Hire an AI image ad production and test planner

Everything it can hand back

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

• A list of your photos saying which can lead an ad, with a shoot suggestion if there are too few
• Five reasons to buy, five ad types and two looks, with the proof for each
• The grid of 50, empty cells marked, counts per row and column, and a budget check
• After your approvals, a pilot row, then all the briefs and finished images with their check results

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

• Fifty versions of one idea.
• Treating "looks good" as approval when the owner asked for changes.
• Quoting a figure the brand states two ways.
• 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're about to make your first large batch of image ads and want each one to teach you something.

• Photo list. Each photo, what it shows, whether it can lead an ad, and a shoot suggestion if you have too few.
• Reasons to buy. Five reasons, each with the buyer, the problem, what only this product does and the proof.
• Ad types and looks. Five ad types covering at least three buyer questions, and two looks.
• Grid. The planned ads with an idea in each cell, empty cells marked, and counts per row and column.
• Budget check. The purchases needed and the estimated spend, shown as a rough planning guide.
• Pilot row. Ten finished ads from one reason, made first so you can approve the look.

How the work is checked

• Every argument and type has its proof on file. EMPTY cells are marked, not faked.
• At least 3 questions are covered. For New, at most 1 "Why now?" type.
• No two cells share an idea. Every idea names a true, particular thing.
• No invented expert, press, study, review, number or deadline. No competitor, no child, no generated customer.
• 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 Claude Hopkins and Eugene Schwartz would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Lists your photos. Notes what each photo shows and whether it can lead an ad, and suggests a shoot if you have too few.
• Picks five reasons to buy. Each needs three separate buyers saying it, or one buyer and a past ad that beat your usual cost per sale.
• Picks five ad types. Uses a skill that finds the image ad types you're missing, covering at least three of the four buyer questions.
• Fills the grid. Every reason meets every type in two looks. Cells it can't fill honestly are marked empty.
• Checks the budget. Works out the sales needed to read every row and column, and shrinks the grid if your budget can't reach it.
• Makes a pilot row. Uses a skill that plans an image ad's layout to brief and make ten ads, then waits for your approval before the other forty.
• Makes and checks the rest. Uses a skill that finds flaws in finished image ads. Failed images are shown, never hidden.

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 image-ad-test-learnings 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/image-ad-test-learnings/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 voice, claims, live offers, guarantee and never-show list
• Buyer research such as reviews, buyer types and their own words
• A list of the product photos you have and what each one shows
• Your cost per sale and past ad results, such as the Results section of your brand file's log.md (optional)

Helpful context (optional)

• A naming rule that puts each ad's row, column and look in its ad name, so results sort into the grid
• A fresh product shoot by view (open, in hand, in use), so more cells can be filled honestly
• Your account's cost per purchase for the last 30 days, so the budget check uses a real number

Tools and access

• Claude: Holds a 50-cell plan and its rules across a long chat without dropping cells.
• Google Sheets: Adds up results by row and column once each ad name carries its code.
• GPT Image: Makes many pictures from the same product reference photos.
• Meta Ads Manager: Runs the sprint and exports purchases per ad, so the grid can be read.
• 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.
• 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.
• 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

• Image ad production and test planner: Share brand facts, buyer research and photos. Get a supported ad grid, pilot row and image production where tools allow, with test assumptions marked.
  • A list of your photos saying which can lead an ad, with a shoot suggestion if there are too few
  • Five reasons to buy, five ad types and two looks, with the proof for each
  • The grid of 50, empty cells marked, counts per row and column, and a budget check
  • After your approvals, a pilot row, then all the briefs and finished images with their check results
• 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
• 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
• 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
• 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
• 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

• You're about to make your first large batch of image ads and want each one to teach you something.
• Past batches looked varied but all made the same argument.
• You want a plan your team can split up and brief, with counts that prove the mix is balanced.

Limits to check before starting

• You only need one ad: use the Single image ad planner, which briefs a single image ad.
• You have no buyer research or product photos yet: gather your reviews and photos first, because this plan leaves out reasons it can't back.
• You want to check finished ads against Meta rules: use the Meta ad policy 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.

• 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 and buyer research underneath, including only offers that are live today.
• List every product photo you have and what it shows. Be honest if you only have one or two.
• Ask for stage 1 only. Read the grid, the budget check and the MISSING lines before you approve anything.
• Reply "approved" to move on. If you ask for changes, it shows the stage again and waits.

Read it as data

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