I'm currently designing a 3-step creator for detecting objects in a live video stream with the help of AI.
The modal below shows the video and the radio button-like object selectors. However, I also want the user to know the limitations of the AI (limitations in darkness, objects must be close enough, etc) in order to set the right expectations for the user.
Right now I have a collapsible section, but I feel like it's a bit shoehorned where it is now and the area is too small to display anything meaningful.
I'd like to be able to display around 100 words of content.
Any ideas of how to present this content?