How to use the A B Test Hypothesis Generator.
An experiment hypothesis needs a mechanism and a measurable outcome. A change described only as more engaging is too vague to interpret.
Make the workflow fit your task.
Describe the observed problem, proposed change and reason it might affect behavior. Choose a primary outcome and guardrails before launch, keeping the measurement window and decision rule explicit.
- What you provide
- Current conversion problem and evidence.
- What you get
- Prioritized experiments with predicted mechanism and metric.
See the input and the result.
Illustrative input and output · a teaching example, not a live WebAct run
Example input
Visitors copy a prompt but overlook the install link.
Completed example
Hypothesis: a nearby install action increases qualified setup visits. Measure clicks and activation separately.
Load this input into the prompt, then copy it to WebAct to try the task. Your result may differ from the illustration.
Decisions and troubleshooting.
Should the hypothesis promise that the variant will win?
No. State a testable expectation and what evidence would support or challenge it. The experiment exists because the outcome is uncertain.
Why do more clicks fail to produce more activation?
Measure the later step separately. A variant can attract curiosity without improving qualified setup or successful use.
Try it with your own source.
Replace the example with your material in the task prompt. Keep the requirements you need, then copy the task into WebAct.
Customize and copy the task ↑