# NOTE ON EDITING THIS FILE
# A crawler that finds a block matching its own name uses ONLY that block and
# ignores "User-agent: *" entirely. So every named block below has to repeat
# the shared Disallow list. If you add a path to the wildcard block, add it to
# the named blocks too, or those crawlers will happily index it.

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/
# Tailored landing pages, link-only, never indexed.
Disallow: /bruin+kashkick
Disallow: /bruin%2Bkashkick
Disallow: /bruin+fluent
Disallow: /bruin%2Bfluent

# Build assets are deliberately crawlable. Google's guidance is not to block
# the CSS/JS a page needs to render, and the previous Disallow: /_nuxt/ did not
# reduce the traffic anyway: the bots hitting it hardest ignore robots.txt.
Allow: /_nuxt/

# LLM crawler indexes
Allow: /llms.txt
Allow: /llms-full.txt

# ---------------------------------------------------------------------------
# AI crawlers, assistants, and AI-training opt-out tokens.
# Named explicitly so our stance is unambiguous: these are allowed, including
# the tokens (Google-Extended, Applebot-Extended) whose only function is to
# opt out of AI training. We want to be cited, so we opt in.
# ---------------------------------------------------------------------------

User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: YouBot
User-agent: cohere-ai
User-agent: meta-externalagent
Allow: /
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /_nuxt/
Disallow: /admin/
Disallow: /api/
Disallow: /bruin+kashkick
Disallow: /bruin%2Bkashkick
Disallow: /bruin+fluent
Disallow: /bruin%2Bfluent

# Sitemap
Sitemap: https://getbruin.com/sitemap.xml