# Documentation: https://firmao.pl/llms.txt (AI-readable site overview)
# =============================================================================
# DEFAULT RULE — allow all crawlers
# =============================================================================
User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /wp-json/
# =============================================================================
# SEARCH ENGINE CRAWLERS
# =============================================================================
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: Yandex
Allow: /
User-agent: Applebot
Allow: /
# =============================================================================
# AI MODEL TRAINING CRAWLERS — explicitly allowed
# =============================================================================
# OpenAI (GPT training)
User-agent: GPTBot
Allow: /
# OpenAI (ChatGPT browsing by users)
User-agent: ChatGPT-User
Allow: /
# OpenAI (SearchGPT)
User-agent: OAI-SearchBot
Allow: /
# Anthropic (Claude training)
User-agent: ClaudeBot
Allow: /
# Anthropic (Claude web features)
User-agent: anthropic-ai
Allow: /
# Google (Gemini AI training)
User-agent: Google-Extended
Allow: /
# Perplexity AI
User-agent: PerplexityBot
Allow: /
# Common Crawl (open dataset used by many AI models)
User-agent: CCBot
Allow: /
# Meta AI
User-agent: Meta-ExternalAgent
Allow: /
# Facebook link previews
User-agent: FacebookExternalHit
Allow: /
# You.com AI
User-agent: YouBot
Allow: /
# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
# Amazon AI
User-agent: Amazonbot
Allow: /
# Cohere AI
User-agent: cohere-ai
Allow: /
# ByteDance / TikTok AI
User-agent: Bytespider
Allow: /
# =============================================================================
# SITEMAP & AI FILES
# =============================================================================
Sitemap: https://firmao.pl/sitemap.xml