Before declaring a winner or a non-result.
Here are my A/B test results: [paste]. Calculate whether the difference is statistically significant, state the effect size, and whether the sample size was adequate. Flag any peeking or bias.
Anything in square brackets is meant to be replaced. The builder turns those into fields you can type into.
Tired of re-pasting the same context into every new chat? That is what the Unimatrix MCP server is for.