Splitting User Stories Into Tasks with AI -- A Foe or an Ally?
Luka Pavlič, Reinhard Bernsteiner, Stephan Schlögl, Christian Ploder
TLDR
AI tools can assist in splitting user stories into tasks, improving granularity and completeness, but require human oversight for accuracy.
Key contributions
- Controlled experiment compared AI-assisted vs. traditional task splitting methods.
- AI tools generate more granular task lists and help prevent task omissions.
- Developers preferred a hybrid AI-human approach for accurate task planning.
- AI serves as a valuable aid in task splitting, requiring human oversight.
Why it matters
This paper provides empirical evidence on integrating Generative AI into agile development for task splitting. It highlights AI's potential to enhance efficiency and completeness while emphasizing the necessity of human oversight for accuracy. This guides practical adoption of AI in software planning.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.