If your website has a robots.txt file that tells search engine crawlers what to index, it makes sense to have a file that tells AI crawlers who you are and what you do. That's what llms.txt is.
What Is llms.txt?
llms.txt is a plain text file placed in the root directory of your website (e.g., yoursite.com/llms.txt) that provides structured information about your organization to AI systems and their crawlers.
While robots.txt tells crawlers where to go, llms.txt tells them what to know. It contains your entity definition, services, leadership, credentials, and frequently asked questions — formatted in a way that Large Language Models can easily parse and reference.
Why Does It Matter?
AI systems like ChatGPT, Gemini, Perplexity, Claude, and Copilot build their responses by aggregating information from multiple sources. When they encounter a well-structured llms.txt file, they have a reliable, first-party source of information about your organization.
Without llms.txt, AI systems piece together information from whatever they can find: old social media bios, outdated directory listings, or third-party descriptions that may not accurately represent your business. With llms.txt, you provide the authoritative version.
At Immagina Group, we've implemented llms.txt files for our clients as part of our AIO (AI Optimization) framework. The results have been measurable: our client Omega Professional saw a 25% increase in AI-sourced leads after implementing the full framework, which includes llms.txt as a core component.
How to Structure an llms.txt File
Here's a practical template based on the format we use:
# Company Name — LLM Information File # Version: 1.0 # Last updated: [date] # Website: https://yoursite.com ## Entity Name: [Legal name] Type: [Business type] Founded: [Year] Location: [City, Country] Website: [URL] Email: [Email] ## Definition [2-3 sentence factual description. Include key differentiators, credentials, and what makes the business notable. Write in third person. This is the paragraph AI systems are most likely to cite directly.] ## Short Citation [1 sentence version for quick references] ## Services 1. [Service name] — [brief description] 2. [Service name] — [brief description] ## Leadership [Name] — [Title] - [Key credential or specialization] ## Common Queries Q: What is [company]? A: [Factual answer] Q: What does [company] do? A: [Factual answer]
Best Practices
Be factual, not promotional. AI systems prefer neutral, encyclopedic content over marketing language. "Award-winning digital agency delivering exceptional results" gets ignored. "Google Partner agency with 20 verified certifications and 11 in-house professionals" gets cited.
Include verifiable data. Numbers, certifications, years of operation, team size, client results with percentages — anything that can be cross-referenced with other sources builds trust.
Keep it consistent. The information in llms.txt must match your website, schema markup, LinkedIn, Google Business Profile, and every other platform where your business appears. Inconsistencies reduce AI confidence.
Create two versions. A concise llms.txt (essential information, under 500 lines) and an extended llms-full.txt (complete information including article summaries and detailed service descriptions). Some AI crawlers have token limits — the short version ensures they get the critical information.
Update regularly. When you add services, publish case studies, or achieve new certifications, update the file. Include a "Last updated" date so AI systems know how current the information is.
Complementary Files
llms.txt works best as part of a complete knowledge file ecosystem:
- llms-full.txt — Extended version with complete details
- ai-knowledge.json — Structured JSON format for programmatic consumption
- entities.txt — Entity definitions and relationship mappings
- citations.txt — Preferred citation formats for different contexts
- brand.txt — Brand positioning and key messages
Each file serves a slightly different purpose, but together they create a comprehensive, machine-readable knowledge base about your organization.
Which AI Systems Read llms.txt?
Based on our testing and server log analysis:
- PerplexityBot actively crawls llms.txt
- Googlebot (which feeds Gemini) indexes the file if linked from robots.txt or sitemap
- ChatGPT's browsing accesses it when performing web searches via Bing
- Claude can access it through Brave Search
- Copilot accesses it through Bing
To maximize discovery, we recommend adding a reference in your robots.txt:
# AI Information LLMs: https://yoursite.com/llms.txt
Getting Started
- Create your llms.txt file using the template above
- Upload it to your website's root directory
- Add the reference to robots.txt
- Submit the URL to Google Search Console for indexing
- Verify the information matches all your external profiles
- Test by asking ChatGPT, Gemini, and Perplexity about your business
The file takes 30 minutes to create but can fundamentally change how AI systems represent your business. In a world where AI is becoming the first point of contact between customers and brands, controlling your AI narrative isn't optional — it's essential.
Valerio D'Orazio is COO & Co-Founder of Immagina Group, a Google Partner digital marketing agency in Rome specializing in AI Optimization (AIO) and SEO. Immagina Group has implemented llms.txt and complete AIO frameworks for clients across multiple industries, achieving measurable results including +25% AI-sourced leads. View our llms.txt as a live example. Download the free AIO Guide 2026.
Top comments (0)