AI Blocks › Test changes to your store
Store test program runner
Give it your store numbers and test results. It ranks ideas, plans one test, reads it, and picks the next.
Store test program runner is a free AI agent for the job "Test changes to your store". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · Made by AI Blocks · Level: advanced · Thinking: high
What it does
Most stores test in bursts. Someone has an idea, runs a test, calls it a win after four days, and forgets what they learned. Without a log, the same ideas come back, a test that clashed with a sale gets trusted, and a store with too few orders keeps testing things it can never measure. This agent runs the program for you. It starts with a baseline of gross profit per visitor. It checks the state of your testing: nothing running, one running, or one that just ended. A running test is left alone. A finished test gets a full read: is the split clean, did it run long enough, what is the lift as a range, what is it worth, did the guardrails hold. The result goes in the log. Then it picks the next test from your ranked ideas, checks your traffic can prove it, and plans the…
You give it
- Orders, sessions, conversion rate, average order value and gross margin for the page and the store
- Your Shopify plan, who builds changes, and the ideas you have
- Numbers from a finished test, with planned sample and dates, and what else happened during it
- Heatmap notes, recordings, survey answers or review quotes (optional)
- Store capture (optional)
- Customer words (optional)
You get
- A call on a finished test, with the lift as a range and the monthly gain in profit
- The next test, with its sample, weeks, main metric and guardrails
- A ranked list of ideas and a list of things to repair instead of test
- A test log that grows each run
Use it when
- You run tests on your store and want a log, a ranked list and one test at a time.
- A test just ended and you want to know if you can trust it before you ship the change.
- You are not sure if your store gets enough orders to test, or what to test first.
How to use it
- Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run this fortnight's check.
- The first time, give it your numbers and your ideas. It sets your baseline and builds the backlog.
- Set up the test it plans in your testing tool. Tell it the start date.
- When the test ends, bring the numbers and anything that happened during the run. It reads the result and picks the next test.
- Run it again every two weeks. It reads its own log.