# Crawl policy: answers yes, training no.
# The crawlers that feed an answer someone is reading get the public site;
# the ones that build a training corpus get nothing. Content-Signal states
# the same decision for anything that reads signals rather than group names,
# and ai-train=no is an express reservation of rights under Article 4 of EU
# Directive 2019/790.

User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no,use=reference
Allow: /
Disallow: /api/
Disallow: /app/
Disallow: /en/app/
Disallow: /fr/app/
Disallow: /es/app/
Disallow: /de/app/
Disallow: /pt/app/
Disallow: /zh/app/
Disallow: /onboarding
Disallow: /en/onboarding
Disallow: /fr/onboarding
Disallow: /es/onboarding
Disallow: /de/onboarding
Disallow: /pt/onboarding
Disallow: /zh/onboarding
Disallow: /ce-setup
Disallow: /en/ce-setup
Disallow: /fr/ce-setup
Disallow: /es/ce-setup
Disallow: /de/ce-setup
Disallow: /pt/ce-setup
Disallow: /zh/ce-setup
Disallow: /login
Disallow: /en/login
Disallow: /fr/login
Disallow: /es/login
Disallow: /de/login
Disallow: /pt/login
Disallow: /zh/login
Disallow: /register
Disallow: /en/register
Disallow: /fr/register
Disallow: /es/register
Disallow: /de/register
Disallow: /pt/register
Disallow: /zh/register
Disallow: /auth/
Disallow: /en/auth/
Disallow: /fr/auth/
Disallow: /es/auth/
Disallow: /de/auth/
Disallow: /pt/auth/
Disallow: /zh/auth/
Disallow: /local-mcp
Disallow: /workflows/
Disallow: /billing/
Disallow: /f/
Disallow: /s/
Disallow: /w/embed

# Answer engines. The rules under * do NOT carry over to a named group, so
# the private paths, and the signals, are repeated here rather than
# inherited. Without the repeat these would be the only crawlers allowed to
# fetch the content and the only ones never told what may be done with it.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot
User-agent: YouBot
Content-Signal: search=yes,ai-input=yes,ai-train=no,use=reference
Allow: /
Disallow: /api/
Disallow: /app/
Disallow: /en/app/
Disallow: /fr/app/
Disallow: /es/app/
Disallow: /de/app/
Disallow: /pt/app/
Disallow: /zh/app/
Disallow: /onboarding
Disallow: /en/onboarding
Disallow: /fr/onboarding
Disallow: /es/onboarding
Disallow: /de/onboarding
Disallow: /pt/onboarding
Disallow: /zh/onboarding
Disallow: /ce-setup
Disallow: /en/ce-setup
Disallow: /fr/ce-setup
Disallow: /es/ce-setup
Disallow: /de/ce-setup
Disallow: /pt/ce-setup
Disallow: /zh/ce-setup
Disallow: /login
Disallow: /en/login
Disallow: /fr/login
Disallow: /es/login
Disallow: /de/login
Disallow: /pt/login
Disallow: /zh/login
Disallow: /register
Disallow: /en/register
Disallow: /fr/register
Disallow: /es/register
Disallow: /de/register
Disallow: /pt/register
Disallow: /zh/register
Disallow: /auth/
Disallow: /en/auth/
Disallow: /fr/auth/
Disallow: /es/auth/
Disallow: /de/auth/
Disallow: /pt/auth/
Disallow: /zh/auth/
Disallow: /local-mcp
Disallow: /workflows/
Disallow: /billing/
Disallow: /f/
Disallow: /s/
Disallow: /w/embed

# Training crawlers.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Bytespider
User-agent: Amazonbot
User-agent: meta-externalagent
User-agent: FacebookBot
User-agent: cohere-ai
User-agent: Diffbot
User-agent: ImagesiftBot
User-agent: Omgilibot
User-agent: AI2Bot
Disallow: /

Host: https://livecontext.ai
Sitemap: https://livecontext.ai/sitemap.xml
Sitemap: https://livecontext.ai/compare/sitemap.xml
Sitemap: https://livecontext.ai/for/sitemap.xml
Sitemap: https://livecontext.ai/marketplace/sitemap.xml
Sitemap: https://livecontext.ai/integrations/sitemap.xml
Sitemap: https://livecontext.ai/videos/sitemap.xml