# robots.txt for https://sidecar.ai
# Posture: OPT-IN — explicitly allow major AI search/retrieval and training crawlers
# so Sidecar can be cited and recommended by AI answer engines.
# To block any single bot, change its "Allow: /" to "Disallow: /".
# Last updated: 2026-06-26

# ============================================================
# DEFAULT RULES (all crawlers) — preserves HubSpot defaults
# ============================================================

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

# -- Sitemap --
Sitemap: https://sidecar.ai/sitemap.xml

# ============================================================
# AI CRAWLER POLICY — explicit allow
# ============================================================

# OpenAI (ChatGPT / SearchGPT)
# GPTBot:         training crawler
# OAI-SearchBot:  SearchGPT result indexing / retrieval
# ChatGPT-User:   user-initiated browsing from inside ChatGPT

User-agent: GPTBot
Allow: /

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

User-agent: OAI-SearchBot
Allow: /

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

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude)
# ClaudeBot:        training crawler
# Claude-SearchBot: live retrieval that drives Claude citation traffic
# Claude-Web:       user-initiated browsing from inside Claude
# anthropic-ai:     legacy identifier still seen in some contexts
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: ClaudeBot
Allow: /

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

User-agent: Claude-SearchBot
Allow: /

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

User-agent: Claude-Web
Allow: /

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

User-agent: anthropic-ai
Allow: /

# Perplexity
# PerplexityBot:    primary retrieval crawler
# Perplexity-User:  user-initiated fetches
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: /

# Google (AI Overviews, AI Mode, Gemini)
# Google-Extended:  controls inclusion in Gemini / AI training (separate from Googlebot;
#                   allowing it does NOT change search ranking)
# GoogleOther:      research and product variants
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Google-Extended
Allow: /

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

User-agent: GoogleOther
Allow: /

# Apple (Apple Intelligence)
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Applebot-Extended
Allow: /

# Microsoft (Copilot follows Bingbot; explicit signal helps)
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Bingbot
Allow: /

# Meta (Meta AI)
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

User-agent: Meta-ExternalAgent
Allow: /

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

User-agent: DuckAssistBot
Allow: /

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

User-agent: YouBot
Allow: /

# Common Crawl — feeds many open-source models and LLM datasets
Disallow: /_hcms/preview/
Disallow: /hs/manage-preferences/
Disallow: /hs/preferences-center/
Disallow: /*?*hs_preview=*
Disallow: /*?*hsCacheBuster=*

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