Get products ready for AI search with Hermes Agent
Getting products ready for AI search with Hermes Agent means asking it, from a terminal or a chat app, to read your products' GEO scores in StoreSEO and fix the gaps you approve, with a hermes cron job for a weekly read-only report.
Last updated: October 2026
Set up Hermes Agent for StoreSEO
Skip this if Hermes Agent is already connected. The full guide, with the alternatives, is on the Hermes Agent page.
- 1
Add StoreSEO to config.yaml
Add this under mcp_servers in ~/.hermes/config.yaml. If the file already has an mcp_servers block, add only the storeseo entry. Then start a new Hermes session, or run /reload-mcp in the one that is open.
YAMLmcp_servers: storeseo: url: "https://mcp.storeseo.com/mcp" auth: oauth - 2
Sign in to your store
On first connect Hermes prints an authorize URL and waits for the sign-in. Run this command to start it yourself or to re-authorize later. Pick your Shopify store and approve. Hermes caches the tokens in ~/.hermes/mcp-tokens/storeseo.json.
Terminalhermes mcp login storeseo
How does this work in Hermes Agent?
You start a Hermes session in a terminal or message it from a chat app and ask which products are least ready for AI shopping agents. Hermes calls storeseo_start, then storeseo_list_resources sorted by score and storeseo_get_resource_seo for the weakest products. The GEO block on each product gives a score and the failing criteria, so the answer is concrete: this product has no FAQs, that one has no AI snippet, a third has alt text missing on two images and a description of a single sentence. Every one of those calls is a read.
Hermes keeps memory across sessions, so you can come back to the same worklist the next day. When you pick a product, it calls storeseo_preview_resource_optimization to draft FAQs and an AI snippet and project the new GEO score, after saying that the preview spends AI credit. You review the draft, say yes, and it calls storeseo_apply_resource_optimization. For a thin description it runs storeseo_scan_product_description and puts StoreSEO's questions to you one by one; you answer, and only after you confirm that the new text replaces the live one does it call storeseo_write_product_description.
The built-in scheduler suits the reporting half of this job. A hermes cron job with a prompt like list my five lowest GEO-scoring products and what each is missing can run every Monday and deliver the result to Telegram or another chat target. It must stay report-only, because a scheduled run has no one to answer the scan's questions or approve a write. Act on the report in a live session afterwards.
-
You: Which products are weakest for AI search? Then scan the worst one.
- storeseo_start read-only
- storeseo_list_resources read-only
-
Hermes Agent: Ceramic Pour Over scores lowest on GEO and has a two-line description. Scanning spends AI credit and writes nothing. Do you want me to run the scan?
-
You: Yes, run it.
- storeseo_scan_product_description preview
-
Hermes Agent: StoreSEO has seven questions. First one, word for word: what materials is this product made from?
What to ask Hermes Agent
Use StoreSEO to list my products with a GEO score under 50 and what each is missing. Read only, change nothing.
Make Merino Beanie ready for AI search: preview FAQs and an AI snippet, show me the projected score, and wait for my yes.
Scan the description of Ceramic Pour Over for AI agents and ask me every question StoreSEO returns, word for word.
- 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 Hermes Agent 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 Hermes Agent
A hermes cron job cannot answer the description scan's questions or say yes to a write, so keep scheduled prompts to reads and state that in the prompt. If you want to enforce it, use Hermes' tools include list to expose only the StoreSEO list and get tools to that job. Edits to config.yaml need a new session or /reload-mcp, and a token pasted into the file is a secret to keep out of version control.
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 hermes cron fix my GEO scores automatically?
It can report them. A scheduled job has no one to answer the scan's questions or approve a write, so ask it for a read-only list of low GEO scores and apply fixes in a live session.
Does Hermes remember my answers to the description questions?
Hermes keeps memory across sessions, but StoreSEO's scan is meant to put its questions to you each time, and the product must have a focus keyword first. Treat the questions as yours to answer.
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 Hermes Agent guides