# Suprflo robots.txt
#
# AI retrieval crawlers are explicitly welcomed: citation in AI answers is a
# primary acquisition channel for this product. Agents are named individually
# rather than relying on the wildcard so that any future tightening of
# "User-agent: *" does not silently cut off AI access.
#
# Two rules this file depends on, both easy to get wrong:
#   1. Disallow lines come BEFORE "Allow: /". Major crawlers (Google, Bing, etc.)
#      resolve conflicts by longest match, so order does not matter for them.
#      We keep Disallow first for clarity and to avoid edge cases with
#      non-standard parsers.
#   2. A named user-agent group REPLACES the wildcard group; rules are not
#      inherited. So every named group must repeat the Disallow list, otherwise
#      naming a crawler accidentally grants it the authenticated app surfaces.

# --- Traditional search + AI retrieval crawlers (fetch live to answer a user) ---
User-agent: Googlebot
User-agent: Bingbot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot
User-agent: Amazonbot
Disallow: /dashboard
Disallow: /login
Disallow: /playground
Disallow: /admin
Disallow: /superadmin
Disallow: /design
Allow: /

# --- AI training crawlers ---
# Allowed: the public marketing copy is intended to inform model knowledge of
# the product. To opt out of training while keeping citations, change the
# "Allow: /" below to "Disallow: /" and leave the group above untouched.
#
# Google-Extended is not listed here. It is a control token (not a crawler)
# used specifically to opt out of Google’s AI training. If absent, training
# may be allowed by default per Google policy.
#
# To opt out, add a standalone block:
#      User-agent: Google-Extended
#      Disallow: /
User-agent: GPTBot
User-agent: anthropic-ai
User-agent: CCBot
User-agent: meta-externalagent
Disallow: /dashboard
Disallow: /login
Disallow: /playground
Disallow: /admin
Disallow: /superadmin
Disallow: /design
Allow: /

# --- Everything else ---
# Disallowed paths are authenticated app surfaces (/dashboard, /login,
# /playground, /admin, /superadmin) or internal tooling (/design). None contain
# marketing content, and all render an empty shell to crawlers regardless.
User-agent: *
Disallow: /dashboard
Disallow: /login
Disallow: /playground
Disallow: /admin
Disallow: /superadmin
Disallow: /design
Allow: /

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