🤖 AI Summary
This study addresses the challenge of endowing traditional business processes with intelligent reasoning and adaptive capabilities while preserving the determinism of existing workflow engines. To this end, the authors propose a “workflow suite” mechanism that enables dynamic intervention by embedding a layer of policy-constrained agents at critical control points. They introduce a novel Task-Decision-Flow (TDF) model that defines three types of collaborative agents and integrates the FRAME policy framework to govern large language model (LLM) invocations, thereby harmonizing structural compliance with normative autonomy. Leveraging a hook-based integration architecture, the approach is implemented and validated within the CUGA FLO system using a loan approval case study, demonstrating a balanced synthesis of process determinism and intelligent flexibility.
📝 Abstract
We introduce the process harness, a new mechanism for uplifting legacy workflows into Agentic Business Process Management (Agentic BPM) without replacing the underlying workflow engine. A process harness places a policy-governed agentic layer around a deterministic workflow engine, intercepting designated control points to contribute reasoning, adaptation, and oversight while the engine retains structural authority over the process. To define the process harness rigorously, we develop the Task-Decision-Flow (TDF) model, specifying both its data schema and its execution semantics. TDF decomposes LLM reasoning across three policy-governed agent types: a TaskAgent for knowledge-intensive task execution, a DecisionAgent for per-case gateway routing, and a FlowAgent that governs runtime flow adaptation through a principled hook mechanism. Each agent reasons within an explicit policy drawn from the process FRAME, the aggregate policy set governing all LLM calls in the system. We then present CUGA FLO as the design and implementation realization of the TDF model, and demonstrate it on a loan approval workflow that exercises all three agent types and hook-driven regulatory override. The process harness uniquely reconciles imperative requirements, realized through deterministic workflow execution that enforces structural compliance, with normative requirements, realized through policy-framed agentic autonomy invoked at designated control points wherever the process demands it.