Design a survey that gets honest, useful answers
Survey questions, scales, and structure that avoid bias and map to the decisions you need to make.
The prompt
Help me design a survey.
Purpose — the decisions this survey will inform: [DECISIONS]
Audience: [customers / employees / students / event attendees]
How it will be sent: [email, in-app, after a purchase]
Length limit: [e.g. "under 5 minutes"]
Must-cover topics: [LIST]
Deliver:
1. A survey of 8–15 questions mapped to my decisions (show which decision each question serves).
2. For each question: type (rating, multiple choice, open), the answer options or scale, and why it's worded that way.
3. A short intro (purpose, time, anonymity) and a thank-you message.
4. A quick check for bias: leading, double-barreled, or loaded questions, and confusing scales.
5. How to analyze the results.
Put demographics and sensitive questions last and make them optional.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Data & Analysis prompts
What to fill in
- DECISIONS
- customers / employees / students / event attendees
- email, in-app, after a purchase
- e.g. "under 5 minutes"
- LIST
How this prompt is built
This prompt follows the RTF structure (Role, Task, Format). RTF tells the model who to be, what to do and what shape the answer should take. It is the quickest structure that still gives noticeably better results than a bare request.
Related prompts
- Turn my monthly or quarterly numbers into an executive business reviewTurns your numbers into an executive business review: headline, performance vs. plan, drivers, risks, and decisions needed, as a report or slides.
- Compare performance against targets and find the biggest gapsCompares actuals against targets for every KPI, sizes each gap, and ranks the gaps that matter most so you know where to focus.
- Check whether my KPIs measure activity or real value, and fix themSorts your KPIs into activity, output, and outcome measures, flags vanity metrics, and redesigns the set around the outcomes that matter.
- Challenge my interpretation of the data and find other explanationsStress-tests your conclusions for alternative explanations, cherry-picking, and averaging traps, then gives you a defensible version.