Scaling CS1 Support with Compiler-Integrated Conversational AI
This addresses the problem of limited instructor availability for CS1 students by offering scalable, always-available AI-assisted debugging support, though it is incremental as it builds on existing LLM-powered compiler technology.
The paper tackles the challenge of scaling support in introductory programming courses by introducing DCC Sidekick, a conversational AI tool integrated into a C/C++ compiler that provides educational error explanations, resulting in 959 students using it for 17,982 error explanations over seven weeks with over 50% of interactions outside business hours.
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.