You probably know about robots.txt, the file that tells crawlers which URLs they may fetch. LLMs.txt is different: it is an emerging Markdown proposal for giving AI tools and agents a concise guide to the most important information on your site.
As AI systems increasingly pull information from websites to answer questions, the practical problem is context. A site may have dozens of pages, navigation, scripts, forms, and marketing copy. LLMs.txt gives you a short, curated summary and links to the pages that matter most.
What it does
An LLMs.txt file sits at the root of your website (yourbusiness.com/llms.txt) and provides structured information in plain Markdown. It can tell language models and AI agents:
- What your business is and does
- How you want to be described
- What information is accurate and current
- What topics you're an authority on
- Contact information and service areas
Pro Tip
Think of LLMs.txt as a briefing document for AI. Instead of letting language models piece together information from your various web pages, you give them a clear, authoritative summary.
Why this matters for GEO
AI systems like ChatGPT and Claude are constantly improving how they gather and verify information. They are looking for authoritative sources, and a concise source map can help when a model or agent is able to fetch it. LLMs.txt does not replace crawlable pages, structured data, or third-party proof. It gives those systems a cleaner starting point.
"If an AI is deciding how to describe your business in a recommendation, you want it pulling from information you've explicitly provided rather than inferring from scattered website content."
What goes in an LLMs.txt file
The format is still evolving, but typical contents include:
Business identity. Your official name, what you do, your primary category.
Service information. What services you offer, what service areas you cover, what makes you different.
Reputation summary. Your aggregate ratings, review counts, notable achievements.
Contact information. Phone, email, address, hours.
Preferred descriptions. How you want AI to describe your business when recommending it.
Update frequency. How often this information changes, so AI systems know when to refresh.
Example structure
```
Family-owned plumbing company serving Austin, Texas with emergency repairs, water heater service, drain cleaning, and remodel plumbing.
Canonical facts:
- Official name: Smith Plumbing
- Category: Plumbing services
- Founded: 2005
- Service area: Austin, TX and surrounding areas within 30 miles
- Phone: 512-555-0123
- Website: https://smithplumbing.com
Core Pages
- Homepage: Services, service area, reviews, and booking.
- Emergency Plumbing: 24/7 emergency service details.
- Water Heaters: Installation and repair details.
Services
- Emergency plumbing repairs (24/7)
- Water heater installation and repair
- Drain cleaning
- Bathroom and kitchen remodeling
Optional
- Privacy Policy: Privacy details.
```
Adoption status
LLMs.txt is a newer proposal and not universally supported. Some AI tools, agents, documentation systems, and directories know how to use it; many ranking and retrieval systems have not publicly committed to it.
Important
Treat LLMs.txt as a low-effort context layer, not a magic traffic lever. The fundamentals still matter more: crawlable pages, accurate schema, consistent citations, strong reviews, and third-party proof.
Even if not every AI reads it today, the file serves as a useful canonical reference for your business information. That alone makes it worth maintaining for many local businesses.
Further Reading
- The llms.txt Specification. Original proposal and format documentation for llms.txt
- Meet llms.txt: A Proposed Standard for AI Website Content. Search Engine Land's coverage of the emerging standard
- What Is llms.txt? Breaking Down the Skepticism. Mintlify's analysis of the llms.txt standard
- What Is LLMs.txt & Should You Use It?. Semrush's practical guide to implementation
Amadeus Peterson is the CTO of Cheers, the GEO platform for local service businesses.