20.500.12556/DKUM-91452 Can large-language models replace humans in agile effort estimation? Lessons from a controlled experiment Effort estimation is critical in software engineering to assess the resources needed for development tasks and to enable realistic commitments in agile iterations. This study investigates whether generative AI tools, which are transforming various aspects of software development, can improve effort estimation efficiency. A controlled experiment was conducted in which development teams upgraded an existing information system, with the experimental group using the generative-AI-based tool GitLab Duo for estimation and the control group using conventional methods (e.g., planning poker or analogy-based planning). Results show that while generative-AI-based estimation tools achieved only 16% accuracy—currently insufficient for industry standards—they offered valuable support for task breakdown and iteration planning. Participants noted that a combination of conventional methods and AI-based tools could offer enhanced accuracy and efficiency in future planning. software engineering agile development iteration planning effort estination generative AI tool accuracy umetna inteligenca ocenjevanje napora načrtovanje ponovitve true true false MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/2076-3417/14/24/12006 © 2024 by the authors Članek v reviji 2024-12-24 10:45:51 2024-12-24 10:45:51 2024-12-25 03:09:36 0000-00-00 00:00:00 2024 0 0 21 str. iss. 20, [article no.] 12006 Vol. 14 Dec. 2024 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2024-12-01 2024-12-18 2024-12-22 004.8 220375555 10.3390/app142412006 2076-3417 applsci-14-12006_(1).pdf applsci-14-12006_(1).pdf 1 425ADBE0E131815428B5EC0AB8A96046 60de4697c0773b4585e0a1a8f3251602399829ec370f21a9b01d9f3d25b47452 1c036f55-c1dc-11ef-8836-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=187567 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0