# Koukla Hair Studio - robots.txt
# Last updated: 2026-08-21 (served by the Node app)
# Policy: allow search + AI crawlers, block admin paths only

# --- Content Signals (https://contentsignals.org) ---
# Express preferences for how automated clients may use this site's content.
#   search    = build a search index and show results (links + short excerpts)
#   ai-input  = use content as input to AI models at run time (RAG / live AI answers)
#   ai-train  = use content to train or fine-tune AI models
# "yes" signals consent to that use. This is a stated preference, not an access control.

# --- Default policy ---
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Allow: /
Disallow: /wp-admin/
Disallow: /loginpage/
Disallow: /wp-login.php
Disallow: /api/
Allow: /wp-admin/admin-ajax.php

# --- Major search engines ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Applebot
Allow: /

# --- AI live-search bots (cite sources back to users) ---
User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# --- AI training bots (feed model knowledge for long-term citation) ---
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

# --- Sitemap ---
Sitemap: https://kouklastudio.com.au/sitemap.xml

# --- AI assistant content index ---
# llms.txt: https://kouklastudio.com.au/llms.txt
# This file points AI assistants (ChatGPT, Claude, Perplexity, etc.) to a curated content index in LLM-friendly Markdown.