Home · Business · Marketing & Content · Market research

YES

As of 13 August 2026, AI can design customer research interview questions.

This still needs a person who signs their name to it.

Can you do it?

5 minutesto a draft.

30 minutesto something you’d act on.

Cost, all in£0

Skill neededchat-fluent

Who has to check ityou

What the alternative costsA human market researcher remains the alternative when the research objective, sampling plan or interview method needs specialist judgement.

If this goes wrong: participants give shallow or biased answers, and you waste interviews before discovering that the guide was poorly designed.

What to actually do

  1. Hand it to a person

    The route this page recommends

    A person who owns the outcome does this end to end, worth it when the failure is dear.

  2. Use a tool built for this

    Second choice

  3. Do it yourself

    The distant third

    A chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.

    How to actually do it

    1. Open a document and write the decision the research must inform, the target participant description, interview length, format and topics that must be covered.
    2. Paste that context into the prompt, replacing each bracketed slot with the facts you already know and leaving out personal data that is not needed.
    3. Run the prompt in ChatGPT, Claude or Gemini and save the complete guide, including the interviewer notes and the explanation of each question's purpose.
    4. Compare every question with the research objective and remove questions that do not inform the decision, duplicate another question or assume the participant's answer.
    5. Read the questions aloud and rewrite any wording that is leading, double-barrelled, vague or unnatural for the people you will interview.
    6. Ask a colleague who understands the customer or research goal to challenge the sequence and bias, then produce the final guide with your consent and recruitment process handled separately.

    Prompt

    Design a customer research interview guide for [product, service or business].

Research objective: [what decision the research needs to inform]
Target participants: [who they are, including relevant experience or behaviour]
Interview format: [remote or in person, one to one or group, and approximate length]
What we already know: [brief evidence or assumptions]
Topics to cover: [list the areas that matter]
Topics to avoid: [sensitive, irrelevant or legally restricted areas]

Create a practical guide with:
1. A short introduction I can read to participants, including a neutral explanation of the purpose and a reminder that there are no right answers.
2. A logical sequence of open questions, starting with recent behaviour and experience before opinions or reactions.
3. Useful, neutral follow-up prompts for each main question.
4. A closing question that allows participants to raise anything we have missed.
5. A brief note explaining which research objective each question serves.

Do not ask leading, double-barrelled, hypothetical or overly broad questions. Do not assume the participant agrees with our framing. Keep the wording natural for a UK audience. Separate questions I should ask from notes for the interviewer. Flag any question that could introduce bias or needs specialist research judgement. Do not invent product facts, participant details or findings.

    Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.

What it gets wrong

  • AI cannot decide whether the stated research objective is the right decision to investigate.
  • AI cannot know which customer assumptions are politically or commercially sensitive in your organisation unless you explain them.
  • AI can miss subtle leading language, especially when your brief already contains a preferred answer.
  • AI cannot replace decisions about sampling, recruitment, consent or how much evidence is enough.
  • AI produces plausible questions without proving that they will generate useful answers from your particular participants.

Even on a YES, the friction has a name: judgement under ambiguity, context depth and verification cost.

How we scored this

Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.

AxisScore (0–2)
Output2
Inputs2
Verification1
Liability2
Effort delta2
Total9 / 10

The methodology and its thresholds are published in full.

FAQ

Can ChatGPT write customer interview questions?
Yes. It can draft a structured guide quickly when you provide the research objective, participant details and topics to cover. Check the questions for leading wording and whether each one informs the decision you need to make.
How do I get AI to write better research questions?
Give it the decision the research must inform, who will be interviewed, what you already know and what you need to learn. Ask for open, neutral questions based on recent behaviour, with follow-up prompts and a warning about possible bias.
Can AI make interview questions unbiased?
It can reduce obvious leading and double-barrelled wording, but it cannot guarantee an unbiased guide. Your framing, assumptions and choice of topics still shape the output, so a colleague with research experience should challenge the draft.
Is AI good for market research?
It is useful for drafting interview guides, organising topics and suggesting follow-up questions. It does not choose the right sample, obtain meaningful consent, conduct sensitive conversations well or decide what the evidence means for your business.

Nearby answers

All Market research rulings

Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.

The newsletter

AI news, new answers and product picks, straight to your inbox.