Scratch Copilot: Supporting Youth Creative Coding with AI
Stefania Druga, Amy J. Ko
TL;DR
The paper tackles the challenge of helping youth translate imaginative ideas into functional block based code by introducing Cognimates Scratch Copilot, an AI powered assistant embedded in a Scratch like environment. It details the system design and a qualitative evaluation with eighteen children across multiple countries, showing improvements in ideation, asset creation, debugging, and platform navigation while underscoring the importance of preserving youth agency. It contributes an initial design framework for youth oriented AI coding tools that emphasizes user control, transparency, and culturally responsive interaction, along with insights into ethical considerations. The findings suggest that AI copilots can boost creative self efficacy and engagement in youth while also highlighting risks of over reliance and the importance of multimodal and contextualized support. Together these results inform scalable, youth centered AI education tools that augment rather than replace creative problem solving in visual programming contexts.
Abstract
Creative coding platforms like Scratch have democratized programming for children, yet translating imaginative ideas into functional code remains a significant hurdle for many young learners. While AI copilots assist adult programmers, few tools target children in block-based environments. Building on prior research \cite{druga_how_2021,druga2023ai, druga2023scratch}, we present Cognimates Scratch Copilot: an AI-powered assistant integrated into a Scratch-like environment, providing real-time support for ideation, code generation, debugging, and asset creation. This paper details the system architecture and findings from an exploratory qualitative evaluation with 18 international children (ages 7--12). Our analysis reveals how the AI Copilot supported key creative coding processes, particularly aiding ideation and debugging. Crucially, it also highlights how children actively negotiated the use of AI, demonstrating strong agency by adapting or rejecting suggestions to maintain creative control. Interactions surfaced design tensions between providing helpful scaffolding and fostering independent problem-solving, as well as learning opportunities arising from navigating AI limitations and errors. Findings indicate Cognimates Scratch Copilot's potential to enhance creative self-efficacy and engagement. Based on these insights, we propose initial design guidelines for AI coding assistants that prioritize youth agency and critical interaction alongside supportive scaffolding.