A systematic review of generative AI usage for IT project management

A new systematic review by researchers Ionut Anghel and Tudor Cioara from the Technical University of Cluj-Napoca provides a comprehensive analysis of how generative AI is being used in IT project management. Published on arXiv on April 23, 2026, the paper applies the PRISMA methodology to synthesize findings from over 50 studies. The results show a clear dominance of OpenAI's GPT models across the included research, with most applications relying on prompt engineering rather than fine-tuning or advanced AI techniques. This suggests the field is still in an exploratory phase, with limited real-world integration into project management tools and processes.

The review also pinpoints three promising research directions for AI-enabled project management. First, process group-specific AI agents that automate tasks within phases like initiation, planning, or execution. Second, project role-based AI agents that simulate or assist specific roles such as project managers, risk analysts, or stakeholders. Third, hybrid collaborative networks that enable human-guided orchestration, where AI agents work together under human oversight. These directions could transform how project teams leverage AI, moving from simple text generation to autonomous, role-aware assistants that streamline workflows and improve decision-making.