# robots.txt — AI Crawler Strategy for commoncause.org
# Updated: March 2026
# Strategy: Allow AI search/retrieval bots (improves AI visibility)
#           Block AI training crawlers (protects content from model training)
#
# See: https://www.commoncause.org/llms.txt for structured AI-readable info

# ─── Traditional search engines (allow all) ───────────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# ─── Anthropic (Claude) — 3-tier strategy ─────────────────────────────────────
# ClaudeBot     = training data collection  → BLOCK
# Claude-SearchBot = search index building  → ALLOW (improves Claude AI answers)
# Claude-User   = real-time user queries    → ALLOW (improves Claude AI answers)

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Legacy Anthropic crawlers (now deprecated, keep blocked)
User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# ─── OpenAI (ChatGPT) — 3-tier strategy ──────────────────────────────────────
# GPTBot        = training data collection  → BLOCK
# OAI-SearchBot = ChatGPT search indexing   → ALLOW (improves ChatGPT answers)
# ChatGPT-User  = real-time user queries    → ALLOW (improves ChatGPT answers)

User-agent: GPTBot
Disallow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# ─── Perplexity ───────────────────────────────────────────────────────────────
# PerplexityBot indexes content for Perplexity AI search
# Allowing improves Common Cause visibility in Perplexity answers

User-agent: PerplexityBot
Allow: /

# ─── Google AI ────────────────────────────────────────────────────────────────
# Google-Extended controls AI Overviews and Gemini training
# Allowing improves Common Cause visibility in Google AI Overviews

User-agent: Google-Extended
Allow: /

# ─── Other AI training crawlers (block) ──────────────────────────────────────
User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: YouBot
Disallow: /

# ─── Default: all other bots ──────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-login.php

# ─── Sitemap ──────────────────────────────────────────────────────────────────
Sitemap: https://www.commoncause.org/sitemap.xml