Exploring Prompt Patterns in AI-Assisted Code Generation: Towards Faster and More Effective Developer-AI Collaboration

  • Sophia Dicuffa
  • , Amanda Zambrana
  • , Priyanshi Yadav
  • , Sashidhar Madiraju
  • , Khushi Suman
  • , Eman Abdullah Alomar

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publication2025 IEEE 4th International Conference on Computing and Machine Intelligence, ICMI 2025 - Proceedings
EditorsAhmed Abdelgawad, Akhtar Jamil, Alaa Ali Hameed
ISBN (Electronic)9798331509132
DOIs
StatePublished - 2025
Event4th IEEE International Conference on Computing and Machine Intelligence, ICMI 2025 - Michigan, United States
Duration: 5 Apr 20256 Apr 2025

Publication series

Name2025 IEEE 4th International Conference on Computing and Machine Intelligence, ICMI 2025 - Proceedings

Conference

Conference4th IEEE International Conference on Computing and Machine Intelligence, ICMI 2025
Country/TerritoryUnited States
CityMichigan
Period5/04/256/04/25

Keywords

  • DevGPT
  • LLMs
  • prompt patterns

Fingerprint

Dive into the research topics of 'Exploring Prompt Patterns in AI-Assisted Code Generation: Towards Faster and More Effective Developer-AI Collaboration'. Together they form a unique fingerprint.

Cite this