Promptly: Using Prompt Problems to Teach Learners How to Effectively Utilize AI Code Generators
Project Overview
This document explores the innovative use of generative AI in education through the pedagogical strategy of 'Prompt Problems,' aimed at teaching students to effectively engage with AI code generators, particularly large language models (LLMs). By shifting the focus from traditional programming techniques to the formulation and understanding of prompts, students learn to generate code through AI. The tool 'Promptly' plays a crucial role in this educational approach, guiding students through programming tasks that require them to create prompts based on visual representations of problems. Empirical findings from a pilot study reveal that this method not only enhances student engagement but also significantly improves their computational thinking skills. However, the study also identifies potential challenges, such as the risk of students becoming overly reliant on AI-generated code and the importance of fostering critical evaluation skills regarding AI outputs. Overall, the document emphasizes the transformative potential of generative AI in education while acknowledging the need for balanced and informed usage.
Key Applications
Promptly - A tool for delivering Prompt Problems
Context: First-year Python programming course at the University of Auckland, targeting students with no prior programming experience.
Implementation: A web-based tool where students create prompts based on visual problem representations. The tool evaluates the generated code against test cases and provides feedback.
Outcomes: Students reported improved engagement with computational thinking skills and exposure to new programming constructs.
Challenges: Students faced difficulties in formulating effective prompts, which often required iterative refinement and understanding of programming concepts.
Implementation Barriers
Educational Barrier
Students may struggle with formulating effective prompts and understanding AI-generated code, leading to potential over-reliance on AI tools.
Proposed Solutions: Explicit instruction on prompt crafting and critical evaluation of AI outputs should be integrated into the curriculum.
Project Team
Paul Denny
Researcher
Juho Leinonen
Researcher
James Prather
Researcher
Andrew Luxton-Reilly
Researcher
Thezyrie Amarouche
Researcher
Brett A. Becker
Researcher
Brent N. Reeves
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Paul Denny, Juho Leinonen, James Prather, Andrew Luxton-Reilly, Thezyrie Amarouche, Brett A. Becker, Brent N. Reeves
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai