# Hoffman Soft Water — robots.txt
# All crawlers, including search and AI/LLM agents, are welcome on the full site.

# Content-Signal states how the content may be USED, which is a separate
# permission from whether it may be crawled.
#   search=yes    — index it and link to it
#   ai-input=yes  — use it as source material for AI answers, with attribution
#   ai-train=yes  — use it as model training data
# ai-input=yes is the directive that keeps us eligible to be cited in AI
# answers. To withdraw training permission, change ai-train to no here and
# remove the training crawlers (CCBot, Google-Extended, Applebot-Extended)
# from the allow list below so the two do not contradict each other.
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Search engines
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# AI / LLM crawlers and answer engines
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

# Sitemaps and LLM guide
Sitemap: https://hoffmansoftwater.com/sitemap.xml
Sitemap: https://hoffmansoftwater.com/snowseo-sitemap.xml
# LLM-readable site summary: https://hoffmansoftwater.com/llms.txt
# Agent access guide:       https://hoffmansoftwater.com/auth.md
# API catalog:              https://hoffmansoftwater.com/.well-known/api-catalog
# Every page also has a Markdown twin at the same path with a .md suffix.