Plan your next
A/B test in minutes
Go from idea to testable experiment — fast.
Upload your page, describe your goals, and let AI generate experiment ideas using Reforge frameworks, ICE scoring, and behavioral psychology.
Context
Experiment Ideas
Hypothesis
Calculator
Variant Preview
Powered by Proven Frameworks
What is AB Test Plan?
AB Test Plan is a free AI-powered tool that takes you from a vague optimization idea to a fully structured, ready-to-run A/B test in minutes. Instead of spending hours researching experiment ideas, calculating sample sizes, and writing hypotheses, you describe your product and goals and let AI do the heavy lifting.
The tool generates experiment ideas scored with the ICE framework (Impact, Confidence, Ease), builds structured hypotheses using the If/Then/Because format, calculates statistically valid sample sizes, projects business impact, and even generates a visual variant of your page to preview the proposed changes.
Every idea is grounded in proven growth and behavioral science frameworks including Reforge Growth Loops, Cialdini's 6 Principles of Persuasion, the Fogg Behavior Model, Jobs-to-be-Done, loss aversion, cognitive load theory, and the endowment effect.
How to Plan an A/B Test
Describe your product and goals
Tell the tool what you're optimizing — your landing page, checkout flow, onboarding, pricing page, or any conversion point. Upload the HTML of your current page and any supporting data like analytics exports or heatmap summaries.
Get AI-generated experiment ideas
The AI analyzes your context and generates 5-8 experiment ideas, each scored with ICE (Impact, Confidence, Ease). Ideas are categorized by type (CRO, onboarding, pricing, copy, layout) and tagged with the behavioral framework they leverage.
Build a structured hypothesis
Select an experiment and refine it into a testable hypothesis: "If we [change], then [metric] will [improve] by [amount] because [behavioral reason]." The tool identifies your primary metric, guardrail metrics, target segment, and risk level.
Calculate sample size and projected impact
Input your baseline conversion rate, minimum detectable effect, significance level, and daily traffic. The calculator tells you exactly how many visitors per variation you need, how many days to run, and the projected monthly and annual revenue uplift if the experiment wins.
Preview control vs variant
If you uploaded your page HTML, the AI generates a modified variant implementing your experiment. Compare control and variant side-by-side, or toggle between them to visualize exactly what will change.