Learning: Let the interviews rewrite your hypotheses
Synthesize everything your customer interviews have said into concrete updates — hypotheses confirmed, overturned, refined, or newly born — proposed one at a time, with you deciding each. Adapted from Chapter 10 of Hidden Multipliers: A multiplier of one's own.
- Input
- Your GOALS.md, HYPOTHESES.md, and QUESTIONS.md, plus a directory of per-interview debrief files.
- Output
- Your working files updated one agreed change at a time — plus tentative observations worth watching and a read on whether it's time to stop interviewing.
What this is about
The interviews are not the goal. The learning is the goal. This skill reads your goals, hypotheses, and questions. It also reads the debriefs from every conversation you have had. It does what the book says to do with them. It finds which hypotheses reality has confirmed. It finds which hypotheses reality has proven wrong. It finds which hypotheses need new numbers. It finds which surprises suggest brand-new beliefs. Then it proposes each change to you one at a time. It never proposes changes in a batch. It updates the working files only when you agree.
The skill uses the same evidence standard as the book. One person who disagrees does not change a hypothesis. Nothing is true for everyone. But a clear pattern across many conversations does change a hypothesis. A single strong new fact also changes a hypothesis. Things you hear only once go into a list of tentative observations. The skill records them and watches them. It does not act on them yet. New hypotheses get new interview questions. When debriefs start to repeat — same stories, same numbers, same words — this is a signal. It means the learning has stopped. It means the interviewing should stop too.
Example invocation
You can invoke the skill like this:
/asb-interview-learning I've done nine interviews since we wrote the
hypotheses — here's the interviews/ directory. What should change?
The skill compares your debriefs to your hypotheses. It walks you through proposed changes one at a time. Each change cites the conversations that support it. It updates your files as you agree. The session ends with a clear verdict: keep interviewing, stop and act, or change direction.
One practical note. Tell the skill where you are working. Name a directory, or point to your existing files, when you start the skill. The skill then keeps the method's files together in that place. If you do not tell it, the skill asks before it creates any file.
From the source
Two sources form the foundation of this skill:
- As in Chapter 10 of Hidden Multipliers: A multiplier of one's own (sections "Learning: Iterate the Hypotheses" and "Stop When It's Boring") — hiddenmultipliers.com. This chapter gives the update rules the skill follows. One voice does not make a pattern. A pattern or a single strong new fact does change a hypothesis. The chapter also gives the dig-deeper approach and the stop signal.
- The Iterative-Hypothesis customer development method — this article is the article version of the method. It says to expect contradictions. It says "no pattern" is still learning. It covers emergent segmentation and market-guru mode. It warns that AI must not do the thinking for you. This is why the skill proposes changes, and you decide.
Supporting articles each supply a piece of the mechanism:
- Stubborn Visionaries & Pigheaded Fools — this article covers the persist-or-stop decision in depth. You cannot know in advance which path you are on. Your job is to find out as fast as possible. The article gives the practical questions behind the skill's stop-or-continue verdict: rate of progress, whether you are still learning, sunk cost, and timebox.
- The "Convergent" theory of finding truth in darkness — this article explains how to tell validated truth from noise. Answers that converge across interviews act like a fundamental law. Answers that diverge into many different and conflicting answers may mean the idea itself is the problem, not the interviews.
- "It's a Balance" isn't always the answer — this article explains what to do when interviews send contradictory signals. Saying "it's a balance" is usually a way to avoid a decision. The real options are: make a clear choice, meet a minimum requirement for one thing while you get the most of another, or find a way to get "both" by asking what else would have to be true.