Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Scaling CS1 Support with Compiler-Integrated Conversational AI

Jake Renzella, Alexandra Vassar, Lorenzo Lee Solano, Andrew Taylor

TL;DR

The paper addresses the challenge of scaling debugging support in CS1 by introducing DCC Sidekick, a compiler-integrated conversational AI that complements the existing DCC Help with context-aware, Socratic-style explanations of compile- and run-time errors. The approach combines a web-based dashboard with compiler-derived error context to enable iterative dialogue and guided learning, while maintaining pedagogical safeguards. In a large CS1 course with 959 students across 11,222 sessions and nearly 18,000 explanations, the tool shows substantial engagement and extensive after-hours usage, indicating strong scalability and learning-support potential. The work provides practical implementation guidance and recommendations for educators seeking to deploy AI-assisted debugging tools responsibly within established teaching workflows.

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.

Scaling CS1 Support with Compiler-Integrated Conversational AI

TL;DR

The paper addresses the challenge of scaling debugging support in CS1 by introducing DCC Sidekick, a compiler-integrated conversational AI that complements the existing DCC Help with context-aware, Socratic-style explanations of compile- and run-time errors. The approach combines a web-based dashboard with compiler-derived error context to enable iterative dialogue and guided learning, while maintaining pedagogical safeguards. In a large CS1 course with 959 students across 11,222 sessions and nearly 18,000 explanations, the tool shows substantial engagement and extensive after-hours usage, indicating strong scalability and learning-support potential. The work provides practical implementation guidance and recommendations for educators seeking to deploy AI-assisted debugging tools responsibly within established teaching workflows.

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.
Paper Structure (23 sections, 5 figures)

This paper contains 23 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Large Language Models and Tools in CS1
  4. The Socratic Method
  5. Motivation
  6. DCC Sidekick
  7. Compiler Integration
  8. Graphical Interface
  9. Prompting Strategy
  10. Additional Guardrails
  11. Risks
  12. Methodology
  13. Data Collection
  14. Usage Logs
  15. Heatmaps and Session Recordings
  16. ...and 8 more sections

Figures (5)

  • Figure 1: The DCC Sidekick Interface, Where Students can Converse with an LLM about an Error they have Encountered
  • Figure 2: Launching DCC Sidekick from the DCC Compiler
  • Figure 3: Diagram of Conversational DCC Sidekick Generative Explanation Toolflow as a Component of the Debugging C Compiler at Compile- and Run-Time
  • Figure 4: The Guardrail System Prompt, used to Rewrite Responses that Contain Code Blocks or Solutions
  • Figure 5: Launches Over Time of the DCC Sidekick Tool, Comparing both Compile- and Run-time Errors