Hire an AI customer return and buyer-fit reviewer

Everything it can hand back

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

• The top and bottom 20 percent of customers by profit, who they are in their own words and which ads and offers brought them in, with an acquisition fit score out of 100
• Every low review tagged, the wrong-job groups, the claim that drew them and a not-for line, with a promise match score out of 100
• The worries and habits holding buyers back, ranked, with two fixes each and one change to test
• Three to five measures of customer progress, each with a formula, a source and an owner

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: Orders are healthy but reviews, returns or repeat orders are weak, and you want to know who is unhappy and why.

• Best and worst customers. The top and bottom 20 percent of customers by profit, the ads that brought them in, and an acquisition fit score.
• Wrong-buyer reviews. Every low review tagged, wrong-job groups, the claim that drew them, not-for lines and a promise match score.
• Switch friction. Ranked worries and habits that hold buyers back, two fixes each, and one change to test.
• Progress measures. Three to five measures of customer progress, each with a formula, a source and an owner.
• HAND-BACK SUMMARY. Each step's file, any step not run, and every MISSING line in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• 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 Clayton Christensen and Alex Hormozi would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Profile best and worst customers. Ranks customers by gross profit, compares the top and bottom 20 percent, splits by discount code and finds the ad angle that sells a benefit the product does not deliver.
• Check for wrong-buyer reviews. Tags every low review as a product failure, a wrong-job buyer, a promise you set or a delivery fault. It traces wrong-job groups to the claim that drew them and writes a not-for line.
• Remove switch friction. Lists the habits and worries that hold buyers back, places each in the path to purchase, ranks them and sets one small change to test with its measure.
• Pick progress measures. Checks the numbers you track for traps, then writes three to five measures of customer progress with a formula, source and owner, plus a repeat-use measure and a check against gaming.

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 find-out-why-good-orders-turn-into-bad-reviews-and-returns 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/find-out-why-good-orders-turn-into-bad-reviews-and-returns/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

• Order data with customers, products, discount codes and refunds
• Your reviews, return notes and support messages
• The product page copy or ad text that draws buyers in. The second step needs it to trace a bad review to a claim
• A question to focus on, such as one product or one ad angle (optional)
• A brief or notes on who you meant to sell to (optional)

Tools and access

• Any good chat AI: Any current chat AI that reads spreadsheets can run the ranking. Attach the export and check one group by hand.
• Shopify: A paid service that needs an account. Its order and customer exports carry discount codes, refunds and first-order source. A plain order export from any store also works.
• Klaviyo: A paid service that needs an account. It can send a post-purchase survey, which gives the customer's own words for each group. The skill works without it.
• Any good chat AI: Any current chat AI can tag reviews and trace them to claims. Paste the text with dates.
• Shopify admin: Its returns report gives reasons and counts to read beside the reviews.
• Any good chat AI: Ranking blockers and drafting fixes is text work any strong chat AI does with this skill.
• Your analytics: You need a baseline figure to judge the test.
• Any good chat AI: Tagging numbers and drafting measures is text work any strong chat AI does with this skill.
• A short survey tool: Optional. Some measures of progress, such as would do it again, can only come from asking. Free survey tools exist, such as Google Forms. Paid ones add features you do not need to start.

Functions and deliverables

• Customer return and buyer-fit reviewer: Review orders, returns and buyer comments. Separate product problems from unmet expectations and plan fixes with measures to check later.
  • The top and bottom 20 percent of customers by profit, who they are in their own words and which ads and offers brought them in, with an acquisition fit score out of 100
  • Every low review tagged, the wrong-job groups, the claim that drew them and a not-for line, with a promise match score out of 100
  • The worries and habits holding buyers back, ranked, with two fixes each and one change to test
  • Three to five measures of customer progress, each with a formula, a source and an owner
• Customer profitability and ad source analyst: Share orders, refunds, costs and first order sources. Get top and bottom profit groups, offer comparisons and a score for new customer sources.
  • The top 20 percent and bottom 20 percent of customers by profit, with the traits of each
  • The angle and first-order offer behind each group, and repeat rate and 90-day profit for discounted versus full-price first orders
  • Angles to scale, angles and offers to stop, and page promises to fix
  • An acquisition fit score out of 100, with what it measures and the sum
• Customer fit reviewer: Share poor reviews. Separate product faults from poor buyer fit and get copy that sets clearer expectations.
  • Each low review tagged: product failure, wrong job, expectation set by your page or ad, or delivery
  • The page or ad claim that drew each wrong-job group
  • Not-for lines and claim edits, with where each goes (near the buy button, in the ad, in the FAQ)
  • A short list of same-job reviews to pin, and a promise-match score out of 100
• Customer switching barrier planner: Rank what stops buyers switching, get two fixes for each, and pick one small change to test first. Built for a buyer switch friction fix.
  • A ranked list of habits and worries with the sums
  • Each worry sorted by type and placed in the path
  • Two fixes for each, with cost and speed
  • Help for getting rid of the old way
  • A line saying who it is not for
  • One small change to test, with its measure and keep rule
• Customer success metric planner: Find which numbers you track miss the customer. Get three to five customer progress measures, each checked for gaming, with an owner.
  • Each number tagged and checked against three data traps
  • Three to five measures of customer progress, each with formula, source and owner
  • A repeat-use measure
  • A gaming check and a guard for each measure
  • A list of numbers to stop reviewing every week
• 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
• Clayton Christensen: Explore why customers buy using Clayton Christensen’s recorded approach. Start with a real situation, the struggle and what the buyer used before.
  • Your problem worked on the way Clayton Christensen would: their questions, their method, their push-back
  • The answer or the work, in Clayton Christensen's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Alex Hormozi: Improve an offer, price or lead plan using Alex Hormozi’s recorded frameworks. Check buyer needs, costs and honest promises before adding more leads.
  • Your problem worked on the way Alex Hormozi would: their questions, their method, their push-back
  • The answer or the work, in Alex Hormozi'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

• Orders are healthy but reviews, returns or repeat orders are weak, and you want to know who is unhappy and why.
• A new ad angle brought a rush of sales and then a rush of refunds.
• You keep adding features and still lose the same kind of buyer.

Limits to check before starting

• You have fewer than about 30 low reviews and want a score: wait for more. It still runs on fewer, but gives rough counts and no promise match score.
• Most of your low reviews are real product faults: fix the product first, then run this.
• You only want to rewrite an ad or page: use the Story image ad writer, then come back here to check who it attracts.

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 from this page. It's a zip with HANDOFF.md (the run order) plus one skill file for each step, best-and-worst-customer-profiler, wrong-buyer-review-checker, switch-friction-remover and customer-progress-measure-picker.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Give it your order export and your reviews, with the discount code on each order if you have it.
• Add the page copy or ad text that draws buyers in, so the second step can trace a bad review to a claim.
• Check the not-for line against what the product really does before it goes on your page.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/find-out-why-good-orders-turn-into-bad-reviews-and-returns 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.