Adoption of Large Language Models in Scrum Management: Insights from Brazilian Practitioners

2026-02-09

AI Summary

This study addresses the empirical gap in understanding the application of large language models (LLMs) within Scrum management activities, particularly regarding their benefits and risks in non-technical agile practices. Through a survey of 70 Brazilian practitioners, it systematically characterizes the current adoption, usage frequency, and user proficiency of LLMs across Scrum artifacts and events. Findings reveal that 85% of respondents possess intermediate to advanced LLM competence, with 52% using them daily; 78% report enhanced efficiency and 75% note reduced manual effort. However, significant challenges persist: 81% encounter “almost correct” outputs, 63% express concerns about data confidentiality, and 59% are affected by hallucinations. The study quantifies both the tangible benefits and critical risks of LLM integration in Scrum, highlighting an uneven support landscape across its practices.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Scrum is widely adopted in software project management due to its adaptability and collaborative nature. The recent emergence of Large Language Models (LLMs) has created new opportunities to support knowledge-intensive Scrum practices. However, existing research has largely focused on technical activities such as coding and testing, with limited evidence on the use of LLMs in management-related Scrum activities. In this study, we investigate the use of LLMs in Scrum management activities through a survey of 70 Brazilian professionals. Among them, 49 actively use Scrum, and 33 reported using LLM-based assistants in their Scrum practices. The results indicate a high level of proficiency and frequent use of LLMs, with 85% of respondents reporting intermediate or advanced proficiency and 52% using them daily. LLM use concentrates on exploring Scrum practices, with artifacts and events receiving targeted yet uneven support, whereas broader management tasks appear to be adopted more cautiously. The main benefits include increased productivity (78%) and reduced manual effort (75%). However, several critical risks remain, as respondents report'almost correct'outputs (81%), confidentiality concerns (63%), and hallucinations during use (59%). This work provides one of the first empirical characterizations of LLM use in Scrum management, identifying current practices, quantifying benefits and risks, and outlining directions for responsible adoption and integration in Agile environments.

Problem

• Large Language Models
• Scrum Management
• Agile Software Development
• Empirical Study
• AI in Project Management

Innovation

• Large Language Models
• Scrum Management
• Agile Software Development
• Empirical Study
• AI in Project Management