User-agent: *
Allow: /

# [AEO & SEO Core] Block dynamic parameters causing duplicate content
# These parameters cause your 1k pages to bloat to 133k
# Disallow: /*?*variant=*  remove this for GMC ads
# Disallow: /*?*page=*     removed 2026-08-03 — paginated collection URLs are
#                          self-canonical; blocking them severs internal-link
#                          discovery for deep products (951 SKUs)
Disallow: /*?*sort_by=*
Disallow: /*?*pr_prod_strat=*
Disallow: /*?*shpxid=*
Disallow: /*?*oseid=*
Disallow: /*?*q=*

# [Strategy] Localized blog pages crawlable — canonical + hreflang handles deduplication
# Shopify emits a SELF-referencing canonical plus full hreflang on /en-XX/, /es/, /fr/ pages
# Blocking prevents Google from reading hreflang signals — removed

# [SEO] Block multi-filter collection results
# Prevents junk pages like /collections/all/red+small+cheap
Disallow: /collections/*+*
Disallow: /*/collections/*+*

# [Shopify Default] Block system pages
# NOTE: /policies is deliberately NOT blocked — Google Merchant Center must crawl
#       the refund/shipping policy pages to verify them. Blocking triggers MC warnings.
Disallow: /admin
Disallow: /cart
Disallow: /carts
Disallow: /checkout
Disallow: /orders
Disallow: /account
Disallow: /search
Disallow: /search?*
Disallow: /pages/search-results
Disallow: /challenge
Disallow: /preview_theme_id*
Disallow: /preview_script_id*
Disallow: /cdn/wpm*/js
Disallow: /a/downloads/*
Disallow: /apps
Disallow: /services

# ----------------------------------------------
# [AEO Support] Explicitly allow AI Crawlers
# Ensures OpenAI, Anthropic, Apple, etc. can access high-quality content
#
# WARNING: a named User-agent group does NOT inherit the "User-agent: *" rules —
# a crawler obeys ONLY its most-specific group. Every bot listed below therefore
# gets a full-site allow with none of the parameter blocks above. That is intended
# for the AI crawlers. Do NOT add "User-agent: Googlebot" here: it would silently
# disable every Disallow above for Google Search. (Removed 2026-08-03.)
#
# Google-Extended stays — it governs AI/Gemini training only, not Search indexing.
# ----------------------------------------------
User-agent: GPTBot
Allow: /

# OAI-SearchBot is the only token here that governs ChatGPT Search visibility.
# Per OpenAI: a site may "allow OAI-SearchBot in order to appear in search
# results while disallowing GPTBot" (training), and "ChatGPT-User is not used
# to determine whether content may appear in Search". So GPTBot = training,
# ChatGPT-User = per-user fetch, OAI-SearchBot = Search indexing. This list had
# the first two and was missing the one that actually drives referral traffic.
# It was already permitted via "User-agent: *"; naming it makes the intent
# explicit so a future tightening of * cannot silently drop it.
# Changes take ~24h to take effect on OpenAI's side. Added 2026-10-30.
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

# Anthropic documents three tokens and each needs its own rule: ClaudeBot
# (collects content that may contribute to training), Claude-SearchBot
# ("navigates the web to improve search result quality"), and Claude-User
# (fetches a site when a Claude user's question requires it). This list had
# only the training one, plus "anthropic-ai", a legacy token Anthropic's
# current docs no longer list. Same gap as OAI-SearchBot above: the token
# that governs discoverability was the one missing. Added 2026-10-30.
User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

# Perplexity documents two tokens: PerplexityBot (makes pages appear and get
# linked in Perplexity's results; "not used to crawl content for AI foundation
# models") and Perplexity-User (fetches a page when a user's question needs it).
# Neither feeds training. Caveat: Perplexity states that because a user
# requested the fetch, Perplexity-User "generally ignores robots.txt rules" --
# so this group records intent rather than controlling behaviour.
# Added 2026-10-30.
User-agent: Perplexity-User
Allow: /

# Amazon documents the same three-way split. Per Amazon: Amazonbot "may be
# used to train Amazon AI models"; Amzn-SearchBot is used to "improve search
# experiences in Amazon products and services" and "does not crawl content for
# generative AI model training" -- allowing it is what makes pages eligible to
# appear in surfaces like Alexa; Amzn-User "supports user actions, such as
# responding to Alexa queries", and Amazon notes "it may not follow all
# robots.txt directives". Training stays allowed here by decision, so Amazonbot
# is allowed too, not just the two non-training tokens. Amazon caches
# robots.txt for up to 30 days and says changes take ~24h to reflect.
# Added 2026-10-31.
User-agent: Amazonbot
Allow: /

User-agent: Amzn-SearchBot
Allow: /

User-agent: Amzn-User
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Google-Extended
Allow: /

# [Sitemap]
Sitemap: https://fitiny.com/sitemap.xml
Sitemap: https://cdn.shopify.com/s/files/1/0331/1013/0821/files/fitiny-video-sitemap-20260916.xml?v=1789572681