# SantaClaritaOpenHouses.com — the Santa Clarita Valley home answer engine.
# PURPOSE-BASED POLICY (rewritten 2026-07-10): we WELCOME live answer/citation
# crawlers -- the bots that fetch a page to answer one user's question and cite
# this site as the source. We DO NOT consent to bulk crawling for AI MODEL
# TRAINING, or to reproduction of this site's compiled data/strategy elsewhere.
# Where a company runs separate bots for these two purposes, they're split
# below. See /.well-known/tdmrep.json for the machine-readable TDM reservation
# (EU AI Act / CDSM Art. 4(3)) and /terms/ for the human-readable policy this
# file implements. One named local agent behind every answer: Connor T.
# MacIvor, CalDRE #01238257, Sync Brokerage, Inc., CalDRE #02031490.

# --- WELCOME: live answer / citation / user-driven browsing ---
User-agent: OAI-SearchBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /
User-agent: ClaudeBot
Allow: /
User-agent: Claude-User
Allow: /
User-agent: Claude-Web
Allow: /

# --- NOT WELCOME: bulk crawling for AI model training ---
# GPTBot = OpenAI's training crawler (distinct from OAI-SearchBot above).
User-agent: GPTBot
Disallow: /
# Google-Extended = governs Gemini/Vertex AI training use, separate from
# Googlebot below (which still serves Search + AI Overviews).
User-agent: Google-Extended
Disallow: /
# Applebot-Extended = Apple Intelligence training use, separate from Applebot
# below (which still serves Siri/Spotlight/Safari search surfacing).
User-agent: Applebot-Extended
Disallow: /
User-agent: anthropic-ai
Disallow: /
User-agent: Amazonbot
Disallow: /
User-agent: cohere-ai
Disallow: /
User-agent: Bytespider
Disallow: /
# CCBot = Common Crawl. Not an answer engine itself -- its dataset is resold
# and redistributed into countless third-party AI training and site-cloning
# pipelines. Zero citation benefit to us; the single highest-leverage block.
User-agent: CCBot
Disallow: /

# --- Search crawlers (indexing for search results, not AI training) ---
User-agent: Googlebot
Allow: /
User-agent: Bingbot
Allow: /
User-agent: Applebot
Allow: /
User-agent: DuckDuckBot
Allow: /

# --- Everyone else: this line is advisory only (well-behaved bots honor it;
# scrapers built to ignore robots.txt do not -- real enforcement against
# those is at the network/WAF layer, not here). ---
User-agent: *
Allow: /

Sitemap: https://santaclaritaopenhouses.com/sitemap-index.xml