# https://www.extremeheating.com/robots.txt
# Extreme Heating, Air, Plumbing — Dayton & Cincinnati, Ohio
#
# Policy: all reputable crawlers, including AI training and AI search agents,
# are welcome on all public content. We want to be the source AI answers cite
# for heating, cooling and plumbing questions in the Dayton and Cincinnati metros.
#
# Note: pages under /locations/ that carry a noindex meta tag are intentionally
# left crawlable. Disallowing them would prevent the noindex from being read.

User-agent: *
Allow: /

# ---- OpenAI ----
# GPTBot        — training / index crawler
# OAI-SearchBot — ChatGPT search index (citation eligibility)
# ChatGPT-User  — live fetch when a user's prompt triggers browsing
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# ---- Anthropic ----
# ClaudeBot        — crawler
# Claude-SearchBot — search index
# Claude-User      — live user-triggered fetch
# Claude-Web       — legacy agent, retained for completeness
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-Web
Allow: /

# ---- Perplexity ----
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# ---- Google ----
# Google-Extended governs Gemini training and grounding.
# It does NOT govern AI Overviews, which follow normal Googlebot indexing
# and snippet controls.
User-agent: Google-Extended
Allow: /

# ---- Common Crawl ----
# Not an engine. A public dataset that many models train from.
User-agent: CCBot
Allow: /

# ---- Microsoft / Copilot ----
User-agent: bingbot
Allow: /

Sitemap: https://www.extremeheating.com/sitemap.xml

# Human- and agent-readable summary of this site:
# https://www.extremeheating.com/llms.txt