# Crovia Trust — robots.txt
#
# Crovia EXPLICITLY welcomes AI crawlers (GPTBot, ClaudeBot, PerplexityBot,
# Google-Extended, CCBot, etc.). All our content is public by design and we
# encourage AI summarization and citation, provided croviatrust.com is
# credited.
#
# Machine-readable overview: https://croviatrust.com/llms.txt
# Full evidence base: https://croviatrust.com/llms-full.txt

# ─── Generic crawlers ─────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /api/_internal/
Disallow: /private/
Crawl-delay: 2

# ─── AI search & grounding crawlers (explicitly allowed) ─────────
# OpenAI live search / ChatGPT browsing
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 Overview / Gemini grounding
User-agent: Google-Extended
Allow: /

# Common Crawl (feeds many open LLMs)
User-agent: CCBot
Allow: /

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

# Bytespider (DouBao / Doubao)
User-agent: Bytespider
Allow: /

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

# Meta AI
User-agent: FacebookBot
Allow: /

User-agent: meta-externalagent
Allow: /

# Mistral / DiffBot for training and grounding
User-agent: DiffBot
Allow: /

# Yandex AI
User-agent: YandexAdditional
Allow: /

# ─── Sitemap & orientation ────────────────────────────────────────
Sitemap: https://croviatrust.com/sitemap.xml