AI-Powered Experiment Planning

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.

Step 1

Context

Step 2

Experiment Ideas

Step 3

Hypothesis

Step 4

Calculator

Step 5

Variant Preview

Powered by Proven Frameworks

ICE ScoringCialdini's PersuasionFogg Behavior ModelJobs-to-be-DoneReforge Growth LoopsLoss AversionCognitive Load TheoryEndowment Effect

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

1

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.

2

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.

3

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.

4

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.

5

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.

Frequently Asked Questions

What is AB Test Plan?
AB Test Plan is a free AI-powered tool that helps you plan A/B tests from start to finish. You describe your product and goals, and it generates experiment ideas scored with the ICE framework (Impact, Confidence, Ease), builds structured hypotheses, calculates the required sample size and test duration, and lets you preview control vs variant side by side.
How does ICE scoring work?
ICE scoring rates each experiment idea on three dimensions: Impact (how much will this move the needle, 1-10), Confidence (how sure are you it will work, 1-10), and Ease (how easy is it to implement, 1-10). The total ICE score helps you prioritize which experiments to run first. Higher scores indicate better candidates for testing.
What frameworks does AB Test Plan use?
AB Test Plan uses multiple proven growth and behavioral frameworks: ICE Scoring for prioritization, Reforge Growth Loops (viral, content, paid, sales), Cialdini's 6 Principles of Persuasion (reciprocity, commitment, social proof, authority, liking, scarcity), Fogg Behavior Model (motivation, ability, trigger), Jobs-to-be-Done, loss aversion, cognitive load theory, and the endowment effect.
How do I calculate the right sample size for an A/B test?
The built-in calculator determines sample size based on four inputs: your baseline conversion rate, the minimum detectable effect (MDE) you want to measure, your desired statistical significance level (typically 95%), and statistical power (typically 80%). It then tells you exactly how many visitors per variation you need and how many days the test will take based on your daily traffic.
What is a good hypothesis format for A/B testing?
A strong A/B test hypothesis follows the "If/Then/Because" structure: "If we [make this specific change] for [this audience/segment], then [this metric] will [increase/decrease] by [estimated amount] because [psychological/behavioral reason]." This format ensures your experiment is specific, measurable, and grounded in behavioral theory.
Is AB Test Plan free?
Yes, AB Test Plan is completely free. You can generate experiment ideas, build hypotheses, calculate sample sizes, and preview variants at no cost. No account or credit card required.
What is the minimum detectable effect (MDE)?
The minimum detectable effect is the smallest relative change in your conversion rate that your test is designed to detect. For example, if your baseline is 5% and your MDE is 10%, you're looking to detect a change from 5% to 5.5% (or higher). A smaller MDE requires a larger sample size, meaning a longer test. Most teams use 5-20% as a practical MDE range.
How long should I run an A/B test?
Run your test until it reaches statistical significance (typically 95% confidence) AND has run for at least 1-2 full business cycles (7-14 days minimum). Don't peek at results early — it inflates false positive rates. Only about 15-25% of A/B tests produce a statistically significant winner, so be patient and trust the math.