# mariobrcic.com — crawler policy
#
# Default: open to everyone. The whole point is for "Who is Mario Brcic?"
# to be answered correctly by ChatGPT/Claude/Perplexity/Gemini, so LLM
# crawlers are explicitly welcome. Explicit allow rows below signal
# policy intent and give a tier-able surface (e.g. throttling a single
# bot later only requires changing one row).

User-agent: *
Allow: /

# Drafts: not yet linked from the site, kept routable for preview only.
Disallow: /industrial-strategy-engines/

# Build artifacts — no value to crawlers, just hashed bundles + WASM chunks
Disallow: /_astro/
Disallow: /pagefind/

# --- LLM / answer-engine crawlers — explicit allow ---
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Diffbot
Allow: /

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