Hire an AI Google Ads performance reviewer

Everything it can hand back

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

• This week against last week and against your break-even, with the sums
• One ranked list of changes to approve, each with its size and reason
• A raise, hold or cut call on budget, with the gate that decided it
• The numbers to watch next week

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

• Changing the account on your own.
• Calling a week good or bad from ROAS alone, without break-even.
• Cutting search terms or products on a few clicks. Use the thresholds in each skill.
• Making many changes in one week while the account is still adjusting to last week's. Say which changes can wait.
• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.

What a good result looks like

An example, not your task: You run Google Ads for your store and want the weekly checks done the same way every Monday.

• This week in one line. Spend, sales, ROAS and CPA against last week and against your break-even, with the sums shown.
• Path taken. Whether it ran a dip investigation, a clean-up only, or a clean-up and scale check, and why.
• Changes to approve. Up to 15 changes, most important first, each with where it goes, its size, its source step and reason.
• Scale call. A raise, hold or cut call on budget, with the scale gate that decided it.
• Watch next week. The one to three numbers that decide next week's path.
• Files and missing. Each step's saved file, then every MISSING line from all steps in one list.

How the work is checked

• Every call is measured against break-even, and the sums are shown.
• No budget increase is proposed unless the scale gates passed this week.
• No new cuts are proposed in a week the dip investigator said to wait, except clear junk search terms.
• Every change says which step proposed it.
• 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

• Get the base numbers. Works out break-even ROAS and CPA from your price and margin once, then reuses them every week.
• Compare the two weeks. Sets this week's spend, sales, ROAS and CPA against last week and shows the change in each.
• Choose the path. If results fell sharply, it runs the dip investigator first. If that says wait, it holds back new cuts this week.
• Clean up waste. Sorts search terms into winners and negatives, then tunes Shopping products and Performance Max if you run them.
• Check before scaling. Only when nothing is broken does it run the scale gate check. A pass means it may propose a budget raise.
• Hand back one list. Merges every proposed change, removes repeats, keeps the more careful call when steps disagree, and stops for your 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 google-ads-weekly-account-keeper 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/google-ads-weekly-account-keeper/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

• Campaign results for the last two weeks, with cost, conversions and conversion value
• Search terms reports, and a Shopping product report if you run Shopping
• Your average order value and gross margin, the first time
• What changed this week, such as a sale, new products or stock running out (optional)

Helpful context (optional)

• A note of every change you made in the account last week
• Stock levels for the products you advertise most

Tools and access

• Claude Code: It can keep the keeper folder, read last week's files and run every step on a schedule.
• Google Ads: Export the campaign, search terms and product reports here, with cost, conversions and conversion value.
• Any good chat AI: It does the arithmetic and asks follow-up questions. Check the sums yourself once.
• Shopify Analytics: Gives your real AOV, new-customer share and repeat rate to paste in.
• Google Ads Keyword Planner: Shows the cost per click for your products, so the skill can check the fit.
• Google Ads: Holds the change history, weekly campaign data and the by-conversion-time columns.
• Shopify: Shows real revenue, orders, sessions and conversion rate for the business-level check.
• Google Analytics 4: Shows sessions and conversion rate by source.
• Google Ads: The search terms report and negative keyword lists live here. Export with the campaign, clicks, conversions and cost columns.
• Any good chat AI: Any current chat AI can sort a pasted report. A stronger one handles very long exports better.
• Google Ads: Product-level Shopping reports and impression share columns come from here.
• Google Merchant Center: Where you fix the titles and images the skill flags.
• Any good chat AI: Any current chat AI can sort a pasted export.
• Google Ads: Search term insights, product, asset, landing page and placement reports come from here.
• Shopify: Your backend revenue and new-customer data check Performance Max against reality.
• Any good chat AI: Any current chat AI can read a pasted export.
• Google Ads: Conversions by campaign, bid strategy and asset counts are all in the account.
• Google Merchant Center: Diagnostics shows the disapproved and warning counts for gate 1.
• Any good chat AI: Claude, ChatGPT and Gemini all add up points and check gates well.

Functions and deliverables

• Google Ads performance reviewer: Compare Google Ads results with break-even. Investigate drops and get ranked changes to approve before budgets move.
  • This week against last week and against your break-even, with the sums
  • One ranked list of changes to approve, each with its size and reason
  • A raise, hold or cut call on budget, with the gate that decided it
  • The numbers to watch next week
• Break-even ROAS and CPA calculator: Share order value, costs and ad figures. Get ad-cost limits, a matching cost check and clear gaps before choosing a test.
  • Sales-to-ad-spend threshold and ad allowance per order, with valid inputs and formulas
  • Matching cost-per-order comparison, or an unresolved result
  • Separate targets where supported costs differ
  • Custom checklist with checked maximum, missing evidence and a proposed next check
• Google Ads dip investigator: Find why your Google Ads results dropped. Give it your results and change history. You get the likely cause and a fix, wait or ignore call.
  • Findings in order, from the business level down to the root cause
  • A fix, wait or ignore decision
  • One sentence stating the root cause
• Search term sorter: Paste your search terms reports. Get winners to promote, negatives to add, placement and a waste score.
  • A winners list with a match type and the places to use each term
  • A negative keyword list with match type and the level to add each at
  • A short list of feed or listing fixes where the same junk keeps appearing
  • A waste score out of 100, with the sum shown
• Google Shopping campaign reviewer: Paste Standard Shopping reports. Get product, search term, bid and budget actions, with a waste score when data allows.
  • A product action list covering negative, feed fix, bid and budget
  • Search term negatives to add
  • A bid or budget change with the expected effect
  • A weekly edit list and a waste score out of 100
• Performance Max campaign reviewer: Share campaign exports and break-even figures. Get proposed exclusions, budget guidance and a custom spend score where the data supports it.
  • Daily, weekly and monthly findings with missing evidence shown
  • Proposed product, page, term and asset changes to review
  • A supported budget proposal or hold, with the source-rule limits
  • A matched trend comparison and descriptive score where unique flagged spend is known
• Google Ads scaling readiness reviewer: Check your Google Ads account before you raise spend. Get pass or fail on five gates, a score out of 100 and a go or wait call.
  • Pass, fail or unknown for each of the five gates, with the evidence
  • A score out of 100, with the sum shown
  • A fix list in order, and a go or wait call with a safe step-up size
• 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

• You run Google Ads for your store and want the weekly checks done the same way every Monday.
• Results dropped this week and you want to know why before you change anything.
• You want to raise your budget, but only when the numbers say it is safe.

Limits to check before starting

• You have less than two weeks of data: wait until you have two full weeks, or check your numbers by hand against break-even.
• You only want to know why one sharp drop happened: use the Google Ads dip investigator on its own.
• You want it to change your account for you without asking: this agent only lists changes and waits for your yes.

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 (a paid tool, needed only to keep files and run on a schedule), add it as a skill or save it in .claude/agents, then ask it to run this week's check. A plain chat works from your exports.
• Put this week's exports in one folder, or attach them in the chat.
• The first time, give it your average order value and margin. It saves the break-even numbers and reuses them.
• Read the change list. Make the changes you agree with in Google Ads yourself. The agent works from exports and needs no connection. Letting it make a change needs a connector with Google Ads API access, which may cost money.
• Run it again next Monday. It compares against last week's files.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/google-ads-weekly-account-keeper 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.