# robots.txt — Dwarkesh Metal Industries
# Ahmedabad, Gujarat, India
#
# Everything on this site is public. Nothing here is disallowed.
# The AI assistants are listed explicitly rather than left to the wildcard:
# they are the crawlers most often blocked by default hosting configs, and
# being crawlable is a precondition for being cited in an AI answer.

# --- Search engines ---
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# --- AI assistants and answer engines ---
# OpenAI: GPTBot trains and indexes; ChatGPT-User and OAI-SearchBot fetch
# pages live when someone asks a question.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

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

User-agent: Claude-User
Allow: /

User-agent: anthropic-ai
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Google's AI products (Gemini, AI Overviews grounding)
User-agent: Google-Extended
Allow: /

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

User-agent: Applebot-Extended
Allow: /

# Microsoft Copilot
User-agent: BingPreview
Allow: /

# Common Crawl — the corpus many models and tools read from
User-agent: CCBot
Allow: /

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

# Amazon
User-agent: Amazonbot
Allow: /

# --- Everyone else ---
User-agent: *
Allow: /

# TODO: uncomment and set the real hostname once the domain is live.
# The sitemap must be an absolute URL; a relative path is invalid here.
Sitemap: https://dwarkeshmetal.co.in/sitemap.xml