Hire an AI product offer and claim evidence reviewer

Everything it can hand back

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

• A long list of what you could really be selling, with the best three as test angles and a test headline for each
• Your offer in one line, a checklist review with a score, and the three changes to test first
• Every claim in your copy paired with its proof, with the gaps and the fixes listed
• A test plan in which only the angle changes

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

• Angles that restate the product's features.
• Proof that is "somewhere on another page". Put it next to the claim or shrink the claim.
• Calling a test result before it has had time and traffic.
• Stock praise words that carry no fact.
• 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 ad or page makes big claims and you want each one to hold up before it goes live.

• Angles to test. Ten or more answers to what you are really selling, the best three with a reason and a test headline each.
• Test plan. A plan in which only the angle changes, with the measure to watch and how long to run it.
• Offer review. The offer in one line, a checklist score, a revised offer and three ranked changes to test, each with a measure.
• Claims and proof table. Each claim with its proof or a gap flag, the claims bigger than their proof, and a fix for each.
• Hand-back summary. Each step's file, every MISSING line in one list and the checks that could not run.

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. Step 2 used the angles, and step 3 used the revised offer.
• The angles are about the buyer's result, not only the product's features.
• Each of the three offer tests names one thing to change and one number to watch.
• 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 Gary Bencivenga and Eugene Schwartz would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Find what you sell. Lists at least ten answers to what you are really selling, pushes each toward the result the buyer wants, drops what you cannot deliver and picks the best three as test angles.
• Review the offer. Takes the angles and checks your offer against an offer checklist. It ranks the changes and picks three to split-test.
• Match claims to proof. Takes the revised offer, lists every claim in your copy and puts the proof next to each. Claims bigger than their proof are shrunk, supported or moved.

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 what-you-really-sell 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/what-you-really-sell/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

• Your product facts: what it is, who it is for, what it costs and its limits
• Your current offer, price and guarantee
• The ad or page copy you want checked
• Your buyer or a persona (optional)
• Customer reviews or buyer words (optional)
• Your proof, such as test results, numbers, reviews and awards, each with its source (optional)

Helpful context (optional)

• Your brand profile, from the Brand profile builder
• Test results, review counts and dates you can show
• A list of claims you are not allowed to make

Tools and access

• Any good chat AI: Every step is a plan or a piece of writing.
• A spreadsheet: Keeps your split-test results once the angles and offer changes go live.
• Any good chat AI: Brainstorming and ranking answers is text work any strong chat AI does well with this skill.
• Any good chat AI: Reviewing terms and ranking changes is text work any strong chat AI does well with this skill.
• 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

• Product offer and claim evidence reviewer: Share product facts, buyer needs and proof. Get angles to test, an offer review and a claim-by-claim evidence map with fixes.
  • A long list of what you could really be selling, with the best three as test angles and a test headline for each
  • Your offer in one line, a checklist review with a score, and the three changes to test first
  • Every claim in your copy paired with its proof, with the gaps and the fixes listed
  • A test plan in which only the angle changes
• Core customer benefit finder: Find what you really sell. Paste your product and buyer, get ten or more reasons to buy, scored, and the best three as test angles.
  • At least ten answers to what you are really selling
  • Each answer pushed from the thing to the result, feeling or status
  • Each kept answer scored, and the dropped ones with reasons
  • The three strongest picks, each with a reason and a test headline
  • A test plan where only the angle changes
• Offer checklist reviewer: Check your offer, price and guarantee against a short checklist. Get a score out of 100 and the three offer changes to split-test first.
  • The offer in one line
  • A checklist review with a score out of 100 and how it was worked out
  • A revised offer
  • The three changes to test first, each with a test and a measure
• 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
• Gary Bencivenga: Review a sales promise and its proof using Gary Bencivenga’s recorded approach. Match the problem, believable claim and clear offer before planning a test.
  • Your problem worked on the way Gary Bencivenga would: their questions, their method, their push-back
  • The answer or the work, in Gary Bencivenga's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• 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

Tasks you can use it for

• Your ad or page makes big claims and you want each one to hold up before it goes live.
• You keep describing your product the same way and want fresh angles to test against each other.
• Your offer converts but you suspect the deal, the guarantee or the way you state the price could do better.
• A reviewer or platform asked you to back up a claim and you need to see what you can prove.

Limits to check before starting

• You have no live offer yet: build your brand profile first with the Brand profile builder, then come back.
• You only want the claims in an ad checked against proof: use the Claim evidence checker on its own.
• You only want the offer reviewed: use the Offer checklist reviewer on its own.

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, ChatGPT or Gemini, in an AI that can read files, and say Follow HANDOFF.md.
• Paste your product facts, your offer and your copy. Add proof if you have it. It works step by step and saves each result.
• Read the three angles before you go on. Cut any you could not honestly deliver.
• Split-test the angles and the offer changes it picks. Those tests need time and traffic, so give them time before you judge them.
• Check each claim fix against your own records before the copy goes live.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/what-you-really-sell 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.