AEO & GEO
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) help AI services understand and cite your storefront. The template provides machine-readable product and collection content without changing the pages shoppers visit.
Make storefront content readable to AI
The home page, product, collection, and search URLs return structured Markdown when a client requests text/markdown or appends .md to the URL, such as /products/[handle].md. The home page's Markdown URL is /index.md. Normal browser requests continue to receive HTML from the same URLs. No setup is required.
Markdown responses send X-Robots-Tag: noindex and a canonical link to the HTML page, so search engines index the shopper page rather than its Markdown copy.
The storefront also publishes /llms.txt, a concise guide for AI agents. It summarizes the store with site.description from the shop config and explains how to buy for a shopper through Shopify's UCP endpoints. It links to store policies, up to 50 collections, the sitemap, and crawl guidance rather than duplicating the full catalog. The sitemap remains the complete URL inventory.
Absolute URLs in /llms.txt, Markdown, the sitemap, and crawl guidance use site.url. If you deploy outside Vercel, set it to your public storefront origin.
Markdown explains what a product or collection is; it does not list or sell inventory. Catalog search, live per-variant availability, cart, and checkout for agents come from Shopify's Universal Commerce Protocol (UCP) endpoints, which the storefront forwards at /.well-known/ucp and /api/ucp/mcp. Markdown responses point agents there instead of repeating product listings or per-variant stock.
Markdown content uses the deployment's configured Shopify country and language. If you add Shopify Markets, make sure AI-readable content uses the same market as the corresponding shopper page.
Included discovery surfaces
| Surface | Outcome |
|---|---|
| Markdown responses | Describes products and collections and points AI clients to UCP |
| Schema.org data | Describes products, collections, breadcrumbs, the organization, and site search |
| Sitemap | Lists storefront content for crawlers |
| Crawl guidance | Points crawlers to the sitemap and blocks cart, account, login, search, and sorted or filtered collection URLs |
/llms.txt | Gives AI agents a concise storefront index |
| Social metadata | Supplies route-specific titles, descriptions, images, prices, and availability |
Markdown responses start with frontmatter listing the page title, description, and canonical URL, plus when Shopify last updated the product or collection. They include the facts needed to interpret each page:
- Products — brand, category, a one-line summary, price or price range with compare-at price, product-level availability, description, options, images, and links to the shopper page and UCP profile.
- Collections — title, description, image, and links to the shopper page and UCP catalog search. Collection contents change often, so products are not listed.
- Search — the query and links to the shopper results page and UCP catalog search.
What’s next
Keep /llms.txt concise and use the sitemap for exhaustive discovery. Common extensions include Markdown responses for additional page types, localized discovery content, and public metaobject content. Include only facts an agent needs to identify, compare, or link to that content.