Hire an AI Meta ad workload and budget planner

Everything it can hand back

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

• A monthly quota of new ads with a low and high range, a start number and a weekly split
• A ranking of channels by what the next $10,000 brings in, with a stop point and a loss limit
• A matrix of 30 to 40 ad concepts with a test order and a name for each ad set
• A brief for each chosen concept with one problem, one angle and a proof shot for every claim
• A Meta test layout with packs, minimum spend, naming and rules for adding ads

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: You are about to plan next month's ads and do not know how many new ones you need.

• step-01-creative-volume-planner.md. A range of new ads per month with a start number, split by format and by week.
• step-02-next-dollar-budget-allocator.md. Channels ranked by new-customer revenue from the next $10,000, with stop points and a loss limit.
• step-03-ad-concept-matrix-builder.md. Ranked ad concepts built from buyer words, each with an angle, an offer, a first line and a test order.
• step-04-creative-brief-writer.md. A brief for each chosen concept with one problem, one angle, a format and a proof shot for every claim.
• step-05-meta-test-campaign-planner.md. The Meta test layout with packs, minimum spend, naming and rules for adding ads.
• 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

• The quota shows all three ways of counting, with each sum.
• Each channel is ranked on new-customer revenue and says what evidence stands behind it.
• Every claim in a brief has a named shot that proves it.
• Every pack has one angle and one avatar.
• 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 John Caples and Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Size the monthly quota. Creative volume planner works out how many new ads you need three ways and gives a range with a start number. It splits the quota by format and by week, and checks the plan does not lean on one concept.
• Rank where the money goes. Next-dollar budget allocator ranks each channel by new-customer revenue per extra $10,000. It grades the evidence, finds each stop point and names the test that would settle the ranking. The budget split goes on to the Meta test layout in step 5.
• Build the concept matrix. Ad concept matrix builder starts from your reviews and facts, not from step 2, and writes buyers as a problem in a situation. Each gets an angle, an offer, a first line and a place in the test order.
• Write the briefs. Creative brief writer reads your reviews and facts again, takes each concept you picked from the matrix and picks one problem and a one-sentence angle. It picks the format, names the shot that proves each claim and writes two versions that change one thing.
• Lay out the Meta test. Meta test campaign planner takes the briefs and sizes the campaigns to your quota and budget split, groups ads into packs, sets minimum spend and names every ad so you can compare results later.

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 plan-a-month-of-meta-ads-with-the-right-number-of-new-a-a86add14 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/plan-a-month-of-meta-ads-with-the-right-number-of-new-a-a86add14/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

• A sheet of your ad spend and results by channel and month
• The question you want answered, such as how many ads you need at this spend
• Your product facts, such as price, what it does and what it costs you
• Customer reviews, support emails or survey answers

Tools and access

• Any good chat AI: Any current chat AI can do the sums. Check them yourself.
• Meta Ads Manager: Source of your ad count, spend, return and winners lost.
• 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.
• Any good chat AI: Any current chat AI can run the persona loop. Paste your reviews in as plain text.
• Meta Ads Manager: Where you name ad sets and read results per concept.
• Any good chat AI: Reading and sorting hundreds of pasted quotes is the heavy part, and any current chat AI handles it.
• Shopify: Product reviews and support emails can be exported from your store apps to paste in.
• Meta Ads Manager: Ad comments and your last test results come from here.
• 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.

Functions and deliverables

• Meta ad workload and budget planner: Share spend, results, buyer research and product facts. Get a proposed ad workload, budget split, concept briefs and test-campaign plan.
  • A monthly quota of new ads with a low and high range, a start number and a weekly split
  • A ranking of channels by what the next $10,000 brings in, with a stop point and a loss limit
  • A matrix of 30 to 40 ad concepts with a test order and a name for each ad set
  • A brief for each chosen concept with one problem, one angle and a proof shot for every claim
  • A Meta test layout with packs, minimum spend, naming and rules for adding ads
• Monthly ad production planner: Plan how many new ads to make each month. Give it your spend, target and hit rate. You get three estimates, a budget and a weekly quota.
  • Ads needed per month by three methods, with the range
  • The creative budget for your spend band
  • Cost per ad and profit per ad by format
  • Who to hire or hold at your stage, a content mix and a weekly quota
• 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
• Ad concept testing planner: Share your product and reviews. Get buyer groups, messages and offers arranged into an ad testing plan.
  • 30 to 40 personas, each a problem plus a situation
  • An angle for each persona, built from named parts, and the offer options for each concept
  • A test order and an ad set name for every concept
  • A first-line hook idea per concept and the proof each one needs
• Creative brief writer: Turn your customer reviews and product facts into an ad brief. It picks one problem, writes a one-line angle, and backs every claim with a shot.
  • A short research summary of what they want, what blocks them and what they tried, with quotes
  • Up to ten reasons to buy, each a possible angle
  • One problem and a one-sentence angle
  • A proof list pairing every claim with the shot that shows it
  • A brief (concept, ad type, angle, who it is for, headline, call to action, visual direction) and two versions that change one thing
• 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
• 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
• John Caples: Write headlines and plan a fair ad test through John Caples’s recorded approach. Lead with the reader’s gain and count replies by version.
  • Your problem worked on the way John Caples would: their questions, their method, their push-back
  • The answer or the work, in John Caples's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• 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

Tasks you can use it for

• You are about to plan next month's ads and do not know how many new ones you need.
• Your ads have gone stale and you want fresh ideas that come from what buyers say, not from a guess.
• You can add budget and want to know which channel should get it.

Limits to check before starting

• You run a brand new store with no spend history: start with a simple test plan, or use the Ad test budget calculator.
• You only need one brief for one ad idea: use the Ad test brief writer.
• You want to check an ad before it goes live: use the Pre-launch ad checker or 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.

• 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 spend and results export first. Say which month and which channels it covers.
• When it pauses, add your reviews, support emails and product facts in one place.
• When it pauses again, pick two or three concepts from the matrix. Choose ones that tackle different problems.
• Check the budget numbers against your own books before you move any money.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/plan-a-month-of-meta-ads-with-the-right-number-of-new-a-a86add14 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.