# Inqery - Robots.txt
# This file tells search engine crawlers which pages or files they can or can't request from your site.
# Learn more: https://developers.google.com/search/docs/advanced/robots/intro

# Default rules for all crawlers
User-agent: *

# Allow crawling of all main content
Allow: /
Allow: /features/
Allow: /product/
Allow: /compare/
Allow: /pricing/
Allow: /docs/
Allow: /company/
Allow: /blog/

# Allow important assets for proper page rendering
Allow: /assets/css/
Allow: /assets/js/
Allow: /assets/images/
Allow: /favicon.ico

# Disallow administrative and development files
Disallow: /.git/
Disallow: /.cursor/
Disallow: /scripts/
Disallow: /tests/
Disallow: /node_modules/
Disallow: /*.log
Disallow: /*.tmp
Disallow: /*.env
Disallow: /error.html

# Disallow project management and documentation
Disallow: /Agent PM/
Disallow: /*.md
Disallow: /README.md
Disallow: /.gitignore

# Special rules for major search engines

# Google Bot - Full access to main content
User-agent: Googlebot
Allow: /
Allow: /assets/
Crawl-delay: 1

# Bing Bot - Full access
User-agent: Bingbot
Allow: /
Allow: /assets/
Crawl-delay: 1

# Yandex Bot - Full access
User-agent: YandexBot
Allow: /
Allow: /assets/
Crawl-delay: 2

# Facebook Bot (for social sharing)
User-agent: Facebookexternalhit
Allow: /
Allow: /assets/images/

# Twitter Bot (for social sharing)
User-agent: Twitterbot
Allow: /
Allow: /assets/images/

# LinkedIn Bot (for social sharing)
User-agent: LinkedInBot
Allow: /
Allow: /assets/images/

# -----------------------------------------------------------------------------
# AI Crawlers — Policy
# -----------------------------------------------------------------------------
# Training crawlers (no user-facing citations): BLOCK
# -----------------------------------------------------------------------------

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: cohere-ai
Disallow: /

# -----------------------------------------------------------------------------
# AI Answer Engines (citation-driving, high-value B2B discovery): ALLOW
# -----------------------------------------------------------------------------

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: Applebot
Allow: /

# Block aggressive crawlers
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

# XML Sitemap location
Sitemap: https://inqery.com/sitemap.xml

# Additional sitemaps for future use
# Sitemap: https://inqery.com/sitemap-blog.xml
# Sitemap: https://inqery.com/sitemap-docs.xml