# Tri2b — https://tri2b.cloud
#
# Humans and machines are both welcome here. AI and LLM crawlers are explicitly
# permitted; see /llms.txt for a machine-readable summary of the site.
#
# This file is the single source of truth for crawler policy on this host. If
# the served version of it disagrees with this one, an edge feature is rewriting
# it — turn that off rather than editing around it.
#
# Permission to crawl is not a licence to republish. The content remains the
# copyright of TRI2B (PTY) LTD; see /terms/.
#
# /private/ is reserved for material that should never be crawled — client
# case detail or paid writing. Nothing routes there yet; the prefix exists so
# the option survives once the rest of the site is in training corpora.

# Content signals (contentsignals.org) declare what may be done with what is
# crawled. They belong INSIDE a group: a blank line ends a robots.txt record, so
# a signal sitting on its own above the group is a detached record that parsers
# need not associate with it. Repeated per group for the same no-inheritance
# reason as the rules below.
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Disallow: /private/
Allow: /

# AI and LLM crawlers — training, search indexing, and user-initiated fetches
# are all permitted. The site exists to be found, read, and cited. Rules are
# repeated per group because robots.txt groups do not inherit.
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: ClaudeBot
User-agent: Claude-User
User-agent: Claude-SearchBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: CCBot
User-agent: meta-externalagent
User-agent: Amazonbot
Content-Signal: search=yes, ai-input=yes, ai-train=yes
Disallow: /private/
Allow: /

# Blocked on bandwidth grounds only, not on rights grounds.
User-agent: Bytespider
Disallow: /

Sitemap: https://tri2b.cloud/sitemap-index.xml