# === Standard crawlers ===
User-agent: *
Allow: /
Allow: /pronounce/
Allow: /blog/
Disallow: /manage
Disallow: /purchase/
Disallow: /auth/

# === AI Search Crawlers — explicitly allowed ===
# ChatGPT / OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Google Gemini
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

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

User-agent: Claude-Web
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

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

# Microsoft Copilot / Bing Chat
User-agent: Applebot-Extended
Allow: /

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

# === Sitemaps ===
Sitemap: https://devglish.com/sitemap-index.xml

# === LLM/AI Agent context ===
# See https://llmstxt.org for specification
# /llms.txt — structured overview for AI agents
# /llms-full.txt — complete product reference with inline content