# robots.txt for 365i.co.uk
# UK web hosting company (est. 2001) by BSolve IT Limited
# https://www.365i.co.uk

# =============================================================================
# DEFAULT: Allow all crawlers
# =============================================================================

User-agent: *
Allow: /

# Block internal/private directories
Disallow: /admin/
Disallow: /cache/
Disallow: /includes/

# Block API endpoints (not useful for indexing)
Disallow: /news/api/
Disallow: /tools/api/

# Block newsletter processing pages
Disallow: /newsletter/subscribe
Disallow: /newsletter/confirm
Disallow: /newsletter/pending

# =============================================================================
# AI CRAWLERS: Explicitly allowed
# =============================================================================

# OpenAI
User-agent: GPTBot
Allow: /

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

# Google AI (Gemini)
User-agent: Google-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

# Microsoft Copilot
User-agent: Bingbot
Allow: /

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

# Apple AI
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

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

# Amazon
User-agent: Amazonbot
Allow: /

# Common Crawl (open dataset used by many AI models)
User-agent: CCBot
Allow: /

# =============================================================================
# SEARCH ENGINE CRAWLERS
# =============================================================================

User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Slurp
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Yandex
Allow: /

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

Sitemap: https://www.365i.co.uk/sitemap.xml
Sitemap: https://www.365i.co.uk/news-sitemap.xml

# =============================================================================
# AI DISCOVERY (ai-visibility.org.uk specifications)
# =============================================================================

# LLM-readable site identity and context
# https://www.365i.co.uk/llms.txt
# https://www.365i.co.uk/llms.html

# AI usage permissions and restrictions
# https://www.365i.co.uk/ai.txt
# https://www.365i.co.uk/ai.json

# Structured identity, brand, and FAQ data
# https://www.365i.co.uk/identity.json
# https://www.365i.co.uk/brand.txt
# https://www.365i.co.uk/faq-ai.txt

# Developer and crawler guidance
# https://www.365i.co.uk/developer-ai.txt
# https://www.365i.co.uk/robots-ai.txt

# Crawl-delay: not set (we welcome frequent crawling)
# Host: https://www.365i.co.uk