Skip to main content
An HTML document is a finished page: a formatted report, a visual summary, a one-pager you send a teammate a link to. Your agent builds it, and it opens as a designed page rather than as a document you edit.
This is not one of the six document formats. Those are views over a document you keep working on. An HTML document is a finished artefact — a snapshot, not a workspace.

​
How one gets created

Ask your agent:
“Turn the Q3 channel numbers into a one-page HTML report I can send to the board.”
Only a connected agent can create one — there is no new-HTML-document button and no editor for them in the app. To change one, ask your agent again and it replaces the page. Tatara checks every HTML document as it is written and tells the agent what to fix if anything is wrong, so what lands in your brain is a page that renders. Pages are shown in a secure sandbox that runs no code and makes no outside requests, which means an HTML document in your brain can never phone home or run something unexpected when you open it.

​
How it renders

An HTML document is read-only. It fills the reading area edge to edge, with no title heading, no width control, and no editor. Two actions sit in the topbar:
  • Open raw in new tab opens the page on its own.
  • Expand gives it the full window.
Unlike a document carrying a render format, an HTML document does have the properties rail, so it can be filed, described, and tagged like anything else. It gains a File card at the top showing the filename, the line embedded · static html · no scripts · sandboxed, and an Open raw ↗ link.

​
If it looks wrong

If the page looks broken or empty, or shows Couldn't load HTML content., ask your agent to rebuild it — that is the fix, and it knows the rules it has to meet. See Troubleshooting.