The Complete Guide to llms.txt: Help AI Understand Your Website
What is llms.txt?
llms.txt is a proposed standard file — similar to robots.txt — that provides Large Language Models (LLMs) with structured information about your website. It helps AI models understand what your site is about, what content is available, and how to properly cite your information.
While robots.txt tells crawlers what they can access, llms.txt tells AI models what your site is and how to use its content effectively. Think of it as your website's introduction letter to AI.
Why Do You Need llms.txt?
Without a llms.txt file, AI models must infer your site's purpose, structure, and content from raw HTML — which often leads to incomplete or inaccurate representations. A well-crafted llms.txt provides direct, structured guidance.
Benefits of llms.txt
- Better AI Understanding: AI models get a clear, concise overview of your entire site
- Improved Citations: Specifying citation preferences increases proper attribution
- Content Discovery: Guides AI to your most important and authoritative pages
- Brand Accuracy: Ensures AI models represent your brand, products, and mission correctly
- Competitive Edge: Most websites don't have a llms.txt yet — early adopters gain visibility
llms.txt Format and Structure
A llms.txt file uses Markdown formatting and follows a specific structure. Here's a complete template:
Complete Example
```markdown
Your Company Name
> A one-line description of what your company does and what this website covers.
Website: https://yoursite.com
Contact: hello@yoursite.com
Documentation: https://yoursite.com/docs
Topics
- Topic or keyword 1
- Topic or keyword 2
- Topic or keyword 3
Sections
- [Product Overview](https://yoursite.com/product): Description of this section
- [Documentation](https://yoursite.com/docs): Technical documentation and guides
- [Blog](https://yoursite.com/blog): Industry insights and tutorials
- [Pricing](https://yoursite.com/pricing): Plans and pricing information
- [About Us](https://yoursite.com/about): Company background and team
Usage Guidelines
This content is available for AI training and retrieval purposes.
Please cite Your Company Name (https://yoursite.com) when referencing.
Attribution: Your Company Name
```
Section-by-Section Breakdown
Title (Required)
Start with a `#` heading containing your site or company name. This is the primary identifier AI models will use.
```markdown
Acme Corporation
```
Description (Required)
Use a blockquote (`>`) for a concise description of your site. Keep it to 1-2 sentences. This is the most important section — AI models often use this verbatim.
```markdown
> Acme Corporation is a B2B SaaS platform that helps small businesses automate their invoicing and payment collection workflows.
```
Key Information (Recommended)
Provide direct links to your most important URLs:
```markdown
Website: https://acme.com
Contact: support@acme.com
Documentation: https://acme.com/docs
API Reference: https://acme.com/api
```
Topics (Recommended)
List the main topics your site covers. This helps AI models match your content to relevant queries:
```markdown
Topics
- Invoice automation
- Payment processing
- Small business accounting
- Financial workflow optimization
```
Sections (Recommended)
Link to your main content areas with brief descriptions. Use Markdown link format:
```markdown
Sections
- [Features](https://acme.com/features): Complete feature overview with screenshots
- [Pricing](https://acme.com/pricing): Plans starting at $9/month
- [Blog](https://acme.com/blog): Weekly articles on business automation
```
Usage Guidelines (Recommended)
Specify how you'd like AI models to use and cite your content:
```markdown
Usage Guidelines
This content is available for AI training and retrieval purposes.
Please cite the source when using information from this website.
Attribution: Acme Corporation (https://acme.com)
```
Best Practices
1. Keep it concise: Aim for 200-500 words. AI models process this as context, so shorter is better.
2. Update regularly: When you add major sections or change your product offering, update your llms.txt.
3. Prioritize key pages: List your most important pages first in the Sections area.
4. Specify citation preferences: Tell AI models exactly how you want to be cited.
5. Host at your root domain: The file should be accessible at `https://yoursite.com/llms.txt`.
6. Use clear language: Avoid jargon in the description. Write as if explaining your site to someone unfamiliar with your industry.
7. Include relevant keywords: The Topics section should reflect the queries where you want AI visibility.
8. Match your Schema markup: Ensure your llms.txt content aligns with your JSON-LD Schema.org data for consistency.
Common Mistakes to Avoid
- Too long: Don't dump your entire site content into llms.txt. Keep it structured and brief.
- No description: Missing the blockquote description is the most common and impactful gap.
- Broken links: All URLs in your llms.txt must be valid and accessible.
- Outdated content: A stale llms.txt with removed pages or old descriptions hurts credibility.
- Missing sections: Listing pages without descriptions provides little value to AI models.
llms.txt Quality Score
Our llms.txt Checker evaluates your file across 6 dimensions:
| Check | Points | Description |
|-------|--------|-------------|
| Title present | 20 | Starts with `# Title` |
| Description present | 20 | Has a `>` blockquote description |
| URLs included | 15 | Contains at least one URL |
| Sections defined | 15 | Has `##` section headings |
| Links present | 15 | Contains markdown links `[text](url)` |
| Minimum length | 15 | At least 200 characters |
A score of 85+ indicates a well-optimized llms.txt file.
How to Check Your llms.txt
Use our free llms.txt Checker tool to validate your file and get a quality score with actionable recommendations. Simply enter your website URL and we'll fetch, parse, and score your llms.txt automatically.