# robots.txt for AI Agent TR
# Updated: 2026-06-29

# ===================================
# General Rules
# ===================================
# Both Turkish (root) and English (/en/) content are fully crawlable.
# hreflang alternates are declared in sitemap.xml via xhtml:link.
User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /*?s=
Disallow: /*?search=
Disallow: /?s=
Disallow: /docs/_mintlify/
Disallow: /docs/.mintlify/
# Homepage redesign preview (temporary — remove on production cutover)

# ===================================
# AI Crawlers - LLM Training & Search
# ===================================

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

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

User-agent: Claude-Web
Allow: /

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

# Microsoft Copilot / Bing AI
User-agent: BingPreview
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

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

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

# Bytedance
User-agent: ByteSpider
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

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

# Common Crawl
User-agent: CCBot
Allow: /

# ===================================
# Sitemaps
# ===================================
Sitemap: https://aiagenttr.com/sitemap.xml
Sitemap: https://aiagenttr.com/sitemap-blog.xml
Sitemap: https://aiagenttr.com/docs/sitemap.xml