Does llms.txt actually improve AI search visibility?

The evidence is mixed. Over 844,000 websites have implemented llms.txt according to BuiltWith tracking, but no major AI platform has publicly confirmed using it as a retrieval or ranking signal. Google's John Mueller stated in 2025 that no AI system currently uses llms.txt. It is a low-effort, low-risk addition but should not be your primary AI optimization strategy.

How do you create an llms.txt file?

Create a plain-text Markdown file named llms.txt and place it in your website's root directory. Include a brief description of your site, then list your most important pages with titles and URLs. Use Markdown formatting with headers and bullet points. Keep it concise - focus on 10 to 30 of your highest-value pages rather than listing every URL.

What is the difference between llms.txt and robots.txt?

robots.txt tells crawlers which pages they can and cannot access - it controls permissions. llms.txt suggests which pages are most important for AI models to understand your site - it provides guidance. robots.txt is universally respected by all major crawlers. llms.txt is a newer proposal with no confirmed adoption by major AI platforms yet.

How to Use llms.txt for AI Visibility

Q: What is llms.txt?

llms.txt is a plain-text Markdown file placed at your website's root directory (yoursite.com/llms.txt) that provides AI language models with a structured summary of your site's most important content. Proposed by Jeremy Howard of Answer.AI in 2024, it acts as an AI-specific guide directing large language models to your key pages, similar to how robots.txt guides traditional web crawlers.

llms.txt is a plain-text Markdown file placed at your website's root directory (yoursite.com/llms.txt) that provides AI language models with a structured guide to your site's most important content. Proposed by Jeremy Howard of Answer.AI in 2024, the file acts as an AI-specific sitemap - telling large language models which pages matter most, what your site is about, and where to find your key content. Think of it as robots.txt for content prioritization rather than access control.

The concept has gained significant traction - over 844,000 websites have implemented llms.txt according to BuiltWith tracking. However, the actual impact on AI search visibility remains debated.

How Does llms.txt Work?

The file follows a simple Markdown structure placed at your domain root:

# Your Company Name

> Brief description of what your company does and what your site covers.

## Main Content

- [Page Title](https://yoursite.com/page-url): Brief description of what this page covers
- [Another Page](https://yoursite.com/another-page): Description of this content

## Documentation

- [Getting Started](https://yoursite.com/docs/getting-started): Onboarding guide for new users
- [API Reference](https://yoursite.com/docs/api): Complete API documentation

## Blog

- [Key Blog Post](https://yoursite.com/blog/key-post): Description of the article

The structure is intentionally simple. You provide a site description, then list your most important pages organized by category with brief descriptions for each.

Should You Implement llms.txt?

The honest answer: implement it, but do not expect it to be a game-changer.

Arguments for implementing:

Low effort - takes 15 to 30 minutes to create and maintain
Zero risk - the file cannot hurt your visibility
Future-proofing - if AI platforms do adopt it, you are already set
Structured summary - forces you to think about which content matters most
Growing adoption - 844,000+ sites have implemented it, creating momentum toward potential adoption

Arguments for realistic expectations:

No major AI platform has publicly confirmed using llms.txt as a retrieval input
Google's John Mueller stated in mid-2025 that no AI system currently uses llms.txt
A Peec AI analysis found no clear evidence that llms.txt improves AI search visibility in measurable ways
SE Ranking's research similarly found no confirmed impact on citations

The bottom line: llms.txt is a low-effort hedge that costs nothing to implement and might matter in the future. But your primary AI visibility efforts should focus on proven strategies - content structure, crawler access, authority signals, and freshness.

How to Create Your llms.txt File

Step 1: Identify Your Key Pages

Select 10 to 30 of your most important pages. Prioritize:

Pages that define your core product or service
High-traffic content that demonstrates expertise
Pages you most want AI models to cite
Documentation or resources that provide unique value
Key blog posts with original data or insights

Step 2: Write the File

Create llms.txt in your website's root directory with this structure:

# [Your Company Name]

> [One to two sentence description of your company and what your site covers. Be specific about your domain expertise.]

## [Category 1]

- [Page Title](https://yoursite.com/url): [One sentence describing the page's content and value]
- [Another Page](https://yoursite.com/url): [Description]

## [Category 2]

- [Page Title](https://yoursite.com/url): [Description]

Step 3: Create llms-full.txt (Optional)

Some implementations include a companion file llms-full.txt that contains the complete text content of key pages in a single file, making it easy for LLMs to consume your most important content in one request. This is more relevant for technical documentation and API references than for marketing content.

Step 4: Maintain It

Update your llms.txt when you publish significant new content, restructure your site, or deprecate old pages. A quarterly review is sufficient for most sites.

What Else Should You Do for AI Visibility?

llms.txt is one small piece of a comprehensive AI visibility strategy. The higher-impact actions are:

Audit AI crawler access - Ensure GPTBot, ClaudeBot, and other crawlers can reach your content
Structure content for extraction - Use definition-first paragraphs, question-based headings, and concise answer blocks
Add structured data - FAQ schema, article schema, and organization schema help AI models understand your content
Keep content fresh - Content updated within 30 to 90 days is cited more frequently
Build authority signals - Author credentials, cited statistics, and external references increase citation likelihood

At Conbersa, we implement llms.txt as part of our technical GEO setup for clients, but we are transparent that it is a future-proofing measure rather than a proven visibility driver. Focus your primary efforts on the fundamentals - crawler access, content structure, and freshness - that have demonstrated impact on AI citations.