Authors :
P. Naveen Raj; M. Madesh; M. S. Ramesh; S. Venkata Lakshmi
Volume/Issue :
Volume 11 - 2026, Issue 3 - March
Google Scholar :
https://tinyurl.com/6adz4urb
Scribd :
https://tinyurl.com/5fbcmunn
DOI :
https://doi.org/10.38124/ijisrt/26mar1009
Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.
Abstract :
Modern software development environments require continuous coordination among team members, timely issue
resolution, and accurate project planning to achieve successful project outcomes. However, many existing project
management tools still rely heavily on manual monitoring and human-driven decision making. Such reliance often leads to
delayed responses to issues, inaccurate scheduling of tasks, inefficient distribution of workload, and an overall reduction in
productivity. To address these challenges, this work proposes an AI-assisted collaborative framework in which an intelligent
agent functions as a virtual team member that supports development activities. The system continuously observes team
communication, task progress, issue updates, and code changes in order to develop contextual awareness of ongoing project
activities. Based on this contextual understanding, the system generates suggestions only when relevant conditions are
detected, such as errors, delays, or inconsistencies. By analysing historical project data together with developer workload
patterns, the framework predicts potential delays and recommends adaptive scheduling and planning strategies in advance.
A human-in-the-loop mechanism is incorporated to ensure that developers retain complete control over final decisions. This
collaborative approach improves productivity, enhances planning accuracy, and supports effective cooperation between
human intelligence and artificial intelligence without replacing human expertise.
Keywords :
AI-Assisted Project Management, Agent-Based Intelligence, Human–AI Collaboration, Intelligent Software Engineering, Context-Aware Recommendation, Predictive Task Scheduling, Code Analysis Automation, Human-in-the-Loop Systems, Developer Productivity, Knowledge-Driven Collaboration.
References :
- Parrish, Michael D., and Steven Corns. "An ai-based conceptual framework to improve program management of complex systems." IEEE Engineering Management Review (2024).
- Kamboj, Payal, Ayan Banerjee, and Sandeep KS Gupta. "Expert knowledge driven human-ai collaboration for medical imaging: a study on epileptic seizure onset zone identification." IEEE Transactions on Artificial Intelligence 5, no. 10 (2024): 5352-5368.
- Hoda, Rashina, Hoa Dam, Chakkrit Tantithamthavorn, Patanamon Thongtanunam, and Margaret-Anne Storey. "Augmented agile: Human-centered ai-assisted software management." IEEE Software 40, no. 4 (2023): 106-109.
- Cinkusz, Konrad, Jarosław A. Chudziak, and Ewa Niewiadomska-Szynkiewicz. "Cognitive agents powered by large language models for agile software project management." Electronics 14, no. 1 (2024): 87.
- Gvilava, N. T. "AUTONOMOUS INTELLIGENT AGENTS IN DECISION SUPPORT SYSTEMS FOR CRITICAL INFRASTRUCTURE." Professional Bulletin: Information Technology and Security 1 (2025): 55-61.
- Rahman, Md Mostafizur, Md Mostafijur Rahman, Maria Khatun Shuvra, Md Mashfiquer Rahman, and Najmul Gony Md. "AI-Powered Defect Prediction: From Code Smells to Failure Forecasting." (2025).
- Takerngsaksiri, Wannita, Jirat Pasuksmit, Patanamon Thongtanunam, Chakkrit Tantithamthavorn, Ruixiong Zhang, Fan Jiang, Jing Li, Evan Cook, Kun Chen, and Ming Wu. "Human-in-the-loop software development agents." In 2025 IEEE/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), pp. 342-352. IEEE, 2025.
- Hoda, Rashina. "Keynote on Augmented Agile: Human-centred AI-assisted Software Project Management at FinanSE Workshop (ICSE 2024)." In Proceedings of the 1st IEEE/ACM Workshop on Software Engineering Challenges in Financial Firms, pp. 17-18. 2024.
- Cinkusz, Konrad, and Jarosław Chudziak. "Agile Software Management with Cognitive Multi-Agent Systems." In 17th International Conference on Agents and Artificial Intelligence. SciTePress, 2025.
- Sen, Prothit, and Sai Mihir Jakkaraju. "Modeling AI-Human Collaboration as a Multi-Agent Adaptation." arXiv preprint arXiv:2504.20903 (2025).
- Pal, Dheeraj Kumar Dukhiram, Subrahmanyasarma Chitta, Venkata Sri Manoj Bonam, Pranadeep Katari, and Shashi Thota. "AI-Assisted Project Management: Enhancing Decision-Making and Forecasting." J. Artif. Intell. Res 3 (2023): 146-171.
- Klieger, Benjamin, Charis Charitsis, Miroslav Suzara, Sierra Wang, Nick Haber, and John C. Mitchell. "ChatCollab: Exploring Collaboration Between Humans and AI Agents in Software Teams." arXiv preprint arXiv:2412.01992 (2024).
- Augusto, Juan Carlos. "Contexts and context-awareness revisited from an intelligent environments perspective." Applied Artificial Intelligence 36, no. 1 (2022): 2008644.
- Liu, Zhangqi. "Human-AI co-creation: a framework for collaborative design in intelligent systems." arXiv preprint arXiv:2507.17774 (2025).
- Mo, Tianjun, Ziyi Jiang, and Qichang Zheng. "Interactive AI agent for code refactoring assistance: A study on decision-making strategies and human-agent collaboration effectiveness." Academia Nexus Journal 4, no. 1 (2025).
Modern software development environments require continuous coordination among team members, timely issue
resolution, and accurate project planning to achieve successful project outcomes. However, many existing project
management tools still rely heavily on manual monitoring and human-driven decision making. Such reliance often leads to
delayed responses to issues, inaccurate scheduling of tasks, inefficient distribution of workload, and an overall reduction in
productivity. To address these challenges, this work proposes an AI-assisted collaborative framework in which an intelligent
agent functions as a virtual team member that supports development activities. The system continuously observes team
communication, task progress, issue updates, and code changes in order to develop contextual awareness of ongoing project
activities. Based on this contextual understanding, the system generates suggestions only when relevant conditions are
detected, such as errors, delays, or inconsistencies. By analysing historical project data together with developer workload
patterns, the framework predicts potential delays and recommends adaptive scheduling and planning strategies in advance.
A human-in-the-loop mechanism is incorporated to ensure that developers retain complete control over final decisions. This
collaborative approach improves productivity, enhances planning accuracy, and supports effective cooperation between
human intelligence and artificial intelligence without replacing human expertise.
Keywords :
AI-Assisted Project Management, Agent-Based Intelligence, Human–AI Collaboration, Intelligent Software Engineering, Context-Aware Recommendation, Predictive Task Scheduling, Code Analysis Automation, Human-in-the-Loop Systems, Developer Productivity, Knowledge-Driven Collaboration.