Hire an AI headline comparison test planner

Everything it can hand back

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

• Headlines for each idea in the brief, with the one to test first marked
• A check of each headline for reader and reward, with stronger versions of the weak ones
• A test plan with the headlines sorted by appeal, a code for each version and a rule for picking the winner

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 need a headline for an ad, email or page and have several ideas but no way to choose.

• outputs/step-01-ad-headline-writer.md. Headlines for each idea in the brief, what they are allowed to say, and the one to test first.
• outputs/step-02-headline-promise-checker.md. A check of each headline for reader and reward, with stronger versions of the weak ones.
• outputs/step-03-keyed-headline-test-planner.md. Headlines sorted by appeal, a code for each version, a small first test and a rule for picking the winner.
• 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

• Step 1 gives a headline set with a character-limit check. Step 2 gives each headline a score and a stronger version built only from your offer's facts. Step 3 gives a shortlist, a keying method and a winning rule set before the test. If one is missing, the run stopped at that step 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 John Caples and Victor Schwab would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Write the headlines. Sets what the headline may say from your brief and facts. Writes one line for each way in and marks the one to test first.
• Check the promise. Takes the headlines and checks each one names its reader and promises a reward worth reading for. Rewrites the weak lines and lists the changes.
• Plan the keyed test. Sorts the checked headlines by appeal, picks two or three to test and gives each a code. Sets a rule for picking the winner on replies per cost.

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 headline-test 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/headline-test/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 brief (who it is for and the ideas to work from)
• Your product facts
• Your offer, including price and any deadline
• Time to run the small test and write down the replies and costs

Helpful context (optional)

• Your past best-performing headlines
• Reviews showing what buyers care about
• The reply path you will key, such as a code or link

Tools and access

• Any good chat AI: Writes, checks and plans the test in one run.
• Meta Ads Manager or Google Ads: Runs the small test and reports replies and cost for each version.
• Meta Ads Manager: Its ad preview shows whether each headline fits under the image on every placement.
• Any good chat AI: Judging and rewriting one short line is work any strong chat AI does well with this skill.
• An ad platform preview: Shows how the line fits in the real placement.
• Any good chat AI: Sorting headlines and writing a test plan is text work any strong chat AI does with this skill.
• A link shortener or form tool: Gives each version its own trackable link or code.

Functions and deliverables

• Headline comparison test planner: Share a creative brief, product facts and real offer. Get headline drafts, promise checks and a tracked comparison-test plan.
  • Headlines for each idea in the brief, with the one to test first marked
  • A check of each headline for reader and reward, with stronger versions of the weak ones
  • A test plan with the headlines sorted by appeal, a code for each version and a rule for picking the winner
• Ad headline writer: Write ad headlines from your buyer and facts. Get plain lines with character counts, a glance test and the one line to test first.
  • A numbered list of headlines or image lines, each with a different way in
  • For each, who it's aimed at, its character count and its glance test result
  • The line to test first, a second to test against it, and the ways in it skipped for lack of proof
  • Any of its own checks the set still misses, each named
• Headline promise checker: Share a headline and offer facts. Check who it speaks to, the benefit it promises and which claims need clearer wording or proof.
  • Whether the line picks out the right reader
  • Whether the reward is clear in the line alone
  • A score out of 100, with how it was worked out
  • Stronger versions, each tied to your offer facts
• Headline test tracking planner: Plan a headline test that tells you which headline wins. Give it your offer and headline options. You get a shortlist, a keyed test plan and a winning rule.
  • Each headline tagged by appeal
  • A shortlist of two or three headlines to test
  • A keyed test plan where only the headline changes
  • A winning rule set before the test, and a place to record why
• 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
• 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
• 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

• You need a headline for an ad, email or page and have several ideas but no way to choose.
• Your headlines get clicks but the wrong people, or the right people but not enough of them.
• You are about to spend on an ad and want a small, fair test before you do.

Limits to check before starting

• You need one obvious headline and have no choice to make: write it yourself, or use the Ad headline writer on its own.
• You have no offer yet, so there is nothing to promise: use the New offer opportunity finder first.
• You want the first line of an ad, not a headline: use the Ad opening writer and reviewer.

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".
• Give it your brief, product facts and offer.
• It works step by step and saves each result. Read the checked headlines before you read the test plan.
• Run the small test and note replies and cost per reply for each version.
• When the winning rule is met, use the winner in your live ad and keep both versions with their counts for the next test.

Read it as data

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