DocsContent
Content
Once an agent has a page, can it read it cheaply and correctly?
An agent pays for every token it reads and most never run JavaScript. This layer is about whether the words are in the response, whether a cheaper machine-readable form is offered, and whether the text is labelled well enough to be interpreted rather than guessed at.
Scored
Detected and validated. Each page lists the checks that can fail it and on whose authority.
Server-side rendering web baseline ► flat
Whether the content exists before JavaScript runs. Most agents never run it.
Markdown twin early production ▲ rising
A clean low-token markdown version of the page for agents.
JSON-LD web baseline ► flat
Structured data describing what this page is about.
Language and encoding web baseline ► flat
Declared language and charset, so text is interpreted correctly.