Design and Deployment of a Course-Aware AI Tutor in an Introductory Programming Course

2026-04-12

AI Summary

This work addresses the concern that novice programmers’ overreliance on large language models for direct coding answers may undermine their problem-solving abilities. To mitigate this, the authors propose an AI teaching assistant system tailored for introductory programming courses, which innovatively integrates course-aligned retrieval-augmented generation (RAG) with Socratic dialogue tutoring. By leveraging context-aware prompting, guided questioning, and explanatory scaffolding—while deliberately withholding complete solutions—the system encourages active student reasoning. The architecture seamlessly combines course materials, a web-based programming environment, and a conversational agent to support conceptual understanding, code implementation, and debugging. User studies demonstrate that this approach significantly enhances students’ engagement with and investment in course content.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Reasoning under Uncertainty: Probabilistic Programming

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Large Language Models (LLMs) have become part of how students solve programming tasks, offering immediate explanations and even full solutions. Previous work has highlighted that novice programmers often heavily rely on LLMs, thereby neglecting their own problem-solving skills. To address this challenge, we designed a course-specific online Python tutor that provides retrieval-augmented, course-aligned guidance without generating complete solutions. The tutor integrates a web-based programming environment with a conversational agent that offers hints, Socratic questions, and explanations grounded in course materials. Students used the system during self-study to work on homework assignments, and the tutor also supported questions about the broader course material. We collected structured student feedback and analyzed interaction logs to investigate how they engaged with the tutor's guidance. We observed that students used the tutor primarily for conceptual understanding, implementation guidance, and debugging, and perceived it as a course-aligned, context-aware learning support that encourages engagement rather than direct solution copying.

Problem

• Large Language Models
• novice programmers
• programming education
• AI tutor
• problem-solving skills

Innovation

• course-aware AI tutor
• retrieval-augmented generation
• Socratic questioning
• programming education
• LLM in education