# Zaions Portfolio — robots.txt
# https://zaions.com
# Last Updated: 2026-04-24
#
# Also see:
#   /sitemap.xml         — full URL index
#   /feed.xml            — RSS feed for blog + content updates
#   /llms.txt            — LLM index file (https://llmstxt.org/)
#   /llms-full.txt       — extended LLM knowledge file
#   /ai.txt              — AI training / access policy
#   /humans.txt          — humans behind the site
#   /.well-known/security.txt — security contact

Sitemap: https://zaions.com/sitemap.xml

# ============================================================
# Default rules (all crawlers)
# ============================================================

User-agent: *
Allow: /

# Private / auth-only routes
Disallow: /admin
Disallow: /admin/
Disallow: /login
Disallow: /logout
Disallow: /forgot-password
Disallow: /settings
Disallow: /settings/
Disallow: /offline
Disallow: /my-queries
Disallow: /data-deletion

# ============================================================
# AI Search & Answer Engine Crawlers (explicit allow)
# ============================================================
# Strategy: zaions.com WANTS to be discoverable by AI answer engines.
# These crawlers power ChatGPT, Claude, Perplexity, Google AI Overviews,
# Bing Copilot, and other systems that answer user questions.

# OpenAI (ChatGPT search, GPT training corpus, OAI Search)
User-agent: GPTBot
Allow: /
Disallow: /admin/
Disallow: /api/

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic (Claude AI)
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google AI (Gemini, AI Overviews, Search Generative Experience)
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# Common Crawl (training corpus for many AI systems)
User-agent: CCBot
Allow: /

# Amazon AI (Alexa, Q, Rufus)
User-agent: Amazonbot
Allow: /

# Meta AI (Meta platforms, Llama, Meta Search)
User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: meta-externalagent
Allow: /

# Apple AI (Siri, Apple Intelligence, Spotlight)
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /

# Mistral AI
User-agent: MistralAI-User
Allow: /

# You.com AI
User-agent: YouBot
Allow: /

# Brave Search AI
User-agent: BraveBot
Allow: /

# ByteDance / TikTok AI
User-agent: Bytespider
Allow: /

# Diffbot (AI knowledge graph, powers many LLM data pipelines)
User-agent: DiffbotBot
Allow: /

User-agent: Diffbot
Allow: /

# Timpi / decentralized search / AI aggregators
User-agent: TimpiBot
Allow: /

# Kagi (privacy-focused search + AI)
User-agent: KagiBot
Allow: /

User-agent: Kagibot
Allow: /

# DuckDuckGo AI / Assist
User-agent: DuckAssistBot
Allow: /

# Neeva / Snowflake AI
User-agent: NeevaBot
Allow: /

# Goose (open-source AI agent framework)
User-agent: GooseBot
Allow: /

# Webz.io (AI data provider)
User-agent: Webzio-Extended
Allow: /

# PetalBot (Huawei AI)
User-agent: PetalBot
Allow: /

# Omigili (news AI)
User-agent: omgili
Allow: /

User-agent: omgilibot
Allow: /

# ============================================================
# Traditional Search Engines
# ============================================================

User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /
Crawl-delay: 1

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /
Crawl-delay: 2

User-agent: YandexBot
Allow: /
Crawl-delay: 2

User-agent: Baiduspider
Allow: /
Crawl-delay: 2

User-agent: Naverbot
Allow: /

User-agent: Seznambot
Allow: /

User-agent: Mojeekbot
Allow: /

# ============================================================
# Blocked Crawlers (SEO scrapers / content harvesters)
# ============================================================

User-agent: MJ12bot
Disallow: /

User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: SerpstatBot
Disallow: /

User-agent: MegaIndex
Disallow: /

User-agent: ZoominfoBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: PetalSearch
Disallow: /