# 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: /

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

# Repo copy: production may prepend Cloudflare "Managed content" rules that Disallow
# GPTBot, ClaudeBot, etc. Those override per–user-agent matching. To allow AI search /
# citation crawlers, update Cloudflare (Bots / managed robots), not only this file.

# Explicit allows for common AI citation crawlers (effective when not overridden upstream)
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-Agent: *
Allow: /
Disallow: /assets/
Disallow: /api/

Disallow: https://data-platform.somi.ai/assets/
Disallow: /data-platform/

# Allow Next.js metadata files for social sharing
Allow: /*/opengraph-image*
Allow: /*/twitter-image*

# Block specific query parameters that don't add SEO value
Disallow: /*?claim=*
Disallow: /*?error=*
Disallow: /*?verified=*
Disallow: /*?token=*
Disallow: /*?utm_*

Sitemap: https://somi.ai/sitemap.xml

# LLM Documentation
Llms: /llms.txt

# Social media crawlers
User-Agent: Twitterbot
Allow: /*/twitter-image*

User-Agent: facebookexternalhit
Allow: /*/opengraph-image*

User-Agent: LinkedInBot
Allow: /*/opengraph-image*