GEO & AI search
llms.txt
Definition
A proposed plain-text file at a site's root that summarizes what the site offers, aimed at giving AI crawlers a fast, structured entry point similar to robots.txt for search crawlers.
Defined in The Agentic Commerce Glossary.
How else it gets framed
The same term carries different emphasis depending on the surface it’s used on. Both readings are correct.
A markdown file at /llms.txt containing a curated map of a site for AI consumption: an H1 with the site name, a one-paragraph summary in a blockquote, then H2 sections of annotated links to the pages that matter most. Voluntary convention — no assistant is obligated to fetch or honor it.
llms.txt for Ecommerce: The Complete Guide →Where llms.txt comes up
The guides that put this term to work, rather than just defining it.
- Commerce GEOllms.txt for Ecommerce: The Complete Guide
- Commerce GEOStructured Data for AI Shopping Agents
- Commerce GEOGEO vs. SEO Budget Split: A Decision Framework
- Commerce GEOCommerce GEO: How to Get Your Products Recommended by AI
- For AgenciesHow Agencies Package Commerce GEO as a Service
- Commerce GEOHow to Run an AI Citation Audit for Your Brand
- For AgenciesPricing Agentic Services: Fixed-Scope Logic for Agencies
- Commerce GEOShould You Block AI Crawlers? A Merchant Decision Guide
- For AgenciesThe Agency Playbook: Adding Agentic Commerce Services in 2026
Related terms
- Retrieval-augmented answer
- An AI response generated by first searching for relevant live pages, then having the model read and synthesize from those specific pages — as opposed to answering purely from training data. Perplexity's shopping answers are retrieval-augmented, which is why what's on your page right now matters more than what a model "knows" about your brand.
- Commerce GEO
- Generative engine optimization applied to commerce — the practice of structuring a catalog and content so AI assistants like ChatGPT, Claude, Gemini, and Perplexity cite and recommend it.
- Shared foundation
- Technical and data work — structured data, attribute completeness, site architecture, page performance — that simultaneously improves classic search rankings and AI-assistant citation accuracy. It should be budgeted once, not split across SEO and GEO line items.
- Answer-first structure
- Writing the conclusion or direct answer as the first sentence of a section, with supporting reasoning and caveats following it — the inverse of narrative or journalistic structure, which builds to a conclusion.
- Corroboration
- Independent confirmation of a claim from a source that isn't the brand itself. In GEO terms, it's the difference between a fact an assistant can state with confidence and one it has to hedge or omit.
- Server-side rendering
- Generating the full HTML — including product facts and JSON-LD — on the server so it's present in the initial response, before any JavaScript runs. The opposite of client-rendering facts into the page after load.
Want to know where you actually stand?
Submit your store and get a /100 agentic-commerce readiness score across catalog, schema, product pages and checkout — plus three fixes you can ship yourself.