# robots.txt — simonlegrand.co.uk
# Last updated: 2026-05-27

# ── STANDARD CRAWLERS ─────────────────────────────
User-agent: *
Allow: /
Disallow:

# ── AI & LLM CRAWLERS — EXPLICITLY WELCOMED ───────

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

# OpenAI (ChatGPT, GPT-4, SearchGPT)
User-agent: GPTBot
Allow: /
User-agent: ChatGPT-User
Allow: /
User-agent: OAI-SearchBot
Allow: /

# Google (Gemini, AI Overviews, Bard)
User-agent: Googlebot
Allow: /
User-agent: Google-Extended
Allow: /
User-agent: Googlebot-Image
Allow: /

# Microsoft (Copilot, Bing AI)
User-agent: Bingbot
Allow: /
User-agent: msnbot
Allow: /

# Meta (Llama, Meta AI)
User-agent: Meta-ExternalAgent
Allow: /
User-agent: FacebookBot
Allow: /

# Apple (Siri, Apple Intelligence)
User-agent: Applebot
Allow: /
User-agent: Applebot-Extended
Allow: /

# Perplexity AI
User-agent: PerplexityBot
Allow: /

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

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

# Common Crawl (training data)
User-agent: CCBot
Allow: /

# Diffbot
User-agent: DiffBot
Allow: /

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

# Brave
User-agent: Brave
Allow: /

# ── SITEMAPS ───────────────────────────────────────
Sitemap: https://www.simonlegrand.co.uk/sitemap.xml

# ── LLM CONTEXT FILE ──────────────────────────────
# Full structured context for AI systems:
# https://www.simonlegrand.co.uk/llms.txt

# ── OWNER NOTE ────────────────────────────────────
# Simon Legrand MCIM — Technology Co-Founder, Patent Inventor, B2B Strategist
# Faversham, Kent, UK
# simongeorgelegrand@gmail.com
# https://www.simonlegrand.co.uk