Using Process Mining to Generate AI Agents from Software Engineering Process Records
2026-07-06 • Software Engineering
Software Engineering
AI summaryⓘ
The authors explore how to design AI agents that work well with humans in software engineering teams. They point out that making these agents too broad or too small can cause problems. To solve this, they use data from software project histories to identify specific roles AI agents can fill based on real work patterns. They tested their method on an open-source project and checked if the AI agents matched what people expected. This approach aims to create AI helpers that fit better with how software teams actually work.
AI agentsSoftware EngineeringMulti-agent systemsProcess miningEvent logsRole discoveryHybrid teamsOpen-source projectsAgent specification
Authors
Saimir Bala, Fabiana Fournier, Lior Limonad, Andreas Metzger
Abstract
Integrating AI agents into Software Engineering (SE) raises an important challenge: how can we specify and realize AI agents that work effectively alongside humans in hybrid SE teams? Determining the right granularity and separation of concerns for such agents is non-trivial. Coarse-grained agents may introduce unmanageable complexity, whereas micro-agents may create severe coordination overhead. Moreover, existing multi-agent SE frameworks typically rely on predefined role structures and do not account for project-specific characteristics or process adaptations. We address this by combining object-centric, imperative, and declarative process mining. Using event logs extracted from software repositories, our approach discovers project-specific agent roles using a predefined SE role vocabulary grounded in repository behavior and generates matching agent specifications and implementations. As proof-of-concept, we applied our approach to a well-established open-source project. We performed functional tests and an exploratory user study to determine how well the generated AI agent specifications are aligned with human expectations.