# quinzi.live
#
# Cloudflare was answering this path with its own managed file -- a page of
# content-signal boilerplate and not one actual directive -- so nothing here
# was ever told what to crawl, and no sitemap was ever advertised. This is the
# origin's answer, served from the site tree like every other page.
#
# TWO AUDIENCES, DELIBERATELY DIFFERENT:
#   1. Search engines are welcome. We want to be found.
#   2. AI training crawlers are not. Her voice, her likeness, her character
#      and our copy are the product; a model trained on them is a competitor
#      built out of our own work. Blocked by name below.
#
# A robots.txt is a request, not a fence. The binding version lives at
# /legal and /terms, which expressly reserve all text and data mining
# rights. Ignoring this file does not create a licence.

# ---------------------------------------------------------------- search
User-agent: *
Allow: /

# ------------------------------------------------- AI training crawlers
# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Common Crawl -- the corpus most other training sets are built from
User-agent: CCBot
Disallow: /

# Google AI training (does NOT affect Google Search ranking)
User-agent: Google-Extended
Disallow: /

# Apple AI training (does NOT affect Siri or Spotlight search)
User-agent: Applebot-Extended
Disallow: /

# Anthropic
User-agent: anthropic-ai
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: ClaudeBot-User
Disallow: /

# Meta
User-agent: FacebookBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

User-agent: meta-externalfetcher
Disallow: /

# ByteDance / TikTok
User-agent: Bytespider
Disallow: /

# Amazon
User-agent: Amazonbot
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

# Others that collect for model training or resale
User-agent: cohere-ai
Disallow: /

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

User-agent: AI2Bot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: Omgili
Disallow: /

User-agent: YouBot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: Webzio-Extended
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: PanguBot
Disallow: /

User-agent: Kangaroo Bot
Disallow: /

User-agent: img2dataset
Disallow: /

Sitemap: https://quinzi.live/sitemap.xml