Hire an AI store test results and rollout reviewer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A verdict: valid or not, the lift as a range, the gain in money and a ship, do not ship or re-test call
• Next test ideas written as hypotheses and ranked by evidence and profit
• Five bold tests your traffic can prove, with the main number and guardrails for each
• A month-by-month order, one test per page, and what not to test at your size

How it does the job well

• Work from the real catalogue, prices, stock and policies. Check variants and currencies.
• Judge changes by contribution margin, not revenue alone.
• Change one thing at a time on a live store and keep a way to roll back.
• Keep product claims consistent with supplier data and labels.

Mistakes it avoids

• Editing live products, prices or themes without approval or a backup.
• Ignoring shipping, returns and fees when judging profit.
• Copying competitor listings.

What a good result looks like

An example, not your task: A test just ended and you aren't sure the result is real.

• Step 1: Verdict. Whether the test can be trusted, the lift as a range, the gain in money and a ship, do not ship or re-test call.
• Step 2: Ranked ideas. Repairs split from tests, each idea written as a hypothesis with its evidence and ranked by profit.
• Step 3: Next tests. Five bold tests your traffic can prove, each with a main number and guardrails, and what not to test.
• Month-by-month order. The tests laid out one per page by month.
• HAND-BACK SUMMARY. Each step's file, any step not run and why, and every MISSING line in one list.

How the work is checked

• The verdict gives a range, not only one number, and a gain in money. The range and the money figure can be redone from the visits, orders and revenue you gave.
• It names anything that could skew the result, such as a sale or an uneven split.
• Each idea is a hypothesis with the evidence it rests on. Broken things are listed as repairs, not tests.
• The tests fit your traffic, there is one test per page at a time, and it says what not to test at your size.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Peep Laja would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Get the verdict. Checks the split and how the test ended, looks for tracking faults and other changes, gives the lift as a range and in money, checks order value and margin, then makes the call.
• Rank the ideas it points to. Splits repairs from tests, writes each idea as a hypothesis, counts the kinds of evidence behind it and ranks the top ideas by profit.
• Pick the next bold tests. Places your store by its traffic, picks tests your traffic can prove, gives each one a main number and guardrails, and lays them out one per page by month.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id read-a-finished-store-test-and-pick-the-next-one only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/read-a-finished-store-test-and-pick-the-next-one/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Test numbers: visits, orders and revenue for each version, with start and end dates
• The test plan, if you wrote one (optional)
• Customer reviews or survey answers (optional)
• Your store's monthly orders and visits, and the pages you could test next

Tools and access

• Any good chat AI: It does the checks and the money sums from your pasted numbers.
• Your testing tool's export: Users per version, conversions and dates come straight from its results page or a CSV.
• Any good chat AI: It writes hypotheses and does the profit sums from your pasted findings.
• A spreadsheet: Keep the leaderboard there so you can re-sort it when new proof comes in.
• Any good chat AI: It picks and orders the tests from your numbers and findings.
• GA4: Sessions and landing page traffic without most bot traffic.

Functions and deliverables

• Store test results and rollout reviewer: Share completed test results, dates and original rules. Get a result review, rollout recommendation and ranked ideas for the next test.
  • A verdict: valid or not, the lift as a range, the gain in money and a ship, do not ship or re-test call
  • Next test ideas written as hypotheses and ranked by evidence and profit
  • Five bold tests your traffic can prove, with the main number and guardrails for each
  • A month-by-month order, one test per page, and what not to test at your size
• Store test evidence reviewer: Check if your store test result can be trusted. Get a ship call, the lift as a range in money, and a trust score out of 100.
  • Pass or fail on the split, run length, early stopping and tracking checks
  • The lift as a range, and what it is worth per month in gross profit
  • One call: ship, do not ship, re-test or inconclusive
  • A trust score out of 100 with the sum shown, and a test log entry
• Test idea ranker: Paste your research findings. Get each test written as a hypothesis and ranked by evidence and profit.
  • Each idea written as a hypothesis with a main metric and a smallest lift worth shipping
  • A ranked leaderboard with evidence points and a profit estimate
  • The one or two tests to run first, and the rest parked with a reason
  • A fix list for anything broken
• Bold store experiment planner: Share store traffic, orders and page findings. Get ranked ideas for bigger tests, with metrics, risks and sample-size checks to complete.
  • Five bold tests in order, each with the reason, main metric, guardrails and risk
  • What not to test at your size
  • A month-by-month plan
  • A reminder to size each test before you run it
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Peep Laja: Review page messaging or an A/B test using Peep Laja’s recorded approach. Start with buyer evidence, clarity and a sound comparison plan.
  • Your problem worked on the way Peep Laja would: their questions, their method, their push-back
  • The answer or the work, in Peep Laja's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• A test just ended and you aren't sure the result is real.
• You won or lost a test and don't know what to test next.
• Your store has modest traffic and past tests ended with no clear answer.
• Your testing tool shows a high chance to win and you want a second check before you ship.

Limits to check before starting

• Your test is still running or ran under two weeks: wait for it to finish, then come back.
• You only want a verdict on one result and no next-test plan: use the Store test evidence reviewer alone.
• You want to know if your traffic is enough before you start a test: use the A/B test traffic checker.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude, in Claude Code or as files in a Claude Project. Say "Follow HANDOFF.md".
• Export the test numbers for both versions, with start and end dates. Say if anything else changed during the test.
• Add research you already have, such as heatmap notes or survey answers.
• Give your monthly orders and visits so the last step can size tests to your traffic.
• Read the verdict first. Check the dates and the money gain before you ship anything.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/read-a-finished-store-test-and-pick-the-next-one for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.