Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Exploring Human-AI Collaboration in Agile: Customised LLM Meeting Assistants

Beatriz Cabrero-Daniel, Tomas Herda, Victoria Pichler, Martin Eder

TL;DR

This action-research study investigates how customised AI meeting assistants can support Agile ceremonies in an industrial setting (Austrian Post Group IT) by deploying two GPT-4–based tools: the Agile Release Train Coach assistant for premeeting planning and the Scrum Team Assistant Tool for real-time guidance during the Daily Scrum and postmeeting summaries. Through iterative prompt engineering, controlled demonstrations, and data from surveys and observations, the study shows that AI can generate accurate, contextual recommendations that aid decision-making, while outcomes depend on non-intrusive, well-communicated interactions and human oversight. Key contributions include a pragmatic readiness assessment framework, design guidelines for modular AI support aligned with Agile values, and evidence that user experience and trust shape adoption more than mere technical capability. The findings offer a practical roadmap for organisations seeking to integrate AI into Agile meetings, highlighting both the potential gains in efficiency and the importance of tailoring tools to team needs and contexts.

Abstract

This action research study focuses on the integration of "AI assistants" in two Agile software development meetings: the Daily Scrum and a feature refinement, a planning meeting that is part of an in-house Scaled Agile framework. We discuss the critical drivers of success, and establish a link between the use of AI and team collaboration dynamics. We conclude with a list of lessons learnt during the interventions in an industrial context, and provide a assessment checklist for companies and teams to reflect on their readiness level. This paper is thus a road-map to facilitate the integration of AI tools in Agile setups.

Exploring Human-AI Collaboration in Agile: Customised LLM Meeting Assistants

TL;DR

This action-research study investigates how customised AI meeting assistants can support Agile ceremonies in an industrial setting (Austrian Post Group IT) by deploying two GPT-4–based tools: the Agile Release Train Coach assistant for premeeting planning and the Scrum Team Assistant Tool for real-time guidance during the Daily Scrum and postmeeting summaries. Through iterative prompt engineering, controlled demonstrations, and data from surveys and observations, the study shows that AI can generate accurate, contextual recommendations that aid decision-making, while outcomes depend on non-intrusive, well-communicated interactions and human oversight. Key contributions include a pragmatic readiness assessment framework, design guidelines for modular AI support aligned with Agile values, and evidence that user experience and trust shape adoption more than mere technical capability. The findings offer a practical roadmap for organisations seeking to integrate AI into Agile meetings, highlighting both the potential gains in efficiency and the importance of tailoring tools to team needs and contexts.

Abstract

This action research study focuses on the integration of "AI assistants" in two Agile software development meetings: the Daily Scrum and a feature refinement, a planning meeting that is part of an in-house Scaled Agile framework. We discuss the critical drivers of success, and establish a link between the use of AI and team collaboration dynamics. We conclude with a list of lessons learnt during the interventions in an industrial context, and provide a assessment checklist for companies and teams to reflect on their readiness level. This paper is thus a road-map to facilitate the integration of AI tools in Agile setups.
Paper Structure (22 sections, 2 figures, 3 tables)

This paper contains 22 sections, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Adapting Agile practices to companies
  4. Generative AI in Software Engineering
  5. Prompt Engineering
  6. Research design
  7. Context
  8. Action
  9. The Agile Release Train Coach assistant
  10. Scrum Team Assistant Tool for the Daily Scrum
  11. Data collection and analysis
  12. Surveys to understand team composition.
  13. Observations before and during the actions.
  14. How the conclusions were drawn.
  15. Execution and results
  16. ...and 7 more sections

Figures (2)

  • Figure 1: AI recommendations, shown using OBS, during an Daily Scrum meeting.
  • Figure 2: Team composition, based on their answers to the initial survey question "How would you feel about using AI support in the meeting?"