# promtable.com — robots policy
# Designed for both classic SERP crawl and AI answer-engine citation.
# Policy: ALLOW citation-class AI crawlers (they cite back to source),
# DISALLOW pure training crawlers that take content without citation.

# -----------------------------------------------------------------------------
# Default
# -----------------------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /admin
Disallow: /admin/*
Disallow: /api/admin/*
Disallow: /api/private/*

# -----------------------------------------------------------------------------
# Answer-engine crawlers (CITE BACK — full allow)
# -----------------------------------------------------------------------------

# OpenAI ChatGPT search (cites sources in answers)
User-agent: OAI-SearchBot
Allow: /

# OpenAI ChatGPT user-initiated browse (cites sources)
User-agent: ChatGPT-User
Allow: /

# Anthropic Claude with web search (cites sources)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity (cites every source)
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google Gemini web answers (separate from search crawl)
User-agent: Google-Extended
Allow: /

# Apple Intelligence / Siri (cites sources)
User-agent: Applebot-Extended
Allow: /

# DuckDuckGo AI assist (cites sources)
User-agent: DuckAssistBot
Allow: /

# Brave Leo AI search
User-agent: BraveSearch
Allow: /

# You.com
User-agent: YouBot
Allow: /

# Cohere AI search products
User-agent: cohere-ai
Allow: /

# -----------------------------------------------------------------------------
# Classic search crawlers
# -----------------------------------------------------------------------------

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Slurp
Allow: /

# -----------------------------------------------------------------------------
# Social previews (Open Graph fetchers)
# -----------------------------------------------------------------------------

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: Discordbot
Allow: /

# -----------------------------------------------------------------------------
# Training-only crawlers — disallow to preserve leverage
# We feed AI answer engines content (so they cite us);
# we don't give pure-training crawlers free pretraining data.
# -----------------------------------------------------------------------------

# OpenAI training crawler (different from OAI-SearchBot)
User-agent: GPTBot
Disallow: /

# Common Crawl (used by many model trainers without citing back)
User-agent: CCBot
Disallow: /

# Bytedance training crawler (Doubao/TikTok AI)
User-agent: Bytespider
Disallow: /

# Diffbot
User-agent: Diffbot
Disallow: /

# ImagesiftBot
User-agent: ImagesiftBot
Disallow: /

# omgili
User-agent: omgili
Disallow: /

# Amazon Alexa training
User-agent: Amazonbot
Disallow: /

# Meta training
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

# -----------------------------------------------------------------------------
# Google's adstxt verifier
# -----------------------------------------------------------------------------
User-agent: Google-adstxt
Allow: /app-ads.txt
Disallow:

# -----------------------------------------------------------------------------
# Sitemaps
# -----------------------------------------------------------------------------

Sitemap: https://promtable.com/sitemap.xml
Sitemap: https://promtable.com/sitemap-pages.xml
Sitemap: https://promtable.com/blog-sitemap.xml
Sitemap: https://promtable.com/use-case-sitemap.xml
Sitemap: https://promtable.com/sitemap-images.xml
Sitemap: https://promtable.com/sitemap-videos.xml