# 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

# Bevel — robots.txt
#
# Allow all crawlers everywhere except admin and per-result share pages
# (the /r/<id> URLs are public but unbounded — letting Google crawl
# them all would dilute the index with thin per-share pages and
# burn through crawl budget on infinite UUIDs).
#
# Exception: social-preview crawlers (Twitterbot, facebookexternalhit,
# Threads' Meta-ExternalAgent, etc.) are allowed into /r/ so link
# unfurls actually render on those platforms. Without the explicit
# allowlist they honor the Disallow above and never fetch the page,
# which means they never see our og:image / og:title and skip the
# card entirely. iMessage and Discord don't check robots.txt before
# unfurling, which is why those platforms previously worked while
# Twitter and Threads didn't.

User-agent: Twitterbot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Facebot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: LinkedInBot
Allow: /

User-agent: Slackbot
Allow: /

User-agent: Slackbot-LinkExpanding
Allow: /

User-agent: TelegramBot
Allow: /

User-agent: WhatsApp
Allow: /

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /api/
Disallow: /r/
Disallow: /results/

Sitemap: https://bevel.ink/sitemap.xml