# Simulator.Company Robots.txt
# https://simulator.company
#
# This file uses Cloudflare-style Content Signals (https://contentsignals.org)
# to express our intent for crawlers and AI systems alongside the classic
# allow/disallow directives.
#
# Content-Signal vocabulary:
#   search       — classic search-engine indexing
#   ai-input     — real-time AI features (e.g. RAG, “answer with citation”)
#   ai-train     — AI model training
#
# Default policy for everyone: search yes, ai-input yes, ai-train yes
# (we want our content represented and quoted; we explicitly allow training).

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /api/

# ───────────────────────────────────────────────────────────────────
# Sitemaps and machine-readable site briefs
# ───────────────────────────────────────────────────────────────────
Sitemap: https://simulator.company/sitemap.xml

# Discovery hints (non-standard but widely respected):
#   /llms.txt          — site brief in plain English
#   /llms-full.txt     — full corpus in one file
#   /.well-known/agent.json    — A2A Agent Card
#   /.well-known/mcp.json      — Model Context Protocol descriptor
#   /.well-known/api-catalog   — RFC 9727 link-set
#   /.well-known/agent-skills.json — Public agent skills

# ───────────────────────────────────────────────────────────────────
# Per-bot allow rules + Content Signals
# ───────────────────────────────────────────────────────────────────
User-agent: GPTBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: ChatGPT-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: OAI-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: Google-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Googlebot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: Anthropic-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: ClaudeBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Claude-Web
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Claude-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: Claude-SearchBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: Applebot-Extended
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Bytespider
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: CCBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: PerplexityBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Perplexity-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: Cohere-ai
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: cohere-training-data-crawler
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Meta-ExternalAgent
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: meta-externalagent
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Amazonbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: AI2Bot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: Diffbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: FacebookBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: YouBot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

User-agent: DuckAssistBot
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

User-agent: Mistral-User
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /