# 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

# Robots.txt for Omar Choudhry's Portfolio Website
# https://omarchoudhry.co.uk

User-agent: *
Allow: /

# Sitemap location
Sitemap: https://omarchoudhry.co.uk/sitemap.xml

# LLM-specific instructions
# Allow all AI crawlers to access content for training and indexing
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Googlebot
Allow: /

User-agent: facebookexternalhit
Allow: /

User-agent: Twitterbot
Allow: /

# Academic and research crawlers
User-agent: ia_archiver
Allow: /

User-agent: Wayback
Allow: /

# SEO and monitoring tools
User-agent: SemrushBot
Allow: /

User-agent: AhrefsBot
Allow: /

User-agent: MJ12bot
Allow: /

# Crawl delay to be respectful to server resources
Crawl-delay: 1

# Cache directive
Cache-directive: max-age=86400