Hire an AI ad channel budget reviewer

Everything it can hand back

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

• Each channel's return estimate against break-even, or unknown when no test backs it, with a trust level
• What a new customer costs on each channel, and the payback time
• Channels that fell two months in a row, with each tested cause marked likely or unknown
• A budget split, or "hold" and the test to run first
• The numbers to watch next month

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

• Moving budget on platform return alone. Retargeting and branded search over-claim; cold channels under-claim.
• Comparing channels at different funnel stages as if they were equal.
• Cutting a cold channel because its return looks low, before the store totals and a test say so.
• Using this when you spend on only one channel. The per-channel account keeper does that job.
• Treating the review as a one-month verdict. One odd month is a note, not a trend.
• Generic copy that could fit any brand.

What a good result looks like

An example, not your task: You spend on more than one channel and the platform numbers add up to more than your store sold.

• This month. One line with total spend, store revenue, blended return and the gap between platform claims and the store.
• Channels. For each channel: spend, reported return, supported return or unknown, break-even, new-customer cost, payback and trust level.
• Fading. Channels whose return fell two months in a row, with the months and each tested cause, marked likely or unknown.
• Budget proposal. A split with the size and reason of each move, or a hold and the test to run first.
• Watch next month. One to three numbers that decide the next review.
• Files and missing. Each step's file, the updated months.md, and every MISSING line in one list.

How the work is checked

• Every return is shown next to break-even, with the sums.
• No budget is proposed into a channel below break-even or one that fell two months running.
• No budget move is proposed when trust is low.
• Store totals are the base for the combined store measure. Each channel estimate has separate source evidence, method and limits; no per-channel causal effect is inferred from totals alone.
• 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 Andrew Chen and Claude Hopkins would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Get the base numbers. Works out break-even return and cost per customer once, then measures every channel against them.
• Check the platform numbers. Sets each platform's return against your store totals and saves a factor for each channel, with a trust level.
• Cost a real customer. Works out what a new customer costs on each channel and how soon it pays back.
• Look for fading channels. After three saved months, flags any channel whose supported return fell two months in a row. Those get no extra budget.
• Choose on trust. If trust is medium or high (50 or more out of 100 on the reality check's scale), it splits the next budget. If trust is low, it holds and hands back the test that would raise it.
• Hand back one review. Gives the channel table, the proposal and the numbers to watch. Nothing moves until you say yes.

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 monthly-channel-budget-reviewer 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/monthly-channel-budget-reviewer/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

• Each channel's spend, reported purchases and purchase value for the month
• Your store's orders, revenue, new-customer orders and refunds for the same month
• Your price, landed cost, shipping and fees, the first time
• A post-purchase "how did you hear about us" answer set (optional)

Helpful context (optional)

• A note of any tracking change or big sale in the month
• Results of any holdout or lift test you have run

Tools and access

• Claude Code: It can keep the reviewer folder and months file, read last month's files and run every step on a schedule.
• Shopify: Export orders, revenue and new-customer counts for the same month as the ad data.
• Any good chat AI: Any current chat AI can do the sums if it shows its working. Check one product by hand first.
• Shopify admin: The Cost per item field on each product feeds live margin reports, so your numbers stay current.
• Any good chat AI: Any chat AI can run the ladder and the score. Check the store base by hand.
• Meta Ads Manager: Lets you compare attribution settings and break results down by new, engaged and existing audiences.
• Shopify: Gives new-customer revenue and orders, and a cohort report for your own repeat data.
• A post-purchase survey app: Collects where buyers say they first heard of you, so you can compare it with platform data.
• Any good chat AI: Adding costs and ranking ads is work any strong chat AI does with this skill, given clean numbers.
• A spreadsheet: Holds the table and lets you check each sum.
• Any good chat AI: Reading a table of results and weighing causes is work any strong chat AI does with this skill.
• A spreadsheet: Keeps the monthly table and charts cost per customer.
• 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.
• A spreadsheet: Holds the scorecard and the values by period.
• Any good chat AI: Sorts and pairs the measures from your pasted list.

Functions and deliverables

• Ad channel budget reviewer: Compare channel claims with store totals. Review costs, weak trends and whether a budget move needs a test first.
  • Each channel's return estimate against break-even, or unknown when no test backs it, with a trust level
  • What a new customer costs on each channel, and the payback time
  • Channels that fell two months in a row, with each tested cause marked likely or unknown
  • A budget split, or "hold" and the test to run first
  • The numbers to watch next month
• Product margin checker: Check your product margin before you set ad targets. Give it a price and every cost. Get gross margin, break-even ROAS and CAC, and a score.
  • Product margin against true gross margin, with the gap in dollars and points
  • Break-even ROAS and break-even CAC
  • The three margins, labelled product, gross (CM2) and contribution (CM3)
  • A go or no-go flag and a score out of 100, with the sum shown
• Ad return evidence checker: Share ad reports and store totals. Get matched comparisons, evidence gaps and a custom review score, without a causal sales claim.
  • A comparison of reported measures, definitions, periods and missing coverage
  • A supported top-ad breakdown with audience and attribution limits
  • The evidence basis and next check for each proposed budget decision
  • A bounded custom checklist score with missing checks shown
• Cost per customer calculator: Work out what a customer really costs from your ad costs, samples and orders. See payback time and which ads to keep. Give it your numbers.
  • The full cost per customer by ad, headline and offer
  • How soon sales cover the cost
  • The most you can pay for a customer
  • A data score out of 100 and which ads to keep
• Channel decline checker: Paste results by channel over time. See which ones are fading and what to refresh or test next.
  • Each channel's trend with the month it began to fall
  • The likely cause for each, with the numbers behind it
  • A score out of 100, with how it was worked out
  • A refresh list, one channel to test next and a date to re-check
• 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
• Marketing scorecard builder: Build a marketing scorecard that puts slow brand measures next to clicks and sales, each with the question it answers and its time lag.
  • A scorecard with long-term results at the top and short-term response at the base
  • The question each measure answers and its time lag
  • Warnings on measures that mislead alone
  • A review rhythm, and a list of data you do not have
• 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
• Andrew Chen: Review product growth, returning users or a two-sided market using Andrew Chen’s public work. Start with the funnel and the smallest useful network.
  • Your problem worked on the way Andrew Chen would: their questions, their method, their push-back
  • The answer or the work, in Andrew Chen'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 spend on more than one channel and the platform numbers add up to more than your store sold.
• You want one calm monthly look at where the budget goes, not weekly tweaks.
• You think a channel is fading but can't tell if it is real.

Limits to check before starting

• You spend on only one channel: use the per-channel account keeper, or read that channel's own report.
• You want to judge single ads or creative: use the Campaign performance reviewer.
• You have no store totals for the month: first pull orders and revenue from your store, then come back.

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 agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to run this month's review.
• Attach each channel's month and your store totals for the same days.
• The first time, give it your price and costs. It saves the break-even numbers.
• Read the proposal. Move budget yourself, or say yes to each move.
• Run it again next month. It reads the saved months and compares.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/monthly-channel-budget-reviewer 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.