Reference architecture guides integration of agentic AI in enterprise software
A Reference Architecture for Integrating Agentic AI into Enterprise Software: Responsibilities, Interactions, and Variability
Artificial Intelligence
Summary
Integrating advanced AI that can think, reason, and act into business software is complex. The authors provide a clear blueprint organizing how different AI parts work together in companies. They tested this blueprint with a system analyzing investment portfolios and confirmed it covers important functions without needing extra parts. This work helps software builders add smarter AI tools to real-world business systems more reliably.
What this means in practice
- •For enterprise software developers: Structure and integrate complex AI capabilities in enterprise systems using a tested blueprint clarifying AI roles and interactions.
- •For financial compliance teams: Implement AI agents to analyze portfolios for environmental, social, and governance metrics to support pre-trade compliance decisions.
Authors
Mingqin Yu, Fethi Rabhi, Liming Zhu, Qinghua Lu
Abstract
Agentic AI moves generative AI applications toward systems that coordinate reasoning, enterprise context, model inference, and external actions. Integrating these capabilities into enterprise software introduces diverse architectural concerns, from orchestration, knowledge and memory, and model access to tools and actions, security, runtime infrastructure, and evaluation. Existing research and industry architectures address many of these concerns but differ in scope, abstraction, responsibility organization, interaction representation, and assumptions about which capabilities are required. This paper presents a technology-neutral reference architecture for enterprise agentic AI integration. We synthesize architectural capabilities from research publications, industry architecture guidance, and interoperability specifications by architectural purpose, organize them into ten responsibilities, and define boundary invariants, typed cross-responsibility interactions, and variation points that distinguish responsibilities from condition-dependent capabilities and replaceable realization mechanisms. We instantiate the architecture as an ESG portfolio-analysis and pre-trade compliance agent over an existing service-oriented ESG metric computation and reporting system, and complement the case with a mapping of an independently published agentic architecture. The case realizes seven of the ten responsibilities; different questions take different interaction paths, controls activate only under their conditions, and the probed boundary invariants hold. The independent architecture maps onto the proposed responsibilities without requiring an additional one. These results provide initial evidence for the architecture's organization and applicability rather than its completeness. The deployment and recorded results are available as a replication package.