Is Interview Question Writer free?

The setup guide and prompt are free. In Claude it works on any plan, including Free. ChatGPT Work on the web needs Plus, Pro, Business, Enterprise or Edu.

What makes a question leading?

It suggests the answer or assumes a problem exists, such as “Don’t you find no-shows frustrating?” It also flags hypothetical, opinion, double-barreled, yes/no and pitch questions, and rewrites each to ask about a specific past instance.

Is this the Mom Test?

It applies the same idea with its own checks and isn’t affiliated with the book. If you already work from The Mom Test, paste your draft questions and use this for the check, the coverage map and the notes template.

Does it run or record the interviews?

No. It writes the guide and a notes template. You rehearse with a colleague, check the intro and consent wording, run the interviews and take notes yourself.

What do I do with the notes afterwards?

Use the notes template it gives you, then paste the completed notes into Build traceable themes from interview notes, the setup on this site that groups them into themes you can trace back to each participant.

Interview Question Writer

Write customer interview questions that don’t lead the answer

Interview Question Writer is an AI agent you set up in the ChatGPT or Claude you already use. Tell it what you want to learn and it writes a short customer interview guide that asks about real past behavior, or paste your draft questions and it flags each leading one and rewrites it.

Pick your AI for the steps and the prompt

About each AI:ChatGPT WorkClaude app

Checked 29 Oct 2026. Not run by JuicyAgents yet. Written from each AI’s official docs; the example is illustrative.

Interview Question Writer · reply in the chat

Clinic interview guide, all 4 draft questions rewritten

Hypothetical“Would you pay for automatic reminders?”Pitch
Leading“Don’t you find no-shows frustrating?”
Rewrite“Tell me about the last no-show. What happened next?”
Reminders beliefNever asked directly
Coverage mapShows G1 and G2 covered

Illustrative example: a fictional founder exploring a booking tool for small clinics, with two goals, an untested belief that clinics would pay for reminders and four draft questions from a teammate.

How it works

What it does for you, and what it leaves to you.

Founders and small teams talking to customers often ask questions that invite hopeful answers: would you pay for this, don’t you find this frustrating, do you like it. The replies sound like validation but say little about what people do today. Practitioners also describe losing track of their goals while listening and probing at the same time.

“Would you use this?” invites a polite yes that says little about what people actually do. Founders often know the fix from The Mom Test, Rob Fitzpatrick’s handbook on spotting bad customer questions and turning them into good ones. This recipe applies that idea with its own checks: paste your draft questions and each leading, hypothetical, opinion, double-barreled, yes/no or pitch question is flagged with a reason and rewritten to ask about a specific past instance. You also get a coverage map, what to listen for, and a notes template that feeds Build traceable themes from interview notes. It cannot remove bias from the room, so rehearse the guide with a colleague first.

You stay in charge. Read every question aloud and check the rewrites still ask what you need to learn. Rehearse the guide with a colleague, check the intro and consent wording, then run the interviews and take notes yourself.

You get

The interview guide: intro, core questions, probes, what to listen for and a close
A coverage map showing which goal each question covers
Your draft questions checked and rewritten, if you pasted any
A notes template with participant ID and goal tags
A recruiting screener, if you select it

It never

Ask people to predict what they would use or pay for
Pitch your idea inside a question
Invent answers, quotes, personas or findings
Contact, recruit or record anyone

The guide it writes

The example above, in words.

All four drafts are flagged and rewritten. “Would you pay for automatic reminders?” is a hypothetical and a pitch; the rewrite asks what they use and pay for reminders today. “Don’t you find no-shows frustrating?” is leading; the rewrite is “Tell me about the last no-show. What happened next?” The bookings, cancellations and reminders question is split, keeping the cancellation part for G1. “Do you like your current system?” becomes a question about the last time the system got in the way. The reminders belief is never asked directly, and the coverage map shows G1 and G2 covered.

Settings

The setup prompt starts with the defaults, marked here.

Interview type

Each type swaps in its own question focus; the check rules and limits stay the same.

Problem discovery, before you build (default)
Feedback on an existing product
Churn or lost deal
Expert or stakeholder

Session length

The guide fits this time. If your goals don’t fit, it proposes dropping the lowest-priority one.

20 minutes
30 minutes (default)
45 minutes

Recruiting screener

Adds a few questions to find people with the recent experience your goals need.

No screener (default)
Add a recruiting screener

Your working rules

Optional. Your product area, topics to avoid, your intro or consent wording and note-taking arrangements. Do not include identifiable participant records.

Optional. Empty unless you fill it in.

Check the first result

Each setup page has a fictional exercise to paste first. A good answer to it meets all of these.

All four drafts are flagged: the first as hypothetical and a pitch, the second as leading, the third as double-barreled, the fourth as opinion and yes/no, each with a reason and a rewrite about a specific past instance.
The reminders belief is never asked directly; the guide asks what they use and pay for reminders today.
The coverage map shows G1 and G2 covered, and each goal has a “listen for” line.
The missing intro is drafted with a recording and consent question and marked for checking; no participant responses or quotes are invented.
The notes template has a participant ID and G1 and G2 tags, and no screener appears unless it was selected.
Removing an essential input causes a question or a blocked item, not an invented fact.

Questions people ask

Is Interview Question Writer free?: The setup guide and prompt are free. In Claude it works on any plan, including Free. ChatGPT Work on the web needs Plus, Pro, Business, Enterprise or Edu.
What makes a question leading?: It suggests the answer or assumes a problem exists, such as “Don’t you find no-shows frustrating?” It also flags hypothetical, opinion, double-barreled, yes/no and pitch questions, and rewrites each to ask about a specific past instance.
Is this the Mom Test?: It applies the same idea with its own checks and isn’t affiliated with the book. If you already work from The Mom Test, paste your draft questions and use this for the check, the coverage map and the notes template.
Does it run or record the interviews?: No. It writes the guide and a notes template. You rehearse with a colleague, check the intro and consent wording, run the interviews and take notes yourself.
What do I do with the notes afterwards?: Use the notes template it gives you, then paste the completed notes into Build traceable themes from interview notes, the setup on this site that groups them into themes you can trace back to each participant.

Have us set it up

Rather not set it up yourself?

We set up Interview Question Writer in your own accounts and the AI you already pay for, test it on your real work, and hand it over with a short walkthrough.

From $299

Runs in your accounts; you own everything
Tested before handover
Money back if we can’t make it work

Request a setup