# 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 jessicahische.com
# Allow normal search engines, block AI/ML training crawlers

# Default: allow all crawlers
User-agent: *
Disallow: /content/
Disallow: /site/
Disallow: /kirby/

# --- AI/ML Training Crawlers: BLOCKED ---

# OpenAI training crawler
User-agent: GPTBot
Disallow: /

# Common Crawl (used for ML training datasets)
User-agent: CCBot
Disallow: /

# Google ML/AI training (separate from Googlebot search)
User-agent: Google-Extended
Disallow: /

# Anthropic training crawlers
User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

# ByteDance / TikTok training crawler
User-agent: Bytespider
Disallow: /

# Meta AI training
User-agent: FacebookBot
Disallow: /

# Diffbot
User-agent: Diffbot
Disallow: /

# Omgili
User-agent: Omgilibot
Disallow: /

# Apple ML training (regular Applebot is allowed)
User-agent: Applebot-Extended
Disallow: /

# Cohere AI training
User-agent: cohere-ai
Disallow: /

# --- AI Search/Browsing Crawlers: EXPLICITLY ALLOWED ---

# ChatGPT browsing/search (NOT training)
User-agent: ChatGPT-User
Allow: /

# Perplexity search
User-agent: PerplexityBot
Allow: /

# Apple search (NOT training — Applebot-Extended is blocked above)
User-agent: Applebot
Allow: /

# Microsoft/Bing Copilot search
User-agent: Bingbot
Allow: /

# Google search (NOT training — Google-Extended is blocked above)
User-agent: Googlebot
Allow: /

Sitemap: https://jessicahische.is/sitemap.xml