# Robots.txt for https://usesparrow.com
# Updated: 2026-03-24

# Allow all crawlers by default
User-agent: *
Allow: /
Disallow: /admin
Disallow: /api/
Disallow: /file/
Disallow: /sign-in
Disallow: /logout
Disallow: /onboarding
Disallow: /pay
Disallow: /email
Disallow: /render
Disallow: /inspect
Disallow: /questionaires
Disallow: /v2
Disallow: /sms
Disallow: /forgot-password
Disallow: /reset-password
Disallow: /.well-known/
Disallow: /local_assets/
Disallow: /brands-app/

# Block specific file types from indexing
Disallow: /*.json$
Disallow: /*.config$

# Allow specific important files
Allow: /sitemap.xml
Allow: /favicon.ico
Allow: /llms.txt

# Google
User-agent: Googlebot
Allow: /
Crawl-delay: 0

# Bing
User-agent: Bingbot
Allow: /
Crawl-delay: 1

# AI Search Crawlers - allowed for search/citation
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Applebot
Allow: /

# AI Training Crawlers - blocked (training only)
User-agent: CCBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Bytespider
Disallow: /

# Sitemaps
Sitemap: https://usesparrow.com/sitemap.xml
Sitemap: https://usesparrow.com/blog/sitemap.xml