and product leaders.

Agent architectureTools · knowledge · outputs · oversight
Approved documents and context
Churn cohort definitions Evidence hierarchy for reason classification Optional: consented exit interviews and cancellation correspondence, to capture the customer's own explanation. Optional: comparable usage, incident and pricing-change timelines, to investigate patterns across the selected churn cohort.
Understand the reasons customers give
Compare grouped cancellation reasons while keeping unknowns visible, so the team can see what customers actually reported.
Turn recurring issues into improvement work
Review practical changes tied to repeated problems, giving the team specific ideas to investigate or test.
Stripe · Read ended subscription events (read)
Verify actual churn and payment state.
Salesforce · Read exit notes (read)
Compare customer reasons with internal interpretations.
Zendesk · Read relevant service history (read)
Check supporting and conflicting evidence.
Human review and permissions
Retention analyst approves labels before aggregation.
  1. 01Gather the context

    Bring together the relevant information from Stripe, Salesforce, Zendesk.

  2. 02Check what matters

    Group stated reasons, keep unknown reasons visible and avoid filling gaps with assumptions.

  3. 03Prepare the result

    Voluntary, involuntary or administrative classification with confidence and citations. Testable proposals tied to observed reasons, not claimed causality.

  4. 04Review proposed changes

    Retention analyst approves labels before aggregation.

Integrations

Payments & billing

Example:
  • Stripe

CRM

Examples:
  • Salesforce
  • HubSpot

Customer support

Examples:
  • Zendesk
  • Intercom

Choose the platforms your team already uses—you don’t need every example shown. Confirm the required features and configure access during implementation.

What you get

Use customer departures to identify recurring problems and choose service or product improvements worth testing.

Understand the reasons customers give
Compare grouped cancellation reasons while keeping unknowns visible, so the team can see what customers actually reported.
Turn recurring issues into improvement work
Review practical changes tied to repeated problems, giving the team specific ideas to investigate or test.

More for retention teams

Start with a blueprint. Build it around your business.

We’ll adapt it to your workflows, connect your systems and build an agent your team can put to work.

30 minutes. One bottleneck. Leave with a clear system concept.