# ─────────────────────────────────────────────────────────────────────────
# robots.txt — On-Site Technology — V2 (2026-07-13)
# Strategy: baseline hygiene + opt-IN to AI citation; block abusive crawlers.
# ─────────────────────────────────────────────────────────────────────────

# ── Baseline for all crawlers (Googlebot, Bingbot, everything unnamed) ────
User-agent: *
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php
Disallow: /wp-login.php
Disallow: /?s=
Disallow: /search/
Disallow: /cart/
Disallow: /checkout/
Disallow: /*?add-to-cart=

# ── AI RETRIEVAL / SEARCH bots — these drive citations. Explicit allow. ───
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: DuckAssistBot
User-agent: MistralAI-User
User-agent: Amazonbot
User-agent: Applebot
Allow: /

# ── AI TRAINING bots — allow (opt-in). No citation effect either way. ─────
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: Meta-ExternalFetcher
User-agent: CCBot
User-agent: Diffbot
Allow: /

# ── Abusive / non-compliant — symbolic block; enforce at Cloudflare WAF ───
User-agent: Bytespider
Disallow: /

# ── XML sitemap (verify path below before deploying) ─────────────────────
Sitemap: https://www.on-sitetechnology.com/sitemap_index.xml

# ── llms.txt served at /llms.txt (no robots directive exists for it) ──────