# Emerging Tech Center — robots.txt
# https://emergingtechcenter.com
#
# We explicitly welcome AI crawlers and search-engine bots. Our content
# is public and we want it to be discoverable, citable, and useful to
# both human researchers and AI assistants.

# ─── All standard search engines ───────────────────────────────────────
User-agent: *
Allow: /
Allow: /api/gigs
Allow: /api/mcp
Disallow: /_vercel/
Disallow: /api/join
Disallow: /api/apply

# ─── AI / LLM crawlers (explicitly allowed) ────────────────────────────
# OpenAI — ChatGPT browsing & training
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic — Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI
User-agent: Google-Extended
Allow: /

# Common Crawl (used by many AI training sets)
User-agent: CCBot
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# Bytespider (TikTok / ByteDance)
User-agent: Bytespider
Allow: /

# DuckAssist
User-agent: DuckAssistBot
Allow: /

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

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

# Diffbot
User-agent: Diffbot
Allow: /

# Amazon (Bedrock, shopping, Alexa)
User-agent: Amazonbot
Allow: /

# Pointers — preferred entry points for AI crawlers
Sitemap: https://emergingtechcenter.com/sitemap.xml