[Home](https://gavek.dk/)/[AEO knowledge hub](https://gavek.dk/aeo/)/llms.txt: a discovery aid, not a substitute for useful pages AEO · evidence and practical implementation # llms.txt: a discovery aid, not a substitute for useful pages Understand what the proposal does and what it cannot establish. Prioritise accurate HTML and working links before adding another discovery file. ## What is being proposed The llms.txt project proposes a concise Markdown description and links to useful material for agents. It is a discovery convention rather than an authentication system, universal indexing protocol or guaranteed ranking signal. A vendor publishing such a file on its own documentation site does not establish that every search product uses third-party files to choose citations. ## Make the maintenance decision explicit The file is most useful when someone owns a compact, accurate description and the linked resources remain available. Record which client or documented integration benefits and what maintenance is required. If your site already generates a public catalogue and Markdown pages, use the same source of truth rather than hand-maintaining contradictory descriptions. Do not put credentials, private prompts or confidential client documents into a public discovery file. ## Test what actually exists Fetch the file and check status, content type, correct business identity and every destination. Fetch a linked Markdown representation and compare it with the public HTML’s substantive facts. An HTML fallback with a 200 status is not a working Markdown resource. Check behaviour after service changes and deployment. Keep the file’s purpose distinct from robots access preferences. ## Do not make the file the strategy Google says its AI search features do not require new AI text files or special schema. If a key service page is blocked or fails to explain scope, fix that before treating discovery conventions as urgent. Where a partner requires a particular format, implement and test that requirement as an integration task. Report it as implemented discovery support, not proof of future model recommendations. ## Continue with the related decision - [AEO learning paths](https://gavek.dk/aeo/) - [AI-referred 404s: recover the right destination without misleading redirects](https://gavek.dk/learn/ai-referral-404-recovery/) - [Discuss the scope of AEO and AI-search work](https://gavek.dk/services/ai-search/) ### Sources, method and review information Editorial publisher: Gavek. Reviewed 8 November 2026. Practical methods and clearly labelled examples are original editorial guidance, not customer results or a disclosed platform algorithm. Check sources when implementing. - [llms.txt · proposal](https://llmstxt.org/) - [Google Search · google](https://developers.google.com/search/docs/appearance/ai-features) Your next move starts here ## Make search a more useful part of your growth. Start with your website. Leave with a clearer picture of what to improve, what to measure and where to focus next. [Discuss your SEO project ↗](https://gavek.dk/contact/)[Explore our services ↗](https://gavek.dk/services/)