# Solum Health robots.txt
# https://getsolum.com

# RULE ORDER MATTERS — do not move `Allow: /` above the Disallow lines.
# RFC 9309 and Google resolve conflicts by LONGEST match, so order is
# irrelevant to them. Several parsers (including Python's urllib.robotparser)
# resolve by FIRST match, and under those a leading `Allow: /` matches every
# path and silently defeats every Disallow below it. Keeping Allow last is
# correct under both models.

# Default policy: allow crawling, block non-content directories
User-agent: *
Disallow: /.claude/
Disallow: /.playwright-mcp/
Disallow: /.well-known/
Disallow: /.git/
Disallow: /.vercel/
Disallow: /cms-data/
Disallow: /*?93051186_page=
Allow: /

# Explicitly allow AI crawlers (for AI discoverability).
#
# These are listed as ONE group with their own copy of the Disallow rules, not
# as eight bare `Allow: /` groups. Under RFC 9309 a crawler obeys only the most
# specific user-agent group that matches it and ignores every other group --
# groups do not inherit or merge. Eight groups containing nothing but `Allow: /`
# therefore exempted these crawlers from every Disallow above, which is the
# opposite of what the previous comment here claimed.
#
# Keep the two lists in sync: any Disallow added to `User-agent: *` must be
# added here too, or these crawlers are not bound by it.
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: PerplexityBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: cohere-ai
Disallow: /.claude/
Disallow: /.playwright-mcp/
Disallow: /.well-known/
Disallow: /.git/
Disallow: /.vercel/
Disallow: /cms-data/
Disallow: /*?93051186_page=
Allow: /

# Sitemap location
Sitemap: https://getsolum.com/sitemap.xml

# AI/LLM-readable site description
# https://llmstxt.org/
LLMs-Txt: https://getsolum.com/llms.txt