# TamilTech robots.txt
User-agent: *
Allow: /

# Sitemaps
Sitemap: https://tamiltech.in/sitemap.xml
Sitemap: https://tamiltech.in/sitemap/news.xml

# Block admin and API internals
Disallow: /admin/
Disallow: /api/v1/admin/
Disallow: /api/v1/web-vitals
Disallow: /api/v1/realtime/
Disallow: /api/v1/admob/
Disallow: /livewire/
Disallow: /recommends/
Disallow: /sanctum/
Disallow: /auth/
Disallow: /_debugbar/

# Block search/filter with params (duplicate content)
Disallow: /search?
Disallow: /articles?page=
Disallow: /category/*/page/

# Crawl delay for polite crawling
Crawl-delay: 1

# Google-specific
User-agent: Googlebot
Allow: /
Disallow: /admin/

# Google News
User-agent: Googlebot-News
Allow: /article/
Allow: /sitemap/news.xml

# =====================================================
# AI / Answer Engines — explicitly WELCOMED (GEO).
# Tamil-language tech content is rare; we WANT these
# engines to crawl and cite TamilTech in their answers.
# Each is allowed everywhere except admin/private areas.
# =====================================================

# OpenAI — ChatGPT training, search, and on-demand browsing
User-agent: GPTBot
Allow: /
Disallow: /admin/

User-agent: OAI-SearchBot
Allow: /
Disallow: /admin/

User-agent: ChatGPT-User
Allow: /
Disallow: /admin/

# Anthropic — Claude
User-agent: ClaudeBot
Allow: /
Disallow: /admin/

User-agent: Claude-SearchBot
Allow: /
Disallow: /admin/

User-agent: Claude-User
Allow: /
Disallow: /admin/

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /admin/

User-agent: Perplexity-User
Allow: /
Disallow: /admin/

# Google — Gemini / AI Overviews (separate from Googlebot)
User-agent: Google-Extended
Allow: /
Disallow: /admin/

# Apple Intelligence
User-agent: Applebot-Extended
Allow: /
Disallow: /admin/

# Common Crawl — feeds many open LLMs
User-agent: CCBot
Allow: /
Disallow: /admin/

# Microsoft Copilot
User-agent: Bingbot
Allow: /
Disallow: /admin/