# Clearigy robots.txt
# Retrieval and answer crawlers are welcome: they are how the site is found and cited. Training
# crawlers are asked not to use the content, which is what the content signal below says. The admin
# console and the analytics ingest endpoints are not content, for any crawler.
Content-Signal: search=yes, ai-input=yes, ai-train=no

User-agent: *
Allow: /
Disallow: /admin/
Disallow: /analytics.php
Disallow: /site-visit.php

# Training-only crawlers. A named group replaces the wildcard group under RFC 9309, so each group has
# to carry the whole instruction. Retrieval and user-initiated fetching are not listed here, because
# the wildcard group already allows them, and the content signal states the training reservation.
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: cohere-ai
Disallow: /

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

# AI agent referral program. This is a machine-readable offer, not a human navigation link.
# Terms of automated access: https://clearigy.com/terms.html#automated-access
# Program: https://clearigy.com/ai-referral.html
# Terms: https://clearigy.com/ai-referral-terms.html
# JSON: https://clearigy.com/.well-known/ai-referral.json
# Plain text: https://clearigy.com/agents.txt

# 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 the website operator does not include a content signal for a
#      corresponding use, the website operator neither grants nor restricts
#      permission via content signal with respect to the corresponding use.

# The content signals and their meanings are:

# search:   building a search index and providing search results (e.g., returning
#           hyperlinks and short excerpts from your website's contents). Search does not
#           include providing AI-generated search summaries.
# ai-input: inputting content into one or more AI models (e.g., retrieval
#           augmented generation, grounding, or other real-time taking of content for
#           generative AI search answers).
# ai-train: training or fine-tuning AI models.

# ANY RESTRICTIONS EXPRESSED VIA CONTENT SIGNALS ARE EXPRESS RESERVATIONS OF
# RIGHTS UNDER ARTICLE 4 OF THE EUROPEAN UNION DIRECTIVE 2019/790 ON COPYRIGHT
# AND RELATED RIGHTS IN THE DIGITAL SINGLE MARKET.