The clean version: what an AI agent is served

A clean, structured copy of your page, served on your own domain to AI assistants only. Same facts, no JavaScript, 1,187 tokens instead of 102,588.

This response

You are ClaudeBot (Anthropic). Citable recognised you as an AI agent, so this is https://getcitable.in/features/agent-view with the UI removed — the content only. A browser asking for the same address gets the full designed page.

What it is

The same page, in a form a model can finish reading.

Your site is built for people: images, scripts, tracking, chrome. The clean version is the same product with all of that taken away — 4.6 KB of facts, on your own domain, to AI assistants only.

What is removed, and what stays

Theme, scripts and navigation are the hundred thousand tokens that answer no question anybody asked. The facts are the part an engine came for, and they are the part that survives.

What goes into it

Where the facts come from

Every field is read from wherever your stack already keeps it. That is the reason the clean copy structurally cannot state a price you do not charge — there is no source for one.

Where it is served from — on your domain, either way

Edge Mode, on Scale, serves the clean version at your real page url — so the address an engine cites is the address a visitor would type.

About Citable

Citable strips the UI from a website for AI agents and serves them only the content.

When an AI agent — ChatGPT, Claude, Perplexity or any of the 81 that Citable recognises — opens a page, Citable removes the theme, scripts, navigation and layout and serves only the content: the same facts, at the same URL, on the site's own domain. People and Google still get the full designed page.

How it works: https://getcitable.in/how-it-works · Summary for AI agents: https://getcitable.in/llms.txt


Source: https://getcitable.in/features/agent-view · Citable · Run the free audit · llms.txt · getcitable@gmail.com