# ============================================================
# corpdev.org — AI Bot Strategy: Inference YES, Training NO
# Updated: March 2026
# ============================================================

# --- TIER 1: AI Search/Inference Bots (ALLOW) ---
# These power AI search products that cite sources and link back

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: AzureAI-SearchBot
Allow: /

# --- TIER 2: Search Engine Bots (ALLOW) ---
# Traditional search + their AI features

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: PetalBot
Allow: /

# FacebookBot = link preview cards on Facebook/Instagram/WhatsApp (NOT training)
# Meta-ExternalAgent = Meta AI training bot (BLOCKED below)
User-agent: FacebookBot
Allow: /

User-agent: GoogleOther
Allow: /

# --- BLOCKED: Training-Only Bots (No attribution, no traffic) ---

User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Omgilibot
Disallow: /

# --- BLOCKED: SEO Tool Bots ---

User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: MJ12bot
Disallow: /

# --- Default: Allow everything else ---

User-agent: *
Allow: /
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/

# Sitemap
Sitemap: https://www.corpdev.org/sitemap_index.xml