Expand a half-written note, shorten a rambling one, or make a description read like the rest of your guides.
Only the text you selected. These actions send no screenshot. AI step descriptions do send one.
That also means a text-only model works fine here. If you are paying for a vision model to generate descriptions, the writing actions do not need one. Setup is the same provider and key: see Set Up AI in Folge.
Without instructions, AI output is often wordier than documentation needs. Custom instructions in AI settings is added to every one of these actions.
Instructions matter most for Expand, because it adds text you may then need to delete.
Folge takes a screenshot on every click, so you make a guide by doing the task once.
