Hire an AI ad test results and concept reviewer

Everything it can hand back

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

• A breakdown of every ad by message and look, with the one idea behind each and the patterns across winners
• A sameness score out of 100, the number of distinct ideas, and which ads to keep and replace
• A verdict for each ad set and ad, false winners flagged, and a read score out of 100
• A Meta test layout for the next round, with a pack plan, minimum spend, naming and scaling rules
• A ranking of channels by the next $10,000, with a stop point for each and a test that could change the ranking

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: A round of ads finished and you cannot tell what won, what to cut or what to make next.

• Step 1: Ad breakdowns. Each ad split into message and look, with the one idea behind it, patterns, gaps and swaps to test.
• Step 2: Sameness. Ads against distinct ideas, which to keep and replace, cold ads above frequency 2, and a sameness score out of 100.
• Step 3: Test read. A verdict per ad set and ad, false winners, concept status, the next brief and a read score out of 100.
• Step 4: Next test layout. Structure, budget split, pack plan, minimum spend, naming, and rules for adding ads and scaling.
• Step 5: Next dollar. Channels ranked for the next $10,000, stop points, a retargeting check and one test that could change the ranking.
• 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 Rosser Reeves would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Map the ads. Splits each ad into message and look, writes the one idea behind it, and finds patterns and gaps across winners and losers. It never copies a rival's words or images.
• Check for sameness. Groups ads by persona, angle, offer and format, counts clusters rather than ads and flags cold ads above frequency 2. It says which to keep and which to replace.
• Read the test. Gives each ad set a verdict against your target, ranks the ads, flags false winners and judges the concept, not one ad. It writes the next brief.
• Plan the next test. Sizes the next Meta test to your spend, groups ads by pack and never adds to a winning ad set. It sets the minimum spend, naming and read rules.
• Place the next dollar. Ranks channels by new-customer revenue per extra dollar, finds each stop point, checks that product ads and retargeting are not eating the budget and plans one test that would change the ranking.

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 find-out-why-your-ad-test-did-not-win-and-plan-the-next-round 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/find-out-why-your-ad-test-did-not-win-and-plan-the-next-round/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

• The ads you ran (required): images, videos and their copy, or a description of each, with which ones won or lost
• Results per ad and ad set, with spend, purchases, return, clicks and frequency
• Your target return or cost per sale
• Spend and results by channel (optional, but step 5 needs it)
• Rival ads you want compared (optional)

Tools and access

• Meta Ad Library: Free and public. Shows a rival's live ads and how long they have run, which is a rough sign of what works.
• Any good chat AI: Any current chat AI that reads images can split ads into parts. Attach the ads instead of describing them.
• Any good chat AI: Any current chat AI can group a pasted table of ads.
• Meta Ads Manager: Source of ad-level frequency over 30 to 60 days for cold campaigns.
• Meta Ads Manager: Its export gives you spend, impressions, CTR and link CTR by ad. The Columns menu has the incremental attribution view.
• Any good chat AI: Any current chat AI can read an export and follow the metric order. Attach the file instead of retyping numbers.
• Meta Ads Manager: It holds the ad set spending limits, the exclusions and the campaign settings the plan is built around.
• Any good chat AI: Any current chat AI can build the plan from your numbers. Check each setting against the live menu.
• Any good chat AI: The ranking is arithmetic and reasoning on numbers you paste, so any current chat AI can do it.
• Meta Ads Manager: Its audience breakdown shows your CPM and frequency on existing customers, and it runs lift studies.
• GA4: Gives a second view of new-customer revenue to set beside the platform reports.

Functions and deliverables

• Ad test results and concept reviewer: Map the ideas tested in your ads, read their real results and plan the next round and proposed budget.
  • A breakdown of every ad by message and look, with the one idea behind each and the patterns across winners
  • A sameness score out of 100, the number of distinct ideas, and which ads to keep and replace
  • A verdict for each ad set and ad, false winners flagged, and a read score out of 100
  • A Meta test layout for the next round, with a pack plan, minimum spend, naming and scaling rules
  • A ranking of channels by the next $10,000, with a stop point for each and a test that could change the ranking
• Successful ad pattern analyst: Share successful ads. Get a breakdown of their messages and visuals, with single-element changes to test.
  • A breakdown of every ad into message and creative, with the one idea behind it
  • Patterns across winners and losers, and gaps against your account
  • A contrast map of what the field does and the opposite
  • A list of one-part swaps and three new ads built from the ideas
• Ad sameness checker: Share your ads with buyer, message, offer and format. Get idea groups, a repeat score and specific changes for repeated ideas.
  • Clusters of ads that are really one concept
  • A sameness score out of 100, with the sum shown
  • Which ads to replace, and what to change in each (persona, angle or offer)
  • A list of cold ads with a frequency above 2
• Ad creative test analyst: Paste your ad test results by ad set. Get keep, leave or replace calls for each ad, false winners flagged and a score for how safe the read is.
  • A verdict for each ad set against your target
  • A table of every ad with keep, leave, replace or retest and the reason
  • False winners flagged, with the path from view to purchase for each ad
  • The next creative brief, and a read score out of 100 with its sum shown
• Meta test campaign planner: Share ad concepts, target cost per sale and budget. Get test groups, naming rules, settings checks and bounded spend plans.
  • A campaign and ad set layout sized to your store
  • A pack plan with ad names, minimum spend and removal date
  • A CBO or ABO call with the trade-off written out
  • A settings checklist, naming guide and rules for adding ads and scaling
• Marketing budget allocation planner: Share channel spend, new-customer sales and test results. Rank small budget changes by evidence, then set stop points and a fallback.
  • A ranking of where the next $10,000 goes, and what a $10,000 move between channels would do
  • A stop point for each channel
  • A test plan to measure the return on the next dollar
  • A rule for how much to put into brand content and how to judge it, if you want that shift
  • A fallback rule and a loss limit
• 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
• Rosser Reeves: Sharpen an ad’s main claim using Rosser Reeves’s recorded approach. Choose one useful benefit, match the picture and plan an honest demonstration.
  • Your problem worked on the way Rosser Reeves would: their questions, their method, their push-back
  • The answer or the work, in Rosser Reeves'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

• A round of ads finished and you cannot tell what won, what to cut or what to make next.
• Your best ad has stopped working and you are not sure whether to make more like it or something new.
• You are about to add budget and want to know where an extra dollar earns the most new customers.

Limits to check before starting

• You have one ad with no spend data: use the Ad survey results calculator first, then come back.
• Your test has only a handful of sales in total: wait for more results, as the reads are too thin to act on.
• You only want a Meta test layout from a brief you already have: use the Ad test brief writer or the Ad test budget calculator.

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".
• Attach the ads themselves where you can, as images or video stills, and paste the results export beside them.
• Say your target return or cost per sale, so each verdict is against your goal and not a general one.
• Read the false winners and the sameness count before you decide what to brief next.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/find-out-why-your-ad-test-did-not-win-and-plan-the-next-round 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.