A critique of AI tool errors in Critical Path Analysis theory


A project control case study



By Dr. Dimitris Antoniadis

London, UK


As the development and implementation of Artificial Intelligence (AI) tools globally continues to rise, we are beginning to see trends in published research considering its benefits and drawbacks. Several bodies have developed rules underpinning its use in their environments, while others (including governments) are continuing to work on building further regulations. The author has reflected on the latest trends in this space, especially the use of AI by project management professionals. In the latter part of January 2024, the author embarked on an extensive review of AI’s current abilities in delivering Critical Path Analysis (CPA) outputs by testing ChatGPT (v3.5), and in cooperation with others, on ChatGPT (v4), as well as several other AI project management AI tools. This article will highlight the limitations in ChatGPT’s and other AI tools functionality in compiling CPA outputs. Using an example from Project Management Institute (PMI), the author will present these errors as well as a critique of the outputs.

Key words: AI, Artificial Intelligence, ChatGPT, Project Control, Critical Path Analysis (CPA)

Introduction and the Case Study

The aim and objectives of this article are, through a case study, to conduct a critique on AI tool outputs on the specific scheduling technique of Critical Path Analysis (CPA). As part of wider research interest in AI and its use in project management and project control the author was reviewing a series of slides issued by the Project Management Institute (PMI) with the title ‘Generative AI Overview for Project Managers – Resources’ (PMI, 2023). These demonstrate the use of ChatGPT in project management, discussing the use of GenAI and generally DOs and DON’Ts in the use of GenAI.

In slide 12 of the PMI presentation a prompt is given (see Table 1 below) for ChatGPT to provide a Critical Path Analysis output for a hypothetical simple schedule of five (5) activities. The author will use the ChatGPT output provided in the PMI slides (see Figure 2) to highlight an interesting ‘error’ in the resulting outputs.

Table 1. The ChatGPT prompt to generate a simple five activity schedule (PMI, 2023).

The ChatGPT output, as presented by PMI, is shown below in two parts Figure 1 and Figure 2 for ease of reading.

Figure 1. Part 1 of PMI Slide 12 with a ChatGPT query to generate the CPA of a five-activity network. (PMI, 2023)


To read entire paper, click here

How to cite this paper: Antoniadis, D. N.  (2024). A critique of AI tool errors in Critical Path Analysis theory – a project control case study; case study, PM World Journal, Vol. XIII, Issue VI, June. Available online at https://pmworldlibrary.net/wp-content/uploads/2024/06/pmwj142-Jun2024-Antoniadis-critique-of-AI-errors-in-critical-path-analysis-case-study.pdf

About the Author

Dr. Dimitris N. Antoniadis

London, UK


Dr Dimitris N. Antoniadis PhD MSc BEng(1st) CEng FAPM FCMI MIMechE, based in UK, has 35+ years’ experience in Programme and Project Management positions having covered project phases from concept to handover and operation / maintenance.

He is currently Director in the Programme, Project Management and PMO with DANTON PROGM, technical advisor to Novacept and having set up the BSC in Project Control he is currently the Course Leader for the partnership between London Metropolitan College and the University of West London.

He held Senior Management posts in major utilities, infrastructure and construction organisations delivering programmes of works ranging from £250M to £3.2Bn. As Head of Programme Management Office (PMO) he has set up and run the departments within challenging partnering environments, setting up all the processes from governance to reporting. He has also led / co-led major business transformation programmes for Client organisations in UK and abroad integrating project management software tools with ERP systems.

He is the author of the book ‘Demystifying Project Control’; contributed chapters in books on complexity, leadership and other project management topics and has written a number of journal and conference papers. He has been a guest speaker at UK Universities as well as  International conferences on various project management topics.

He was awarded the PhD, from Loughborough University, UK, on the subject of ‘Managing Complexity in Project Teams’, where he developed a framework for managing the effects of complexity on projects.

Parts of his work can be seen in www.danton-progm.co.uk

Dr. Antoniadis can be contacted at dnanton00@gmail.com