# robots.txt — simcon.ai
# Stand: 2026-10-01

# ------------------------------------------------------------
# Sitemaps
# ------------------------------------------------------------
Sitemap: https://www.simcon.ai/sitemap.xml

# ------------------------------------------------------------
# Standard-Regeln für alle Crawler
# ------------------------------------------------------------

User-agent: *
# Wichtige Bereiche sperren
Disallow: /bootcamp/
Disallow: /checkout/
Disallow: /trial/
Disallow: /blog/
Disallow: /identity-confirmation
Disallow: /getintouch
Disallow: /verify-access

# HubSpot/Vorschau & ähnliche Utility-Parameter sperren
Disallow: /*?*utm_*
Disallow: /*?*gclid*
Disallow: /*?*fbclid*
Disallow: /*?*hs_preview*
Disallow: /*?*hsLang*
Disallow: /hubfs/*.zip

# Hinweis: CSS/JS/Assets werden NICHT pauschal gesperrt (HubSpot /hubfs/ bleibt crawlbar)

# ------------------------------------------------------------
# KI-Crawler — gewünschte Whitelist (explizit erlauben)
#   Alle NICHT hier gelisteten AI-/Scraper-Bots werden unten explizit gesperrt (sofern bekannt).
#   Diese Gruppen erben die Standard-Regeln (z. B. Disallow für /checkout/), sind aber generell zugelassen.
# ------------------------------------------------------------

# OpenAI / ChatGPT Atlas
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: GPTBot
Allow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: ChatGPT-User
Allow: /

# Google KI (Datenverwendung)
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Google-Extended
Allow: /

# Anthropic
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: ClaudeBot
Allow: /

# Perplexity
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: PerplexityBot
Allow: /
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Perplexity-User
Allow: /

# Microsoft / Bing (inkl. Rendering)
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: bingbot
Allow: /
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: BingPreview
Allow: /

# Mistral
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: MistralAI-User/1.0
Allow: /

# Common Crawl (nur wenn gewünscht — hier: erlaubt)
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: CCBot
Allow: /

# ------------------------------------------------------------
# Bekannte AI-/Scraper-Bots (Default: blockieren)
#   Diese Liste ist eine „Best Effort“-Sperre verbreiteter Scraper/Crawler.
#   (Ergänzbar bei Bedarf.)
# ------------------------------------------------------------
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Amazonbot
Disallow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Bytespider
Disallow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: DataForSeoBot
Disallow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Diffbot
Disallow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: omgili
Disallow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Omgilibot
Disallow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: ai2bot
Disallow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: FacebookBot
Disallow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Twitterbot
Disallow: /

Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Applebot
Disallow: /

# ------------------------------------------------------------
# Ende
# ------------------------------------------------------------
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*