Splitting User Stories Into Tasks with AI -- A Foe or an Ally?

2026-05-08

AI Summary

This study addresses the time-consuming and error-prone nature of decomposing user stories into actionable tasks in agile development, highlighting the need for effective support mechanisms. The authors present the first empirical evaluation—through controlled experiments and developer surveys—of a generative AI tool (GitLab Duo) for task decomposition, alongside a proposed human-AI collaborative workflow. Findings indicate that AI assistance yields more granular and comprehensive task lists, though manual filtering is required to remove irrelevant suggestions. Developers consistently favored a hybrid approach that integrates AI-generated outputs with traditional methods, as it enhances planning efficiency while preserving accuracy and contextual relevance.

Abstract

In agile software development, breaking down user stories into actionable tasks is a critical yet time-consuming process. This paper investigates the potential of Generative AI tools to assist in task splitting, aiming to enhance planning efficiency. We conducted a controlled experiment comparing traditional task-splitting methods with AI-assisted approaches using GitLab Duo. Our findings indicate that while current AI tools are not yet mature enough to replace developers, they can aid in generating more granular task lists and ensuring no important tasks are overlooked. Participants favored a hybrid approach, combining AI tools with conventional methods to maintain high accuracy in planning. This study highlights the potential benefits and limitations of integrating Generative AI into agile development processes, suggesting that AI tools can serve as valuable aids in task splitting, provided there is human oversight to filter out irrelevant tasks.

Problem

• user story splitting
• task decomposition
• agile software development
• Generative AI
• planning efficiency

Innovation

• Generative AI
• task splitting
• agile software development
• human-AI collaboration
• user stories