# robots.txt — https://www.unifiedstate.us
# Policy: fully open to search + AI crawlers. Only WP admin plumbing blocked.
#
# GROUP MATCHING — the thing most robots.txt files get wrong:
# a crawler obeys ONLY the single most specific User-agent group that matches
# it, and ignores every other group INCLUDING "*". So a Disallow you want a
# named bot to honour has to be repeated inside that bot's own group. That is
# why Disallow: /wp-admin/ appears in every group below rather than once.

User-agent: *
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# ── Anthropic / Claude ───────────────────────────────────────
# Three current agents. Claude-Web and Anthropic-AI are DEPRECATED and were
# removed from this file; rules naming them are matched by nothing.
#   ClaudeBot        — collects training corpus
#   Claude-User      — fetches a page when a Claude user asks about it
#   Claude-SearchBot — indexes content for Claude's search results
# These are independent: allowing one does not allow the others.

User-agent: ClaudeBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: Claude-User
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: Claude-SearchBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# ── OpenAI ───────────────────────────────────────────────────
User-agent: GPTBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: OAI-SearchBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: ChatGPT-User
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# ── Perplexity ───────────────────────────────────────────────
User-agent: PerplexityBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: Perplexity-User
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# ── Google, Apple, Amazon, Meta, Common Crawl, ByteDance ─────
# Google-Extended and Applebot-Extended govern AI training use only; they do
# not affect ordinary Googlebot / Applebot search indexing.

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Amazonbot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: meta-externalagent
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: CCBot
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

User-agent: Bytespider
Allow: /
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

# ── Sitemaps ─────────────────────────────────────────────────
# Sitemap lines are global — they apply regardless of User-agent group.
# wp-sitemap.xml covers WordPress posts/pages ONLY. Static .html files served
# straight off disk (including everything under /carrier/) are invisible to
# WordPress and must be declared separately, or they are never discovered.
Sitemap: https://www.unifiedstate.us/wp-sitemap.xml
Sitemap: https://www.unifiedstate.us/sitemap-static.xml

# ── AI content digest ────────────────────────────────────────
# Not a standard robots.txt directive — a comment pointer, which is the
# conventional way to surface it.
# https://www.unifiedstate.us/llms.txt