Hire an AI sales claim demonstration planner

Everything it can hand back

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

• A verdict on whether your product has a difference buyers could notice
• Three to five claims, one sentence each, ranked, with the weak ones struck out
• A pass or fail on the top claim against three tests, with fixes
• A script table matching every spoken line to a picture that shows it
• A playback count, what stole the rest, and what to cut

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: Your ads say many things, or your product looks the same as its rivals.

• Step 1 file: product difference check. A verdict on whether buyers could notice a difference in your product, or whether it needs work first.
• Step 2 file: candidate claims. Three to five one-sentence claims from three roads, ranked, with the weak ones struck out.
• Step 3 file: claim test. A pass or fail for the top claim on being a real offer, unique and strong enough, with fixes.
• Step 4 file: demonstration plan. A script table where every spoken line is matched to a picture that shows the same thing.
• Step 5 file: distraction check. How many viewers repeated the claim, what took attention from the rest, and what to cut.
• 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

• 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 Rosser Reeves and Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Checks you have something real to say. Gives a verdict on whether the product has a difference a buyer could notice, or needs work first.
• Drafts the candidate claims. Writes three to five claims in the form buy this and get this benefit, from three roads, and strikes the weak ones.
• Tests the best claim. Passes or fails the top claim on being a real offer, unique and strong enough to move many buyers.
• Plans the demonstration. Finds something to watch that proves the claim and locks every spoken line to a picture of the same thing.
• Checks nothing steals attention. Counts how many viewers repeated the claim, finds the second claim or picture that took the rest and lists the cuts.

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 selling-claim-demo 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/selling-claim-demo/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, with what it does, how it is made and how it is used
• What rivals say in their ads or on their pages (optional)
• Customer words, such as reviews (optional)
• After the pause, what ten viewers said the ad said, word for word

Tools and access

• Any good chat AI: The work is reading evidence and weighing it, which any strong chat AI handles well with this skill.
• Your CRM export: Won and lost deal notes in one list give the check more to work with than memory.
• Any good chat AI: Sorting facts and judging claims is text work any strong chat AI does well with this skill.
• The Meta Ad Library: Shows what rivals actually say in live ads.
• Any good chat AI: Testing a claim against facts is text work any strong chat AI does with this skill.
• The Meta Ad Library: Shows what your rivals are actually saying in live ads.
• Any good chat AI: Matching spoken lines to pictures is text work any strong chat AI does well with this skill.
• A phone camera: A demonstration filmed on a phone shows quickly whether it reads at a glance.
• Any good chat AI: Sorting viewer answers into causes is text work any strong chat AI does well with this skill.
• A shared sheet or notepad: Keeping the ten answers verbatim in one place keeps the sort honest.

Functions and deliverables

• Sales claim demonstration planner: Share product differences, competitors and proof. Get candidate claims, claim checks, a demonstration script and a review after real viewer feedback.
  • A verdict on whether your product has a difference buyers could notice
  • Three to five claims, one sentence each, ranked, with the weak ones struck out
  • A pass or fail on the top claim against three tests, with fixes
  • A script table matching every spoken line to a picture that shows it
  • A playback count, what stole the rest, and what to cut
• Product differentiation checker: Check if your product is truly the same as rivals or just described badly. Paste your product facts and won and lost deals to get a plain verdict.
  • A short list of the real alternatives, with doing nothing counted
  • For each, what you do that they do not, tied to a customer type and why it matters
  • A test of the four usual causes of missing your difference
  • A verdict, the evidence behind it and the next three steps
• Product promise finder: Paste your product facts and rivals. Get three to five one-sentence selling claims to build an ad on, ranked by pull.
  • Three to five claims, one sentence each, with the road each came from
  • A score for each on whether buyers can see it, rivals say it and strangers would switch
  • A product change worth making, if no claim survives
  • One top claim, chosen by total score, ready for the USP claim checker
• USP claim checker: Check your ad claim before you spend on it. Paste your ad and product facts. You get a pass or fail on offer, rivals and pull, plus a score.
  • Your claim in one sentence
  • A pass or fail on each of the three tests, with a reason
  • A score out of 100, with how it was worked out
  • Fixes, one claim to keep and a demonstration to prove it
• Product claim demo planner: Paste your claim and product facts. Get a short script where every spoken line has a picture showing the same thing.
  • The claim as one spoken line
  • The demonstration, with what it needs to be filmed
  • A script table, with time, spoken words and the picture for each
  • A list of shots cut and why
• Ad distraction checker: Check your ad for distractions. Paste it with ten viewers' answers. See what stole attention from your claim and what to cut.
  • A playback count and what it means
  • What viewers remembered instead, sorted by cause
  • Each line checked for picture that does not match its words
  • A cut list in order of share stolen, and a retest plan
• 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
• Rosser Reeves: Sharpen an ad’s main claim using Rosser Reeves’s recorded approach. Choose one useful benefit, match the picture and plan an honest demonstration.
  • Your problem worked on the way Rosser Reeves would: their questions, their method, their push-back
  • The answer or the work, in Rosser Reeves's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Claude Hopkins: Write specific ads or plan a small buyer test using Claude Hopkins’s recorded approach. Replace vague praise with facts and track cost per customer.
  • Your problem worked on the way Claude Hopkins would: their questions, their method, their push-back
  • The answer or the work, in Claude Hopkins'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 ads say many things, or your product looks the same as its rivals.
• You need one claim buyers will remember and act on.
• People like your ad but cannot say what it promises.

Limits to check before starting

• Your product has no real difference yet: run the Product differentiation checker first, or fix the product before you write any claim.
• You only need ad copy written from a claim you already have: use the Ad response copy editor.
• You want to plan which ads to test against each other: use the Ad test brief writer.

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's a zip with HANDOFF.md and the 5 skill files in the order they run: Product differentiation checker, Selling proposition finder, USP claim checker, Claim demonstration planner and Ad distraction checker.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your product facts and any rival ads. Ask it to run the first four steps.
• Show the script or a rough cut to ten people who have not seen it. Ask only what it said, and write their words down.
• Bring the answers back for the last step.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/selling-claim-demo 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.