# robots.txt for IKAD Mechanical Inc.
# Site: https://ikad.ca/
# Last updated: 2026-05-21

# ---------------------------------------------------------------
# Default crawl policy
# ---------------------------------------------------------------
User-agent: *
Allow: /
Disallow: /_build/
Disallow: /temp-extract/
Disallow: /api/

# ---------------------------------------------------------------
# Major search engine crawlers (explicitly allowed)
# ---------------------------------------------------------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Slurp
Allow: /

# ---------------------------------------------------------------
# AI / LLM training and search crawlers (explicitly allowed)
# IKAD welcomes AI engines citing our content with attribution.
# ---------------------------------------------------------------
# OpenAI / ChatGPT
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /

# Anthropic / Claude
User-agent: ClaudeBot
Allow: /
User-agent: Claude-Web
Allow: /
User-agent: anthropic-ai
Allow: /
User-agent: Claude-SearchBot
Allow: /

# Google Gemini / AI Overviews
User-agent: Google-Extended
Allow: /
User-agent: GoogleOther
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /
User-agent: Perplexity-User
Allow: /

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

# Apple Intelligence / Siri
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

# Common Crawl (used by many AI datasets)
User-agent: CCBot
Allow: /

# Meta AI / Llama
User-agent: meta-externalagent
Allow: /
User-agent: FacebookBot
Allow: /

# Cohere AI
User-agent: cohere-ai
Allow: /
User-agent: cohere-training-data-crawler
Allow: /

# Amazon Alexa / Rufus
User-agent: Amazonbot
Allow: /

# Other AI search and research crawlers
User-agent: PetalBot
Allow: /
User-agent: Diffbot
Allow: /
User-agent: ImagesiftBot
Allow: /
User-agent: Timpibot
Allow: /
User-agent: YouBot
Allow: /
User-agent: NeevaBot
Allow: /
User-agent: Brave-Bot
Allow: /
User-agent: Mistral-AI
Allow: /
User-agent: AI2Bot
Allow: /
User-agent: omgili
Allow: /
User-agent: omgilibot
Allow: /

# ---------------------------------------------------------------
# Aggressive backlink scrapers (disallowed to protect link profile)
# ---------------------------------------------------------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# ---------------------------------------------------------------
# Sitemaps and machine-readable manifests
# ---------------------------------------------------------------
Sitemap: https://ikad.ca/sitemap.xml

# Additional discovery files for AI engines:
# https://ikad.ca/llms.txt        (summary for AI ingestion)
# https://ikad.ca/llms-full.txt   (deep content for AI ingestion)
# https://ikad.ca/humans.txt      (team and credits)
# https://ikad.ca/.well-known/security.txt (security policy)