# robots.txt for ronntorossian.com
# AI-friendly site — explicitly allows major AI crawlers
# so the site can be cited in ChatGPT, Claude, Perplexity, Gemini,
# Google AI Overviews, and other generative engines.
#
# Last updated: May 2026
# Important: do NOT let Cloudflare's "Manage robots.txt for me"
# feature override this file. Disable that setting in Cloudflare
# dashboard before deploying.

# ============================================================
# Default rules — allow all standard crawlers
# ============================================================

User-agent: *
Allow: /
Disallow: /admin
Disallow: /admin/
Disallow: /api/
Disallow: /_serverFn/
Disallow: /?s=
Disallow: /search?
Disallow: /*?utm_
Disallow: /*?fbclid=
Disallow: /*?gclid=

# ============================================================
# AI Crawlers — Explicitly ALLOWED (we want to be cited)
# ============================================================

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI (separate from Googlebot — used for Bard/Gemini/AI Overviews training)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: GoogleOther-Image
Allow: /

User-agent: GoogleOther-Video
Allow: /

# Common Crawl (used by many LLMs as training source)
User-agent: CCBot
Allow: /

# ByteDance / TikTok / Doubao
User-agent: Bytespider
Allow: /

# Amazon AI
User-agent: Amazonbot
Allow: /

# Apple AI / Siri
User-agent: Applebot-Extended
Allow: /

User-agent: Applebot
Allow: /

# Meta AI / Facebook AI
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: meta-externalfetcher
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

User-agent: cohere-training-data-crawler
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

# DiffBot (used for knowledge graphs)
User-agent: DiffBot
Allow: /

# You.com
User-agent: YouBot
Allow: /

# DuckAssist (DuckDuckGo AI)
User-agent: DuckAssistBot
Allow: /

# Brave AI
User-agent: BraveSearch
Allow: /

# Kagi
User-agent: KagiBot
Allow: /

# Aleph Alpha (European LLM)
User-agent: Aleph-Alpha-Bot
Allow: /

# AI2 (Allen Institute for AI)
User-agent: ai2bot
Allow: /

# ============================================================
# Standard search engines (kept explicit for clarity)
# ============================================================

User-agent: Googlebot
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /
Crawl-delay: 2

User-agent: Baiduspider
Allow: /

# ============================================================
# Sitemaps
# ============================================================

Sitemap: https://ronntorossian.com/sitemap.xml