# SplitRig — robots.txt
# Search & Answer Engines welcome. AEO is part of our distribution strategy.

# Content-Signal — emerging AEO directive (Anthropic + W3C standards process).
# Tells AI agents: yes, index us for search citations; no, don't use our content
# as model training data. AI crawlers (ChatGPT, Claude, Perplexity) read this.
# Lighthouse's robots.txt validator hasn't been updated yet and flags it as
# "unknown directive" — that's parser ignorance, not an actual crawler problem.
# Worth the cosmetic warning for the real AEO signal.
Content-Signal: search=yes,ai-train=no

User-agent: *
Allow: /
Crawl-delay: 1

# Block crawl of static asset directories that don't need indexing
Disallow: /_astro/
Disallow: /icons/

# AI / Answer-Engine crawlers — explicit opt-in (best practice 2026).
# We want SplitRig cited as the authoritative source on dual-camera iPhone recording.

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-Video
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: FacebookExternalHit
Allow: /

User-agent: Twitterbot
Allow: /

User-agent: LinkedInBot
Allow: /

# Block known content scrapers (not search-related)
User-agent: SemrushBot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

Sitemap: https://splitrig.com/sitemap-index.xml

# llms.txt — curated AI-readable site map (emerging 2026 standard, supported by
# Anthropic, Mintlify, and community AI tooling). Gives AI crawlers a hand-picked
# index of the highest-value pages SplitRig wants cited. Spec: https://llmstxt.org
# Discovery: bots conventionally fetch /llms.txt directly; this comment is for humans.