AI search readiness Get products ready for AI search with Claude Cowork
Getting products ready for AI search with Claude Cowork means using Anthropic's desktop agent to track StoreSEO GEO scores on a schedule, then working through fixes with you in a live session, because a scheduled task has nobody there to say yes.
Last updated: October 2026
Set up Claude Cowork for StoreSEO
Skip this if Claude Cowork is already connected. The full guide, with the alternatives, is on the Claude Cowork page.
- 1
Add StoreSEO as a custom connector
In Cowork, open Customize, then Connectors, choose + Add and then Add custom connector. If you already added StoreSEO to your Claude account, look for it in that list first. Use this URL.
URLhttps://mcp.storeseo.com/mcp
- 2
Approve your store and check it
Sign in when the browser opens: pick your Shopify store and approve access. Then start a task and ask this first, so you know the connector works before you delegate real work.
PromptUse StoreSEO to show me my store's SEO score breakdown.
How does this work in Claude Cowork?
Cowork runs on your desktop and can use the apps connected to it, so StoreSEO sits beside your files and other connectors. There are two different ways to use it for this job. In a live session you ask: which of my products are weakest for AI shopping agents, and prepare fixes for the worst three. Cowork calls storeseo_start, which returns a GEO overview, then storeseo_get_resource_seo on each candidate and reads out the failing criteria. It previews FAQs and an AI snippet with storeseo_preview_resource_optimization and waits for your yes before storeseo_apply_resource_optimization.
The second way is a recurring task, and it needs different wording. A task scheduled in Cowork runs on its cadence without you in the conversation, so it cannot wait for an approval. For this job that points to a weekly report: read the GEO overview, list the lowest-scoring products and the criteria that fail, and write you a summary or a file. The prompt should say in plain words not to apply, generate, preview, publish, write descriptions or change schema. Previews spend AI credit even though they save nothing, so a report-only task should skip them too.
Put the two together. Monday's task reports which products fell behind or never improved. You open Cowork when you have time, paste the list in and say: work through these with me. That session is where product schema, FAQs, the AI snippet and any description rewrite happen, with the agent asking and you answering. Cowork can keep the weekly summaries as files on your computer, which gives you a trail of how scores moved between runs.
-
You: Run my weekly AI-readiness check. Read only, no changes.
- storeseo_start read-only
- storeseo_get_resource_seo read-only
- storeseo_get_resource_seo read-only
-
Claude Cowork: Two products need attention: Merino Beanie (GEO 41, no FAQs, no AI snippet) and Ceramic Pour Over (GEO 38, thin description). I changed nothing. Saved the summary to weekly-geo.md.
-
You: Good. Keep Monday's task to this, and I will fix them in a live session.
What to ask Claude Cowork
Every Monday, use StoreSEO to read my GEO overview and my five lowest GEO products with their failing criteria. Summarize only. Do not preview, apply, write or change anything.
Open a session: take the three weakest AI-readiness products from my last report and prepare FAQs and AI snippets for them. Preview and wait for me.
Compare this week's GEO report with last week's file and tell me which products improved.
- Which of my products have the lowest GEO score, and what is missing for AI shopping agents?
- Make the product Merino Beanie ready for AI search: FAQs, AI snippet and product schema. Preview first.
- Scan the description of my best seller for AI agents and ask me the questions it needs.
- Rewrite the description of Ceramic Pour Over from my answers. Keep a copy of the old one for me.
- Is product JSON-LD schema enabled on my store? If not, explain what turning it on changes.
What StoreSEO does: ai search readiness
GEO is StoreSEO's AI readiness score for products. The agent reads which GEO criteria fail, fixes the ones a tool can fix (FAQs, AI snippet, alt text, product schema), and can rewrite a thin description from your own answers to StoreSEO's questions.
Requires: FAQs, AI snippets and descriptions spend AI Content Optimizer credit. The product needs a focus keyword, set in the StoreSEO app, before a description scan or rewrite.
- 1
Read the GEO checklist
The agent reads the product's GEO block: the score and every AI-readiness criterion that passes or fails.
