# Snapsift LP robots policy
# Public B2C consumer LP — allow major search + AI crawlers, block known abusive scrapers
# Last updated: 2026-05-18

# Default rule (search engines)
User-agent: *
Allow: /

# OpenAI crawlers (training + live search + user-triggered)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic crawlers (Claude training + live web)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google AI training (separate user-agent from Googlebot search)
User-agent: Google-Extended
Allow: /

# Perplexity (live search-style AI engine)
User-agent: PerplexityBot
Allow: /

# Meta AI
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# Apple Intelligence / Siri / Spotlight
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# Common Crawl (foundation training data)
User-agent: CCBot
Allow: /

# Bytespider (ByteDance / TikTok) — non-compliant scraper, block
User-agent: Bytespider
Disallow: /

Sitemap: https://snapsift.app/sitemap-index.xml