/euxlab-grill-the-ask
you invokewrites docs/interview-guide.md
Critical questions about requirements, scope and users, every claim graded, and the questions for the interviews.
When you reach for it
A stakeholder ask has arrived. "We need a new dashboard." "Make the portal easier." You reach for this before any research or design is planned, because the ask is not yet sharp enough to research.
Input, output, writes
- Input
- A vague stakeholder ask, and you in the room to be interviewed about it.
- Output
- One file: the ask sharpened, a graded assumption register, and the interview questions, each naming the assumption it tests.
- Writes
- docs/interview-guide.md
Completion criterion
The question frontier is empty, every assumption in the register carries a grade, and every C and D assumption is either covered by a numbered question or carries an explicit written decision to accept the risk untested. A colleague who was not in the room could run the sessions from the file.
Checkable, and demanding. A skill that cannot say whether it is finished is a prompt.
Anti-patterns
- Recording assumptions at the end instead of in the round they were made.
- Grading generously. "Users find the export confusing" is a D until someone names who watched it happen.
- A question with no assumption ID under it. That is curiosity, and curiosity is what makes sessions run 90 minutes.