Glossary
Multimodal prompt
A multimodal prompt is an instruction that combines more than one kind of input, such as text together with a photo, a document or a recording.
What it means in practice
Say what you want done with each part, for example which picture to look at and what to extract. Check anything the model read from an image, because small text and numbers are easy to misread.
Example
Uploading a photo of a handwritten price list and asking for a clean table of the items.
Term: Multimodal AIGuide: From a call or photo to a quote signed the same dayGuide: Tell AI how to think, not just what to doAll terms