Surveys and interview guides that work
Listen to this lesson
Nigerian voice narration
Fictional training case. Adeyemi needs input from 50 officers across three fictional parastatals but can only visit twice. This lesson covers drafting then de-biasing a questionnaire — catching leading and double-barrelled questions — and piloting before full rollout. Work through the example, identify the evidence needed and practise the method with cleared or synthetic inputs. Any additional figures in the explanation are separate practice examples, not claimed rows in a downloadable file.
Worked example
Adeyemi asks AI to draft a 12-question survey on AI tool use. Question 7 reads: 'Don't you agree that AI tools have made your work faster and easier?' She asks AI to review its own draft for leading and double-barrelled questions. AI flags Q7 as both leading (assumes agreement) and double-barrelled (faster AND easier are two separate claims), suggesting a split and neutral rewrite: 'How has AI tool use affected your work speed?' and 'How has AI tool use affected the ease of your work?' as separate, neutrally-worded items. She then asks AI to design a 5-person pilot: observe where respondents hesitate or ask for clarification, then cut or rewrite those items before the full 50-person rollout.
The method
Have AI review its own first draft specifically for leading phrasing and double-barrelled items, splitting any compound question into separate neutral ones, then pilot on a small group and track where respondents hesitate before finalising for full rollout.
Worked practice and common mistakes
A neutral question also needs a balanced response scale: much slower, slower, no change, faster, much faster, and not applicable where suitable. Wording can improve while the options still bias the result. Use the pilot to define ambiguous terms and time the survey. Pilot before the main collection so limited visits are not consumed by preventable questionnaire problems.
Review before using the result
A leading question suggests the answer you want. A double-barrelled question hides which of two things was actually answered. Pilot with a small group before the full rollout to catch confusing items early.
Your workplace practice
Use the recommended free assistant with this lesson's fictional example. Draft a 12-question survey on [topic] for civil servants. Then review it: flag leading questions, double-barrelled questions and jargon, and suggest rewrites. Finally, propose a small pilot plan. Keep a copy of the input and draft. Compare the result with the verification steps above, record any correction, and retain placeholders where evidence is missing. The expected result is a checked draft for human review, not an automatically approved decision. Course examples and practice responses are fictional; amounts, dates, rules and thresholds are not official guidance or supplier quotations.
Open ChatGPT (free tier) and paste this prompt there. Drafts balanced survey and interview questions quickly.
Draft a 12-question survey on [topic] for civil servants. Then review it: flag leading questions, double-barrelled questions and jargon, and suggest rewrites. Finally, propose a small pilot plan.
Why this tool: Drafts balanced survey and interview questions quickly.
Hit a free limit? Switch to ChatGPT or Gemini and continue — the prompt works in any assistant.