codexkit-a-b-test-planner

What problem does it solve?

Design and run statistically rigorous product experiments with clearly defined hypotheses, success criteria, and guardrails to avoid biased conclusions.

Core Features & Use Cases

• Define falsifiable hypotheses and success criteria for experiments.
• Compute required sample sizes and study durations from baseline metrics and MDE.
• Specify randomization plans, exclusion criteria, and rollout rules for safe deployment.
• Use cases include feature launches, UX optimizations, and funnel experiments across single or multi-variant tests.

Quick Start

Create a complete A/B test plan for a new checkout flow and estimate required sample size.