It’s difficult to generate the code for a whole person interface utilizing a Massive Language Mannequin (LLM). Person interfaces are complicated and their implementations typically encompass a number of, inter-related information that collectively specify the contents of every display, the navigation flows between the screens, and the information mannequin used all through the applying. It’s difficult to craft a single immediate for an LLM that incorporates sufficient element to generate an entire person interface, and even then the result’s regularly a single massive and obscure file that incorporates all the generated screens. On this paper, we introduce Athena, a prototype utility era surroundings that demonstrates how the usage of shared intermediate representations, together with an app storyboard, information mannequin, and GUI skeletons, can assist a developer work with an LLM in an iterative style to craft an entire person interface. These intermediate representations additionally scaffold the LLM’s code era course of, producing organized and structured code in a number of information whereas limiting errors. We evaluated Athena with a person examine that discovered 75% of individuals most popular our prototype over a typical chatbot-style baseline for prototyping apps.
