# Simple Online Ruler crawler policy
# Search/answer-engine visibility is allowed for all surfaces.
# AI training access (GPTBot, Google-Extended) is allowed because this is a
# free public utility with no proprietary content. To opt out of training,
# change the relevant "Allow: /" to "Disallow: /" and set ai-train=no below.
# Crawler names change often; verify against each operator's official docs.

# --- Content Signals (https://contentsignals.org/) ---
# Declares how automated systems may use this site's content.
# As a condition of accessing this website, you agree to abide by
# the following content signals:
# (a) If a Content-Signal = yes, you may collect content for the
#     corresponding use.
# (b) If a Content-Signal = no, you may not collect content for the
#     corresponding use.
# (c) If no signal is present for a use, no permission is granted or
#     restricted via content signal for that use.
#
# search:   building a search index and providing search results.
# ai-input: inputting content into AI models for RAG / grounding /
#           real-time generative AI answers.
# ai-train: training or fine-tuning AI models.

# --- Search engines ---
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# --- Answer engines / AI search ---
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# --- AI training / grounding (opt-out by switching to Disallow) ---
User-agent: GPTBot
Allow: /

User-agent: Google-Extended
Allow: /

# --- Everyone else ---
User-agent: *
Content-Signal: ai-train=yes, search=yes, ai-input=yes
Allow: /

Sitemap: https://simpleonlineruler.com/sitemap.xml