# Peridot — https://peridot.noetisphereai.com
#
# Search engines are welcome. Training crawlers are not.
#
# The rule below is the machine-readable half of a reservation made in words at
# /terms.html and in full in the application's licence: Noetisphere expressly
# reserves the rights of reproduction and extraction for text and data mining,
# including for the training of artificial intelligence systems, for the
# purposes of Article 4(3) of Directive (EU) 2019/790 and its equivalents.
# Permission is withheld and can be granted only in writing, in advance:
# info@noetisphereai.com
#
# This file asks. It cannot enforce — a crawler that ignores robots.txt is not
# stopped by robots.txt, and the honest place to say so is here rather than in
# a summary that implies otherwise. What it does is remove the defence that no
# reservation was expressed, which is what makes the legal route usable.

User-agent: *
Allow: /

# The coupon console. Nothing on this site links to it and the page carries
# its own noindex, but a Disallow is the half a well-behaved crawler reads
# BEFORE fetching — the meta tag only works on a page already retrieved.
#
# This is not what protects it. Access is decided by Cognito group membership
# on every request (amplify/functions/coupons/handler.ts); naming the path here
# tells a crawler not to index it and tells anybody reading this file that it
# exists, which is a trade worth making because the URL was never the secret.
Disallow: /admin.html

# ── Model training and dataset collection ──────────────────────────────
# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

# Anthropic
User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: Claude-Web
Disallow: /

# Common Crawl — the corpus many others are built from
User-agent: CCBot
Disallow: /

# Google and Apple publish these as TDM opt-out tokens rather than as crawlers:
# they do not fetch anything, they signal that fetched pages must not be used
# for model training. Search indexing is unaffected by them, which is why
# Googlebot and Applebot themselves are left alone above.
User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

# Others
User-agent: PerplexityBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Amazonbot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: AI2Bot
Disallow: /