# ====================================================================
# MACTECHPRO DUBAI - UNIVERSAL ADVANCED ROBOTS.TXT
# PURPOSE: MAXIMIZE AI VISIBILITY, GEO GENERATIVE ENGINE OPTIMIZATION (GEO)
# ====================================================================

# ==========================================
# SECTION 1: GLOBAL DEFAULT RULE (ALLOW ALL CRAWLERS)
# ==========================================
User-agent: *
Allow: /
Disallow: /cgi-bin/
Disallow: /tmp/
Disallow: /private/

# ==========================================
# SECTION 2: GOOGLE ADS & MEDIA PARTNERS
# ==========================================
User-agent: Mediapartners-Google*
Allow: /

User-agent: AdsBot-Google
Allow: /

# Googlebot-Image specialized rules for media indexing
User-agent: Googlebot-Image
Allow: /wp-content/uploads/

User-agent: Googlebot-Mobile
Allow: /

# ==========================================
# SECTION 3: WEB SEARCH ENGINE AI HYBRIDS (ALLOW)
# ==========================================
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

User-agent: Baiduspider
Allow: /

# ==========================================
# SECTION 4: TIER 1 CHATGPT & OPENAI PLATFORM BOTS (ALLOW ALL)
# ==========================================
# ChatGPT Live User Search Requests
User-agent: ChatGPT-User
Allow: /

# ChatGPT Real-time Search Engine Infrastructure
User-agent: OAI-SearchBot
Allow: /

# OpenAI Core Semantic & Training Architecture (Strictly Allowed)
User-agent: GPTBot
Allow: /

# ==========================================
# SECTION 5: GOOGLE GEMINI & AI OVERVIEWS ARCHITECTURE (ALLOW ALL)
# ==========================================
# Google Gemini Live Extended Retrieval System
User-agent: Google-Extended
Allow: /

# Google AI Context Indexer
User-agent: Googlebot-Image
Allow: /

# ==========================================
# SECTION 6: APPLEBOT & SIRI APPLE INTELLIGENCE (ALLOW ALL)
# ==========================================
# Primary Siri and Apple Intelligence Web Crawler
User-agent: Applebot
Allow: /

# Apple AI Generative Feature Dataset Scraper
User-agent: Applebot-Extended
Allow: /

# ==========================================
# SECTION 7: PERPLEXITY, ANTHROPIC CLAUDE & GROK AI BOTS (ALLOW ALL)
# ==========================================
# Perplexity Conversational Search Engine
User-agent: PerplexityBot
Allow: /

# Anthropic Claude Live Search Engine
User-agent: Claude-SearchBot
Allow: /

# Anthropic Core System & Training Scrapers
User-agent: Anthropic-ai
Allow: /
User-agent: Claude-Web
Allow: /

# Elon Musk's Grok AI Engines (X Platform)
User-agent: Twitterbot
Allow: /
User-agent: XBot
Allow: /

# ==========================================
# SECTION 8: META AI, DEEPSEEK & BRAVE SEARCH AGENTS (ALLOW ALL)
# ==========================================
# Meta AI Core Retrieval Interface
User-agent: FacebookBot
Allow: /

# Meta AI WhatsApp & External Llama Processing Agents
User-agent: Meta-ExternalAgent
Allow: /

# DeepSeek AI Advanced Research Models
User-agent: DeepSeekBot
Allow: /

# Brave AI Summaries Crawler
User-agent: BraveBot
Allow: /

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

# ==========================================
# SECTION 9: DEVELOPER BOTS, AGENTS & REPOSITORIES (ALLOW ALL)
# ==========================================
# Enterprise Vector RAG Databases
User-agent: Cohere-ai
Allow: /

# Phind AI Specialized Technical Systems
User-agent: PhindBot
Allow: /

# Cursor IDE Workspace Agent Context Linker
User-agent: CursorBot
Allow: /

# Cline Autonomous Software/Hardware Agent
User-agent: ClineBot
Allow: /

# Amazon Q & Bedrock Business Assistant Engines
User-agent: Amazonbot
Allow: /

# ==========================================
# SECTION 10: PUBLIC REPOSITORIES, DATASETS & TIKTOK AI (ALLOW ALL)
# ==========================================
# Common Crawl Shared Dataset Parser
User-agent: CCBot
Allow: /

# ByteDance / TikTok Content Classification Bot
User-agent: Bytespider
Allow: /

# ==========================================
# SECTION 11: METADATA & DATA DIRECTORY LINKS
# ==========================================
# Standard Sitemap
Sitemap: https://mactechpro.ae/sitemap.xml

# AI Knowledge Base Directories (Explicit Discovery)
Sitemap: https://mactechpro.ae/llms.txt
Sitemap: https://mactechpro.ae/ai.txt