Customer Interviews (the Mom Test)

First-time founders run "interviews" that are really pitches in disguise, then walk away with a notebook full of "yeah, I'd totally use that" - and build the wrong thing for a year. The problem isn't the people; it's the questions. Anyone, even your mom, will lie to you if you ask whether your idea is good. They won't lie about their own life. This skill makes you ask about their life, their past behaviour, and their real pain - never your idea - so the data you collect is worth building on.

The method

Built on the Founder OS scaffold (High tier). Full question bank, rules, and synthesis template in references/interview-guide.md.

Step 1 - Pick who to talk to

Talk to people who plausibly have [PROBLEM] now, not a random "target market." Define a tight screen for [ICP]: a role, a behaviour, a recent trigger ("bought X in the last month", "manages Y today"). 5-10 of the right people beats 50 randoms. Friends and family don't count - they protect your feelings (see Constraints).

Step 2 - Write non-leading questions

The whole game is removing yourself and your idea from the question. Bad questions invite a compliment ("Would you use an app that…?"). Good questions excavate the past ("Walk me through the last time you dealt with [PROBLEM]"). Build a script of 5-8 questions about their life and past behaviour, ordered from broad to specific. Keep [ONE_LINER] out of your mouth.

Step 3 - Run the conversation

Make it a conversation, not a survey. Open broad, then dig for specifics: "When was the last time?", "What did you do next?", "How much did that cost you - in time or money?". Shut up and listen - silence pulls out the truth. Don't pitch, don't correct, don't sell. Your job is to learn, not to be liked.

Step 4 - Spot good vs. bad signals

Score what you heard against the signal table. Specific past stories, emotion, money/time already spent, and concrete commitments are gold. Generic futures, compliments, and "yes I would" are noise - a draft is not a decision, and a polite "yes" is not a customer. Capture each as a real signal or an anti-signal.

Step 5 - Synthesise 5-10 interviews into a read

Batch the conversations, then decide once. Cluster what you heard into the pain, the current workaround, and the language customers actually use. Produce a go / pivot / kill read on the [RISKIEST_ASSUMPTION], grounded in evidence, not vibes. Carry the customer's own words into scope-mvp.

Output

• Interview plan: who ([ICP] screen), how many, the 5-8 non-leading questions.
• Per-interview notes: signals vs. anti-signals, with verbatim quotes.
• Synthesis: top 3 pains in the customer's words, current workarounds, any commitments secured.
• Read: go / pivot / kill on the [RISKIEST_ASSUMPTION], with the evidence that decided it.

Constraints

• Talk about their life, not your idea. The moment you describe your solution, the data goes soft.
• Past behaviour over future intent. "I would" is a wish; "I did / I paid" is a fact.
• Friends and family are not customers - their job is to love you, which biases every answer.
• No pitching, no leading, no rescuing. If you find yourself explaining, you've stopped learning.
• Commitment beats compliment. A real signal costs them something: time, money, reputation, a referral.
• Stay theme-agnostic; the founder supplies the domain, you supply the discipline.

Copy-paste version

Act as a sharp customer-discovery coach trained in The Mom Test, helping a first-time founder.
My idea (for context only - keep it OUT of my questions): [ONE_LINER].
Who I want to talk to: [ICP]. The problem I think they have: [PROBLEM].
Help me:
1. Tighten my screen for WHO to interview (a behaviour or recent trigger, not a demographic), and how many.
2. Write 5-8 non-leading questions about their LIFE and PAST BEHAVIOUR - never about my idea. For each, show the leading version I should avoid and why.
3. Give me 3 dig-deeper follow-ups to pull out specifics (last time it happened, what they did next, what it cost them).
4. Give me a signal vs. anti-signal checklist so I can tell real pain and commitment from polite compliments.
5. After I paste my notes from 5-10 interviews, synthesise them into the top 3 pains in the customer's words, current workarounds, and a go / pivot / kill read on my riskiest assumption.
Stop me if I start pitching, leading, or counting "I would use that" as validation.