From Intelligent Automation to Agentic AI: Engineering the Next Generation of Enterprise Systems
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V5I4P114Keywords:
Agentic AI, Intelligent Automation, Robotic Process Automation (RPA), Business Process Management (BPM), AgentOps, Vector Databases, Governance and SafetyAbstract
Businesses are shifting away, however, and realizing agentic AI systems of autonomous, goal-oriented, software agents that are able to perceive, reason, make actions, and learn end-to-end systems. In this paper, a conceptual and engineering blueprint of such transition is proposed. We define agentic enterprise systems initially on a set of directions of autonomy, adaptivity, coordination, and governance, and propose an Observe-Reason-Act-Learn cognitive loop as the fundamental behavioral pattern. Based on this, we showcase a high-level reference architecture connecting an enterprise knowledge layer (data lake, vector search, knowledge graphs) with an autonomous agent layer with a reasoning and planning layer based on the use of LLM-based paradigms and multi-agent coordination engine to coordinate cross-domain workflows. It describes in the methodology section how to model agent roles and skills, break down business processes into tasks that can be performed by agents, establish protocols of cooperation, and deploy memory and tool-use systems that are based on enterprise APIs and robots-pilots. These patterns are illustrated by an implementation sketch that illustrates how these patterns can be achieved with the use of contemporary agent frameworks in hybrid cloud/on-premise settings. Quantitative evidence that has been synthesized so far on the basis of emerging deployments shows significant cost, productivity, and cycle-time improvements compared to conventional IA, as well as new failure modes in the areas of hallucinations, governance gaps, and safety. The paper ends with the overview of major research directions in the field of reliability, privacy-preserving knowledge access specially in rare disease and alignment of autonomous agents and claims that a powerful AgentOps and governance are the key to the full potential of agentic enterprise systems
References
[1] Balasubramaniam, S., Prasanth, A., Kumar, K. S., & Kadry, S. (2024). Artificial Intelligence‐Based Hyperautomation for Smart Factory Process Automation. Hyperautomation for Next‐Generation Industries, 55-89.
[2] Hess, T. J., Rees, L. P., & Rakes, T. R. (2000). Using autonomous software agents to create the next generation of decision support systems. Decision Sciences, 31(1), 1-31.
[3] Goyal, Mahesh Kumar, and Rahul Chaturvedi. "Synthetic data revolutionizes rare disease research: How large language models and generative AI are overcoming data scarcity and privacy challenges." International Journal on Recent and Innovation Trends in Computing and Communication 11.11 (2023): 1368-1380.
[4] Weyns, D. (2010). Architecture-based design of multi-agent systems. Springer Science & Business Media.
[5] Kolp, M., Giorgini, P., & Mylopoulos, J. (2001, August). A goal-based organizational perspective on multi-agent architectures. In International Workshop on Agent Theories, Architectures, and Languages (pp. 128-140). Berlin, Heidelberg: Springer Berlin Heidelberg.
[6] Poernomo, I., Reussner, R., & Schmidt, H. (2002, June). Architectures of enterprise systems: Modelling transactional contexts. In International Working Conference on Component Deployment (pp. 233-243). Berlin, Heidelberg: Springer Berlin Heidelberg.
[7] Viswanathan, Venkatraman. "Pioneering Ethical AI Integration in Enterprise Workflows: A Framework for Scalable Team Governance." Available at SSRN 5375619 (2024).
[8] Intelligent automation, uipath, online. https://www.uipath.com/automation/intelligent-automation
[9] Mackworth, A. K., & Zhang, Y. (2003). A formal approach to agent design: An overview of constraint-based agents. Constraints, 8(3), 229-242.
[10] Agentic AI: The next wave of intelligent process automation, ATOS, online. https://atos.net/en/blog/agentic-ai-the-next-wave-of-intelligent-process-automation
[11] Wagner, T., Phelps, J., & Guralnik, V. (2004). Centralized vs. decentralized coordination: Two application case studies. In An Application Science for Multi-Agent Systems (pp. 41-75). Boston, MA: Springer US.
[12] Coria, J. A. G., Castellanos-Garzón, J. A., & Corchado, J. M. (2014). Intelligent business processes composition based on multi-agent systems. Expert Systems with Applications, 41(4), 1189-1205.
[13] Sioutis, C., & Tweedale, J. (2006, October). Agent cooperation and collaboration. In International Conference on Knowledge-Based and Intelligent Information and Engineering Systems (pp. 464-471). Berlin, Heidelberg: Springer Berlin Heidelberg.
[14] Qin, Y., Hu, S., Lin, Y., Chen, W., Ding, N., Cui, G., ... & Sun, M. (2024). Tool learning with foundation models. ACM Computing Surveys, 57(4), 1-40.
[15] What is automation?, IBM. online. https://www.ibm.com/think/topics/automation
[16] Chan, A., Salganik, R., Markelius, A., Pang, C., Rajkumar, N., Krasheninnikov, D., ... & Maharaj, T. (2023, June). Harms from increasingly agentic algorithmic systems. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency (pp. 651-666)
