Prompt Programming: A Platform for Dialogue-based Computational Problem Solving with Generative AI Models

2025-03-06

AI Summary

Computing science students increasingly rely on generative AI for programming but lack systematic training in prompt engineering and critical code evaluation. Method: This study develops a dialogue-based prompt programming platform tailored for programming education, introducing the first prompt framework supporting multi-function coupling problems. It integrates dynamic code sandbox execution, fine-grained prompt behavior logging, and visualized progress graph modeling. Contribution/Results: (1) It pioneers an on-demand execution and iterative optimization mechanism within multi-turn natural language dialogues; (2) it empirically identifies canonical patterns of prompt strategy evolution; (3) large-scale pedagogical deployment (N > 900) reveals that over 87% of prompts occur in multi-turn interactions, 65% of students autonomously test generated code, and both AI-augmented problem-solving proficiency and critical thinking skills show statistically significant improvement.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Computing students increasingly rely on generative AI tools for programming assistance, often without formal instruction or guidance. This highlights a need to teach students how to effectively interact with AI models, particularly through natural language prompts, to generate and critically evaluate code for solving computational tasks. To address this, we developed a novel platform for prompt programming that enables authentic dialogue-based interactions, supports problems involving multiple interdependent functions, and offers on-request execution of generated code. Data analysis from over 900 students in an introductory programming course revealed high engagement, with the majority of prompts occurring within multi-turn dialogues. Problems with multiple interdependent functions encouraged iterative refinement, with progression graphs highlighting several common strategies. Students were highly selective about the code they chose to test, suggesting that on-request execution of generated code promoted critical thinking. Given the growing importance of learning dialogue-based programming with AI, we provide this tool as a publicly accessible resource, accompanied by a corpus of programming problems for educational use.

Problem

• Teaching students to interact with AI models using natural language prompts.
• Developing a platform for dialogue-based computational problem solving.
• Promoting critical thinking through on-request execution of generated code.

Innovation

• Dialogue-based interaction with generative AI models
• Support for multi-function interdependent problems
• On-request execution of generated code