By Dennis D. McDonald, Ph.D.* and Michael Kaplan, PMP** 

Background 

In Envisioning the Future of Project Management with "ProjectAI": A Bold Leap into AI-Driven Success Michael Kaplan proposed using AI tools such as ChatGPT to support project management processes through a project’s entire lifecycle, not just in the creation of initial project planning documents as we discussed in Orchestrating AI Large Language Model Tools to Enhance Project Management Document Creation. In that article we outlined a process where AI can support the development of project planning documents.  

Our experiments with tools like ChatGPT and GPT-4, and Michael’s own Python scripting experiments, have convinced us of the value of AI tools in the creation of project related documents. Sample applications include help in the creation of detailed project management plans and even in creation of “use cases” that help make requirements explicit. 

Defining the Project Management Role of AI  

An important question is this: beyond creation of detailed project management documentation at the beginning of a project, what role can AI play in managing projects once they are underway? Examples include standard project management oversight tasks including progress monitoring, risk management, automated progress reporting, change management, and issue management. In other words, is it possible to use AI tools, once a project is underway, to help do the following: 

1. Compare ongoing progress with what the initial planning documents said.

2. Report on where the project stands now compared with the planning documents.

3. Analyze the information generated during (1) and (2), and

4. Recommend changes or improvements when justified by deviation from the original project plans. 

This more “holistic” approach to analyzing AI’s potential role in project management, where we go beyond AI’s help in designing and initiatin g a project,  raises some important technical questions: 

1. Once a project is planned and underway, how can AI tools can also be used to help generate project status reports that are informative and actionable? What systems and tools will be needed to demonstrate this capability?

2. Our research indicates there are occasions where efficient use of AI tools in project management requires the ability to store project report history as well as interactions with existing data sources and AI tools. Can this technically feasible requirement for project-specific data storage be satisfied both securely and economically?

3. AI tools can query and process data extracted from a wide range of structured and unstructured data sources. Will it be possible to use AI to analyze a variety of project staff communications accurately and efficiently, even the information contained in text and email messages? 

Designing a Phased Demonstration Project 

We envision the need for a two phased demonstration project to begin to answer some of the questions posed above and in our previous article. Phase 1 will be a demonstration of how project planning documents can be generated. Phase 2 will then be an attempt to use AI tools to help manage a project once it gets underway. 

System Architecture Components 

Michael has already outlined a preliminary modular system architecture that includes chat agents, vector databases, cloud project management system APIs, and SharePoint integration. We are currently working though the details of what would be needed to implement this architecture by using the above phased approach involving prototyping, system testing, and realistic testing. We expect, of course, that this system architecture will evolve just as AI tools continue to evolve! 

Components of a Phase 1 Demonstration Project 

The below list outlines the initial components of a Phase 1 demonstration project including: 

• A set of functional and technical requirements describing what the project is to accomplish.   

• A set of design templates describing the contents and structure of desired project planning documents. The LLM, based on its analysis of the requirements documents, will use these templates as models for drafting requirements-specific project planning documents for each project. 

• A content management system to store requirements documents, design templates, and documents produced by project management and the LLM.  

• Interactive access to a large language model such as GPT-4.  

• A control system including programmed prompts that guides how the LLM analyzes requirements and, guided by design templates, drafts project specific planning documents for management review by management.  

Phase 1 Task Sequence 

Our experiments so far have focused on individual components of the above list, for example, interacting with ChatGPT to draft use cases and detailed requirements based on various inputs. We now want to move to test out a more complete process. We envision Phase 1 working as follows to generate project specific planning documents for a proposed project: 

1. Task 1: With the aid of the LLM the project manager prepares the requirements documents and the design templates. 

2. Task 2: The control system instructs the LLM to read and analyze the requirements documents and the design templates. 

3. Task 3: The LLM, guided by the control module, drafts the desired planning documents based on the structure and content guidelines provided by the design templates.  

4. Task 4: Management reviews the draft documents and identifies changes, corrections, and/or additions. These are then analyzed by the LLM and used as the basis for updating the LLM-generated planning documents. 

Summary and Next Steps 

We intend to employ LLM resources such as GPT-4 to help develop the baseline requirements for the sample projects, the various project design templates, and the Python scripting that will be used as part of the control module.  

We envision a two-phase project where Phase 1 is described above: formalizing the tools and processes for creating actionable project plans that consider both project specific requirements reflecting “local conditions” (also referred to as “context”) as well as project management “best practices” as filtered through the LLM.  

We then anticipate that a Phase 2 project will examines the role that LLM tools can play in supporting project oversight and management based on the LLM’s intelligent comparison of project plans with progress reports and with other data and documentation created during the project. 

For More Information 

We are currently publicizing the above design of a phased demonstration project to identify potential participants and sponsors. If readers are interested in commenting, keeping up with this work, or in supporting it with real world project requirements and/or resources, please contact either of the two authors; contact information is provided in the author bios below. 

About the Authors 

*Dennis D. McDonald, Ph.D. 

Dennis’ writing, editing, and research work combines analytical and communication skills with extensive project management experience. His industry work includes support for civilian and military contractors, higher ed data governance, corporate database and software consolidation and retirement, adoption of collaborative technologies for knowledge sharing, and open data system development. His writing and content development work includes proposals (business and technical), project planning, research reports and white papers, and market research. He is a member of Alexandria Virginia’s Public Records Advisory Commission and a volunteer for the Alexandria Film Festival. He has served as a private school Board of Trustees member and has been a part owner of an IT-focused consulting company. He is a AAAS member and CMMC Registered Practitioner (RP). His web site is located at www.ddmcd.com and his email address is ddmcd@ddmcd.com.  

**Michael Kaplan, PMP 

Michael Kaplan is a highly successful Senior Program Manager with over two decades of experience delivering impressive results for enterprises. His expertise in program management, project management, and digital transformation has enabled him to protect the national power grid and secure the critical systems of six global banks against cyberattacks. He has also played a pivotal role in enabling 30 organizations to transition into digital enterprises, implementing VMware software and leveraging Agile, Waterfall, and hybrid methodologies. Michael has excelled in team management, leadership, communication, and collaboration. He is certified as a Project Management Professional, Certified Scrum Master, and ITIL, and proficient in the use of various tools. Michael has worked with a broad range of clients in the financial and insurance sectors, healthcare, educational institutions, and government agencies. His natural talent for connecting the dots across people, process, and technology domains, his commitment to delivering excellence, and his professionalism make him a highly respected Program Project Management Consultant. He can be reached via email at kaplan.usa@gmail.com.