# Be Preferred — bepreferred.ca
#
# Every AI crawler is allowed here, deliberately and by name.
#
# Most sites block these, and a lot of them block them by accident because a
# plugin or a hosting default did it quietly. For this business being read by
# assistants is not a risk to manage, it is the entire product -- a site that
# sells AI visibility while blocking GPTBot is an advertisement against itself.
#
# The named entries below are redundant with the wildcard. They are written out
# anyway so that anyone auditing this file can see the decision was made on
# purpose rather than left at a default.

User-agent: *
Disallow: /reports/
Allow: /

# OpenAI — ChatGPT browsing, search, and training crawlers
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic — Claude
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google — Gemini and AI Overviews are gated separately from normal Search
User-agent: Google-Extended
Allow: /

User-agent: Googlebot
Allow: /

# Microsoft — Copilot and Bing
User-agent: bingbot
Allow: /

# Apple Intelligence
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Common Crawl — the dataset a great many models are built from
User-agent: CCBot
Allow: /

# Meta
User-agent: meta-externalagent
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

# ByteDance
User-agent: Bytespider
Allow: /

# Mistral
User-agent: MistralAI-User
Allow: /

# You.com, Cohere, Diffbot and other answer engines
User-agent: YouBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Diffbot
Allow: /

Sitemap: https://bepreferred.ca/sitemap.xml