# https://www.hivedesk.com/robots.txt

User-agent: *
Allow: /
Disallow: /admin
Disallow: /signin
Disallow: /reset-password
Disallow: /dashboard
Disallow: /internal-tools
Disallow: /api/
Disallow: /_next/

# --- AI Crawlers: Allow search/answers, block training-only ---

# GPTBot: Used for both ChatGPT answers AND training.
# Allowing so HiveDesk appears in ChatGPT responses.
User-agent: GPTBot
Allow: /

# OAI-SearchBot: OpenAI's dedicated search crawler for ChatGPT Search.
User-agent: OAI-SearchBot
Allow: /

# ChatGPT-User: Real-time browsing when users ask ChatGPT to look something up.
User-agent: ChatGPT-User
Allow: /

# PerplexityBot: Powers Perplexity AI search answers.
User-agent: PerplexityBot
Allow: /

# Claude-Web: Used when Claude searches the web for answers.
User-agent: Claude-Web
Allow: /

# ClaudeBot: Anthropic's web indexing crawler for knowledge building.
User-agent: ClaudeBot
Allow: /

# Google-Extended: Controls AI training (Gemini) only.
# Does NOT affect Google Search ranking or AI Overviews.
User-agent: Google-Extended
Disallow: /

# Applebot-Extended: Apple AI training only (not Apple Search).
User-agent: Applebot-Extended
Disallow: /

# CCBot: Common Crawl — feeds many AI training datasets.
User-agent: CCBot
Disallow: /

# Bytespider: ByteDance/TikTok AI training.
User-agent: Bytespider
Disallow: /

# Meta-ExternalAgent: Meta AI training crawler.
User-agent: Meta-ExternalAgent
Disallow: /

# FacebookBot: Meta AI training.
User-agent: FacebookBot
Disallow: /

# cohere-ai: Cohere model training.
User-agent: cohere-ai
Disallow: /

# anthropic-ai: Anthropic model training crawler.
User-agent: anthropic-ai
Disallow: /

# Diffbot: AI data extraction for training.
User-agent: Diffbot
Disallow: /

# Omgilibot: Webz.io data harvesting.
User-agent: Omgilibot
Disallow: /

Sitemap: https://www.hivedesk.com/sitemap.xml