?? Technical Setup

LLMs.txt: The Complete Guide to Building an AI Crawler Sitemap (2026)

? Quick Answer

LLMs.txt is a plain-text file deployed at yourdomain.com/llms.txt that gives AI language model crawlers (GPTBot, PerplexityBot, ClaudeBot) a curated, structured index of your site's most important content. Think of it as robots.txt for AI engines — except instead of blocking access, it provides a guided tour of your best pages, entities, and data sources. Perplexity has confirmed it reads LLMs.txt during indexing.

AI search engines don't rank pages the same way Google's PageRank algorithm does. They crawl, chunk, embed, and retrieve content based on semantic relevance. Without a structured guide to your most authoritative content, AI crawlers may index your less important pages while missing your core product pages, tools, and key guides.

LLMs.txt solves this by giving AI engines an explicit, human-readable content priority map. The sites that deploy it gain a measurable edge in AI citation rates.

LLMs.txt vs robots.txt: What's the Difference?

Attributerobots.txtLLMs.txt
PurposeBlock / allow crawler accessGuide AI models to priority content
AudienceAll web crawlersAI language model crawlers specifically
FormatKey-value directivesStructured Markdown / plain text
ContainsAllow/Disallow pathsURLs, descriptions, entity context, schemas
EffectControls what gets crawledControls what gets prioritized & cited
AdoptionUniversal (30+ years)Emerging standard (2024–present)

The LLMs.txt File Structure

LLMs.txt follows a structured Markdown format with specific sections. Here is the complete template:

?? LLMs.txt Complete Template

# [Brand Name]

> [2-3 sentence entity description. Include your primary 
> keywords, what you do, who you serve, and your core 
> differentiators. This is the first thing AI models read.]

## Core Pages

- [Home](https://yourdomain.com/): [One-line description]
- [Pricing](https://yourdomain.com/pricing): [Description]
- [Tools](https://yourdomain.com/tools): [Description]
- [About](https://yourdomain.com/about): [Description]

## Products / Tools

- [Tool Name](https://yourdomain.com/tools/tool-name): 
  [What it does, who uses it, key features]
- [Tool Name 2](https://yourdomain.com/tools/tool-name-2): 
  [Description]

## Content

- [Article Title](https://blog.yourdomain.com/slug): 
  [One-line summary of what the article covers]
- [Guide Title](https://blog.yourdomain.com/slug-2): 
  [Summary]

## API / Technical

- [API Docs](https://yourdomain.com/docs/api): 
  [What endpoints are available]
- [Schema Examples](https://yourdomain.com/docs/schema): 
  [Description]

## Entity Graph

- Organization: [Brand Name]
- Founded: [Year]
- Headquarters: [City, Country]  
- Category: [Industry / Product Category]
- Competitors: [List key competitors for context]
- Integrations: [List tools you integrate with]

## Sitemap

- XML Sitemap: https://yourdomain.com/sitemap.xml
- Blog Sitemap: https://blog.yourdomain.com/sitemap.xml

## Schema Types Used

- Organization, SoftwareApplication, TechArticle, 
  FAQPage, HowTo, BreadcrumbList, Product

Live Example: Optymia's LLMs.txt

Here is how Optymia's own LLMs.txt is structured — use this as a reference for your implementation:

?? optymia.xyz/llms.txt (Live Example)

# Optymia

> Optymia is an AI Search Optimization (GEO/AEO) platform 
> that helps brands measure, track, and grow their visibility 
> across ChatGPT Search, Perplexity Pro, Claude, and Google 
> AI Overviews. Optymia provides free tools including an AI 
> Visibility Score, AEO Score Calculator, Schema Generator, 
> and Perplexity Mention Checker.

