# 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.

# 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
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

User-agent: *
Allow: /

# Block auth & app pages from indexing
Disallow: /dashboard
Disallow: /systems
Disallow: /documents
Disallow: /reports
Disallow: /team
Disallow: /settings
Disallow: /monitoring
Disallow: /alerts
Disallow: /integrations
Disallow: /onboarding
Disallow: /checkout
Disallow: /trial-expired
Disallow: /upgrade
Disallow: /billing
Disallow: /ack/
Disallow: /portal/
Disallow: /survey/
Disallow: /accept-invite

# ── AI / LLM crawlers — explicitly allowed ──────────────────────────────────
# We *want* AI assistants to read and cite ComplyLayer's compliance content.
# See https://complylayer.com/llms.txt for machine-readable product description
# and https://complylayer.com/llms-full.txt for full-content version.
# Anthropic-style declaration: https://complylayer.com/ai.txt

# OpenAI (ChatGPT browsing + training)
User-agent: GPTBot
Allow: /
Disallow: /dashboard
Disallow: /systems
Disallow: /documents
Disallow: /reports
Disallow: /team
Disallow: /settings
Disallow: /monitoring
Disallow: /alerts
Disallow: /integrations
Disallow: /onboarding
Disallow: /checkout
Disallow: /trial-expired
Disallow: /upgrade
Disallow: /billing
Disallow: /ack/
Disallow: /portal/
Disallow: /survey/
Disallow: /accept-invite

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude search + training)
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 AI (Bard / Gemini / AI Overviews)
User-agent: Google-Extended
Allow: /

# Common Crawl (used to train many LLMs)
User-agent: CCBot
Allow: /

# Meta (Llama training)
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /

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

# Bytespider (TikTok/ByteDance)
User-agent: Bytespider
Allow: /

# xAI (Grok)
User-agent: xAI-Bot
Allow: /

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /

# Cohere
User-agent: cohere-ai
Allow: /

# You.com
User-agent: YouBot
Allow: /

# ── Sitemaps & resources ────────────────────────────────────────────────────
Sitemap: https://complylayer.com/sitemap.xml