How LLMs read products
When a shopper asks ChatGPT, Perplexity or Gemini for a product recommendation, the model doesn't scroll your website. It queries a catalog index — a structured representation of products, scored by semantic relevance to the query.
The quality of that representation decides whether you appear.
What LLMs look for
- Clear semantic identity — one sentence answering "what is this product and who is it for?". Vague titles ("SKU-23487 · Premium Item") are skipped.
- Structured attributes — material, use case, size, season, audience. JSON-LD is the preferred format.
- Keywords in the shopper's language — people ask in the language they think in. Keywords that match the language of your own content match the way your shoppers search.
- Reasoning — why should someone buy this vs the alternatives? When is it the right choice?
- Signals of quality — reviews, returns rate, certifications.
llms.txt— a store-level manifest telling crawlers what your catalog offers and where to find structured data.- Markdown endpoints — clean text/markdown representations of products and other entities.
What Clione does about each
| LLM need | Clione artifact |
|---|---|
| Semantic identity | core_identity text |
| Structured attributes | synthetic_properties JSON + JSON-LD |
| Keywords | search_keywords[], in the same language as the entity's content |
| Reasoning | reasoning.{recommended_for, decision_logic, objection_handler} |
| Quality signals | Quality scores — see Understanding Quality Scores |
| Catalog manifest | llms.txt served on your store's own domain |
| Markdown for crawlers | .md documents for every entity, served on your store's own domain |
Where llms.txt and the .md documents live
Crawlers give more weight to content on your own domain than to a reference on a third-party host, so Clione serves both from your storefront's domain:
- Shopify — through Clione's Shopify app, at
https://<your-store>/apps/clione/llms.txt, with the.mddocuments under the same/apps/clione/path. Shopify keeps the root/llms.txtfor its own file. The Clione SEO app embed links that root/llms.txtand adds discovery links toagents.jsonand the MCP server under/apps/clione/. - BigCommerce — on a subdomain you point at Clione (for example
md.yourstore.com) and verify in the dashboard.llms.txtand the.mddocuments are served from that domain.
Why the traditional SEO stack isn't enough
Keyword stuffing, backlink farming, exact-match titles — these assume a keyword-matching crawler. LLMs use embeddings: they compare the meaning of the query against the meaning of your product text. Well-written product identity beats aggressive SEO copy every time.
That's the whole bet of Clione: enrich once, serve semantically, win the LLM channel.
It's not just products
Every entity in your catalog — products, collections, categories, and pages — gets the full signal treatment. The same four signal formats (.jsonld, .llm, .md, .meta) are available for all entity types. Collections and categories get CollectionPage schema; pages get WebPage schema, or AboutPage, ContactPage or BlogPosting where that fits the page. All bundled with FAQPage if FAQ entries exist. The LLM doesn't just see your products — it sees your entire store's semantic structure.