# Allow all user agents to access everything
User-agent: *
# Content Signals declare how this content may be used:
#   search   = may appear in a search index
#   ai-input = may ground a generated answer (RAG / AI Overviews / chat citations)
#   ai-train = may be used to train or fine-tune a model
# ai-train is yes on purpose: the named AI crawlers below are allowed explicitly,
# so declaring no here would contradict them. Flip both to change the stance.
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Disallow auth/app pages (no SEO value)
Disallow: /login
Disallow: /signup
Disallow: /forgotPassword
Disallow: /resetPassword
Disallow: /onboarding
Disallow: /api/

# Disallow authenticated app pages
Disallow: /explorer
Disallow: /workspace
Disallow: /trash
Disallow: /shared
Disallow: /profile

# Block Next.js internal assets from crawling (saves crawl budget)
Disallow: /_next/static/chunks/
Disallow: /_next/static/css/
Disallow: /_next/static/media/
Disallow: /_next/data/

# Allow specific search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# Allow AI crawlers for AI Overview / ChatGPT / Perplexity citations
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Allow public assets
User-agent: *
Allow: /images/

# Sitemap
Sitemap: https://thedrive.ai/sitemap.xml

# LLMs
LLMs-Txt: https://thedrive.ai/llms.txt
LLMs-Full-Txt: https://thedrive.ai/llms-full.txt