Scratch Copilot: Supporting Youth Creative Coding with AI

2025-05-06

AI Summary

Children aged 7–12 face challenges in translating creative ideas into functional programs within block-based programming environments (e.g., Scratch), compounded by a lack of age-appropriate AI support. Method: We designed and implemented a negotiable AI programming collaborator—integrated into a block-based environment—that leverages a lightweight large language model and program semantic understanding to deliver real-time creative scaffolding, code generation, debugging assistance, and multimedia asset creation, augmented with multi-turn dialogue, error awareness, and visual feedback. Contribution/Results: Its core innovation lies in centering child agency through a negotiation mechanism enabling children to actively adopt, revise, or reject AI suggestions—thus balancing AI scaffolding with the development of independent problem-solving skills. In an exploratory evaluation with 18 international children, the system significantly enhanced creative self-efficacy and engagement, empirically validating the “critical collaboration” paradigm for AI-integrated programming education in childhood.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Multiagent Systems: Agreement, Argumentation & Negotiation
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Addressing children's difficulty in translating ideas into Scratch code
• Lack of AI tools for kids in block-based coding environments
• Balancing AI assistance with fostering independent problem-solving

Innovation

• AI-powered assistant in Scratch-like environment
• Real-time support for ideation and debugging
• Prioritizes youth agency and creative control