Experiment Analysis
Checks the sample ratio before anything else, since broken randomisation invalidates every result that follows.
Free — no card needed
Create a free account
to open Experiment Analysis — and the other 364 prompts across 21 categories.
Already have an account?
Running it, start to finish
- Run the sample ratio check before looking at any result.
- Confirm the primary metric was declared in advance.
- Report effect size with an interval, not just significance.
What you get back
The output this produces, every time.
- Checks the sample ratio first, since broken assignment invalidates everything downstream.
- Distinguishes confirmatory from exploratory analysis based on whether the metric was pre-declared.
- Separates practical from statistical significance, which diverge at large sample sizes.
Getting better results
Where this usually goes wrong, and how to avoid it.
- Stop if the sample ratio fails. No result is usable, and the pull to analyse it anyway is strong because the data is sitting there.
- Treat segment findings as hypotheses. Searching segments until one shows an effect reliably produces results that do not replicate.
- Check the guardrail metrics. A variant that improves the target and degrades retention or load time is frequently a bad change.
More Data Analysis prompts
All Data Analysis →- Data Analysis
Segmentation Analysis
Produces segments that are actionable and stable, since statistically clean but unusable is the standard failure.
ClaudeChatGPT002Open → - Data Analysis
Metric Definition Review
Treats two teams reporting one metric differently as a governance problem rather than a query bug.
ClaudeChatGPT000Open → - Data Analysis
A/B Test Design and Reading
Designs a test that can actually detect the effect you care about, and states the decision rule before the data arrives.
ClaudeChatGPT000Open →
Written for The AI University. Every prompt in this library is original work — authored, tested and revised here, not collected from elsewhere. 365 of them, free with an account.