# ─────────────────────────────────────────
# navneetjha.com — robots.txt
# Optimised for AI visibility & GEO
# ─────────────────────────────────────────

# ── CONTENT SIGNALS ──
# search:   yes — index and return in search results
# ai-input: yes — use content for RAG, grounding, AI answers
# ai-train: yes  — use for model training

User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no
Allow: /
Disallow: /private/
Disallow: /admin/

# ── SEARCH ENGINES ──
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

# ── AI CRAWLERS — EXPLICITLY ALLOWED ──

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /
Content-Signal: ai-input=yes

# OpenAI (ChatGPT)
User-agent: GPTBot
Allow: /
Content-Signal: ai-input=yes

# OpenAI (SearchGPT)
User-agent: OAI-SearchBot
Allow: /
Content-Signal: ai-input=yes

# Google AI (Gemini, AI Overviews)
User-agent: Google-Extended
Allow: /
Content-Signal: ai-input=yes

# Googlebot for AI features
User-agent: Googlebot-AI
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /
Content-Signal: ai-input=yes

# Meta AI
User-agent: meta-externalagent
Allow: /
Content-Signal: ai-input=yes

# Apple
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

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

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

# Mistral
User-agent: MistralBot
Allow: /

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

# Brave Search
User-agent: Brave
Allow: /

User-agent: SemrushBot
Allow: /

# ── BLOCKED — BAD BOTS & SCRAPERS ──
User-agent: AhrefsBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

# ── SITEMAPS ──
Sitemap: https://navneetjha.com/sitemap-index.xml
Sitemap: https://navneetjha.com/sitemap-0.xml