User-agent: *
Allow: /
Disallow: /admin
Disallow: /admin/
Disallow: /es
Disallow: /es/

# AI Preferences signal is served via HTTP response header (see _headers)
# per IETF AI Preferences draft spec. Format kept here as comment for visibility:
#   Content-Signal: search=yes, ai-train=yes, ai-input=yes

# ── Explicitly allow AI crawlers (GEO signal) ──

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Google (AI surfaces)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Google-CloudVertexBot
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Meta
User-agent: FacebookBot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

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

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

User-agent: cohere-training-data-crawler
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

# AI2
User-agent: AI2Bot
Allow: /

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

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

# Kagi
User-agent: Kagibot
Allow: /

# Huawei Petal
User-agent: PetalBot
Allow: /

# Timpi
User-agent: Timpibot
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# ImageSift
User-agent: ImagesiftBot
Allow: /

# Omgili (Webz.io)
User-agent: omgili
Allow: /

User-agent: omgilibot
Allow: /

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

# LLM content files — see https://getbrazilvisa.com/llms.txt and /llms-full.txt