What problem does it solve?
This skill helps product, marketing, and growth teams design and run statistically valid experiments to determine the best performing changes, reducing guesswork and accelerating evidence-based decisions.
Core Features & Use Cases
- Hypothesis-driven test design using a formal structure (Because observations/data, we believe changes will cause outcomes).
- Support for test types including A/B, A/B/n, MVT, and split URL to match various experimentation needs.
- Guidance on sample size, duration, power, and how to define primary, secondary, and guardrail metrics.
- Guidance on variant design, traffic allocation, implementation approaches (client-side vs server-side), and result interpretation.
- Templates and tooling for documentation, playbooks, and ongoing growth experimentation programs to build reusable patterns.
Quick Start
Define the test context and baseline metrics, write a clear hypothesis, choose a suitable test type, calculate the required sample size, implement the variants, and start the experiment with predefined success criteria.