For the complete documentation index, see llms.txt. This page is also available as Markdown.

Choosing a Model

The AI Assistant can run on several AI models. Faster models answer small edits in seconds; stronger models handle large diagrams, documents and research decks more reliably. You pick the model per chat session from the selector under the composer.

The Model Selector

Below the message box, next to the attachment button, the current model is shown with its provider icon. Click it to open the list and pick another model. The choice applies to the current chat session; a new session starts with the default again.

The model selector under the composer

The list shows only the models your administrator has enabled. See AI Configuration.

Which Model to Use

Task
Suggested model

Renaming, recolouring, moving a few elements

The default fast model

A diagram of 10 to 30 elements from a prompt

A mid-range model

BPMN, C4 or ArchiMate diagrams with several containers

A stronger model

Rebuilding a board from a PDF or a long document

A stronger model

Research slide decks

The strongest model available

A model hint appears under the composer when the Assistant thinks a different model would suit your request better, for example when you ask for a deck while a fast model is selected.

Runs That Stop Early

Every run has a token budget. If a task is too large for the selected model, the Assistant stops, keeps your board unchanged and shows a Draft saved card. Switch to a stronger model and click Continue draft, or type "continue".

A run that stopped early: the board is unchanged and the draft can be continued

Last updated