Hire an AI honest drawback ad writer

Everything it can hand back

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

• A brief that names the drive behind buying, the feeling the ad must leave and the old ways of saying it to avoid
• A flaw-first ad with headline options, checked so the product backs every line
• Fresh versions of the same true claim, with a pick and a swap test that shows a rival couldn't use it

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 state facts that are all true and still don't make anyone act.

• step-01-buyer-instinct-brief-writer.md. The drive underneath why people buy, the feeling the ad must leave, and old ways of saying it to avoid.
• step-02-flaw-first-ad-writer.md. The true flaw chosen, what it shows about the product, headline options, the ad body and a check that the product backs each line.
• step-03-fresh-line-rewriter.md. Fresh versions of the same true claim, a swap test against rivals and one picked line.
• 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 Bill Bernbach and Eugene Schwartz would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Write the brief. Reads your facts and buyer words and names the drive underneath why people buy. Writes the feeling the ad must leave and what to avoid saying.
• Write the flaw-first ad. Takes the brief and lists your product's true weaknesses. Picks the one a buyer already sees and writes an ad that names it and shows what it proves.
• Make the wording fresh. Takes the ad and writes fresh versions of its claim. Runs a swap test against rivals and picks one, cutting any words that don't carry the point.

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 flaw-first-ad 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/flaw-first-ad/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, including what it does and what it doesn't
• What buyers say about it, in their own words, such as reviews (optional)
• A short description of your typical buyer (optional)
• A few rival ads or pages (optional)

Helpful context (optional)

• Fifty or more reviews, in the buyers' words
• Your best-performing ad so far
• A list of claims you are not allowed to make

Tools and access

• Any good chat AI: Reads long reviews and writes all three steps in one run.
• Meta Ad Library: Shows the live ads your rivals run, so the swap test has real lines to check against.
• Any good chat AI: Reading buyer words and drafting a brief is text work any strong chat AI does well with this skill.
• Any good chat AI: Sorting weaknesses and rewriting lines is text work any strong chat AI does well with this skill.
• Any good chat AI: Rewriting and comparing lines is text work any strong chat AI does well with this skill.

Functions and deliverables

• Honest drawback ad writer: Use buyer evidence to write an ad that opens with a real product drawback, then find fresh wording for supported claims.
  • A brief that names the drive behind buying, the feeling the ad must leave and the old ways of saying it to avoid
  • A flaw-first ad with headline options, checked so the product backs every line
  • Fresh versions of the same true claim, with a pick and a swap test that shows a rival couldn't use it
• Buyer motivation brief writer: Share product facts and customer words. Get a short ad brief with supported wants, possible motives, one feeling and a message angle.
  • The stated want and the drive underneath it, with buyer words as evidence
  • The feeling the ad must leave, in one line
  • What the reader should take away
  • One fresh angle chosen and the stale ones to avoid
• Flaw-first ad writer: Write an ad that names your product's real flaw first, then shows what it proves. Give it your facts and brief. You get ad copy and hooks.
  • A list of true weaknesses, with the one chosen and why
  • Ad copy that states the flaw first and turns it
  • Hooks built on the same turn
  • A note on what in the product backs each line
• Fresh line rewriter: Rewrite an ad line that sounds like every rival's. Give it your claim and get fresh ways to say it, each checked with a swap test.
  • Your claim in its flat form
  • A list of how rivals say it
  • Several fresh versions that keep the claim the same
  • A swap-test result for each, and one picked line
• 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
• Bill Bernbach: Develop an honest ad idea using Bill Bernbach’s recorded approach. Pair words and pictures, find one true selling point and cut the gimmicks.
  • Your problem worked on the way Bill Bernbach would: their questions, their method, their push-back
  • The answer or the work, in Bill Bernbach'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 ads state facts that are all true and still don't make anyone act.
• Your ad sounds like every rival's, and you need a line only you could run.
• Your product has an obvious weakness, such as a price or a size, and you want to turn it into a reason to buy.

Limits to check before starting

• Your product has no real weakness a buyer already sees: use the Ad angle planner to find a stronger angle.
• You only need a strong opening line for an ad you already have: use the Ad opening writer and reviewer.
• You want to check an ad's claims against proof: use the Ad claims checker.

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 holds HANDOFF.md plus one skill file for each step.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your product facts. Add reviews and rival ads if you have them.
• It works step by step and saves each result. Read the brief first, since the ad is written from it.
• Check the flaw is true and one you are happy to say out loud before the ad goes live. Skip flaws about safety, health or legal claims.

Read it as data

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