Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note2 min read

A Process Harness for Uplifting Legacy Workflows to Agentic BPM: Design and Realization in CUGA FLO

Source

arXiv

arxiv.org/abs/2606.27188v1

Read the source

Source

Plain-Language Brief

The authors introduce a new mechanism called 'process harness' for upgrading legacy workflows to an Agentic Business Process Management (Agentic BPM) without replacing the existing engine. The process harness involves a policy-governed agentic layer that interacts with a deterministic workflow engine at designated control points, allowing for reasoning, adaptation, and oversight while maintaining the structural authority of the engine. The authors present a model called Task-Decision-Flow (TDF) to define this mechanism, which includes three types of policy-governed agents: TaskAgent, DecisionAgent, and FlowAgent. They also present CUGA FLO as an implementation of the TDF model, demonstrating it on a loan approval workflow that utilizes all three agent types and hook-driven regulatory override.

What the Document Says

  • The authors introduce the process harness for upgrading legacy workflows to Agentic Business Process Management (Agentic BPM).
  • A process harness consists of a policy-governed agentic layer around a deterministic workflow engine.
  • It places reasoning, adaptation, and oversight functions while the engine retains structural authority over the process.
  • The authors develop the Task-Decision-Flow (TDF) model for defining the process harness.
  • TDF includes three types of policy-governed agents: TaskAgent, DecisionAgent, and FlowAgent.
  • Each agent operates within an explicit policy drawn from the process FRAME.
  • The authors present CUGA FLO as a realization of the TDF model.
  • They demonstrate CUGA FLO on a loan approval workflow that exercises all three agent types and hook-driven regulatory override.

Key Concepts Mentioned

  • process harness
  • Agentic Business Process Management (Agentic BPM)
  • deterministic workflow engine
  • policy-governed agents
  • TaskAgent
  • DecisionAgent
  • FlowAgent
  • Task-Decision-Flow (TDF) model
  • process FRAME
  • CUGA FLO

Claims Made by the Document

  • The process harness can upgrade legacy workflows to Agentic BPM without replacing the underlying engine.
  • A process harness involves a policy-governed agentic layer around a deterministic workflow engine.

Evidence Used

  • Introduction of the process harness
  • Description of the process harness structure

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.