User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

Sitemap: https://raspberry.tips/sitemap_index.xml

# -----------------------------------------------
# AI Training Crawlers - blocked
# (scrape content for model training without attribution or traffic)
# -----------------------------------------------

# OpenAI - training crawler
User-agent: GPTBot
Disallow: /

# Anthropic - training crawler
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

# Google - Gemini/Bard training (Allow: Gemini grounding cites + links sources)
User-agent: Google-Extended
Allow: /

# Common Crawl - base dataset for many AI models
User-agent: CCBot
Disallow: /

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /

# Meta
User-agent: FacebookBot
Disallow: /

# Meta - AI training crawler
User-agent: Meta-ExternalAgent
Disallow: /

# Apple - AI training opt-out (Applebot for Siri/Spotlight stays allowed)
User-agent: Applebot-Extended
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

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

# Diffbot - AI data extraction
User-agent: Diffbot
Disallow: /

# Omgili / Webz.io
User-agent: omgili
Disallow: /
User-agent: omgilibot
Disallow: /

# ImagesiftBot
User-agent: ImagesiftBot
Disallow: /

# -----------------------------------------------
# AI Search / Assistant Crawlers - allowed
# (bring referral traffic, cite sources)
# -----------------------------------------------

# OpenAI search indexing crawler (separate from ChatGPT-User)
User-agent: OAI-SearchBot
Allow: /

# Perplexity AI - cites sources, drives traffic
User-agent: PerplexityBot
Allow: /

# OpenAI browsing plugin (ChatGPT real-time search)
User-agent: ChatGPT-User
Allow: /

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