Audit intermediate Works with: Any AI

Customer Satisfaction Survey Design Audit

Table output Has example

Check questions, timing and bias.

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

[VERIFY] is an editorial flag, not a blank to fill. Wherever the prompt shows [VERIFY], check that item against a reliable source before you use it.

Audit our post-ticket satisfaction survey. Survey wording, scale, timing, response rate and recent results: [SURVEY_DETAILS]. How results are used: [RESULTS_USE]. Complaints about the survey: [COMPLAINTS].

Check for leading wording, double-barrelled questions, response bias, survey fatigue, how scores are used to judge agents, and whether open comments are read. Check what the survey does not capture.

Return a table with Question, Problem and Rewrite, a score from 1 to 10 for validity and respect, and rules for using scores fairly. Data protection rules are [VERIFY] for [JURISDICTION].

Also suggest a version with two questions and one optional comment, an approach for following up low scores with care, and an explanation of how to show scores to the team without ranking individuals unfairly. Further, suggest testing the survey with five customers by asking them to explain each question in their own words, and a plan to close the loop with customers who give low scores.

End with a plain-language paragraph I could forward to a colleague who has not seen the material, summarising the main findings and the agreed next steps.

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.

Question review (invented post-ticket survey)
Q1 "How satisfied were you with our excellent support?" Leading. Rewrite: "How satisfied were you with the support you received?"
Q2 "Was the agent friendly and fast?" Double-barrelled. Split.
Q3 Scale 1 to 10 with no labels at 3 and 8. Add labels.
Timing: sent immediately, before the problem is confirmed fixed. Send after 48 hours.
Response rate 9%; mostly very satisfied or very dissatisfied (bias).
Use: scores shown per agent weekly. Risk of unfair ranking with small samples; show trends at team level.
Two-question version: overall rating plus an optional comment.

• audit