An llms.txt file is a plain Markdown text file you publish at yoursite.com/llms.txt to give AI models like ChatGPT, Claude, and Gemini a short, curated map of your most important pages. It does not control crawling and it does not guarantee rankings or citations. What it does is hand AI a clean summary of your brand and a shortlist of the pages you most want understood, instead of leaving a model to guess from your full site, menus, footers, and duplicate pages included.
A Simple Way to Think About It
The Warehouse vs. The Catalogue
📦 The Unmarked Warehouse
Thousands of boxes stacked floor to ceiling, no labels, no directory. A visitor with ten minutes grabs whatever is closest, not necessarily your best stock.
📋 The One-Page Catalogue
Same warehouse, but a single sheet taped to the front door lists exactly which boxes hold the good stuff. The visitor still walks the whole building, but now knows where to look first.
That catalogue sheet is what llms.txt does for your website. The next section covers exactly what belongs on it.
Who This Guide Is For
This is written for Malaysian business owners, marketers, and developers who want their brand understood and cited accurately by AI tools. It covers what an llms.txt file is, how it differs from robots.txt, what actually goes inside one, and where its limits are. It does not cover training your own model or building AI features into your product.
What Is an llms.txt File?
An llms.txt file is a Markdown document at your domain root that summarises your site and links to your most important pages, so an AI model can quickly work out what you do and which of your pages to trust. A large website can bury a model in navigation menus, footers, and near-duplicate content. llms.txt cuts through that by handing over a short, human-written guide to the pages that actually matter. A companion file, llms-full.txt, can hold the full text of those key pages for models that want the complete content in one place rather than following links.
The format was proposed in 2024 by Jeremy Howard of Answer.AI and is documented at llmstxt.org. It is worth the ten minutes because AI has become a real discovery channel: ChatGPT alone reached around 1 billion monthly users in 2026, and by early 2026 roughly 68% of Google searches ended without a click as AI-generated answers took over the top of the results page. Shaping how AI understands your business is no longer a nice-to-have.
Not sure whether AI crawlers can actually reach and read your best content? Newnormz runs a free SEO audit and website health check that pinpoints exactly what is holding your rankings and AI visibility back through our SEO service.
llms.txt vs robots.txt: What Is the Difference?
These two files sound similar and sit in the same location on your domain, but they do different jobs for different audiences.
| Aspect | robots.txt | llms.txt |
|---|---|---|
| Purpose | Controls what crawlers may access | Guides AI models to your key content |
| Audience | Search engine crawlers | Large language models |
| Format | Directives (Allow, Disallow) | Human-readable Markdown |
| Location | yoursite.com/robots.txt | yoursite.com/llms.txt |
| Status | Long-established standard | Proposed in 2024, growing adoption |
What Goes Inside an llms.txt File?
The proposed format is deliberately simple. A typical file includes an H1 with your site or brand name, a short blockquote summary of what your business does, grouped sections of links (for example Services, Guides, About) each with a one-line description, and an optional “Optional” section for secondary links a model can skip when it is short on space. A basic example looks like this:
# Newnormz > A Malaysian SEO agency helping brands rank on Google and get found by AI tools. ## Services - [SEO Services](https://www.newnormz.com.my/seo-service-malaysia/): SEO for Malaysian businesses - [Local SEO](https://www.newnormz.com.my/local-seo-malaysia/): ranking for city and suburb searches ## Guides - [Blog](https://www.newnormz.com.my/blog/): guides on SEO, Google Ads, and AI search
How to Create an llms.txt File: 4 Steps
1. List your most important pages
Choose the pages you want AI to understand and cite: core service pages, flagship guides, your About page. Aim for quality over quantity. Ten strong pages beat a hundred mediocre ones.
2. Write it in Markdown
Add your brand name as an H1, a one-line summary as a blockquote, then grouped links with short descriptions, following the example above.
3. Upload it to your root
Publish the file so it is reachable at yoursite.com/llms.txt, the same place robots.txt sits. On WordPress, a plugin or a simple file upload through your host handles this in a few minutes.
4. Keep it updated
Refresh it whenever you add a key page or change your positioning, so AI is always working from your latest, most accurate summary rather than something you wrote a year ago.
