Process mining evolves to guide action with AI and governance
From Event Logs to Governed Action: A BlueSky Agenda for Agentic Process Mining
Artificial IntelligenceComputational Engineering, Finance, and Science
Summary
Process mining traditionally looks back at what happened in business operations by analyzing event logs. This paper suggests a new direction where process mining helps decide if specific actions should happen, considering rules, privacy, and risks. The authors propose creating new kinds of data and contracts that computers can use to make accountable decisions, not just show reports. This approach combines advances in AI, process management, and privacy to move from hindsight to guided action.
What this means in practice
- •For business process managers: Design workflows that automatically decide to act, delay, ask, or refuse operations based on integrated process evidence and governance rules.
- •For enterprise software developers: Build intelligent process mining tools that move beyond reporting to supporting real-time decision-making under privacy and risk constraints.
A position paper. It proposes an approach and reports no results.
Authors
Yiyuan Yang, Zheshun Wu, Yong Chu, Zhenghua Chen, Zenglin Xu, Qingsong Wen
Abstract
Process mining has long turned event logs into process knowledge: discovered models, conformance evidence, bottleneck diagnoses, and runtime predictions. Agentic AI changes the target. Process-aware agents will not only ask what happened. They will ask whether a proposed action should be taken, given the available evidence, privacy budget, organizational authority, and downstream risk. This BlueSky paper proposes event-to-action process mining: a process-mining agenda for transforming heterogeneous operational event data into governed action. The goal is not another dashboard, a generic enterprise simulator, or a language interface over logs. We argue that the community needs four mineable artifacts: event-object representations, action evidence packages, governance contracts, and benchmarks where act, defer, ask, and refuse are all valid outputs. This agenda is timely because agentic business process management (BPM), LLM-assisted process mining, object-centric event standards, causal process monitoring, and privacy-preserving learning are maturing separately. Bringing them together defines a data-mining target inside process mining: mining logged organizational behavior for accountable action, not only retrospective insight.