Hire an AI customer review evidence checker

Everything it can hand back

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

• Themes by source, with counts, share and change, and quotes
• Each claim on your pages with its strongest proof, and every claim with none flagged
• Which quotes to show, where they go and from which review, and what to drop
• Line-by-line mismatches on pages whose proof changed
• Every rating shown, with its source and whether it still matches
• A list of buyers who could fairly be asked for a review, for approval

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

• Editing a quote to make it cleaner or stronger.
• Showing a rating without its source, or two sources as one number.
• Promoting a review that claims a result the product cannot promise.
• Asking a customer for a review three days after delivery.
• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.

What a good result looks like

An example, not your task: Your pages show quotes and ratings nobody has checked in a year.

• This month. New reviews and average rating by source, and the theme that moved most since last month.
• Who could be asked. Buyers who could fairly be asked for a review, with the date to ask, for your approval.
• Themes. Each theme with its count, share, change and quotes as written, and where sources disagree.
• Claims and proof. Each claim on your pages with its strongest proof, and every claim with no proof flagged.
• Proof to show. Which quote or number to show, where it goes, from which review, and which old quote to drop.
• Page mismatches. Lines on changed pages that no longer match the proof on file.

How the work is checked

• Every quote is as written, with its source and date, and no quote was edited.
• Every claim has proof or is flagged, and no claim was softened by the agent.
• No review request proposes a reward, and none goes to anyone asked in six months.
• Every rating shown names its source.
• 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 Eugene Schwartz and Victor Schwab would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read last month. Picks up the proof published and the claims flagged last time.
• List who could be asked. Buyers 7 to 14 days after delivery, minus refunds and anyone asked in six months, as a list for approval with no reward.
• Find the themes. Themes by source with quotes and counts, compared with last month, with the one that moved most on top.
• Pair claims with proof. Each claim on your pages with its strongest proof from the reviews, and every claim with none flagged, never softened.
• Place the proof. Which quote or number to show, where, from which review, and what to drop for age.
• Re-check the pages that change. Line by line against the proof on file, with every rating checked against its source.
• Log and hand back. Updates the themes, shown and asks files, then stops. You publish.

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 monthly-review-proof-keeper 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/monthly-review-proof-keeper/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

• Last month's new reviews from your site, widget, retailers and public sites, as written, names removed
• The text of each page that shows proof, with every quote, rating and number (advised)
• Your product facts and what you can claim (advised)
• A read-only connection to your store, for the ask list (optional)
• Last month's keeper file, once it exists

Helpful context (optional)

• The date each quote on your pages was published
• Your page templates, so proof spots are known by name

Tools and access

• Claude Code: It can keep the themes, shown and asks files between months and run on the first working day.
• Your review widget: Export reviews with date, rating and source. A read-only store connection lets the ask list read orders directly.
• Any good chat AI: A chat AI can read a CSV and group comments into themes.
• Google Sheets or Excel: Use them to clean and export your survey results first.
• Any good chat AI: The work is sorting and writing from facts you supply, which any strong chat AI does well with this skill.
• Any good chat AI: A short prompt works in any strong chat AI. Paste it, then add your details under it.
• Any good chat AI: Listing claims and matching them to proof is text work any strong chat AI does well with this skill.

Functions and deliverables

• Customer review evidence checker: Check page claims against real reviews and other proof. Get quote choices, rating mismatches and gaps to review.
  • Themes by source, with counts, share and change, and quotes
  • Each claim on your pages with its strongest proof, and every claim with none flagged
  • Which quotes to show, where they go and from which review, and what to drop
  • Line-by-line mismatches on pages whose proof changed
  • Every rating shown, with its source and whether it still matches
  • A list of buyers who could fairly be asked for a review, for approval
• Survey-ready order finder: Find buyers to email for a post-purchase survey: Shopify orders fulfilled 7 to 14 days ago, minus refunds, cancels and no-consent.
  • A CSV of customers ready to load into your email or SMS tool
  • One row per customer, even if they bought more than once
  • Counts of orders left out for refunds, cancels, no consent and guest checkout
  • A read-only session log. Nothing in your store changes
  Source: 40rty AI.
• Feedback theme finder: Share customer ratings and comments to get score summaries, counted themes, quotes, and recommended actions.
  • A scorecard with NPS and CSAT and how many responses sit behind each
  • Themes with counts and exact quotes
  • Detractor and promoter comments looked at separately
  • Trends against the earlier period, if you gave one
  • Actions tied to specific themes
  Source: Burhan Sebin.
• Ad evidence planner: Find proof for each claim in your ad. Give it your claims and product facts. You get a proof map and a list of claims with no proof.
  • Each claim paired with its strongest proof and the kind of proof it is
  • The doubt a reader is likely to have about each claim
  • Claims with no proof, each marked cut, shrink or test offer
  • A note on where in the ad each proof should sit
• Customer proof placement planner: Share buyer doubts, reviews, ratings and other proof. Get a page placement plan, weak evidence flagged and gaps to fill.
  • A map of doubt, proof and place on the page
  • The two proof items for the first screen
  • A drop list with a reason for each item
• Claim evidence checker: Share your copy and evidence. See which claims are supported, which go too far and how to fix them.
  • Unique stated and implied claims, with proof or a gap flag
  • Evidence scope, dates, quote permissions and claim-by-claim findings
  • An evidence-match score with evaluated/total coverage
  • A fix for each gap and any separate rule checks still needed
• 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
• Eugene Schwartz: Match a headline or sales page to what buyers already want and know. Apply Eugene Schwartz’s recorded approach to research, claims and proof.
  • Your problem worked on the way Eugene Schwartz would: their questions, their method, their push-back
  • The answer or the work, in Eugene Schwartz's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Victor Schwab: Review ad headlines and openings using Victor Schwab’s recorded approach. Name the reader, support the promise and plan how to track responses.
  • Your problem worked on the way Victor Schwab would: their questions, their method, their push-back
  • The answer or the work, in Victor Schwab'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

• Your pages show quotes and ratings nobody has checked in a year.
• Your rating badge and the public review site disagree.
• You want review requests that are fair, timed right and never rewarded.

Limits to check before starting

• You have no reviews yet: collect a few first, or ask recent buyers yourself, then come back.
• You need to reply to reviewers: use the Public review response manager.
• Your claims are about health, money or safety: ask a qualified person to check them, because a review is not enough proof.

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.

• 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 last month.
• Export the month's reviews from each source with date and rating. Put them in one folder with your page texts, or attach them in the chat.
• Add your product facts and claims once. It saves them.
• Read the flagged claims first. Fix or remove them on your pages yourself.
• Place the proof you approve. Send review requests yourself to the list you approve. Run it again next month.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/monthly-review-proof-keeper 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.