# ============================================================
# robots.txt — masonnguyengeo.com
# Policy: SEARCH = OPEN | AI-CITATION = OPEN | AI-TRAINING = CLOSED
# Aligned to ARM Agency master template · 2026-07-31
# ============================================================

User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no,use=reference
Allow: /

# ── TIER 1 — SEARCH INDEXING (distribution, always allow) ──

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Bravebot
Allow: /

User-agent: YandexBot
Allow: /

# ── TIER 2 — AI ANSWER / CITATION ENGINES (this IS the GEO play) ──
# These fetch content live to cite/quote/link you in AI answers.
# Blocking them = blocking your own AI-visibility strategy.

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Grok
Allow: /

User-agent: Grok-Extended
Allow: /

User-agent: Manus
Allow: /

User-agent: ManusBot
Allow: /

User-agent: Kimi
Allow: /

User-agent: MoonshotBot
Allow: /

User-agent: Codex
Allow: /

User-agent: OpenAI-CodexBot
Allow: /

User-agent: Copilot
Allow: /

User-agent: CopilotBot
Allow: /

User-agent: Gordon
Allow: /

User-agent: GordonBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: MistralBot
Allow: /

# ── TIER 3 — TRAINING-ONLY SCRAPERS (block — zero citation upside) ──
# Pure IP absorption into model weights. No link, no visit, no attribution.

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: ImagesiftBot
Disallow: /

# ── SITEMAP ──
Sitemap: https://masonnguyengeo.com/sitemap.xml