Frontend builders create UI prototypes to guage alternate options, which is a time-consuming means of repeated iteration and refinement. Generative AI code assistants allow speedy prototyping just by prompting by way of a chat interface moderately than writing code. Nevertheless, whereas this interplay offers builders flexibility since they’ll write any immediate they want, it makes it difficult to regulate what’s generated. First, pure language by itself will be ambiguous, making it troublesome for builders to exactly talk their intentions. Second, the mannequin could reply unpredictably, requiring the developer to re-prompt by way of trial-and-error to restore any undesired adjustments. To deal with these weaknesses, we introduce Squire, a system designed for guided prototype exploration and refinement. In Squire, the developer incrementally builds a UI element tree by pointing and clicking on totally different alternate options recommended by the system. Further affordances let the developer refine the looks of the focused UI. All interactions are explicitly scoped, with ensures on what parts of the UI will and won’t be mutated. The system is supported by a novel intermediate illustration known as SquireIR with language help for managed exploration and refinement. By way of a person examine the place 11 frontend builders used Squire to implement cell net prototypes, we discover that builders successfully discover and iterate on totally different UI alternate options with excessive ranges of perceived management. Builders moreover scored Squire positively for usability and basic satisfaction. Our findings recommend the robust potential for code era to be managed in speedy UI prototyping instruments by combining chat with explicitly scoped affordances.
