llms.txt is a proposed standard for a plain-text file at the root of a website that summarises the site for AI systems: what the business does, its key facts and links to its most useful pages. It was proposed in 2024 and support from AI companies is still emerging, so treat it as a low-cost extra rather than a replacement for clear pages, structured data and good SEO.
Where it came from
The format was proposed in September 2024 by Jeremy Howard of Answer.AI, and is documented at llmstxt.org. The idea is simple: large language models work better with short, clean, well-organised text than with full web pages full of menus, scripts and layout.
What goes in it
A good llms.txt is short and factual:
- A heading with your business name
- A one-paragraph summary of what you do, for whom and where
- Key facts such as prices, service areas and contact details
- Links to your most important pages, each with a short description
- Optionally, a longer llms-full.txt with the full text of key pages
Do AI assistants actually use it?
Honestly, it varies and it is changing. Some developer tools and AI products read llms.txt files; others don’t say whether they do. The major AI assistants rely mostly on their own crawling and on search indexes. That is why we treat llms.txt as one small part of being AI-ready, alongside the things that clearly matter: crawlable pages, structured data, consistent facts and a good reputation elsewhere on the web.
How it differs from robots.txt and sitemaps
The three files do different jobs:
- robots.txt tells crawlers what they may and may not access
- sitemap.xml lists every page you want found
- llms.txt summarises what matters most, in plain language
Our approach
Every ExIQ Web site includes an llms.txt and an llms-full.txt, generated from the same data as the pages so the facts always match. You can read ours at exiq.com.au/web/llms.txt.