# Content signals — what we permit for content collected from this site.
#   search:   building a search index and returning links and short excerpts
#   ai-input: using content to ground a generated answer (RAG, AI search)
#   ai-train: training or fine-tuning models
#
# ai-input=yes is what lets ChatGPT, Claude, Perplexity and Gemini cite this
# site in an answer. It does not permit training, which is a separate signal.
User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no
Allow: /
# Paid-traffic landing pages; every page is noindex, so skip the crawl entirely.
Disallow: /lp/
# Form and chat endpoints; nothing to index, and GET /api/lead answers 405.
Disallow: /api/

# --- AI answer engines: explicitly welcome ---
# These crawlers index for, or fetch live on behalf of, AI assistants. They are
# how the site gets surfaced and cited in an answer.

User-agent: OAI-SearchBot
Allow: /
Disallow: /api/

User-agent: ChatGPT-User
Allow: /
Disallow: /api/

User-agent: Claude-SearchBot
Allow: /
Disallow: /api/

User-agent: Claude-User
Allow: /
Disallow: /api/

User-agent: PerplexityBot
Allow: /
Disallow: /api/

User-agent: Perplexity-User
Allow: /
Disallow: /api/

User-agent: Google-Extended
Allow: /
Disallow: /api/

User-agent: Applebot-Extended
Allow: /
Disallow: /api/

# --- Model training crawlers ---
# Allowing these is a separate decision from being cited in answers: a site can
# be quoted by ChatGPT with GPTBot disallowed. Flip Disallow to Allow to permit
# training on this content.

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

Sitemap: https://hvactruenorth.com/sitemap.xml