- 2
Turn on product schema if it is off
Product JSON-LD is a shop-wide setting, so enabling it clears that criterion for every product at once. If you then decide not to apply the rest, the agent switches back off only the schema it turned on.
- 3
Preview FAQs and the AI snippet
The preview generates FAQs and an AI snippet (summary, benefits, best for) and projects the new SEO and GEO scores without saving.
- 4
Scan the description
For a thin or missing description, StoreSEO scores it on seven pillars (identity, materials, dimensions, features, use cases, what is included, care) and returns questions. The agent asks you each one, word for word.
- 5
Write and apply
With your answers, StoreSEO writes the description and saves it immediately; the response holds the only copy of the old text. The previewed FAQs and snippet are applied after your yes.
AI search readiness reference
| Scope | Products only; collections, pages and articles have no GEO score |
|---|---|
| Fixable by tools | FAQs, AI snippet, image alt text, product schema, description |
| Fixed only in the app or admin | Product title, category, product type, image count, inventory, variant barcode, SKU, price, image |
| Description pillars | Identity, materials, dimensions, features, use cases, what is included, care |
| Description write | Saved immediately to Shopify and StoreSEO; no undo and no revision history |
| Old description | Returned once in the write response, the only remaining copy |
| Product schema | Shop-wide toggle; credits the schema criterion on every product |
| Prerequisite | A focus keyword on the product, set in the StoreSEO app |
Rules Claude Cowork follows
- The scan's questions go to you word for word and in order; the agent does not answer them for you.
- A description is only written without questions when you decline to answer or authorize a bulk run without them.
- Writing a description replaces the current one at once with no undo, so the agent asks first and keeps the old text the response returns.
- If the agent enabled product schema for this flow and you stop before applying, it turns that schema back off; it never disables a schema you already had on.
- Criteria only you can fix get one link to the product's fix page, not a link per criterion.
In Claude Cowork
A scheduled task runs without you in the conversation, so nobody is there to say yes. Keep any scheduled StoreSEO task for this job to reads and reports, and tell it in plain words not to preview, apply, write descriptions or change schema settings. Cowork also follows the custom connector rules of Claude: the Free plan allows one custom connector, and on Team and Enterprise an owner adds the connector under Organization settings, Connectors. If StoreSEO is missing in Cowork, check Customize, Connectors inside Cowork itself.
What runs without asking. Reads such as SEO scores, store listings, settings and Google reports run straight away. Generating a preview spends AI credit but writes nothing, and StoreSEO tells the agent to say what a generation will cost before it runs one. Applying content, optimizing images, changing settings, publishing llms.txt or agents.md, writing a product description and deleting anything wait for your yes in the conversation. That yes is an instruction the agent follows, not a lock on the server, so your client's own tool-approval setting is the hard stop.
Questions
Can Claude Cowork improve my AI-readiness scores on a schedule?
It can report on them on a schedule, which is the safe use. A scheduled task has nobody present to approve changes, so keep it to reading GEO scores and writing a summary, and make the fixes in a live Cowork session where you can say yes.
Why should a scheduled Cowork task skip previews?
A preview writes nothing to your store but it spends AI Content Optimizer credit, and each re-run spends again. A weekly task that previews every low product could use your credit with no one reading the drafts, so read first and preview when you are in the session.
What is a GEO score in StoreSEO?
GEO is StoreSEO's AI readiness score for products. It measures how well a product can be understood by AI shopping agents and generative search, using criteria such as FAQs, an AI snippet, image alt text, product schema and the quality of the description.
Can I undo a rewritten product description?
Not inside StoreSEO. The new description is saved immediately and StoreSEO keeps no revision history. The response returns the previous description once, so ask the agent to keep it for you before it writes.
Why does the agent ask me questions before writing a description?
StoreSEO scans the description on seven pillars and returns questions for the facts it cannot infer, such as materials or what is in the box. Your answers become stated facts in the new copy instead of guesses.
Does enabling product schema affect every product?
Yes. Product JSON-LD is a shop-wide setting, so turning it on clears that criterion for every product at once, and turning it off removes it everywhere.
Keep going
AI search readiness with other agents
More Claude Cowork guides