# 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

# robots.txt for www.aice-lab.org
# Source of truth: layouts/robots.txt (Hugo)
#
# Cloudflare prepends an "AI Audit Content Signals" block at the edge with
# the default policy: search=yes, ai-train=no. That policy stands. AI bots
# that CF lists (GPTBot, ClaudeBot, Google-Extended, CCBot, Bytespider,
# Applebot-Extended, Amazonbot, meta-externalagent, etc.) are blocked from
# training; the default User-agent: * with Content-Signal allows search
# indexing and AI answer generation (RAG / "ai-input").
#
# We layer ON TOP only with disallows for aggressive SEO scrapers — they
# consume bandwidth without adding value, and CF doesn't filter them by
# default. We do NOT add explicit User-agent blocks for search engines or
# AI crawlers that CF already addresses, to avoid override semantics.

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: BLEXBot
Disallow: /

Sitemap: https://www.aice-lab.org/sitemap.xml