# Seadvise — crawler policy
#
# Split by crawler FUNCTION, not by vendor. Measured citation retention after
# blocking is highest for pure-training bots (Google-Extended 92.3%, GPTBot
# 88.2%) and lowest for the retrieval bot (ChatGPT-User 70.6%). Blocking
# training is close to free; blocking retrieval is what costs citations.
#
# Two things this file cannot do:
#   - Disallow governs collection, not retention. It cannot remove content
#     already in model weights or Common Crawl archives.
#   - Blocking Google-Extended does NOT opt out of AI Overviews or AI Mode,
#     which draw from the live Search index. data-nosnippet around specific
#     banded values is the only surgical control.

# === Search indexing: allow fully. This is the SEO. ===
User-agent: Googlebot
Allow: /

User-agent: bingbot
Allow: /

# === AI retrieval: allow. This is what produces citations. ===
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Applebot
Allow: /

User-agent: DuckAssistBot
Allow: /

# === AI training: disallow. Measured citation cost is near zero. ===
# TDM rights reserved under Art. 4(3) Directive (EU) 2019/790 and
# 15 a § lag (1960:729) om upphovsrätt. Policy: https://seadvi.se/tdm-policy
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Amazonbot
Disallow: /

# === Everyone else ===
User-agent: *
Allow: /

# Public marketing and pricing pages. These must precede the /shipping/ and
# /cargo-owner/ disallows below, which would otherwise block them.
Allow: /ports/pricing
Allow: /shipping/pricing

# Authenticated application surfaces
Disallow: /admin
Disallow: /login
Disallow: /port/
Disallow: /shipping/
Disallow: /cargo-owner/

# Registration and token flows — no indexing value, and the token routes must
# never be indexed.
Disallow: /register
Disallow: /cargo-owner-register
Disallow: /shipping-register
Disallow: /confirm/
Disallow: /restore/
Disallow: /sentry

# Query surface — the dataset, not the entities. Blocking the facet parameter
# space is also good SEO: it prevents index bloat from combinatorial URLs.
Disallow: /search
Disallow: /export
Disallow: /api/
Disallow: /*?q=
Disallow: /*?filter=
Disallow: /*?sort=
Disallow: /*&sort=

Sitemap: https://seadvi.se/sitemap.xml