# =========================================================
# robots.txt — VEGA I.T. | https://vegait.com
# Atualizado: 2026-04
# =========================================================

# Regra padrão: todos os crawlers bem-vindos
User-agent: *
Allow: /

# Bloquear pastas de sistema (não indexar internals do Next.js)
Disallow: /_next/
Disallow: /api/
Disallow: /404
Disallow: /500

# Sitemap principal
Sitemap: https://vegait.com/sitemap.xml

# =========================================================
# AI CRAWLERS — Todos explicitamente permitidos para GEO
# (Generative Engine Optimization)
# =========================================================

# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

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

User-agent: anthropic-ai
Allow: /

# Google (Gemini, Bard, Search Generative Experience)
User-agent: Google-Extended
Allow: /

User-agent: Googlebot
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

# Microsoft (Copilot / Bing AI)
User-agent: Bingbot
Allow: /

User-agent: msnbot
Allow: /

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

User-agent: Meta-ExternalFetcher
Allow: /

# Cohere (Command)
User-agent: cohere-ai
Allow: /

# Apple (Siri, Spotlight)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

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

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

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

# Common Crawl (treina muitos modelos)
User-agent: CCBot
Allow: /

# Diffbot (Knowledge Graph)
User-agent: Diffbot
Allow: /

# Scrapy / generic research
User-agent: ia_archiver
Allow: /