Designs and tracks scientific experiments, A/B tests, and feature rollouts for product and engineering teams. Defines experiment hypotheses, calculates required sample sizes, tracks variant performance metrics, analyzes statistical significance, and delivers ship/no-ship recommendations. Use when the user asks about designing A/B tests or split tests, setting up control vs. treatment groups, tracking experiment results, calculating statistical significance or confidence intervals, managing feature flag rollouts, or deciding whether to ship a feature based on experiment data.