# AI search and assistant crawlers are welcome. The wildcard already
# covers them; naming them in the same group states it outright, and
# they share the rules below rather than getting a group of their own
# (a named group would replace the wildcard rules, not add to them).
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: meta-externalagent
User-agent: Amazonbot
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: *
Allow: /

# Authenticated and transactional surfaces — no crawl value, and every
# one of them either 302s to a login or carries a single-use token.
#
# Login and register are deliberately NOT listed. They are linked from
# the header of every page, so blocking the crawl would not keep them
# out of the index — it would only strip the snippet and leave a bare
# URL. They must stay crawlable for the crawler to read the noindex
# they carry (App\Http\Middleware\NoIndex), which is the directive
# that actually excludes them.
Disallow: /admin/
Disallow: /client/
Disallow: /api/
Disallow: /t/
Disallow: /s/
Disallow: /c/
Disallow: /r/
Disallow: /rv/
Disallow: /a/
Disallow: /unsubscribe
Disallow: /resubscribe
Disallow: /invoices/

# utm_* and other campaign parameters never change the page content;
# the canonical tag already collapses them, this saves the crawl budget.
Disallow: /*?utm_

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