# aramb.ai

# Content-Signal states the policy for everyone: index us, cite us, do not
# train on us. It is a Cloudflare-proposed extension, so the explicit
# per-crawler groups below carry the same intent for crawlers that ignore it.
User-agent: *
Content-Signal: search=yes,ai-train=no,use=reference
Allow: /

# /v1, /v2, /present and the two decks are duplicates or sales collateral, and
# are kept out of the index with X-Robots-Tag: noindex (see public/_headers),
# NOT with Disallow. Disallow blocks the fetch, which means a crawler never
# reads the noindex — so a disallowed page that someone links to can still be
# indexed, on the strength of the link alone. Letting it be crawled is what
# makes the noindex work.

# ---------------------------------------------------------------------------
# AI TRAINING CRAWLERS — blocked.
#
# Every agent below collects corpus for MODEL TRAINING. The retrieval and
# answer crawlers are deliberately NOT here — OAI-SearchBot, ChatGPT-User,
# Claude-User, Claude-SearchBot, PerplexityBot and Googlebot itself stay
# allowed, because being cited in an answer is the entire point of the
# structured data and llms.txt on this domain. Blocking those would trade away
# the AEO work to stop the training, and the two are separate crawlers.
#
# The -Extended agents matter for exactly this reason: Google-Extended governs
# Gemini training ONLY and has no effect on Google Search ranking or indexing,
# and Applebot-Extended is the same split for Apple. Blocking them costs no
# search visibility.
User-agent: Amazonbot
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: CloudflareBrowserRenderingCrawler
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: GPTBot
Disallow: /

User-agent: meta-externalagent
Disallow: /

# The index of indexes — marketing, blog + compare, docs, console.
# A Sitemap line is global: it belongs to the file, not to the group above it.
Sitemap: https://aramb.ai/sitemap.xml