# traditional search
User-agent: Googlebot
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: Slurp
Allow: /

# AI search and live lookup: these are the citation drivers
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: Meta-ExternalAgent
Allow: /

# AI training: allowed, on the owner's instruction of 22 September 2026
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: Amazonbot
User-agent: cohere-ai
Allow: /

# discovery and data
User-agent: Bytespider
User-agent: Diffbot
User-agent: YouBot
Allow: /

# everything else, and the content-usage signal
#
# Content-Signal states permission to AI operators. The three signals are search (appear in
# search results), ai-input (be used as input to an AI answer) and ai-train (be used to train
# models). Leaving one out states NO PREFERENCE rather than permission, so all three are
# stated. Ben's decision, 22 September 2026: all three yes.
#
# Honest note for whoever reads this next: Google's robots.txt parser supports four fields and
# ignores everything else, so Google will not act on this line. It is a Cloudflare-led
# convention aimed at AI operators, and it is one line with nothing to maintain.
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# the AI Discovery Files published on this host are listed in /robots-ai.txt
Sitemap: https://eastcambsovencleaning.com/sitemap.xml