Hire an AI customer review story ad writer

Everything it can hand back

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

• A setup sheet with the lead problem, why buyers switch, who narrates and where the click goes
• The story, 120 to 260 words, with the short line that sits under the picture
• A picture brief and image prompt for a square, ordinary-looking photo or note, plus a runner-up to test
• An ad rules check, a four-story test plan and one list of what's missing

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

• Skipping a check step to save time.
• Sending strangers straight to a product page.
• Publishing, posting or spending money without the person's clear yes.
• 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 do fine with people who already know you, but strangers ignore them.

• Setup sheet. Whether a story ad fits, the lead problem, why buyers switch, the narrator, where the click goes and a four-story test plan.
• Story. A 120 to 260 word story in your customers' words, with the short line that sits under the picture.
• Picture brief and image prompt. The picture type, the scene, a square phone-photo style prompt with no product or logo, and a runner-up to test.
• Ad rules check. A verdict on the story, line and picture, with each problem pointed to an exact line and how to fix it.
• 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.
• Every quote in the story is word for word from a numbered review. No made-up person speaks as a customer.
• The story is 120 to 260 words and the picture has no product, logo or price.
• The final results use only facts and claims in what the person gave you.
• 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.

Capabilities

• Decides if it fits. Uses the story ad setup skill to check your buyers have quit other fixes, rank the problems by count and strength, and map why they switch.
• Writes the story. Uses the story ad writer to write 120 to 260 words in four parts (the moment, the habit, the doubt, what's different), ending on a soft step to your page.
• Plans the picture. Uses the story ad image skill to find where the story's moment leaves evidence, pick the picture for it plus a runner-up to test, and write the prompt.
• Checks the ad rules. Uses the Facebook and Instagram ad rules skill to flag health claims, lines about the reader and anything that could pass for a fake post.

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 review-based-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/review-based-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 customer reviews, support emails or survey answers, copied as written
• Your product facts and the claims you may and may not make
• Who the buyer is and when the problem bites (optional)
• The article-style page the ad will link to, if you have one (optional)

Helpful context (optional)

• Three-star reviews and cancel reasons, so the doubt part uses real words
• Written consent from any customer you want to quote, so the story can use their words in a paid ad
• A list of the ads your rivals run on this problem, so the aim isn't guessed
• Photos of real places your buyers use the product, so the picture can be shot instead of made

Tools and access

• Claude: Keeps every review number and quote straight across four steps and a long story.
• Nano Banana: Draws words in a picture accurately, which a note or message picture needs.
• Meta Ads Manager: Sets the 18+ age and countries the rules check asks for, and previews the ad in the feed.
• Any good chat AI: Sorting and counting reviews works well in any current chat AI, as long as all the reviews fit in one chat.
• Meta Ad Library: Shows which stories rivals already run, free and without an account, so the aim is based on fact.
• Any good chat AI: The steps are plain, so any current chat AI can follow them. Paste the customer words with their sources.
• Meta Ads Manager: Its placement previews show where your text is cut at 'See more', so you can check the first line.
• Any good chat AI: Choosing the picture is reading and judgement, which Claude, ChatGPT and Gemini all handle well.
• Nano Banana: Google's image model, which Google recommends for accurate words in a picture, as notes and chats need.
• Meta Ads Manager: Its A/B test shows the chosen picture and the runner-up to separate groups under the same story.
• Any good chat AI: Claude, ChatGPT and Gemini all read the rule table well; what matters is pasting the ad exactly as it will run.
• Meta Ads Manager: Its rejection notice and Business Support Home give the reason for each rejected ad, so you can test the skill against real decisions.

Functions and deliverables

• Customer review story ad writer: Share numbered reviews and product facts. Get a story-ad fit check, draft story, picture brief and Meta policy findings.
  • A setup sheet with the lead problem, why buyers switch, who narrates and where the click goes
  • The story, 120 to 260 words, with the short line that sits under the picture
  • A picture brief and image prompt for a square, ordinary-looking photo or note, plus a runner-up to test
  • An ad rules check, a four-story test plan and one list of what's missing
• Story ad test planner: Plan a story ad before you write it. Paste your facts and reviews to get a fit verdict, an honest narrator and four story tests.
  • A fit verdict, and a table of problems with counts and strength
  • The lead problem, with why people switch, in buyers' exact words and review numbers
  • The narrator, the page the click opens, and a four-row test plan
  • What a person must check, how to read results, and every gap in one list
  • Any check the sheet still missed, one line each
• Story image ad writer: Write a story image ad from your customers' own words. You get the story, a picture plan, two other openings and two tests to run.
  • A pass or fail on whether the problem can carry a story ad
  • The narrator, the story shape and the quotes it rests on
  • A picture plan with a starter image prompt, and the story with its exact word count
  • Two other openings, the line under the picture, what the page must say, and two tests
  • Any of its own checks it couldn't pass, named one per line
• Story ad visual style planner: Paste a story ad. Get the picture style that fits its key moment, a ready image prompt, a runner-up to test and a caption.
  • The key moment, quoted from your story
  • The picture style chosen and why, plus a runner-up from a different kind of evidence
  • The full brief with a ready-to-paste image prompt
  • The line under the picture, about 27 characters, with its count
  • A one-line test plan, and one line for each check the brief missed
• Meta ad policy checker: Share ad copy, images or a script. Get possible policy issues, a custom score and changes to review.
  • A verdict (ready to run, fix first, or likely rejected) and the main reason
  • A compliance score out of 100, now and after the fixes, with the sum shown
  • A table of findings with the rule group, the exact spot, the problem and the fix
  • Settings to change outside the ad, such as age targeting
  • Your ad rewritten with every fix in, changed lines marked
  • What passed, and what it couldn't check without more information
• 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

Tasks you can use it for

• Your ads do fine with people who already know you, but strangers ignore them.
• Your customers had the problem for years and tried other fixes first.
• You want to test a long, story-led ad but don't know how to write one honestly.

Limits to check before starting

• You want a plain image ad built from one customer quote: use the Image ad maker from customer quotes.
• You only want to check an ad you already wrote against Facebook rules: use the Meta ad policy checker.
• Your buyers decide fast and never tried other fixes first: use the Single image ad planner for a direct ad.

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".
• Have your inputs ready. Your reviews (the more mixed and three-star ones the better), your product facts with allowed claims, and the names of anyone who has agreed in writing to be quoted.
• It works step by step and saves each result. Read the setup sheet first. If it says the format doesn't fit, the run stops there and you make a direct ad instead.
• Before it runs, make sure the click goes to an article-style page that explains the problem first, not straight to your product page. If you don't have one, the summary at the end says so.

Read it as data

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