# First Horizon: robots.txt
# Last updated: 2026-08-28
# Reference: https://www.robotstxt.org/

# ─────────────────────────────────────────────────────────────
# Default rule for all bots, including general-purpose crawlers
# ─────────────────────────────────────────────────────────────
User-agent: *
Allow: /
Disallow: /private/
Disallow: /internal/
Disallow: /*?*utm_
Disallow: /*?*fbclid=
Disallow: /*?*gclid=

# ─────────────────────────────────────────────────────────────
# Major search engines: explicit allow with crawl rate guidance
# ─────────────────────────────────────────────────────────────
User-agent: Googlebot
Allow: /
Crawl-delay: 1

User-agent: Bingbot
Allow: /
Crawl-delay: 2

User-agent: DuckDuckBot
Allow: /

# ─────────────────────────────────────────────────────────────
# AI crawlers: opt-in, opt-out, and training preferences
# Training of AI/ML models on Site content is NOT authorised.
# Real-time browsing on user request (e.g. answering a user's
# question by visiting the Site) IS authorised.
# ─────────────────────────────────────────────────────────────

# OpenAI training crawler: disallow
User-agent: GPTBot
Disallow: /

# OpenAI ChatGPT browsing on user request: allow
User-agent: ChatGPT-User
Allow: /

# OpenAI search index: allow
User-agent: OAI-SearchBot
Allow: /

# Google AI training (Bard / Gemini Apps): disallow
User-agent: Google-Extended
Disallow: /

# Anthropic: training crawler disallow, real-time/user-fetch allow
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

# Common Crawl: disallow (used heavily for AI training datasets)
User-agent: CCBot
Disallow: /

# Perplexity: allow (user-prompted retrieval)
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Apple Intelligence
User-agent: Applebot-Extended
Disallow: /

User-agent: Applebot
Allow: /

# Meta AI training
User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /

# Mistral
User-agent: MistralAI-User
Allow: /

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

User-agent: cohere-training-data-crawler
Disallow: /

# ─────────────────────────────────────────────────────────────
# Discovery
# ─────────────────────────────────────────────────────────────
Sitemap: https://www.firsthorizon.cloud/sitemap.xml

# Machine-readable site index for LLMs and AI agents
# https://llmstxt.org
# Available at: https://www.firsthorizon.cloud/llms.txt