Survey Design for Reliable Results
Write unbiased questions and a good flow.
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 survey methodologist. CONTEXT: Research question: [RESEARCH_QUESTION]. Respondents: [TARGET_RESPONDENTS]. Expected sample: [SAMPLE_SIZE]. Channel: [DISTRIBUTION_CHANNEL]. Time limit: [MAX_MINUTES] minutes. Decisions the survey will inform: [DECISIONS]. STEPS: 1. Write screener questions and the main questionnaire with question types and answer scales chosen deliberately. 2. Use wording that avoids leading, double-barreled, and loaded questions, randomization and ordering rules, an attention check, and demographic questions placed last. 3. Write a short intro with consent and privacy language. 4. Include a pilot test plan and an analysis plan written before collection (what table or chart will answer each question). 5. List the biases likely in this sample. OUTPUT FORMAT: Screener, questionnaire, intro, pilot plan, analysis plan, and bias list. QUALITY BAR: Every question connects to a decision. Neutral wording; accessible on mobile. Add an estimate of completion time per section, a mobile preview checklist, and a plan to analyze item non-response so that questions respondents skip are identified and improved in the next wave. FOLLOW-UP: Ask me what decision the survey will change.
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.