Adnan KhanAdnanProduct & AI
San Francisco Bay Area
Get in touch

Source note3 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' to upgrade legacy workflows into Agentic Business Process Management (Agentic BPM) without replacing the existing workflow engine. The process harness uses policy-controlled agents to provide reasoning, adaptation, and oversight while preserving the engine's structural authority over the process. A model called Task-Decision-Flow (TDF) is developed to define this process harness, which includes a data schema and execution semantics. The TDF model consists of three types of policy-governed agents: TaskAgent, DecisionAgent, and FlowAgent. These agents operate within an explicit policy drawn from the process FRAME, an aggregate policy set governing all calls in the system. The authors present CUGA FLO as a design and implementation realization of the TDF model and demonstrate it on a loan approval workflow.

What the Document Says

  • The process harness is a mechanism for upgrading legacy workflows into Agentic Business Process Management (Agentic BPM).
  • It works by placing a policy-governed agentic layer around a deterministic workflow engine.
  • This allows the engine to retain structural authority over the process while intercepting designated control points for reasoning, adaptation, and oversight.
  • The Task-Decision-Flow (TDF) model is developed for defining the process harness, consisting of data schema and execution semantics.
  • TDF decomposes LLM reasoning across three policy-governed agent types: TaskAgent, DecisionAgent, and FlowAgent.
  • Each agent operates within an explicit policy drawn from the process FRAME.
  • CUGA FLO is presented as the design and implementation realization of the TDF model.
  • It is demonstrated 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)
  • policy-governed agents
  • Task-Decision-Flow (TDF) model
  • CUGA FLO

Claims Made by the Document

  • The process harness can upgrade legacy workflows into Agentic BPM without replacing the underlying workflow engine.
  • It reconciles imperative requirements with normative requirements.

Evidence Used

  • The introduction and description of the process harness in the text.

Methods / Approach

  • Development of Task-Decision-Flow (TDF) model
  • Design and implementation of CUGA FLO

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.