# ── Standard crawlers ────────────────────────────────────────────────────────
User-agent: *
Allow: /

Disallow: /innerdocs/
Disallow: /chatbot-knowledge/
Disallow: /logs/
Disallow: /PhpFunctions/
Disallow: /oldlanding/
Disallow: /extrafiles/
Disallow: /azure/
Disallow: /backupsite/

# ── AI / LLM crawlers — explicitly allowed ───────────────────────────────────
# OpenAI (ChatGPT training + browsing)
User-agent: GPTBot
Allow: /

# OpenAI (ChatGPT on-demand fetch when answering users)
User-agent: ChatGPT-User
Allow: /

# OpenAI (ChatGPT search index)
User-agent: OAI-SearchBot
Allow: /

# Google AI (Gemini, AI Overviews)
User-agent: Google-Extended
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: Claude-Web
Allow: /

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

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

# Common Crawl (used by many LLM training sets)
User-agent: CCBot
Allow: /

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

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

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

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

Sitemap: https://www.asystir.com/sitemap.xml