# Dayko.ai, robots.txt
# Last updated: 2026-06-17
# Documentation: https://dayko.ai/llms.txt

# ── Standard crawlers ────────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /api/
Disallow: /admin/
Disallow: /.env
Disallow: /dashboard/

Sitemap: https://dayko.ai/sitemap.xml

# ── AI SEARCH BOTS, Allow citation and search indexing ─────────────────────
# Strategy: Allow all citation/search bots. These drive AI-referred traffic.
# Blocking any of these removes Dayko from that engine's citation pool.

# OpenAI (ChatGPT Search, real-time retrieval, training)
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# Anthropic (Claude Search, real-time retrieval, training)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Legacy Anthropic identifiers, kept for backwards compatibility
User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

# Perplexity (search indexing and real-time retrieval)
# Note: Perplexity-User has been documented ignoring robots.txt.
# Server-layer rules (Cloudflare Bot Management) recommended for Perplexity.
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI (Gemini training, AI Overviews / SGE)
User-agent: Google-Extended
Allow: /

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

# Meta AI (Meta AI assistant)
User-agent: FacebookBot
Allow: /

# Cohere (Command models)
User-agent: cohere-ai
Allow: /

# ── BULK SCRAPERS, Block ────────────────────────────────────────────────────
# These bots perform large-scale archival crawling not related to AI search citation.
# Block to avoid content being used for mass model training without consent.

# Common Crawl (bulk archive, not AI search)
User-agent: CCBot
Disallow: /

# Bytespider (ByteDance, documented non-compliance with robots.txt as of Aug 2025)
User-agent: Bytespider
Disallow: /

# ── MACHINE-READABLE FILES ───────────────────────────────────────────────────
# AI agents: see llms.txt for structured site context
# llms.txt: https://dayko.ai/llms.txt
# Markdown endpoints: https://dayko.ai/index.md, /kindle.md, /echo.md, /pronto.md
# WebMCP: https://dayko.ai/.well-known/webmcp.json