Hire an AI Meta retargeting ad sequence planner

Everything it can hand back

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

• The visitors who left split into price, trust, quality and not ready yet, each marked measured or guess
• One ad concept per objection, with one claim and its proof, a test order and what to measure
• A three-ad sequence of an objection ad, a proof ad and a cross-sell, with the audience and window
• A ranking of where the next dollar earns most, a stop point for retargeting and a cap

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: People visit your store, leave without buying, and your retargeting ads all say the same thing.

• Retargeting objection ad planner. Visitors split by price, trust, quality and not ready yet, with one ad concept, claim and proof for each.
• Retargeting ad sequence planner. An objection ad, a proof ad and a cross-sell ad, with a pairing table, audience and window.
• Next-dollar budget allocator. A ranking of channels for the next dollar, a stop point for retargeting and a spend cap.
• 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.

Capabilities

• Retargeting objection ad planner. Splits the visitors who left into price, trust, quality and not ready yet, and maps one ad concept to each, with one claim and its proof.
• Retargeting ad sequence planner. Orders the ads into an objection ad, a proof ad and a cross-sell, with a pairing table and the audience and window to use.
• Next-dollar budget allocator. Ranks channels by new-customer revenue for each extra dollar, checks the plan is not too heavy on retargeting, and sets a stop point.

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 win-back-visitors-who-did-not-buy-on-meta 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/win-back-visitors-who-did-not-buy-on-meta/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 store conversion rate
• Why visitors left, from surveys, reviews, chat, calls or your own list
• Your product list with margins, and your proof, offer and guarantee
• Your spend and new-customer revenue by channel
• How many visitors you can retarget (optional)

Tools and access

• Meta Ads Manager: It runs catalog retargeting and lets you keep each objection ad in its own ad set.
• Any good chat AI: Any current chat AI can sort survey text into objection groups and draft the ad concepts.
• Any good chat AI: It works from text you paste, so any current chat AI will do.
• Meta Ads Manager: Its custom audiences let you build one consolidated visitor audience and exclude recent buyers.
• 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

• Meta retargeting ad sequence planner: Share buyer feedback, product facts and store results. Get objection-led ad drafts, a short sequence and a proposed retargeting budget limit.
  • The visitors who left split into price, trust, quality and not ready yet, each marked measured or guess
  • One ad concept per objection, with one claim and its proof, a test order and what to measure
  • A three-ad sequence of an objection ad, a proof ad and a cross-sell, with the audience and window
  • A ranking of where the next dollar earns most, a stop point for retargeting and a cap
• Retargeting objection ad planner: Plan retargeting ads that answer why visitors left. Give it your conversion rate and exit reasons. You get one ad per objection and a test order.
  • A split of the visitors who left into price, trust, quality and not ready yet, with each share marked as measured or a guess
  • One ad concept per objection, with one claim and its proof
  • A test order, the audience setup and what to measure
• Retargeting ad sequence planner: Plan your retargeting ad sequence: an objection ad, a proof ad, then a cross-sell, built from the real reasons visitors did not buy.
  • A retargeting sequence: objection ad, proof ad, cross-sell ad
  • A cross-sell pairing table
  • The audience and window to use
• 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

Tasks you can use it for

• People visit your store, leave without buying, and your retargeting ads all say the same thing.
• Your retargeting looks cheap on paper, but your new customer numbers have stopped growing.
• You have reviews and survey answers that explain why people hesitate, but no ads that use them.

Limits to check before starting

• Your store has no retargeting traffic yet: build the audience first, then come back to this.
• You only need to check an ad against Meta's rules: use the Meta ad policy checker.
• You want to set the test budget for new ads, not retargeting: use 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's a zip with HANDOFF.md plus three skill files, in the order they run: Retargeting objection ad planner, Retargeting ad sequence planner, Next-dollar budget allocator.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste your reviews, survey answers and support questions. Add your conversion rate and spend by channel.
• Mark which numbers are measured and which are guesses. The plan labels shares the same way.
• Build the ads in the order it gives and keep the spend under the cap.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/win-back-visitors-who-did-not-buy-on-meta 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.