Scratch Copilot: Supporting Youth Creative Coding with AI

TL;DR

This paper introduces Cognimates Scratch Copilot, an AI assistant integrated into a block-based coding environment for children, supporting creative coding processes and highlighting the importance of youth agency in AI interactions.

Contribution

It presents the design, implementation, and qualitative evaluation of an AI-powered coding assistant tailored for children, emphasizing user agency and interaction dynamics.

Findings

Supported key creative processes like ideation and debugging

Children actively negotiated AI suggestions, maintaining creative control

Identified design tensions between scaffolding and independence

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.