# =====================================================================
# Example only — review before use. Generated by idealbusiness.ai, 30 Oct 2026.
# =====================================================================
#
# WHAT THIS IS
# Text for the "Robots.txt" box in Shoptet admin:
#   Vzhled a obsah -> Editor -> HTML kód -> Robots.txt
# Source: https://podpora.shoptet.cz/html-kody/
#
# READ FIRST
# 1. Shoptet ADDS this text to the END of its own standard robots.txt.
#    Do not paste a whole robots.txt file. Its standard "User-agent: *"
#    rules and its "Sitemap:" line stay in place.
# 2. When this box contains ANY text, Shoptet's built-in Content Signals
#    settings (search / AI answers / AI training) stop taking effect.
#    That is why this example writes its own Content-Signal line.
#    If you need NO other custom rules, leave the box EMPTY and use the
#    built-in settings above the editor instead.
# 3. Lines starting with "#" are comments and are ignored. You can
#    delete them to save space (the box allows max 8,192 characters).
# 4. robots.txt states preferences. It does not technically block
#    anyone, and it is not a legal contract (contentsignals.org).
# 5. Robots.txt never guarantees rankings or citations in AI answers.
#
# ---------------------------------------------------------------------
# PART 1: Content Signals for everyone
# This text lands right after Shoptet's "User-agent: *" rules, so the
# line below applies to all crawlers.
#   search=yes    -> search index, links and short excerpts
#   ai-input=yes  -> using your pages in AI answers (grounding, RAG)
#   ai-train=no   -> no training or fine-tuning of AI models
# Want to allow training? Change "ai-train=no" to "ai-train=yes".
# Syntax: https://contentsignals.org/
# ---------------------------------------------------------------------

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no

# ---------------------------------------------------------------------
# PART 2: AI search/answer services need NO extra group
# Shoptet's standard "User-agent: *" rules already let every crawler in
# (except private pages like cart and login). So OAI-SearchBot (ChatGPT
# search), Claude-SearchBot, PerplexityBot, Googlebot (incl. AI Overviews
# and AI Mode) and Bingbot (Copilot) are allowed without any extra lines.
# Do NOT add a separate group for them: a crawler named in its own group
# ignores the "User-agent: *" rules, including Shoptet's Disallow lines.
# If your box contains an old group like "User-agent: OAI-SearchBot" +
# "Disallow: /", DELETE it - it keeps you out of that assistant's answers.
# Sources: developers.openai.com/api/docs/bots,
#   support.claude.com/en/articles/8896518, docs.perplexity.ai/guides/bots,
#   developers.google.com/search/docs/appearance/ai-features
# ---------------------------------------------------------------------

# ---------------------------------------------------------------------
# PART 3: YOUR CHOICE - AI training
# The Content-Signal line above already says "ai-train=no". To ALSO
# block the crawlers/tokens used for AI training, UNCOMMENT the block
# below (remove the "# " at the start of each line).
#
#   GPTBot             OpenAI training. Independent of OAI-SearchBot:
#                      blocking it does NOT remove you from ChatGPT search.
#   ClaudeBot          Anthropic training data
#   Google-Extended    Gemini training AND grounding in Gemini Apps /
#                      Vertex AI. Does not affect Google Search inclusion
#                      or ranking. Blocking it may reduce use in Gemini answers.
#   Applebot-Extended  Apple foundation-model training. You stay in Apple
#                      search results.
#   CCBot              Common Crawl (open dataset widely used for AI training)
#
# Sources: developers.openai.com/api/docs/bots,
#   support.claude.com/en/articles/8896518,
#   developers.google.com/search/docs/crawling-indexing/google-common-crawlers,
#   support.apple.com/en-us/119829, commoncrawl.org/ccbot
# ---------------------------------------------------------------------

# User-agent: GPTBot
# User-agent: ClaudeBot
# User-agent: Google-Extended
# User-agent: Applebot-Extended
# User-agent: CCBot
# Disallow: /

# ---------------------------------------------------------------------
# PART 4: Sitemap
# Shoptet already adds a "Sitemap:" line to your robots.txt
# automatically. Uncomment the line below ONLY if your live robots.txt
# has none, and replace YOUR-SHOP with your domain.
# ---------------------------------------------------------------------

# Sitemap: https://www.YOUR-SHOP.cz/sitemap.xml

# ---------------------------------------------------------------------
# AFTER SAVING: open https://www.YOUR-SHOP.cz/robots.txt and check that
# the Content-Signal line appears at the end. OpenAI says
# changes for its search take about 24 hours to take effect.
# ---------------------------------------------------------------------