# As a condition of accessing this website, you agree to abide by the following
# content signals:

# (a)  If a Content-Signal = yes, you may collect content for the corresponding
#      use.
# (b)  If a Content-Signal = no, you may not collect content for the
#      corresponding use.
# (c)  If the website operator does not include a Content-Signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via Content-Signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.
# use:      how AI systems may consume the content (immediate, reference, or full).

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.

# BEGIN Cloudflare Managed content


User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# Training crawlers
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: MistralAI-Training
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: GoogleOther
Disallow: /

User-agent: Baiduspider
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: AwarioSmartBot
User-agent: AwarioRssBot
Disallow: /

User-agent: Google-CloudVertexBot
Disallow: /

User-agent: QualifiedBot
Disallow: /

User-agent: Cotoyogi
Disallow: /

User-agent: ICC-Crawler
Disallow: /

User-agent: atlassian-bot
Disallow: /

User-agent: FishBot
Disallow: /

User-agent: BorderxBot
Disallow: /

User-agent: NavuBot
Disallow: /

User-agent: SemrushBot-SWA
Disallow: /

User-agent: WARDBot
Disallow: /

User-agent: magpie-crawler
Disallow: /

User-agent: KimiBot
Disallow: /

User-agent: CitibotSiteCrawler
Disallow: /

# END Cloudflare Managed Content

# robots.txt for foldlaundry.com
# Canonical host is the apex (https://foldlaundry.com).
# www.foldlaundry.com 301-redirects to the apex via Express middleware.
# api.foldlaundry.com serves the JSON API and is not customer-facing.
#
# Sept 2026: AI agents and AI search crawlers are EXPLICITLY welcome.
# Fold wants to be discovered, cited, and booked by agents (Meta Muse,
# ChatGPT, Claude, Perplexity, Gemini, and whatever comes next). The
# agent-facing surface is listed under "Agent surface" below and must
# stay allowed. Do not add a blanket Disallow for any of these bots.

# ---------------------------------------------------------------------
# AI agents & AI search — all explicitly allowed
# ---------------------------------------------------------------------
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: anthropic-ai
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Gemini
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: FacebookBot
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Amazonbot
User-agent: Bytespider
User-agent: DuckAssistBot
User-agent: YouBot
User-agent: cohere-ai
User-agent: CCBot
Allow: /
Disallow: /app
Disallow: /admin
Disallow: /driver
Disallow: /route
Disallow: /route-api/
Disallow: /cleaning
Disallow: /flow
Disallow: /test
Disallow: /test/
Disallow: /healthz
Disallow: /readyz
Disallow: /openapi.json
Disallow: /docs

# ---------------------------------------------------------------------
# Everyone else (search engines etc.)
# ---------------------------------------------------------------------
User-agent: *

# Public marketing pages — search engines welcome.
Allow: /
Allow: /how-it-works
Allow: /service-areas
Allow: /hotel-laundry-los-angeles
Allow: /hotel-laundry-san-francisco
Allow: /airbnb-laundry-los-angeles
Allow: /airbnb-laundry-san-francisco
Allow: /airbnb-guest-laundry
Allow: /airbnb-guest-laundry-los-angeles
Allow: /airbnb-guest-laundry-san-francisco
Allow: /guides
Allow: /pricing
Allow: /club
Allow: /hotels
Allow: /business
Allow: /students
Allow: /terms
Allow: /privacy

# Agent surface — machine-readable entry points. Keep these allowed.
Allow: /ai
Allow: /mcp
Allow: /agent/
Allow: /agent/v1/openapi.json
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /pricing.json
Allow: /.well-known/
Allow: /.well-known/mcp.json

# Customer app + staff tools — not for search engines.
Disallow: /app
Disallow: /admin
Disallow: /driver
Disallow: /route
Disallow: /route-api/
Disallow: /cleaning
Disallow: /flow
Disallow: /test
Disallow: /test/

# Internal API catalog (auth/admin/driver endpoints) — not the public
# agent surface. Agents should use /mcp and /.well-known/mcp.json instead.
Disallow: /healthz
Disallow: /readyz
Disallow: /openapi.json
Disallow: /docs

# JSON API paths Googlebot discovers inside page scripts — not pages.
# (GSC "Not found (404)" was listing these; blocking keeps the report clean.)
Disallow: /markets/
Disallow: /windows
Disallow: /hotels/setup-intent
Disallow: /hotels/bookings
Disallow: /hotels/partners
Disallow: /markets
Disallow: /neighborhoods
Disallow: /orders/
Disallow: /auth/

# Sitemap canonical location
Sitemap: https://foldlaundry.com/sitemap.xml