Home / Workflows / Run an A/B test on a landing page
Statisticsintermediate3-step workflow~18 min

Run an A/B test on a landing page

Check whether a conversion-rate difference between two variants is statistically real, then bound and rank the results.

Workflow

Step 1 of 3

A/B Test Significance (two-proportion z-test)

Run a two-proportion z-test on conversions and visitors for variant A vs. B.

ab_test({"conversions_a": 100, "visitors_a": 100, "conversions_b": 100, "visitors_b": 100})
Step 2 of 3

Confidence Interval Calculator

Get a confidence interval around the observed conversion rate.

confidence_interval({"mode": "mean", "mean": 100, "std_dev": 100})
Step 3 of 3

Percentile Calculator

Rank the winning variant's conversion rate against historical runs.

percentile({"numbers": []})

Install

One command wires up every tool below for Claude Code:

claude mcp add --transport http wingman https://wingmanprotocol.com/mcp

Claude Desktop, Cursor and Continue configs are on /install. A free key (500 calls/month, no card) is on /pricing; beyond that it is x402 pay-per-call in USDC on Base.