# usectl robots.txt
# We welcome AI agents and search crawlers.
# The llms.txt file at the root describes the site for AI consumption.

User-agent: *
Allow: /

# Content Signals (Cloudflare / IETF draft).
# search=yes     → allow traditional search indexing
# ai-train=yes   → allow training use
# ai-input=yes   → allow AI search / answer-engine use
Content-Signal: search=yes, ai-train=yes, ai-input=yes

# ── Explicit allow for major AI crawlers ─────────────────────────────

# OpenAI
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

# Anthropic
User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

# Google (AI training opt-in)
User-agent: Google-Extended
Allow: /

# Apple (AI training opt-in)
User-agent: Applebot-Extended
Allow: /

# Perplexity
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# Common Crawl (used by many AI training datasets)
User-agent: CCBot
Allow: /

# Meta (Llama training and Meta AI)
User-agent: Meta-ExternalAgent
Allow: /

User-agent: FacebookBot
Allow: /

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

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

# DuckDuckGo Assist
User-agent: DuckAssistBot
Allow: /

# Amazon
User-agent: Amazonbot
Allow: /

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

# ByteDance / Doubao
User-agent: Bytespider
Allow: /

# Diffbot
User-agent: Diffbot
Allow: /

# xAI (Grok)
User-agent: xAI-Bot
Allow: /

Sitemap: https://usectl.com/sitemap.xml