# AudioCodes.com Robots.txt
# Last Updated: September 2025
# This file controls how search engines and AI crawlers access AudioCodes.com

# Default rule for all robots
User-agent: *
Allow: /


# ==========================================
# MAJOR SEARCH ENGINES
# ==========================================

# Google Search Bot (Standard)
User-agent: Googlebot
Allow: /
Crawl-delay: 1

# Google Images
User-agent: Googlebot-Image
Allow: /

# Bing Search Bot
User-agent: bingbot
Allow: /
Crawl-delay: 1

# Baidu
User-agent: Baiduspider
Allow: /
Crawl-delay: 1


# Yahoo Search Bot
User-agent: Slurp
Allow: /
Crawl-delay: 1

# ==========================================
# AI CRAWLERS & LANGUAGE MODELS
# ==========================================

# AI & Crawler Guidelines
# AI-Guidelines: https://www.audiocodes.com/ai-guidelines
# For details on permitted uses, attribution, and contact information.

# OpenAI - GPT Training Data Collection
User-agent: GPTBot
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# OpenAI - Search Integration for ChatGPT
User-agent: OAI-SearchBot
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# OpenAI - User-triggered requests from ChatGPT
User-agent: ChatGPT-User
User-agent: ChatGPT-User/2.0
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# Anthropic Claude AI
User-agent: anthropic-ai
User-agent: ClaudeBot
User-agent: claude-web
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# Perplexity AI
User-agent: PerplexityBot
User-agent: Perplexity-User
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# Google Extended (for AI/Gemini)
User-agent: Google-Extended
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# Microsoft Bing AI/Copilot
User-agent: BingBot
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# Meta/Facebook
User-agent: FacebookBot
User-agent: meta-externalagent
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# LinkedIn
User-agent: LinkedInBot
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# ByteDance (TikTok)
User-agent: Bytespider
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# DuckDuckGo AI
User-agent: DuckAssistBot
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1


# ==========================================
# RESEARCH & ACADEMIC CRAWLERS
# ==========================================

# Allen Institute for AI
User-agent: AI2Bot
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# Common Crawl (Open Web Archive)
User-agent: CCBot
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# Diffbot (Structured Data Extraction)
User-agent: Diffbot
Disallow: /

Next Stage
# ==========================================
# EMERGING AI SEARCH ENGINES
# ==========================================

# You.com AI Search
User-agent: YouBot
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# Timpi Search
User-agent: TimpiBot
Allow: /products/
Allow: /solutions/
Allow: /voiceai/
Allow: /saas/
Allow: /company/
Allow: /news/
Allow: /services-support/
Allow: /library/
Allow: /investor-relations/
Allow: /success-stories/
Allow: /carrers/
Allow: /blog/
Crawl-delay: 1

# ==========================================
# FORUM & DISCUSSION CRAWLERS
# ==========================================

# Omgili (Forum/Discussion Indexer)
User-agent: omgili
Disallow: /

# ==========================================
# BLOCKED CRAWLERS
# ==========================================

# Aggressive or unwanted crawlers
User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

# Generic crawlers that don't identify themselves properly
User-agent: Python-requests
Disallow: /

User-agent: wget
Disallow: /

User-agent: curl
Disallow: /

# ==========================================
# SITEMAPS
# ==========================================

# Point crawlers to your sitemaps
Sitemap: https://www.audiocodes.com/sitemap.xml
Sitemap: https://www.audiocodes.com/video-sitemap.xml