From Reactive to Proactive: Integrating Agentic AI and Automated Workflows for Intelligent Project Management (AI-PMP)

Lingyi Meng

doi:10.63313/FE.9003

Authors

Lingyi Meng University of Pittsburgh, Pittsburgh, USA Author

DOI:

https://doi.org/10.63313/FE.9003

Keywords:

AI-PMP, Agentic AI, Intelligent Agents, Multi-Agent Systems (MAS), Automated Workflows, Project Management, PMBOK, Knowledge Management, Project Monitoring and Control, Proactive Systems

Abstract

The Project Management Body of Knowledge (PMBOK® Guide) has always been the go-to resource for project lifecycles. Modern projects require a holistic approach with the need to move from static manual, reactive ways of working to proactive, intelligent systems, owing to the interconnected, data-driven and dynamic nature of today. While project management tools now come equipped with data aggregation and simple analytics tools, it mostly stays in a passive repository and puts the overall cognitive load of synthesizing and deciding decisions back on the project manager. The aim of this paper is to examine the new paradigm, AI-PMP — which is a merging of PMP with Artificial Intelligence. It is particularly concerned with Agentic AI and automatically performed workflows. We argue that intelligent agents such as those based on autonomy, proactivity, and social competency change fundamental aspects of the project such as the execution, monitoring, communication, and knowledge management. By deploying a multi-agent system (MAS) architecture, in which advanced and specialized agents (e.g., for risk, schedule, or quality) have access to semantically rich, automated workflows project management can reach unprecedented levels of efficiency, predictive accuracy, and even stakeholder satisfaction. In this paper a theoretical perspective will be presented for this integration, as well as an analysis, regarding challenges in the traditional PMP process groups, major limitations as well as major future research, both technical, human and ethical issues. The study's results indicate that Agentic AI is more than a simple assistive technology, but the core of the upcoming generations of autonomous PMP systems and a key to achieving a fully human-supervised transition in project execution.

References

[1] H. Kerzner, Project Management: A Systems Approach to Planning, Scheduling, and Con-trolling, 12th ed. Hoboken, NJ, USA: John Wiley & Sons, 2017.

[2] K. Beck et al., "Manifesto for Agile Software Development," 2001. [Online]. Available: https://agilemanifesto.org/

[3] Project Management Institute, "A Guide to the Project Management Body of Knowledge (PMBOK® Guide) – Seventh Edition," Project Management Institute, Inc., Newtown Square, PA, USA, 2021.

[4] V. V. Mišić and G. Perakis, “Data analytics in operations management: A review,” Manufac-turing & Service Operations Management, vol. 22, no. 1, pp. 158–169, Jan. 2020. DOI: 10.1287/msom.2019.0805.

[5] A. T. T. Shenhar and D. Dvir, Reinventing Project Management: The Diamond Approach to Successful Growth and Innovation. Boston, MA, USA: Harvard Business Review Press, 2007.

[6] M. Wooldridge, An Introduction to MultiAgent Systems, 2nd ed. Chichester, UK: John Wiley & Sons, 2009.

[7] Project Management Institute, "The Standard for Project Management," Project Manage-ment Institute, Inc., Newtown Square, PA, USA, 2021.

[8] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Hoboken, NJ, USA: Pearson, 2020.

[9] F. Bellifemine, G. Caire, and D. Greenwood, Developing Multi-Agent Systems with JADE. Chichester, UK: John Wiley & Sons, 2007.

[10] V. Dignum, "Responsible autonomy," in Proc. 26th Int. Joint Conf. Artif. Intell. (IJCAI), 2017, pp. 4698–4704.

[11] M. Dumas, M. La Rosa, J. Mendling, and H. A. Reijers, Fundamentals of Business Process Management, 2nd ed. Berlin, Germany: Springer, 2018.

[12] W. M. P. van der Aalst, "Process Mining: Data Science in Action," Berlin, Germany: Springer, 2016.

[13] Feifei Li & Zhe Xu, “A multi-agent system for distributed multi-project scheduling with two-stage decomposition,” PLOS ONE, vol. 13, no. 10, Art. e0205445, Oct. 2018.

[14] Kanj, H., Aly, W. H. F., & Kanj, S., “A Novel Dynamic Approach for Risk Analysis and Simula-tion Using Multi-Agents Model,” Applied Sciences, vol. 12, no. 10, article 5062, 2022. DOI: 10.3390/app12105062

[15] F. Tao, Q. Qi, L. Wang, and A. Y. C. Nee, "Digital Twins and Cyber–Physical Systems toward Smart Manufacturing and Industry 4.0: Correlation and Comparison," Engineering, vol. 5, no. 4, pp. 653–661, 2019.

[16] R. Santhikumar, K. Kartillkayani, M. K. Mishra, S. Thota, I. S. Beschi & B. P. Mishra, “Utiliza-tion of Big Data Analytics for Risk Management,” in Proc. 2022 4th International Confer-ence on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India, Sept. 21–23, 2022, pp. 1559–1565. DOI: 10.1109/ICIRCA54612.2022.9985709

[17] M. Alavi and D. E. Leidner, "Knowledge Management and Knowledge Management Systems: Conceptual Foundations and Research Issues," MIS Q., vol. 25, no. 1, pp. 107–136, 2001.

[18] N. R. Jennings and S. Bussmann, "Agent-based control systems: Why are they suited to en-gineering complex systems?," IEEE Control Syst. Mag., vol. 23, no. 3, pp. 61–73, 2003.

[19] D. A. Norman, "The 'Problem' with Automation: Inappropriate Feedback and Interaction, not 'Over-Automation'," in Human Factors in Hazardous Situations, Oxford, UK: Clarendon Press, 1990, pp. 569–576.

[20] A. Adadi and M. Berrada, "Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)," IEEE Access, vol. 6, pp. 52138–52160, 2018.