# RumX - Rum Database & Community Reviews
# For AI systems, see: https://rumx.com/llms.txt
#
# Content Signals (contentsignals.org): declared per user-agent group below,
# because specific groups do not inherit from *. Meanings:
#   search    = building a search index / providing search results
#   ai-input  = real-time content use in AI answers (RAG, grounding)
#   ai-train  = training or fine-tuning AI models
# Decision 2026-06-05 (see docs/audits/agent-readiness-audit-2026-06-05.md):
# all three = yes — parametric brand familiarity in AI models is a
# distribution channel for the marketplace.


User-agent: *
# Block Algolia InstantSearch filter parameter URLs (infinite combinations, same content)
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
# NOTE: ?item= is intentionally NOT disallowed. The redirect-to-rxid edge function
# (netlify/edge-functions/redirect-to-rxid.js) 301s any ?item= variant to the clean
# canonical URL. Disallowing crawl prevented Google from ever seeing the 301, which
# left ~30+ ?item= variants indexed and ranking on brand queries (verified in GSC
# 2026-04-29). Allow crawl so the 301 can do its job and consolidate ranking signal.
#
# NOTE: ?utm_ is intentionally NOT disallowed (removed 2026-05-14). Same mechanism
# as ?item= above: every external backlink with utm_source/medium/campaign/content
# (newsletters, partner widget embeds, affiliate links, social shares) carries the
# tag. Blocking crawl prevented Googlebot from seeing the <link rel=canonical> on
# the UTM variant URL, which left link equity stuck on the variant instead of
# consolidating onto the clean PDP/shop/brand URL. Canonical coverage verified
# 2026-05-14 across PDP/Shop/Brand/Distillery/Bottler/Expert/Blog/Awards × EN/DE/FR
# (18/18 clean canonicals + hreflang alternates). Netlify Edge cache normalises
# utm_* out of the cache key (verified: identical Age across utm variants), so
# allowing crawl does not inflate cache slots. Codex consult 2026-05-14 concurred.
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# AI crawlers and user-triggered fetchers - explicitly welcome.
# Repeat the same parameter/non-content exclusions here because specific
# user-agent groups do not inherit rules from User-agent: *.

User-agent: OAI-SearchBot
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes


User-agent: ChatGPT-User
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes


User-agent: GPTBot
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes


User-agent: Claude-SearchBot
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes


User-agent: Claude-User
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes


User-agent: ClaudeBot
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes


User-agent: PerplexityBot
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes


User-agent: Perplexity-User
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes


User-agent: Google-Extended
Disallow: /rums/?q=
Disallow: /search/?q=
Disallow: /*?rums_unified
Disallow: /*&rums_unified
Disallow: /app/
Disallow: /checkout/
Disallow: /?rumId=
Disallow: /*?rumId=
Disallow: /*&rumId=
Disallow: /*/widgets/?
Disallow: /*?finder_
Disallow: /fonts/
Allow: /
Content-Signal: search=yes, ai-input=yes, ai-train=yes

Sitemap: https://rumx.com/sitemap.xml