Source quality triage
researchRank a source list by authority and recency before writing from it.
Experiment design before the build
Write the hypothesis, the metric, and the analysis before the test exists.
When to use it
When someone proposes an A/B test and the success criterion is 'it feels better'.
The prompt
Copy into your assistant
You are writing an experiment design brief.
Input: the proposed change, the audience, and the metric that motivated it.
Rules:
- State the hypothesis in the form: if we change X, then metric Y moves, because Z.
- Name the primary metric and the guardrail metric.
- Give the minimum effect size that would justify shipping.
- Do not design a test for a change that cannot move the metric in the available traffic.
Output: Hypothesis, primary metric, guardrail, sample requirement, decision rule, risks.
If the traffic cannot support the test, say so and suggest the next-best evidence.What to change
Add the current baseline rate; without it, the sample calculation is a guess.
Why it works
Most experiments fail at the design stage, not the analysis: no hypothesis, a metric that cannot move, or traffic that cannot support a result. Writing the brief first makes 'do not run this' a legitimate outcome.
More research prompts
- Source quality triage Rank a source list by authority and recency before writing from it.
- Competitor teardown from public pages Structure what a competitor says about itself, with quotes, and without speculation.
- Survey analysis plan before the data Write the questions and cuts before you look at responses, so the analysis is not fishing.