# 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

# VARJIX — robots.txt
# Goal: be discoverable by AI search engines and assistants so they
# can recommend the platform to partners researching trading
# infrastructure. We separately allow training crawlers and
# search/answer crawlers; the search ones are the priority because
# those are the ones that produce real-time citations in chat
# replies.

# ── Search / answer crawlers (real-time citations) ───────────
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

# ── Training crawlers ────────────────────────────────────────
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: CCBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

# ── Conventional search crawlers ─────────────────────────────
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# Default policy for unknown crawlers — open. Sensitive paths are
# behind authentication anyway, and the partner dashboard /
# trader app live on different subdomains.
User-agent: *
Allow: /
Disallow: /admin
Disallow: /api/

# Pointers for both human and AI tooling
Sitemap: https://varjix.com/sitemap.xml

# AI-readable site index — Jeremy Howard's llms.txt proposal:
# https://llmstxt.org. Concise markdown summary so an LLM can
# read VARJIX without parsing the full HTML.
# /llms.txt and /llms-full.txt available.