# 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

# aibarometer.eu
#
# Two very different things get called "AI crawlers", and they are treated differently here.
#
#   Training crawlers collect pages to train a model. Rights over the text and data on this
#   site are expressly reserved under Article 4(3) of Directive (EU) 2019/790 (the DSM
#   Directive), so text and data mining for that purpose is not permitted and those crawlers
#   are disallowed below.
#
#   Retrieval crawlers fetch a page to answer a question a person has just asked, and cite
#   the page they took the answer from. That is what this site is for, so they are allowed.
#
# Blocking the first is not a reason to block the second. Ordinary search engines are
# unaffected by either group.
#
# To reach a human about any of this, see /legal.

# --------------------------------------------------------------------------------------
# Everyone else, including Googlebot and Bingbot
# --------------------------------------------------------------------------------------
User-agent: *
# Content Signals (https://contentsignals.org), the machine-readable form of the above:
# indexable for search, quotable in an AI answer, not available as training data.
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# --------------------------------------------------------------------------------------
# Text and data mining for model training — rights reserved, Art. 4(3) DSM
# --------------------------------------------------------------------------------------
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: CCBot
User-agent: Bytespider
User-agent: Applebot-Extended
User-agent: meta-externalagent
Disallow: /

# --------------------------------------------------------------------------------------
# Retrieval and citation — allowed
#
# These fetch a page in order to answer a question and attribute the answer. Amazonbot is
# here because Amazon documents it as serving Alexa answers rather than model training;
# move it up if that changes. Google-Extended gates Gemini grounding only and has no effect
# on Googlebot or on ordinary Search, so it is allowed: the point is to be quoted.
# --------------------------------------------------------------------------------------
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Amazonbot
Allow: /

Sitemap: https://aibarometer.eu/sitemap.xml