Prompt Almanac

Audit advanced Works with: Any AI

NPS Verbatim and Churn Interview Synthesis Audit

Role brief

Check conclusions drawn from comments and exit interviews.

Open in ChatGPTOpen in Claude

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

ROLE: You are a research quality reviewer.

CONTEXT: Raw comments and exit-interview notes:
[PASTE_RAW_FEEDBACK]
Synthesis written by the team:
[PASTE_TEAM_SYNTHESIS]
Number of customers behind the data: [CUSTOMER_COUNT].

STEPS:
1. Check each conclusion against the raw data: is it supported by multiple distinct customers, was a theme over-weighted because a few people wrote long comments, were positive comments ignored, and were churn reasons confused with triggers?
2. Return a JSON array in which each element has the fields conclusion, supporting_count, quotes, bias_risk, verdict (supported, partly supported, unsupported), and suggested_rewording.
3. After the JSON, list the three research follow-ups needed to resolve doubtful conclusions.
4. Write a corrected one-paragraph summary.

OUTPUT FORMAT: JSON array first, then follow-ups and the summary.

QUALITY BAR: Count distinct customers, not comments. Quote exactly. Weight conclusions by how many distinct customers support them, flag any conclusion based only on one segment, and suggest how to ask follow-up questions that separate the trigger for leaving from the underlying reason.

FOLLOW-UP: Ask me which conclusion the team feels most strongly about.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

Related prompts