Hire an AI ad recall survey reviewer

Everything it can hand back

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

• A survey with questions, sample size and scoring rule
• Recall, the buying rate in each group and the pull as a number, with a margin
• Which of four patterns you have, and the next step
• A keep, fix or replace call, with the cost of starting over
• A plan for reaching more different people before repeating

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: Your ad has run a while, sales are muddy and your team wants something new.

• outputs/step-01-recall-and-pull-survey-planner.md. The questions, who to ask, the sample size, the scoring rule and an answer sheet to fill in.
• outputs/step-02-ad-recall-and-pull-calculator.md. Recall, the buying rate in each group, the pull with its margin, and which of four patterns you have.
• outputs/step-03-campaign-keep-or-change-checker.md. A keep, fix or replace call, the real reasons to change, and the cost of starting over.
• outputs/step-04-reach-before-repeat-planner.md. A plan that reaches new people first and says when to add repeats.
• 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 and Victor Schwab would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Plans the recall and pull survey. Writes the questions, the sample size and the rule for what counts as knowing the ad.
• Works out recall and pull. Scores the answers, finds the buying rate in each group, subtracts, checks the margin and names the pattern.
• Decides to keep or change. Separates real reasons to change from boredom, prices a restart and gives a keep, fix or replace call.
• Plans who sees it. Ranks where the next spend reaches the most new people and holds repeats until most buyers are reached.

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 ad-works-check 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/ad-works-check/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 current ad, or the claim it makes
• Who could buy and how you can reach some of them
• After the pause, the filled-in answer sheet from the survey
• Spend by year and sales for the same period (optional)

Tools and access

• Any good chat AI: Writing neutral questions and scoring rules is text work any strong chat AI does well with this skill.
• A free survey form: Collects word-for-word answers in a sheet, ready for the calculator.
• Any good chat AI: Scoring answers and doing small sums is something any strong chat AI does well with this skill.
• A spreadsheet: Lets you check the counts and rates yourself.
• Any good chat AI: Weighing evidence against opinion is text work any strong chat AI does well with this skill.
• A spreadsheet: Lets you keep spend and recall by year.
• Any good chat AI: Ranking and sums are work any strong chat AI does well with this skill.
• Your ad platform's reach report: Shows unique people reached rather than impressions.

Functions and deliverables

• Ad recall survey reviewer: Plan a survey and compare buying between groups. Use the results to decide whether to keep, change or replace the ad.
  • A survey with questions, sample size and scoring rule
  • Recall, the buying rate in each group and the pull as a number, with a margin
  • Which of four patterns you have, and the next step
  • A keep, fix or replace call, with the cost of starting over
  • A plan for reaching more different people before repeating
• Ad response survey planner: Plan a short ad recall survey. Find who remembers your ad, then see if they buy more. You get the questions, sample size and answer sheet.
  • The questions, in order
  • How many people to ask in each group
  • A scoring rule for answers that are vague or wrong
  • An answer sheet ready to fill in
• Ad survey results calculator: Share ad survey results. Get recall and purchase response calculations, with an explanation of what they mean.
  • Recall as a share of everyone asked
  • The buying rate in each group and the pull
  • A rough margin, and whether the gap is bigger than it
  • Which of four patterns it is, and the next step
• Ad change decision checker: Share recall, sales pull and why someone wants a change. Get a keep, fix or replace call and the restart cost.
  • A verdict: keep, fix the delivery, fix the claim or replace
  • The real reasons to change it, checked one by one
  • The cost of starting again in lost recall, worked out
  • If you change, what to keep and how to test it first
• Ad reach planner: Plan your ad budget to reach more new people before repeats. Give it your channels, costs and buyer pool. You get a ranked reach plan.
  • The share of your buyers you reach now
  • A ranked list of where the next money reaches the most new people
  • The point where repeats should start
  • A check on whether the ad is ready to be spread
• 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
• Victor Schwab: Review ad headlines and openings using Victor Schwab’s recorded approach. Name the reader, support the promise and plan how to track responses.
  • Your problem worked on the way Victor Schwab would: their questions, their method, their push-back
  • The answer or the work, in Victor Schwab'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

• Your ad has run a while, sales are muddy and your team wants something new.
• A new manager or agency wants to start again.
• You are not sure whether people even notice your ad.

Limits to check before starting

• Your ad is brand new and has no sales history: run it first, then come back. Until then, a simple test with a small group of buyers is enough.
• You already have survey answers: use the Ad survey results calculator on its own.
• You need a better claim, not a verdict: use the Big problem splitter to break down what the ad should say.

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".
• Paste your ad and say who buys. Ask it to plan the survey.
• Ask at least a hundred buyers the questions exactly as written, and write down their words.
• Bring the answer sheet back for the rest.

Read it as data

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