Supporting Novice Programmers with Scaffolded and Open-ended Generative AI Interfaces: Insights from a Design-based Research Study

In this study, we explore student experiences in coding and learning programming with scaffolded and unscaffolded generative AI interfaces. Specifically, we supported higher education students in using ChatGPT, an open ended interface for interacting with generative AI; and Giuseppe, a specialized interface with an OpenAI backend service that offers personalized supports specifically for helping students overcome early-stage challenges in learning to code, and working on education technology prototyping projects. This study contributes to the field by offering design insights for scaffolding initial learning interactions between generative AI interfaces and novice programmers. Our findings suggest that those new to coding welcome additional scaffolds at the outset of learning to code. The need for this scaffolding tended to fade with our participants as they gained familiarity with programming terminology and constructs as well as with using generative AI for learning technical skills and content.