Hire an AI Shopify Google Ads launch reviewer

Everything it can hand back

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

• A numbered tracking build checklist, a list of which ID goes where and a test plan
• A tracking score out of 100 with the one purchase action that should be primary and fixes in order
• A feed score out of 100, issues ranked by sales lost and a fix list
• A three-stage launch plan with budget per campaign and the signals to move to the next stage

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 spend on Google Ads for the first time and want to know sales are counted once and your products are approved.

• Step 1: Tracking build. A numbered build checklist, which ID goes where, conversion actions, enhanced conversions and a test plan.
• Step 2: Tracking check. Three rule results, Google's count against your store orders, the primary purchase action, fix steps and a score out of 100.
• Step 3: Feed check. Disapproved, warning and limited items, issues ranked by sales lost, a fix list, a feed score and a pass gate.
• Step 4: Launch plan. Readiness, a budget check, three stages with budget and bid strategy, settings for each campaign and a bid ladder.
• 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

• Exactly one purchase action is primary, and the GA4 import is not.
• Google's order count and your Shopify order count are compared for the same dates, with the gap shown.
• Feed issues are ranked by sales lost, not by how many products they touch.
• Both scores show how they were worked out.
• 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

• Build the tracking. Gives a numbered checklist to link GA4, turn on enhanced conversions, set one primary purchase action and add the Shopify pixel, plus a test plan.
• Check the test order. Pauses while you test. Then checks your screenshots against three rules, compares Google's count with your orders and scores the setup. If it finds faults, you fix them and run the check again until it passes.
• Check the product feed. Pauses while you fix tracking. Then sorts Merchant Center problems, ranks them by sales lost and scores the feed. You fix the feed faults and check again before the launch plan.
• Plan the launch. Matches daily budget to order value, picks the hero products and orders campaigns into three stages with gates for moving on.

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 launch-google-ads-with-trusted-tracking-and-a-clean-feed 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/launch-google-ads-with-trusted-tracking-and-a-clean-feed/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

• What you have now, such as the Google and YouTube app, GA4, Tag Manager and your current conversion actions
• Your store country and the checkout details you collect, such as email and phone
• Screenshots from a test order, showing the Google Ads conversion page and Tag Assistant
• Your Merchant Center issues list and product count
• Your monthly Google budget, average order value and margin

Tools and access

• Shopify: The Google and YouTube app and customer events (custom pixel) are where the build starts.
• Google Tag Manager: Holds the Conversion Linker, GA4 purchase event and Google Ads conversion tag.
• Google Ads: Where the conversion actions, enhanced conversions and Diagnostics are.
• Google Ads: The Goals and Conversions page lists every action with its settings.
• Google Tag Manager: Shows which tags fire and which values they pass.
• Shopify: Gives the order count and revenue to reconcile with.
• Google Merchant Center: Products, then Diagnostics, is where the issues and Autofix are.
• Shopify: Where price and availability are changed, so the feed stays in sync.
• Any good chat AI: Groups your issues by cause and works out the score.
• Google Ads: Where the campaigns, budgets and bid strategies are set up.
• Google Merchant Center: Holds your product feed, which Shopping and feed-only Performance Max need.
• Any good chat AI: Turns your numbers into the staged plan and lists the gaps.

Functions and deliverables

• Shopify Google Ads launch reviewer: Share Shopify setup, test-order evidence and product feed data. Get tracking and feed issues, required checks and a launch plan.
  • A numbered tracking build checklist, a list of which ID goes where and a test plan
  • A tracking score out of 100 with the one purchase action that should be primary and fixes in order
  • A feed score out of 100, issues ranked by sales lost and a fix list
  • A three-stage launch plan with budget per campaign and the signals to move to the next stage
• Shopify Google tracking builder: Share your Shopify and Google setup. Get a purchase-tracking checklist, ID map and test plan for duplicate events.
  • A numbered build checklist with the setting to choose at each step
  • A list of what to copy where (conversion ID, four labels, container ID)
  • A test plan that confirms each event fires once
  • Enhanced conversion steps and a server-side outline for larger spend
• Google Ads purchase tracking checker: Check your Google Ads purchase tracking for double counting. Paste your conversion actions and get pass or fail on three rules, a score out of 100 and fixes.
  • Pass or fail on the three common mistakes
  • Which action should be the only primary one
  • Fix steps in order
  • A score out of 100 and how it was worked out
• Google Merchant Center feed checker: Share product diagnostics and catalogue counts. Get prioritised feed fixes and a score based on the checks completed.
  • Issues grouped as disapproved, warnings and limited performance, with counts
  • A fix list split into automatic, manual and policy fixes
  • A feed score out of 100 and how it was worked out
  • A prevention plan for update frequency, checking before upload and price sync
• Google Ads launch planner: Plan your Google Ads launch for your online store. Give it budget and sales so far. Get the launch order, a budget for each campaign and bid steps.
  • A ready or not yet verdict, with the fixes to make first
  • The launch order with the signal that starts each step
  • A daily budget for each campaign and a 30, 60 and 90 day sequence
  • A bid plan with the points where you change strategy
• 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 are about to spend on Google Ads for the first time and want to know sales are counted once and your products are approved.
• Google reports more purchases than your Shopify orders, and you do not trust the numbers.
• Merchant Center shows disapproved products or warnings and you want to know which to fix first.

Limits to check before starting

• Your store is not on Shopify: use a person who knows your platform, or set up tracking by hand with your platform's own guide.
• You have not placed a test order yet: place one first, because the tracking check needs screenshots from a real order.
• You already run campaigns and want to read results: use the Ad results report writer.

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".
• Tell it what tracking you already have, even if it is a mess. It builds on what exists.
• When it pauses, add the tags, place one real test order and save screenshots before you continue.
• Fix the tracking faults, then export your Merchant Center issues list for the feed step.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/launch-google-ads-with-trusted-tracking-and-a-clean-feed 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.