# robots.txt for supplemental.pl
# Last updated: 2026-09-18
#
# IMPORTANT: In Cloudflare Dashboard set AI Crawlers to "Do not block"
# (Security > Bots > AI Crawlers) to prevent CF from injecting Disallow
# rules that override this file.

# ============================================
# CONTENT SIGNALS (Article 4, EU Directive 2019/790)
# ============================================
# search=yes   — building search index, returning hyperlinks and excerpts
# ai-input=yes — RAG, grounding, real-time generative AI search answers
# ai-train=no  — training or fine-tuning AI models on this content

# ============================================
# DEFAULT POLICY: open for all crawlers
# ============================================
User-agent: *
Content-Signal: search=yes,ai-input=yes,ai-train=no
Allow: /
Disallow: /*?*view=
Disallow: /*?*format=
Disallow: /cdn-cgi/

# ============================================
# AI / LLM CRAWLERS — explicit allow
# ============================================
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: cohere-ai
Allow: /

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

User-agent: Bytespider
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: DuckAssistBot
Allow: /

User-agent: YouBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: Diffbot
Allow: /

User-agent: FacebookBot
Allow: /

User-agent: Meta-ExternalAgent
Allow: /

User-agent: Meta-ExternalFetcher
Allow: /

User-agent: CloudflareBrowserRenderingCrawler
Allow: /

# ============================================
# Sitemaps & AI manifest
# ============================================
Sitemap: https://supplemental.pl/sitemap.xml

# LLMs.txt manifest (https://llmstxt.org)
# https://supplemental.pl/llms.txt
# https://supplemental.pl/llms-full.txt

# FAQ (indexable): https://supplemental.pl/faq/
# Hub pages: https://supplemental.pl/hub-pages/
# AI Chatbot (Claude-powered): https://supplemental.pl/#ai-chatbot
# Available 24/7, free, EU food law specialist
# Konstruktor Praw (voice): https://supplemental.pl/rozmowa/