# couchcushionphilosopher.com robots.txt
# AI Search Optimized — Updated March 2026
#
# Strategy: Allow AI RETRIEVAL crawlers (powers search results)
#           Block AI TRAINING crawlers (protects content from model training)


# ── Traditional Search Engines ──

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /


# ── AI RETRIEVAL Crawlers — ALLOW ──
# These power real-time AI search results (ChatGPT, Claude, Perplexity, etc.)

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: YouBot
Allow: /

User-agent: PhindBot
Allow: /

User-agent: Cohere-ai
Allow: /

User-agent: Applebot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /


# ── AI TRAINING Crawlers — BLOCK ──
# These collect data for model training, not search results

User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: img2dataset
Disallow: /


# ── Default ──

User-agent: *
Allow: /

# Protected content
Disallow: /creators
Disallow: /assets/downloads/arc-*

Sitemap: https://couchcushionphilosopher.com/sitemap.xml

# AI-readable site description files (informational — not a standard robots.txt directive)
# llms.txt:      https://couchcushionphilosopher.com/llms.txt
# llms-full.txt: https://couchcushionphilosopher.com/llms-full.txt