# Robots.txt — Manifest Behavioral Health
#
# Stance: AI crawlers ARE permitted. Healthcare content benefits substantially
# from being cited by AI search engines (Google AI Overviews, Perplexity,
# ChatGPT browsing, Claude). The privacy concern with AI crawlers is training
# data — these directives govern indexing/citation, not training-by-default.
# If you later want to opt out of training, add `Google-Extended` to a Disallow
# block. For now we permit it: citation share is the primary AEO outcome.

# Single wildcard group — one User-agent: * block so directives are unambiguous
# for Googlebot (two separate groups previously made Disallow rules ambiguous).
User-agent: *
Allow: /
Disallow: /thanks/
Disallow: /admin/

# Explicit allowlist for the major AI search/citation crawlers — redundant with
# the wildcard above, but makes intent legible to ops and to bot operators that
# look for their own UA in robots.txt before crawling.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot-Extended
Allow: /

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