Interview Debrief: One conversation, distilled into evidence
Turn raw notes or a transcript from one customer interview into a brief on-the-record report — concise answers mapped to your questions, plus the surprises that fit nowhere. Adapted from Chapter 10 of Hidden Multipliers: A multiplier of one's own.
- Input
- Raw material from one customer conversation — a transcript, your scribbled notes, or a voice-memo dump — plus your QUESTIONS.md.
- Output
- A brief per-person debrief file in your interviews directory: one concise answer per question asked, and an addenda of things you heard that fit no question.
What this is about
If you do not write down an interview, you will misremember it. Confirmation bias will quietly keep only the parts you liked. The book's method uses a spreadsheet: one row per question, one column per interview. This skill gives you the same discipline without the spreadsheet. After each conversation, give it your raw material — a transcript or hasty notes. The skill turns this material into a brief, structured debrief file. The file has one concise answer for each interview question, and honestly marks the questions you never asked. It also has an addenda section that lists everything interesting that did not fit a question. The biggest learning often hides there.
The debrief is short on purpose. It records evidence, not prose. Each conversation adds one file to a directory. This directory becomes your record of what real customers actually said. As interviews add up, you can use these files to update your hypotheses.
Example invocation
You can invoke the skill like this:
/asb-interview-debrief Here's the transcript from my call with a gym owner
this morning — file it against my QUESTIONS.md.
The skill drafts the debrief. It writes one brief answer for each question you asked. It keeps exact phrases from the interview. It honestly marks the questions you skipped. It also adds an addenda section for everything interesting that did not fit a question. The skill asks you to fill gaps the transcript cannot supply — for example, unclear answers or surprises that never made it into your notes.
One practical note: tell the skill where you are working. Name a directory, or point to your existing files, when you invoke it. The skill then keeps the method's files together in that location. If you do not name a location, it asks before it creates anything.
From the source
Two sources form the foundation of this skill:
- As in Chapter 10 of Hidden Multipliers: A multiplier of one's own (section "Learning: Iterate the Hypotheses") — hiddenmultipliers.com — this skill replaces the book's spreadsheet with per-interview record-keeping: notes next to each question, notes next to each hypothesis, and the rule that new learning often comes from straying off-script.
- The Iterative-Hypothesis customer development method — the published article version of the method. It states exactly where AI may help: clean up transcripts and summarize, so the thinking stays yours.