Hire an AI reference layout image ad maker

Everything it can hand back

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

• A list of what's missing before anything is built
• Keep, change or drop for every spot, and a verdict on the layout
• A plan per layout with the ad's type, eye path, zones, labelled copy, a claims table, an assets table and risks
• After you approve, 4:5 and 9:16 images and a review deck with the reference beside your version

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

• Handing over images you haven't looked at.
• Keeping the reference's claims, badges or numbers, or patching a main spot you can't prove.
• Typing the brand name in place of the logo.
• Leaving the owner to find the typo.
• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.

What a good result looks like

An example, not your task: You've saved ads from other brands, or bought templates, whose layout you like and want versions for your own product.

• KIT CHECK. What is missing before anything is built, such as logo, typefaces, photos or sources, plus notes to check.
• REFERENCE. The ad type, layout shape, eye path and the spot that carries the main point.
• SPOT BY SPOT. For each spot, the proof it needs, what you have, and keep, change or drop, then a verdict.
• ZONES. Where each thing sits in the 4:5 and 9:16 sizes, top to bottom, in percent.
• COPY AND CLAIMS. Every line labelled as a fact, a customer's words or a line to test, with its source.
• ASSETS. For each slot, a real file, a picture to generate, or MISSING.

How the work is checked

• No kept spot relies on proof that isn't on hand, and no cell is left blank to imply a rival lacks something.
• Every line has a label, every quote matches its source word for word, and anything the reference claimed that this brand can't is cut or switched, with the change recorded.
• The brand name is never typed as text. The real logo is placed.
• Real photos were used before generated ones, and the product is a real, named variant, right in colour, shape and print. If it can't be shown truthfully in this layout, the type changes, never the product.
• 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 Al Ries and Robert Cialdini would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Checks what you have. Looks for your logo file, typefaces, photos and quotable figures, asks once for anything missing, and marks each gap.
• Names the ad type. Uses a skill that finds the image ad types you're missing to place the reference on a map of nine types, from a product shot to a customer quote.
• Reads the layout. Notes the skeleton, the eye path, how the frame is shared, and which spot carries the main point.
• Tests every spot. Writes what each spot claims and the proof it needs, then marks it keep, change or drop. A failed main spot switches the type, never gets patched.
• Plans with labelled words. Zones in percent for each size, every line labelled as a fact, a customer's words or a line to test, with conditions beside their claims.
• Builds both sizes. Uses a skill that writes image prompts for the picture, then sets real type and your logo on top. Each size is composed on its own.
• Checks and revises. Checks headline length, type size, contrast, spelling, claims and the product against its photo, then revises one spot at a time until you have no notes.

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 copy-winning-ad-layout 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/copy-winning-ad-layout/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 brand file, with the figures you may quote, approved claims, never-say list, colours and typefaces
• Your real product photos and logo file, named by what each shows
• The reference ad or template, as an image or a short description of its layout
• Customer quotes with their source, if the layout has a quote or review spot (optional)
• A direction for each layout naming the buyer and their doubt, in a sentence (optional, but it outranks the workflow's own reading)

Helpful context (optional)

• Your logo as an SVG file, so it stays sharp at every size
• Your brand typefaces as font files, so the type matches your other ads
• Rival facts you have checked, with the date and where you found them, so comparison rows can stay
• A product photo shot at the same angle and light as the reference, so less of the picture has to be generated

Tools and access

• GPT Image: Takes several reference photos at once and makes targeted edits, so the product stays close to the real one.
• Nano Banana: Handles many reference images and shiny surfaces such as foil pouches and glass.
• Figma: Sets real type and your logo over the picture and exports 4:5 and 9:16 from one file.
• Meta Ad Library: Shows the full ad a layout came from, including its main text, so you can see every spot it relies on.
• Meta Ads Manager: Exports impressions, link clicks, purchases and spend per ad for the dates you pick.
• Google Sheets: Works out medians and click rates from the export, so you can check its numbers.
• Any good chat AI: Coding ads and writing cards works well in any strong chat AI that can read images.
• 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.

Functions and deliverables

• Reference layout image ad maker: Rebuild an ad layout with your real product, supported claims and brand style. Get feed and story versions with a review record.
  • A list of what's missing before anything is built
  • Keep, change or drop for every spot, and a verdict on the layout
  • A plan per layout with the ad's type, eye path, zones, labelled copy, a claims table, an assets table and risks
  • After you approve, 4:5 and 9:16 images and a review deck with the reference beside your version
• Image ad variety reviewer: Find the image ad types you're missing. Attach your ads and results to get an ad gap grid, up to three test briefs and a score out of 100.
  • A grid of your ads by type and look, with the empty spots shown
  • The signals in your numbers, each with the figures behind it
  • Up to three ad cards, each a different type, traced to a signal
  • A log of claims that were cut, so they don't creep back in
  • A score out of 100 for the plan, with one line for each check it missed
• 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
• Brand style guide writer: Share the finished identity, voice rules and real examples. Get a versioned guide for logo, colour, type, images, copy and use.
  • An eight-section brand style guide
  • Logo clear space and misuse rules
  • Colour and type specifications
  • Voice and imagery guidance
  • A list of gaps if you asked for an audit
  Source: RampStack.
• 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
• Al Ries: Clarify what a brand should stand for using Al Ries’s recorded approach. Examine its category, focus, name and launch story.
  • Your problem worked on the way Al Ries would: their questions, their method, their push-back
  • The answer or the work, in Al Ries's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Robert Cialdini: Review a pitch, page or request using Robert Cialdini’s recorded principles. Use real proof, honest expertise and genuine limits without pressure or tricks.
  • Your problem worked on the way Robert Cialdini would: their questions, their method, their push-back
  • The answer or the work, in Robert Cialdini'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've saved ads from other brands, or bought templates, whose layout you like and want versions for your own product.
• You want a comparison or labelled-product layout but aren't sure your facts can fill it.
• You need the same ad in feed and story sizes, each composed properly, not cropped.

Limits to check before starting

• You can't show or describe the reference ad: describe what you want in a plain brief for a designer, or find an ad first in the Meta Ad Library.
• Your product has no real photos: take clear photos of the product first, then come back.
• You only want ad ideas, not a layout: ask your AI for a list of angles to test, then pick one.

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.

• Start a chat with the skill. Open it if you added it to your AI, or copy it and paste it in.
• Paste your brand file underneath and attach your logo file and product photos.
• Attach the reference ad or template image. If you can only describe it, say so, and check the plan against the real image later.
• Write one sentence of direction, such as "use this to show what's in one pack, for people who quit greens powders" or "use this to compare our three sizes, for first-time buyers".
• Read the dropped spots and the verdict first. Fix every MISSING line, approve the plan, then leave notes in the review deck until it's right.

Read it as data

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