# Content signals policy — https://contentsignals.org/
# As a condition of accessing this website, you agree to abide by the following
# content signals: a signal of "yes" grants permission for that use, "no"
# withholds it, and a use with no signal is neither granted nor restricted.
#   search:   building a search index and returning links and short excerpts.
#   ai-input: feeding content to an AI model at answer time (RAG, grounding).
#   ai-train: training or fine-tuning AI models.
# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF EU DIRECTIVE 2019/790.

# Hullside AI-crawler policy: assistant and search bots that cite sources and
# send readers are welcome. Bulk training scrapers that give nothing back are
# not. Mirrors the DroneXL policy.

# --- Welcome: AI search & assistant crawlers ---
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: GPTBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# --- Everyone else ---
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /
# /search/ is noindex and generates a URL per query; keep crawlers out of it
# entirely rather than spending budget discovering that.
Disallow: /search/

# No AI training — robots-only opt-out tokens
User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

# AI training crawlers
User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Amazonbot
Disallow: /

Sitemap: https://hullside.co/sitemap-index.xml
Sitemap: https://hullside.co/news-sitemap.xml
Sitemap: https://hullside.co/image-sitemap.xml