# See https://www.robotstxt.org/robotstxt.html for documentation

# Sitemap location — referenced by all major search engines
Sitemap: https://lawnworksmn.com/sitemap.xml

# Bing sitemap notification (submit to Bing Webmaster Tools for faster indexing)
# Ping URL: https://www.bing.com/ping?sitemap=https://lawnworksmn.com/sitemap.xml
# IndexNow is also supported — see IndexNowSubmitJob for push-based notifications

# ===========================================
# PROTECTED AREAS - Disallow for all crawlers
# These rules are inherited by every block below
# ===========================================

# ===========================================
# SEARCH ENGINE CRAWLERS - Full Access
# ===========================================
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Bingbot
User-agent: Slurp
User-agent: DuckDuckBot
User-agent: Yandex
User-agent: Applebot
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /tech/
Disallow: /login
Disallow: /logout
Disallow: /webhooks/
Allow: /reviews
Disallow: /review
Disallow: /lp/
Disallow: /*?ref=
# Parameterized review filter pages — canonical is /reviews; no crawl value in source-filtered variants
Disallow: /reviews?
# Parameterized resource pagination — tag filter pages use clean /resources/tag/:tag paths instead
Disallow: /resources?

# ===========================================
# AI SEARCH & ASSISTANT CRAWLERS - Full Access
# Explicitly allowing these signals to AI platforms
# that our content is available for their search
# and answer products.
# ===========================================
User-agent: GPTBot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: PerplexityBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: anthropic-ai
User-agent: Google-Extended
User-agent: Bytespider
User-agent: meta-externalagent
User-agent: cohere-ai
User-agent: YouBot
User-agent: Amazonbot
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /tech/
Disallow: /login
Disallow: /logout
Disallow: /webhooks/
Allow: /reviews
Disallow: /review
Disallow: /lp/
Disallow: /*?ref=
# Parameterized review filter pages — canonical is /reviews; no crawl value in source-filtered variants
Disallow: /reviews?
# Parameterized resource pagination — tag filter pages use clean /resources/tag/:tag paths instead
Disallow: /resources?

# ===========================================
# DEFAULT - Allow all other well-behaved crawlers
# ===========================================
User-agent: *
Allow: /
Disallow: /admin/
Disallow: /portal/
Disallow: /tech/
Disallow: /login
Disallow: /logout
Disallow: /webhooks/
Allow: /reviews
Disallow: /review
Disallow: /lp/
Disallow: /*?ref=
# Parameterized review filter pages — canonical is /reviews; no crawl value in source-filtered variants
Disallow: /reviews?
# Parameterized resource pagination — tag filter pages use clean /resources/tag/:tag paths instead
Disallow: /resources?