# robots.txt — Wasema.com
# Updated: 2026-06-06
# Strategy: Allow AI SEARCH bots (citations + referral traffic), block AI TRAINING bots (no traffic in return)

# ─────────────────────────────────────────────
# ✅ ALLOW — Search-focused AI bots (bring citations and referral traffic)
# ─────────────────────────────────────────────

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

# ─────────────────────────────────────────────
# ❌ BLOCK — Training-only bots (scrape content, give nothing back)
# ─────────────────────────────────────────────

# OpenAI training crawler (different from ChatGPT-User search bot)
User-agent: GPTBot
Disallow: /

# Google Gemini training (does NOT affect Google Search rankings — safe to block)
User-agent: Google-Extended
Disallow: /

# Anthropic training crawler (separate from ClaudeBot search citations)
User-agent: anthropic-ai
Disallow: /

# Common Crawl — feeds many AI training datasets
User-agent: CCBot
Disallow: /

# ByteDance / TikTok training crawler
User-agent: Bytespider
Disallow: /

# Cohere AI training
User-agent: cohere-ai
Disallow: /

# ─────────────────────────────────────────────
# General crawl settings
# ─────────────────────────────────────────────

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /login
Disallow: /register
Disallow: /go/
Crawl-delay: 2

# Sitemap
Sitemap: https://wasema.com/sitemap.xml

# LLM context file (new 2026 standard)
# LLMs: https://wasema.com/llms.txt