The week's pick
Random Articles
Reseach Article
Domain-Specific Contexts versus General Enterprise Contexts: Effects on AI-Driven Agile Requirements
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 187 - Number 139 |
| Year of Publication: 2026 |
| Authors: Ajay Roy |
10.5120/ijca9a6d76e6230d
|
Ajay Roy . Domain-Specific Contexts versus General Enterprise Contexts: Effects on AI-Driven Agile Requirements. International Journal of Computer Applications. 187, 139 ( Aug 2026), 13-21. DOI=10.5120/ijca9a6d76e6230d
Abstract
Speed is the lifeblood of modern software engineering, where global tech firms rely on Agile frameworks to slash time-to-market. Within this high-velocity environment, Artificial Intelligence has become indispensable, embedding itself across every stage of the Software Development Life Cycle (SDLC) to ensure teams hit their delivery targets. Yet, the caliber of output from these AI solutions is far from uniform. Consider Atlassian Rovo, a native agent inside Jira designed to draft user stories directly within the workflow. Our research leveraged Rovo for this specific purpose, pitting its generated content against Microsoft Copilot 365 in a head-to-head evaluation. While both tools aim to accelerate the requirements phase, our comparative study highlights distinct variations in the clarity, context-awareness, and overall utility of the user stories produced by each platform.Ten user stories, ranging from standard CRUD operations to complex financial logic, served as the testbed. Rovo achieved a mean INVEST fit of 4.6/5 and a technical accuracy of 4.6/5. The Copilot scored 3.6 and 3.1 points. Human revision time decreased by 60% Rovo (3.2 vs. 8.0 min). This variance stems from the context. We compared Atlassian Rovo, which accesses structured development artifacts (Jira/Confluence), with Microsoft Copilot 365, which queries unstructured communication logs (Outlook/Teams). The data confirms a singular truth: domain-specific contexts outperform general enterprise contexts in requirements engineering research. Structured artifacts help reduce hallucinations, whereas conversations can add noise.
References
- M. A. Sami, M. Waseem, Z. Zhang, Z. Rasheed, K. Systä, and P. Abrahamsson, “Early Results of an AI Multiagent System for Requirements Elicitation and Analysis,” in Product-Focused Software Process Improvement. PROFES 2024, D. Pfahl, J. Gonzalez Huerta, J. Klünder, and H. Anwar, Eds., vol. 15452. Cham, Switzerland: Springer, 2025, pp. 313–330. https://doi.org/10.1007/978-3-031-78386-9_20.
- G. Quattrocchi, L. Pasquale, P. Spoletini, and L. Baresi, “Can LLMs Generate User Stories and Assess Their Quality?” IEEE Transactions on Software Engineering, 2024. Available: https://arxiv.org/pdf/2507.15157v1.
- N. F. Liu, K. Lin, J. Hewitt, A. Paranjape, M. Bevilacqua, F. Petroni, and P. Liang, “Lost in the Middle: How Language Models Use Long Contexts,” Transactions of the Association for Computational Linguistics, vol. 12, pp. 157–173, 2024. https://doi.org/10.1162/tacl_a_00638.
- H. Cheng, J. H. Husen, Y. Lu, et al., “Generative AI for Requirements Engineering: A Systematic Literature Review,” Software: Practice and Experience, vol. 56, no. 2, pp. 141–170, 2026. https://doi.org/10.1002/spe.70029.
- A. Avasiloaie, A. Semenescu, E. Popovici, and I. Chiva, “Enhancing Agile Requirement Discovery with AI-Driven Multimodal Systems and Synthetic User Story Generation,” UPB Scientific Bulletin, Series C: Electrical Engineering, vol. 87, 2025.
- S. K. Sahu and S. Ranganathan, “From Needs to Insights: User Stories Guide Data Processing and Networking for IDMS Development for IoT,” in IoT Security, Academic Press, 2026, pp. 409–431.
- T. Davenport and N. Mittal, “How Generative AI is Changing the Nature of Requirements Engineering,” Journal of Systems and Software, vol. 210, pp. 111–125, 2026.
- O. Abed, K. Nebe, and A. B. Abdellatif, “AI-Generated User Stories Supporting Human-centered Development: An Investigation of Quality,” in HCI International 2024 Posters. HCII 2024. Communications in Computer and Information Science, vol. 2120, C. Stephanidis, M. Antona, S. Ntoa, and G. Salvendy, Eds. Cham, Switzerland: Springer, 2024, pp. 1–10. https://doi.org/10.1007/978-3-031-62110-9_1.
- L. Zheng, Y. Wang, and Z. Cui, “Modeling Contextual Goals and Detecting Context Conflicts from BDD-Based User Stories,” International Journal of Computers and Applications, vol. 46, no. 12, pp. 1057–1068, 2024. https://doi.org/10.1080/1206212X.2024.2387444.
- J.-P. Steghöfer, “Faster than the Team, Faster than the Customer: Tool Integration, Collaboration, and Organisational Lag in AI-assisted Requirements Engineering,” arXiv preprint, 2026. Available: https://arxiv.org/abs/2606.01772.
- A. Brockenbrough and D. Salinas, “Using Generative AI to Create User Stories in the Software Engineering Classroom,” in Proc. 36th International Conference on Software Engineering Education and Training (CSEE&T), Würzburg, Germany, 2024, pp. 1–5. https://doi.org/10.1109/CSEET62301.2024.10662994
Index Terms
Keywords