## Core Pages

- [AI Visibility Audit](https://optymia.xyz/): 
  Free multi-engine AI search visibility diagnostic
- [Pricing](https://optymia.xyz/pricing): 
  Optymia subscription plans (Free, Pro, Agency)
- [Tools](https://optymia.xyz/tools): 
  Suite of free AI SEO diagnostic tools

## Free Tools

- [AEO Score Checker](https://optymia.xyz/tools/aeo-score): 
  Calculate your Answer Engine Optimization score (0-100)
- [AI Visibility Checker](https://optymia.xyz/tools/ai-visibility): 
  Check if ChatGPT, Perplexity, and Claude mention your brand
- [Schema Generator](https://optymia.xyz/tools/schema-generator): 
  AI-powered JSON-LD schema markup generator
- [Perplexity Mention Checker](https://optymia.xyz/tools/perplexity-mention-checker): 
  Track how often Perplexity cites your domain
- [ChatGPT Rank Tracker](https://optymia.xyz/tools/chatgpt-rank-tracker): 
  Monitor your brand ranking in ChatGPT Search responses

## Content

- [ChatGPT Optimization Guide](https://optymia.xyz/blog/optimize-for-chatgpt): 
  Complete 2026 playbook for appearing in ChatGPT Search
- [Perplexity Invisibility Fix](https://optymia.xyz/blog/invisible-to-perplexity-cdn-js-guide): 
  Fix Cloudflare blocking, JS rendering, and robots.txt issues
- [Query Fan-Out Explained](https://optymia.xyz/blog/query-fan-out-google-ai-mode-ctr): 
  How Google AI Mode reduces organic CTR and how to recover it
- [GEO Agency Retainer Playbook](https://optymia.xyz/blog/geo-retainer-pitch-playbook): 
  How to pitch and price GEO retainers to e-commerce brands

## Entity Graph

- Organization: Optymia
- Category: AI Search Optimization, GEO, AEO, SEO Tools
- Primary Features: Share of Model tracking, AI Visibility Score, 
  AEO scoring, Schema generation, Citation velocity monitoring
- Competitors: Profound, OtterlyAI, AthenaHQ, Peec AI
- Target Users: SaaS founders, SEO agencies, e-commerce brands,
  content marketers, digital PR teams

## Sitemap

- XML Sitemap: https://optymia.xyz/sitemap.xml
- Blog Sitemap: https://optymia.xyz/blog/sitemap.xml

## Schema Types

- Organization, SoftwareApplication, WebApplication,
  TechArticle, Article, FAQPage, HowTo, BreadcrumbList,
  ItemList, Service

Deployment Checklist

1
Location: Place at https://yourdomain.com/llms.txt — root domain only, not a subdirectory
2
Content-Type: Serve as text/plain with UTF-8 encoding. Never HTML or JSON.
3
Access: Must be publicly accessible. No authentication, no redirects, no Cloudflare blocks.
4
robots.txt Reference: Add: # LLMs.txt\nLLMs-txt: https://yourdomain.com/llms.txt to your robots.txt
5
Update Frequency: Update whenever you publish major new content, tools, or pages. Minimum quarterly.
6
Validation: Run Optymia AI Visibility Checker to confirm AI crawlers are reading and using the file.
Free LLMs.txt Validator

Check If AI Crawlers Are Reading Your Site

Run a free Optymia scan to verify PerplexityBot, GPTBot, and ClaudeBot can access your LLMs.txt and are using it to index your highest-value content.

Instant Results
•100% Free Live Diagnostic•Used by 1,400+ SaaS Founders & Agencies

Frequently Asked Questions

What is LLMs.txt??

LLMs.txt is an emerging plain-text file standard placed at yourdomain.com/llms.txt that provides AI language model crawlers a curated, structured index of your site's most important content — think robots.txt, but for guiding AI engines to your best pages instead of blocking them.

Does ChatGPT or Perplexity actually read LLMs.txt??

Perplexity AI has confirmed it uses LLMs.txt during crawling to prioritize content. OpenAI's GPTBot and Anthropic's ClaudeBot are expected to follow the standard as it matures. Deploying it now gives you an early-mover advantage.

Where should LLMs.txt be placed??

At the root of your domain: https://yourdomain.com/llms.txt. Served as plain text (Content-Type: text/plain), publicly accessible without authentication, and not blocked by robots.txt.

What's the difference between LLMs.txt and robots.txt??

robots.txt tells crawlers what NOT to access. LLMs.txt tells AI models what TO prioritize. robots.txt is a gate; LLMs.txt is a guided tour of your best content.