# https://kilo.land/robots.txt
# Pre-development land-risk intelligence for Hawaiʻi.
# Marketing pages are public; the assessment tool is invite-only.

User-agent: *
Allow: /
Disallow: /app
Disallow: /api/
Disallow: /login

# ── AI posture (2026-07 IP-protection decision) ────────────────────
# We split AI crawlers into two buckets:
#   • AI SEARCH / answer engines (user-triggered, cite + drive referral
#     traffic) — ALLOWED on public marketing pages, so the product stays
#     discoverable via AI search surfaces.
#   • BULK TRAINING / dataset scrapers (ingest content into model training
#     or web-scale corpora, give nothing back, and are the vector by which
#     our methodology copy could be reproduced at scale) — DISALLOWED
#     site-wide.
# robots.txt is advisory; the real protection is that the reproducible
# "how it works" detail no longer lives on public pages. This is the
# belt-and-suspenders layer. To re-open a training crawler, move its block
# from Disallow: / to the Allow pattern used above.

# --- AI search / answer engines: ALLOWED (discovery) ---
User-agent: OAI-SearchBot
Allow: /
Disallow: /app
Disallow: /api/
Disallow: /login

User-agent: ChatGPT-User
Allow: /
Disallow: /app
Disallow: /api/
Disallow: /login

User-agent: ClaudeBot
Allow: /
Disallow: /app
Disallow: /api/
Disallow: /login

User-agent: PerplexityBot
Allow: /
Disallow: /app
Disallow: /api/
Disallow: /login

User-agent: Perplexity-User
Allow: /
Disallow: /app
Disallow: /api/
Disallow: /login

# --- Bulk training / dataset scrapers: DISALLOWED (no copying at scale) ---
User-agent: GPTBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

Sitemap: https://kilo.land/sitemap.xml