Hire an AI customer review image ad planner

Everything it can hand back

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

• Each ad's argument in one sentence, and its words with character counts for the image, text, headline and button
• A picture and layout plan for each ad
• An image prompt per ad, ready for an image tool
• A check of every ad, with what a person still has to look at

How it does the job well

• Start from the user's task and the content, then the layout. Decoration comes last.
• Design every state: empty, loading, error, long text and mobile.
• Keep one visual system. Reuse spacing, type and colour tokens instead of one-off values.
• Check text contrast (at least 4.5:1 for body text) and keyboard focus as you go.

Mistakes it avoids

• Writing a health or "gut" claim the brand file does not confirm.
• Skipping a check step to save time.
• Publishing, posting or spending money without the person's clear yes.
• Designing only the happy path at desktop width.
• Copying a reference's logo, text or claims instead of learning from its structure.
• Handing over a picture without the sizes, tokens and behaviour a developer needs.

What a good result looks like

An example, not your task: You want several image ads to test, and each one should argue something different.

• Brand file. Your facts, offers, prices and claims, each tagged with where it came from.
• Buying reasons. Reasons people buy ranked by separate people, with customer words and what nearly stopped them.
• Ad plans. For each ad, its one-sentence argument, buyer, picture job, layout, image words and feed copy with character counts.
• Image prompts. One prompt per ad and shape, with your exact words and each product photo named by its job.
• Pre-launch check. Mistakes that should stop launch, items worth a look, and what only a person can judge on a phone.
• 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.
• Every number and claim on an ad is in the brand file, and the guarantee is in the brand's own words.
• Character counts are shown and inside the limits.
• Every health claim matches a confirmed claim in the brand file and is marked for a person to judge before launch.
• 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 Eugene Schwartz and Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Builds your brand file. Uses the brand file skill to read your website, check the basics with you once, and tag every fact, offer and claim with where it came from.
• Finds why people buy. Uses the buying reasons skill to rank the reasons in your reviews by how many separate people say them, each in a customer's exact words.
• Writes and plans each ad. Uses the image ad planner to write the one sentence each ad argues, pick what the picture must prove, and write the image words and feed copy to Meta's lengths.
• Writes the image prompts. Uses the image prompt skill to turn each plan into one prompt that keeps your real product, its pack and your exact words.
• Checks before launch. Uses the pre-launch check to flag mistakes that should stop launch, point to anything worth a second look, and list what only you can judge on a phone.

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-image-ads 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-image-ads/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 website, as a link or saved pages
• Your customer reviews, copied as written
• Your product facts and the claims you may and may not make
• What you want made, such as "three ads, square and 4:5"
• Your ad results, so it doesn't repeat what already runs (optional)

Helpful context (optional)

• Full-size photos of your pack from the front and in use, so the prompts can attach the real product
• Your logo as an SVG and your font files, so words can be set as real type after the image is made
• Support emails or survey answers as well as reviews, so more reasons count as patterns
• The opening lines of image ads you already run, so the new ones argue something different

Tools and access

• Claude: Holds the brand file, every review number and five steps of work in one run.
• GPT Image: Takes several product photos as references and keeps short headline words readable.
• Nano Banana: Takes many reference photos at once and handles shiny packs such as foil pouches.
• Meta Ads Manager: Its preview shows where the text above the image and the headline get cut off.
• Claude: Long-context chat models can take hundreds of reviews in one chat with their source IDs. Check your plan's limit.
• Gemini: Also takes long inputs, and works inside Google Sheets if your reviews live there.
• Google Sheets: One row per quote with its source ID lets you count separate people with COUNTUNIQUE, so counts can be checked.
• 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.
• GPT Image: Takes several labelled reference images and follows exact quoted words for headlines and labels.
• Nano Banana: Mixes many reference images and keeps the pack's shape across new scenes.
• FLUX: Gives tight control when the prompt leads with the subject and ties each hex colour to one object.
• Claude: Reads full-size images closely, so it can spell-check the words in the picture and spot the safe zones.
• Meta Ads Manager: Its safe zone guardrail marks the area the app's buttons and labels won't cover, so you see what might get hidden.

Functions and deliverables

• Customer review image ad planner: Share your website, real reviews and ad brief. Get a brand file, buying reasons, ad plans, image prompts and preflight findings.
  • Each ad's argument in one sentence, and its words with character counts for the image, text, headline and button
  • A picture and layout plan for each ad
  • An image prompt per ad, ready for an image tool
  • A check of every ad, with what a person still has to look at
• Customer buying reasons finder: Paste reviews or support emails to find customer buying reasons in their exact words, ranked by how many people said them, with a score out of 100.
  • A ranked map of reasons by force, each with its best exact quote, backups and how many people said it
  • The reasons customers give that your brand never says
  • A ranked list of what nearly stopped them, in customers' words
  • A "check before use" list of risky quotes, with the reason each is flagged
  • A score out of 100 for how many of its own checks the map passes, with each miss named
• 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
• Product image ad prompt writer: Share your approved ad, product facts and photos. Get an image prompt, photo roles and a checklist for the first image.
  • One prompt in five blocks plus a keep line, with its character count
  • A subject block that says which hand holds what, which hand tears or pours, and how they move
  • A one-line role for every attached photo
  • A six-line pass-or-fail check for the first image, with failure notes for your mistakes list
  • A list of what was left out or added, and a MISSING line for any fact it needed
• Pre-launch ad checker: Share your ad, audience and approved facts. Get located issues, fixes, human checks and a custom score before launch.
  • A version-bound list of observed problems and the smallest fixes
  • The buyer argument checked against the supplied facts and proof
  • A clear list of media, destination, tracking or spec checks still needed
  • A scoped verdict and observed/eligible coverage
  • An internal editing score, with any post-fix score marked provisional
• 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
• 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
• 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

• You want several image ads to test, and each one should argue something different.
• Your image ads are pretty but nobody can say what they're for.
• You have good reviews and want them working in your ads.

Limits to check before starting

• You have no reviews yet, or you sell a service with no customer words: write a plain product ad by hand from your own facts first.
• You want only the image prompt for one ad you already planned: use the Product image ad prompt writer.
• You want a story format such as panels or a swipe set: use the Carousel ad writer or the Comic strip image ad maker.

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 website link, your reviews, your product facts with the claims you may make, and a line on what you want, such as "three ads for Facebook and Instagram feeds, square and 4:5".
• It works step by step and saves each result. Check the list of buying reasons and the ad plans before it writes the image prompts.
• Paste each image prompt into your image tool together with a real photo of your product. Then look at every finished image on your phone before it runs.

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-image-ads 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.