Scaling CS1 Support with Compiler-Integrated Conversational AI

TL;DR

This paper presents DCC Sidekick, an AI-powered debugging assistant integrated into a C/C++ compiler, which significantly supports large-scale CS1 courses by providing accessible, context-aware error explanations based on extensive usage data.

Contribution

The paper introduces DCC Sidekick, a novel compiler-integrated conversational AI tool that enhances debugging support and demonstrates scalable adoption in large CS1 courses.

Findings

Over 50% of interactions occurred outside business hours.

959 students engaged in 11,222 sessions over seven weeks.

17,982 error explanations provided, showing high adoption.

Abstract

This paper introduces DCC Sidekick, a web-based conversational AI tool that enhances an existing LLM-powered C/C++ compiler by generating educational programming error explanations. The tool seamlessly combines code display, compile- and run-time error messages, and stack frame read-outs alongside an AI interface, leveraging compiler error context for improved explanations. We analyse usage data from a large Australian CS1 course, where 959 students engaged in 11,222 DCC Sidekick sessions, resulting in 17,982 error explanations over seven weeks. Notably, over 50% of interactions occurred outside business hours, underscoring the tool's value as an always-available resource. Our findings reveal strong adoption of AI-assisted debugging tools, demonstrating their scalability in supporting extensive CS1 courses. We provide implementation insights and recommendations for educators seeking to incorporate AI tools with appropriate pedagogical safeguards.