# 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: /

User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# END Cloudflare Managed Content

# Robots.txt for Ruxagency (https://www.ruxagency.com)
# Global Search Engines & AI Retrieval Crawler Policy

# Content Signals Specification (https://contentsignals.org / draft-romm-aipref-contentsignals)
# Declares granular AI preferences: allows search indexing and real-time AI grounding/RAG input
Content-Signal: ai-train=no, search=yes, ai-input=yes

User-agent: *
Allow: /
Allow: /.well-known/
Allow: /.well-known/api-catalog
Allow: /.well-known/agent-skills/
Allow: /docs/api
Allow: /openapi.json
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /sitemap.xml
Allow: /ror.xml
Allow: /sitemap.html
Allow: /services
Allow: /services/*
Allow: /tools
Allow: /tools/*
Allow: /process
Allow: /work
Allow: /work/*
Allow: /about-us
Allow: /contact
Allow: /locations
Allow: /blog
Allow: /blog/*
Allow: /in/
Allow: /usa/
Allow: /uk/
Allow: /ca/
Allow: /ae/
Allow: /au/
Allow: /sg/

# AI Search & Retrieval Crawlers (Explicit Full Access for LLM Grounding)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Anthropic-AI
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Bytespider
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Diffbot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Amazonbot
Allow: /

# Canonical Sitemaps
Sitemap: https://www.ruxagency.com/sitemap.xml
Sitemap: https://www.ruxagency.com/ror.xml