Design the actual research question before you design the study
A vague question guarantees findings nobody can act on.
- Use it for
- Researchers and PMs about to run interviews, a survey, or usability testing.
A lot of research produces interesting-but-unactionable findings because the question behind it was never made specific enough to be answerable. "Understand how users feel about onboarding" isn't a research question, it's a topic — and a topic doesn't tell you who to talk to, what to ask, or what would count as an answer. The study design inherits the vagueness and produces findings that are true but don't point anywhere.
This prompt forces the question into an answerable shape before any study gets designed around it.
When not to use this
If you already have a sharp, specific question and just need a study design, skip straight to designing it — this is for the step before that, when the "question" is still really a topic or a vague sense of wanting to know more.
Did this work?
You end up with a specific, answerable research question and a study design that could actually answer it — not "let's learn more about onboarding," which no study design can cleanly resolve.
Tested on claude-opus-5. Evidence status is draft; it moves to battle-tested only on recorded runs, never by hand.