Example: A Sample llms.txt File
Here is a fuller llms.txt for a fictional Kuala Lumpur skincare brand, Suriya Skin, to show how the pieces fit together:
# Suriya Skin > A Kuala Lumpur skincare brand making gentle, dermatologist-tested products for humid tropical weather. ## Core pages - [Shop All Products](https://www.suriyaskin.my/shop/): full range of cleansers, serums, and moisturisers - [About Suriya Skin](https://www.suriyaskin.my/about/): our story, ingredients, and manufacturing standards - [Skincare Journal](https://www.suriyaskin.my/journal/): guides on tropical skincare, acne, and sun care - [Contact and Stockists](https://www.suriyaskin.my/contact/): where to buy and how to reach us
This file lives at the site root, reachable at suriyaskin.my/llms.txt, the same way robots.txt does. It gives an AI model the brand name, a one-line summary, and a short, curated list of the pages the business most wants understood, so tools like ChatGPT and Gemini can describe Suriya Skin accurately without wading through the entire site.
Common Mistakes to Avoid
| Mistake | Why It Hurts |
|---|---|
| Treating it as a ranking hack | It is a curation aid, not a shortcut past strong content and authority |
| Listing every page on your site | A bloated file defeats the purpose. Point only to your best pages |
| Writing vague one-line descriptions | Models cannot tell what a page offers if the description does not say |
| Letting the file go stale | An outdated file gives AI outdated information about your brand |
| Blocking the listed pages elsewhere | Make sure pages in llms.txt are actually crawlable and not disallowed in robots.txt |
Does llms.txt Actually Work?
Be honest with yourself here. No major AI provider has publicly confirmed that it uses llms.txt as a ranking or citation signal, so this is not a guaranteed win. What it is, is cheap and sensible: a clear, curated summary of your brand that can only help a model describe you accurately, never hurt it. Treat llms.txt as a forward-looking add-on sitting on top of the fundamentals: strong content, clear site structure, and real topical authority, the areas where an SEO agency in Malaysia and answer engine optimization work actually move the needle.
Frequently Asked Questions
What is an llms.txt file?
An llms.txt file is a Markdown text file at your website root that gives AI models a curated guide to your most important pages. It summarises your business and links to key content so tools like ChatGPT and Gemini can understand and cite you more accurately.
Is llms.txt the same as robots.txt?
No. Robots.txt tells search crawlers what they may access. llms.txt is a human-readable guide that tells AI models what content matters and where to find it. They serve different audiences and can sit on the same site side by side.
Does Google or ChatGPT officially use llms.txt?
No major AI vendor has publicly confirmed it as an official signal. It is a proposed standard from 2024 with growing adoption. Because it costs almost nothing to add and can only help how AI understands your brand, many businesses adopt it as a sensible precaution.
Where do I put the llms.txt file?
Place it at your domain root so it is reachable at yoursite.com/llms.txt, exactly like robots.txt. Write it in plain Markdown with your brand name, a short summary, and grouped links to your most important pages.
Will llms.txt improve my SEO?
Not directly. It is aimed at AI models, not traditional rankings. Your SEO still depends on content quality, structure, links, and technical health. Treat llms.txt as a complement to that work, not a replacement for it.
The Bottom Line
llms.txt is a small, low-cost step that gives AI a clean guide to your brand, but it will not replace strong content or real authority. Get the fundamentals right first, then treat this as the ten-minute extra it is.
Can AI tools actually find and understand your site?
Get a Free Audit of Your Site’s Crawlability, Structure, and AI Visibility
Newnormz has run SEO campaigns across F&B, healthcare, ecommerce, and local services in Malaysia, backed by a performance guarantee of 70 percent of targeted keywords on Google’s first page.
30 minutes, no obligation, no jargon.
Bryan Tan is an SEO Specialist and CEO at Newnormz, helping hundreds of businesses achieve first-page rankings on Google. With a passion for driving organic growth, Bryan blends innovative strategies with hands-on experience to optimize websites for maximum visibility. Always at the forefront of the latest SEO insights and trends, he consistently adapts to the evolving digital landscape.
