# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content


User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

User-agent: *
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /

# Auth-protected areas
Disallow: /chat
Disallow: /chat/
Disallow: /dashboard
Disallow: /profile
Disallow: /admin
Disallow: /admin/
Disallow: /subscriptions
Disallow: /subscriptions/
Disallow: /subscriptions/manage
Disallow: /subscribe
Disallow: /credit-bundles
Disallow: /affiliate
Disallow: /waitlist
Disallow: /testing-guide
Disallow: /gdpr
Disallow: /gdpr/
Disallow: /user
Disallow: /user/
Disallow: /api/
Disallow: /webhook/
Disallow: /email/verify
Disallow: /email/verify/

# Public marketing pages stay indexable — only paywalled routes are blocked above.

# AI search / citation crawlers (OAI-SearchBot, ChatGPT-User, Claude-SearchBot,
# Claude-User, PerplexityBot, Perplexity-User) share the same policy as "*"
# (see docs/seo/ai-crawler-policy.md). RFC 9309 lets a group list more than
# one User-agent line in front of one shared rule block, so they are listed
# above instead of repeating the block per agent. They serve answer engines
# (ChatGPT, Claude, Perplexity) that cite sources — distinct from
# training-data crawlers (GPTBot, ClaudeBot, Google-Extended), which
# Cloudflare currently blocks at the edge pending a business decision.

# Sitemap
Sitemap: https://askregulus.co.uk/sitemap.xml