# Toffin Indonesia — robots.txt
# Default policy: allow all crawlers, including AI/LLM bots
# Last updated: 2026-05-22

# ── All crawlers (default) ──
User-agent: *
Allow: /


# ════════════════════════════════════════════════════════════════════
# AI / LLM crawlers — explicit allow
# Toffin marketing content publik, OK di-include di AI search & training
# untuk maksimasi brand visibility (free exposure via ChatGPT/Claude/Gemini/Perplexity)
# ════════════════════════════════════════════════════════════════════

# OpenAI (ChatGPT training + ChatGPT browsing + AI search)
User-agent: GPTBot
Allow: /


User-agent: ChatGPT-User
Allow: /


User-agent: OAI-SearchBot
Allow: /


# Anthropic (Claude training + browsing)
User-agent: ClaudeBot
Allow: /


User-agent: Claude-Web
Allow: /


User-agent: anthropic-ai
Allow: /


# Common Crawl (data feed untuk banyak LLM training)
User-agent: CCBot
Allow: /


# Perplexity AI (search engine dengan citation)
User-agent: PerplexityBot
Allow: /


# Google AI (Gemini training, terpisah dari Googlebot regular)
User-agent: Google-Extended
Allow: /


# Apple (Apple Intelligence training)
User-agent: Applebot-Extended
Allow: /


# ByteDance (TikTok/Doubao)
User-agent: Bytespider
Allow: /


# AI/LLM resources (untuk discovery by AI agents):
# https://www.toffin.id/llms.txt         — structured site index
# https://www.toffin.id/llms-full.txt    — full content compilation

# Sitemap location
Sitemap: https://www.toffin.id/sitemap.xml