Hire an AI shopping recommendation reviewer

Everything it can hand back

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

• A list of 30 to 60 shopper questions in topic groups, with the ones your store does not answer marked
• A log of who each assistant named, linked or left out, your share of voice and a visibility score out of 100
• A gap list with fix, build or influence on each item, quick wins first, and a topic coverage score out of 100
• Rewritten product pages with a plain first screen, spec table, short FAQ, title and a markup checklist

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: Shoppers ask ChatGPT, Gemini or Perplexity what to buy and you want your store in the answers.

• Step 1: Shopper questions. 30 to 60 questions shoppers ask about your category, in topic groups, with the ones your store does not answer marked.
• Step 2: AI panel log. For each question, which stores each assistant named, linked or left out, with your share of voice and sources cited.
• Step 3: Gap list. The gaps that keep you out of answers, each tagged fix, build or influence, with quick wins first.
• Step 4: Rewritten pages. Product pages with plain facts up top, a spec table, a short FAQ, a title and a markup checklist.
• 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.
• Every answer in the panel log was pasted back by the person, not written by the AI.
• Every number on a rewritten page comes from the facts the person gave.
• 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

• Map shopper questions. Starts from money terms and adds the long tail and the sub-questions assistants run. Groups them into topics and marks the ones no page of yours answers.
• Run the AI panel. Records for each question who the assistants name, link or leave out, works out your share of voice, and lists the sources they cite.
• Find the gaps. Checks six gaps, ties your brand to topics, tags each fix, build or influence, and puts quick wins first.
• Rewrite the product pages. Puts plain facts in the first screen, adds a spec table, a short FAQ and a title, and lists the markup to add. Health, money and legal claims are checked.

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 get-your-store-recommended-by-ai-assistants 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/get-your-store-recommended-by-ai-assistants/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 and collections with prices
• The page address and text of the product pages you want rewritten
• Specs, materials, sizing, shipping and returns
• Reviews and customer questions (optional)
• Search terms and past sales (optional)
• Your rivals (optional)

Tools and access

• Perplexity: Shows the searches it runs for each question, so you can see fan-out directly.
• Google Search: People Also Ask boxes give related questions. Click deeper levels for second-level ones.
• Any good chat AI: Turns keywords into questions and groups them.
• Any good chat AI: Records and counts the runs you paste in, and sorts the sources.
• A spreadsheet: Enough for a small panel. A paid answer tracker only pays off at hundreds of questions.
• Ahrefs Brand Radar or Semrush: Paid trackers can run large panels. Check the vendor's current price and pick the cheapest one that does the job.
• Any good chat AI: Sorts panel results into the six gaps and ranks them.
• Ahrefs Brand Radar: A paid tool that speeds up the missed citation and competitor filters. Not required.
• A spreadsheet: Keeps your gap table and ranked list in one place.
• Shopify: Product and collection templates hold the title, H1, spec table and FAQ. Themes often make the logo the home page H1, so check section level.
• A schema validator: Free tools show if product, offer and review markup is valid.
• Google Search Console: Shows if the page is indexed and which queries it gets.

Functions and deliverables

• AI shopping recommendation reviewer: Share product facts, pages and access to AI search tools. Get a question map, observed mentions, gaps and product-page copy drafts.
  • A list of 30 to 60 shopper questions in topic groups, with the ones your store does not answer marked
  • A log of who each assistant named, linked or left out, your share of voice and a visibility score out of 100
  • A gap list with fix, build or influence on each item, quick wins first, and a topic coverage score out of 100
  • Rewritten product pages with a plain first screen, spec table, short FAQ, title and a markup checklist
• Customer search question mapper: Get the questions shoppers ask AI about your products, grouped by topic, with follow-up searches and the pages your store still lacks.
  • About 30 questions in a shopper's own words, grouped by topic
  • The follow-up searches an AI runs for each topic, marked seen or likely
  • One store page assigned to answer each topic
  • A gap list of questions no page answers, with the 5 to build first
  • A plain note that chat questions have no official search volume
• AI search visibility tester: Share your store and shopper questions. Test or collect AI answers, then count brand mentions, links and cited sources in those runs.
  • A results table: question, assistant, run, named, linked, position, rivals
  • Share of voice for each assistant and each question group
  • A ranked list of the sites AI cited when it did not name you
  • A test plan with questions you leave alone and questions you act on
  • A visibility score out of 100, with the sum shown
• AI search recommendation gap finder: Share AI search test results. See where your store is missing or misread, with six gap checks and actions ranked for review.
  • A gap table across the six gaps, with evidence
  • A ranked action list tagged fix, build or influence
  • A platform priority note
  • A score out of 100 for how many of your topics you cover
• Product page editor for AI search: Edit a product page so AI tools quote it right. Give it your page and facts. You get a change list, spec table, FAQ and markup checklist.
  • A page change list in priority order
  • A spec table and FAQ draft
  • A title, H1 and meta description draft
  • A markup checklist for product, offer and review
• 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

• Shoppers ask ChatGPT, Gemini or Perplexity what to buy and you want your store in the answers.
• A rival is named in AI answers and you cannot tell why you are not.
• Your product pages describe the product in marketing words, with the plain facts missing.

Limits to check before starting

• You have no product pages yet: build them first, then come back. For the facts to put on them, use the Brand profile builder.
• You sell to other businesses and want lead lists: use a simple prospect list in a spreadsheet, or ask a sales person to build one.
• You only want one product page rewritten: use the Product page editor for AI search on its own.

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 is a zip with HANDOFF.md plus one skill file for each step.
• Give the folder to Claude, in Claude Code or as files in a Claude Project, and say "Follow HANDOFF.md".
• Give it your products with prices. Add reviews or customer emails if you have them, because real customer words make better questions.
• Run the questions it writes in each AI assistant you can use, then paste the answers back. The workflow only records and scores them. It cannot run them for you.
• Give it the page text and facts for the product pages to rewrite. Check every fact before you publish.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/get-your-store-recommended-by-ai-assistants 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.