Hire an AI Google Shopping margin and title reviewer

Everything it can hand back

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

• Shopping tiers with a break-even and a target for each, and a budget split
• A call on every product with enough clicks, plus search terms to block
• A waste score and the weekly edit to make
• New titles and descriptions in one order for the whole catalogue, rolled out in batches

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 Shopping campaign has one target for every product, whatever the margin.

• Step 1: Tiers and targets. Shopping tiers by margin, with a break-even and a target for each tier, and a budget split.
• Step 2: Weekly read. A call on each product with enough clicks, search terms to block, impression share and a waste score.
• Step 2: Weekly edit. The changes to make this week, in order.
• Step 3: Titles. New titles and descriptions in one order, using words buyers typed, with rollout batches.
• 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

• Set tiers and targets. Checks you have enough products and sales to split, picks tiers by margin or by past return, and sets each target from break-even. It also decides where Performance Max fits.
• Read the first two weeks. Pauses while you build the tiers and run them for two weeks and export the report. Then it checks each product has enough clicks to judge, sorts search terms into blocks and feed problems, reads impression share and writes the weekly edit.
• Fix the weak titles. Pauses while you pull the converting search terms for the products it said to feed. Then it writes titles and descriptions in one order, keeps every word true to the product and rolls them out in small batches.

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 build-shopping-by-margin-tune-it-weekly-and-fix-titles 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/build-shopping-by-margin-tune-it-weekly-and-fix-titles/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 products with price, margin and past return on ad spend
• The weekly Shopping report with search terms, after the first two weeks
• The converting search terms for the products to fix, and their current titles
• Photos of the products (optional)

Tools and access

• Google Ads: Standard Shopping campaigns, product-level reports and Performance Max settings live here.
• Google Merchant Center: Custom labels let you group products by margin tier.
• Any good chat AI: Any current chat AI can work from a pasted product list.
• 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 Merchant Center: Shows how each product title and image performs and where the feed has problems.
• Google Ads Keyword Planner: Gives the words buyers use for a product, in the country you sell to.
• Any good chat AI: Writes titles to a fixed pattern from your product facts.

Functions and deliverables

• Google Shopping margin and title reviewer: Group Shopping products by margin. Read real weekly results and use searches that led to sales to improve product titles.
  • Shopping tiers with a break-even and a target for each, and a budget split
  • A call on every product with enough clicks, plus search terms to block
  • A waste score and the weekly edit to make
  • New titles and descriptions in one order for the whole catalogue, rolled out in batches
• Google Shopping margin-tier planner: Share product margins and ad results. Get a Google Shopping tier plan, break-even targets and a Performance Max test.
  • A campaign structure, by ROAS tier or by margin tier, with reasons
  • A target ROAS for each campaign
  • A Performance Max catch-all setting with a 4 to 6 week test plan
  • A note on any tier that is too small to run
• 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
• Shopping feed title writer: Rewrite your Google Shopping feed titles with the search terms that already sell. You get new titles, descriptions, image fixes and a rollout plan.
  • A new title for each product and variant, in one fixed order
  • A description of about 1,000 characters for each product, checked against its facts
  • An image checklist and a test plan
  • A rollout plan in small batches, with custom label ideas
• 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

• Your Shopping campaign has one target for every product, whatever the margin.
• Some products take spend and never sell and you cannot tell which.
• Your titles are the supplier's names and do not match what people search.

Limits to check before starting

• You have fewer than about 30 products: fix your titles first with the Shopping feed title writer, then split into tiers later.
• You run Performance Max only: product-level calls need Standard Shopping, so tune your asset groups by hand instead.
• You want a check of a whole Google Ads account: use the Google Ads report auditor.

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".
• Give it real margins per product. It marks any margin you guessed.
• When it pauses, build the tiers, run them two weeks and export the weekly report with search terms.
• Pause again to pull converting search terms for the products it chose to fix.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/build-shopping-by-margin-tune-it-weekly-and-fix-titles 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.