TY - GEN
T1 - Exploring Prompt Patterns in AI-Assisted Code Generation
T2 - 4th IEEE International Conference on Computing and Machine Intelligence, ICMI 2025
AU - Dicuffa, Sophia
AU - Zambrana, Amanda
AU - Yadav, Priyanshi
AU - Madiraju, Sashidhar
AU - Suman, Khushi
AU - Alomar, Eman Abdullah
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - The growing integration of AI tools in software development, particularly Large Language Models (LLMs) such as ChatGPT, has revolutionized how developers approach coding tasks. However, achieving high-quality code often requires iterative interactions, which can be time-consuming and inefficient. This paper explores the application of structured prompt patterns to minimize the number of interactions required for satisfactory AI-assisted code generation. Using the DevGPT dataset, we analyzed seven distinct prompt patterns to evaluate their effectiveness in reducing back-and-forth communication between developers and AI. Our findings highlight patterns such as 'Context and Instruction' and 'Recipe' as particularly effective in achieving high-quality outputs with minimal iterations. The study emphasizes the potential for prompt engineering to streamline developer-AI collaboration, providing practical insights into crafting prompts that balance precision, efficiency, and clarity.
AB - The growing integration of AI tools in software development, particularly Large Language Models (LLMs) such as ChatGPT, has revolutionized how developers approach coding tasks. However, achieving high-quality code often requires iterative interactions, which can be time-consuming and inefficient. This paper explores the application of structured prompt patterns to minimize the number of interactions required for satisfactory AI-assisted code generation. Using the DevGPT dataset, we analyzed seven distinct prompt patterns to evaluate their effectiveness in reducing back-and-forth communication between developers and AI. Our findings highlight patterns such as 'Context and Instruction' and 'Recipe' as particularly effective in achieving high-quality outputs with minimal iterations. The study emphasizes the potential for prompt engineering to streamline developer-AI collaboration, providing practical insights into crafting prompts that balance precision, efficiency, and clarity.
KW - DevGPT
KW - LLMs
KW - prompt patterns
UR - https://www.scopus.com/pages/publications/105017003735
UR - https://www.scopus.com/pages/publications/105017003735#tab=citedBy
U2 - 10.1109/ICMI65310.2025.11141320
DO - 10.1109/ICMI65310.2025.11141320
M3 - Conference contribution
AN - SCOPUS:105017003735
T3 - 2025 IEEE 4th International Conference on Computing and Machine Intelligence, ICMI 2025 - Proceedings
BT - 2025 IEEE 4th International Conference on Computing and Machine Intelligence, ICMI 2025 - Proceedings
A2 - Abdelgawad, Ahmed
A2 - Jamil, Akhtar
A2 - Hameed, Alaa Ali
Y2 - 5 April 2025 through 6 April 2025
ER -