# robots.txt — Leadbox Platform (2026)
# Site: southsidedodge.ca · Policy: ai-train=yes · Generated: 2026-09-03

# ── Default: everyone may crawl ──────────────────────────────────────
# Content-Signal (contentsignals.org): machine-readable usage policy.
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Disallow: /wp-admin/
Allow: /wp-admin/admin-ajax.php

Sitemap: https://southsidedodge.ca/sitemap_index.xml

# LLM guidance: https://southsidedodge.ca/llms.txt

# ── AI search & assistant crawlers — always allowed ─────────────────
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: ClaudeBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot
User-agent: Amazonbot
User-agent: Bingbot
User-agent: DuckAssistBot
User-agent: Meta-ExternalFetcher
Allow: /

# ── AI model-training crawlers / opt-out tokens ──────────────────────
User-agent: GPTBot
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: meta-externalagent
Allow: /

# ── Bulk scrapers with no search or referral value — blocked ────────
User-agent: CCBot
User-agent: Bytespider
User-agent: PetalBot
User-agent: Timpibot
Disallow: /