# Content signals (https://contentsignals.org): our explicit intent for automated use.
# search    = index this content and link to it in search results
# ai-input  = use this content to answer a user's question right now (AI search, RAG)
# ai-train  = use this content to train a generative model
# We say yes to all three: being found, cited, and known is the whole point.
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /

# Major LLM crawlers — allow explicit access for AI search engines
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Applebot-Extended
Allow: /

# XML sitemap — every public URL
Sitemap: https://sistava.com/sitemap.xml

# AI agent discovery (llms.txt standard)
# https://llmstxt.org
# LLM-friendly summary: /llms.txt
# Every public page, plain text: /llms-full.txt
# Full guide map for AI: /ai/guide_map.md
#
# Clean markdown for any public page, two ways:
#   1. append .md to the URL      → https://sistava.com/en/pricing.md
#   2. send Accept: text/markdown → same URL, markdown body
# HTML responses also carry a Link: rel="alternate" type="text/markdown" header.
#
# Machine-readable interface list (RFC 9727): /.well-known/api-catalog
# A2A Agent Card (public, platform level):    /.well-known/agent-card.json
# Security contact (RFC 9116):                /.well-known/security.txt