Formal Framework for Agentic AI in Business Process Analysis

Agentic AI holds significant promise for automating and dynamically adapting business processes (BP), enabling autonomous decision-making. However, realizing this potential requires a high degree of formal precision in defining BP entities and their interactions. This paper introduces a formal framework specifically designed for Agentic BP analysis, utilizing the AGO (Agents, Goals, Objects) methodology. The AGO methodology captures the essential modeling perspectives: "who is acting" (Agents), "why it is carried out" (Goals), and "what the relevant entities are" (Objects). Grounded in set theory and mathematical logic, the framework formally defines these AGO entity types and their intricate interactions. All these definitions are organized into a comprehensive Business Process Knowledge Base (BPKB). This BPKB facilitates structured querying, allows for incremental updates, and supports the automatic generation of BP workflows, all while ensuring the soundness and completeness of the derived process paths.