# GenSight.AI — robots.txt
# Last updated: 2026-05-19

# Default rules for all crawlers
User-agent: *
Allow: /

# Block authenticated and app-internal pages
Disallow: /dashboard.html
Disallow: /benchmarks.html
Disallow: /claim
Disallow: /audit-results
Disallow: /api/
Disallow: /bot-analytics
Disallow: /auth-confirm

# Explicit allowlist for AI training and retrieval crawlers.
# All listed bots are welcome to index public content.
# Listed individually so future tightening (if needed) is one-line edits.

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

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

# llms.txt — discovery hint for LLM crawlers and agents
# https://llmstxt.org for the emerging convention
# This is non-standard and ignored by robots.txt-only parsers; it is here as a discoverability signal for the few crawlers that look for it in robots.txt.
# llms.txt: https://gensight.ai/llms.txt