Experiment Backlog and Prioritization
Choose which tests to run first.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
Prioritize an experiment backlog. Ideas with hypotheses and effort: [EXPERIMENT_IDEAS]. Traffic and metric baselines: [TRAFFIC_AND_BASELINES]. Team capacity: [CAPACITY]. Score each idea on potential impact (1 to 5), confidence (1 to 5), ease (1 to 5), and learning value, and compute the ICE score = impact x confidence x ease (shown). Check feasibility: can we reach a detectable difference with our traffic in a reasonable time? Use the rough rule that detecting a small lift on a low conversion rate needs many visitors; compute the approximate sample size if I give baseline and target lift using n per group = 16 x p(1-p) / delta squared, shown, and mark it as approximate. Produce a ranked table with recommended order, tests to combine or drop, and a calendar fitting capacity. Add a log template for results and learnings. Provide the ranked table with the ICE arithmetic, a sample-size estimate for the top three tests using my baselines, and a calendar that shows which tests can run in parallel without interfering with each other.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.