# Spotless Mynd Robots.txt
# Allow all crawlers for maximum SEO/AEO visibility
# Last updated: 2025-01-18

# =====================================================
# SEARCH ENGINE CRAWLERS
# =====================================================

# Google
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Storebot-Google
Allow: /

# Bing / Microsoft
User-agent: Bingbot
Allow: /

User-agent: msnbot
Allow: /

# Yahoo
User-agent: Slurp
Allow: /

# DuckDuckGo
User-agent: DuckDuckBot
Allow: /

# Yandex
User-agent: YandexBot
Allow: /

# Baidu
User-agent: Baiduspider
Allow: /

# =====================================================
# SOCIAL MEDIA CRAWLERS
# =====================================================

User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Pinterest
Allow: /

User-agent: Slackbot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

# =====================================================
# AI / LLM CRAWLERS - EXPLICITLY ALLOWED
# =====================================================

# 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: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

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

User-agent: Gemini
Allow: /

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

User-agent: FacebookBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Microsoft Copilot
User-agent: Copilot
Allow: /

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

# Neeva (now part of Snowflake)
User-agent: NeevaBot
Allow: /

# Common Crawl (used for training data)
User-agent: CCBot
Allow: /

# Diffbot (AI-powered web data extraction)
User-agent: Diffbot
Allow: /

# =====================================================
# DEFAULT RULES
# =====================================================

User-agent: *
Allow: /
Disallow: /api/
Disallow: /dashboard
Disallow: /admin

# =====================================================
# RESOURCE LOCATIONS
# =====================================================

# Sitemap
Sitemap: https://spotlessmynd.com/sitemap.xml

# LLM/AI Content Files - Machine-readable site information
# Primary LLM content file
LLMS: https://spotlessmynd.com/llms.txt

# Extended LLM content (detailed version)
LLMS-Full: https://spotlessmynd.com/llms-full.txt

# AI transparency file
AI: https://spotlessmynd.com/ai.txt

# Human-readable attribution
Humans: https://spotlessmynd.com/humans.txt

# Crawl-delay (be respectful of server resources)
Crawl-delay: 1