Hire an AI product evidence ad planner

Everything it can hand back

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

• A list of true facts rivals do not state, each as a claim with a number or something visible
• The one anchor fact, marked backed or unproven, and questions to ask your maker next
• Twenty or more headlines labelled by type
• The three best headlines after a cover test
• An image ad plan with layout, feed text and an image prompt built on the anchor fact

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: You make, source or test something with care, but your ads sound like everyone else's.

• Step 1: Facts rivals never state. Kept facts as claims with a number or picture, marked backed or unproven, the anchor fact, and questions to ask your maker.
• Step 2: Headlines. Twenty or more headlines from your claims, each labelled by type and reason.
• Step 3: Cover test. What a stranger thinks each headline offers, scores on five rules, and the three best headlines.
• Step 4: Image ad plan. One-sentence ad, chosen claim, layout zones, feed text and an image prompt built on the anchor fact.
• 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 Claude Hopkins and John Caples would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Find the facts rivals never state. Reads every step and standard in your notes, keeps what buyers do not know, turns each into a number or a picture and marks what rivals already say.
• Write headlines from the claims. Pulls the real figures and writes headlines sorted by self-interest, news and curiosity. News lines appear only when something is truly new.
• Pick the three best by cover test. Reads each headline alone, writes what a stranger would think it offers and scores it on five rules. Three that differ go forward.
• Plan the image ad. Picks one claim your proof backs and rivals cannot copy, sets the reading order and writes feed text and an image prompt.

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 build-ads-on-true-facts-your-rivals-never-state 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/build-ads-on-true-facts-your-rivals-never-state/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

• Notes on how it is made, sourced and tested (the full text, not a summary)
• Your product facts, such as price and what it is
• Rival ads or claims (optional, and without them rivals are not checked)
• Your offer (optional)
• Your buyer and their words (optional)
• Product photos (optional)

Tools and access

• Any good chat AI: Any current chat AI can read long notes and build the fact table. Paste the full notes in the message.
• Any good chat AI: Writing and labelling many short lines is something any strong chat AI does well with this skill.
• Any good chat AI: Reading, scoring and ranking lines is text work a strong chat AI does well with this skill.
• Any good chat AI: Planning one ad from your facts and counting characters works well in any strong chat AI.
• Nano Banana: Takes many reference images and draws legible text, so the pack and any typed words come out close to real.
• Canva: Sets your three reads as real text over the picture, so you can resize them and run the blur check.
• Meta Ads Manager: Its ad preview shows where the first line and headline get cut on each placement before you spend.

Functions and deliverables

• Product evidence ad planner: Use maker and test evidence to find supported ad claims, write headlines and plan an image ad around one fact.
  • A list of true facts rivals do not state, each as a claim with a number or something visible
  • The one anchor fact, marked backed or unproven, and questions to ask your maker next
  • Twenty or more headlines labelled by type
  • The three best headlines after a cover test
  • An image ad plan with layout, feed text and an image prompt built on the anchor fact
• Product process fact researcher: Find true facts about how your product is made that rivals never state. Paste maker or supplier notes, get a fact table and top five ad claims.
  • A table of facts: what it is, true or not, whether a rival says it, and the proof
  • Your top five facts as ad and page claims, each with a number or something to picture
  • Claims that need proof before you use them
  • Questions to ask your maker to find more
• Ad headline variation writer: Turn your buying reasons into twenty or more headlines, each labelled self-interest, news or curiosity, with a real detail from your facts.
  • At least twenty numbered headlines
  • For each, its type, the buying reason it serves and the detail it uses
  • A count by type and the lines cut with a reason
  • MISSING notes for any news or figures it could not use
• Headline and cover test planner: Share headline or cover options and verified offer facts. Get a ranked shortlist, clear reasons and a response test to compare your strongest options.
  • For each line, what a stranger would think it offers
  • A score on five rules, with a reason for each
  • The lines cut outright and the rule each broke
  • Three picks that differ, and how to run an outside read
• Single image ad planner: Paste your facts. Get the layout, image words, feed copy and an image prompt.
  • The one sentence the ad argues, with the claim and where it came from
  • The ad type, the look and the layout, with the types ruled out and why
  • A zone map in reading order, and the words on the image with a word count
  • Feed copy with three headlines, each with its character count
  • A prompt for an image model, and a list of every guess and gap
  • Any of its five checks the plan still misses, one line each
• 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
• 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
• John Caples: Write headlines and plan a fair ad test through John Caples’s recorded approach. Lead with the reader’s gain and count replies by version.
  • Your problem worked on the way John Caples would: their questions, their method, their push-back
  • The answer or the work, in John Caples'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

• You make, source or test something with care, but your ads sound like everyone else's.
• You have notes from a maker visit, a supplier call or a test, and you have not used them.
• You need a claim a rival cannot copy by changing their wording.

Limits to check before starting

• Your product has no real process behind it to mention: write the angles first with the Ad angle planner.
• Your facts are not written down yet: build them first with the Brand profile builder, then come back.
• You already have claims and only want headlines: use the Ad headline 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 every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your maker, supplier or test notes in full. Short notes give short results.
• Check every claim marked unproven before you run it.
• Paste two or three rival ads if you have them. Without them, step 1 marks each claim "rivals not checked".
• The top headline from step 3 goes into step 4 as the line on the image.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/build-ads-on-true-facts-your-rivals-never-state 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.