Checks whether a number is real or just noise: peek-safe A/B tests you can look at as often as you like without inflating false positives, two-sided change detection, and a guard for when a metric moved only because its sample size did. Zero dependencies, standard library only.
Eval-integrity statistics for AI benchmark claims — multiple-testing correction, power/MDE for model gaps, judge-bias and leaderboard-rank checks. Catches a
benchmark number that won't survive a second look.
MCP-first A/B testing server that enables agents to manage experiments (create, update traffic splits, read results, apply winning variants) from tools like Claude Code, with self-hosted Cloudflare backend.
Checks whether a trading backtest survives its own statistics: deflated Sharpe, multiple-testing correction against a best-of-N-noise benchmark, minimum track record length, and fill realism. Takes no market data and no API keys, and cannot recommend a trade — it only reports that a result is weaker than claimed or not yet provable.
Enables rapid analysis of landing pages for SEO compliance, conversion structure, color contrast accessibility, and performance metrics with automated optimization suggestions and code snippets.
Provides tools for newsletter growth loops, welcome sequences, subject line audits, list metric interpretation, and monetization readiness based on engagement.
