Result: Optimised Intelligent Software Company Management System using Multi-Agent Framework.

The software development industry faces ongoing challenges in managing complex projects and resources effectively. The Intelligent Software Company Management System (ISCMS) is an innovative approach designed to enhance the efficiency of software company operations through a multi-agent framework. This system automates key roles within a software company, including Client, Architect, Developer, Engineer, Tester, and Project Manager, with each agent responsible for specific operational tasks. These agents work together to manage projects, allocate resources, and handle client interactions, resulting in greater efficiency and streamlined project delivery. ISCMS is built on a powerful tech stack comprising Autogen, CREW AI, LangGraph, Python, and advanced Language Learning Models (LLMs) like Gemini and OpenAI, ensuring it can scale and adapt to various project needs and organizational structures. This research explores the performance of ISCMS by comparing the efficiency of three agent frameworks--Autogen, CREW AI, and LangGraph--under the same project conditions. The findings reveal notable differences in performance, shedding light on the strengths and weaknesses of each framework in managing software operations. By clearly defining agent roles and leveraging cutting-edge technologies, ISCMS offers a versatile platform that not only automates management processes but also improves communication and productivity within development teams. This research contributes valuable insights into the practical application of multi-agent systems in corporate management and highlights the most effective frameworks for optimizing software company operations. [ABSTRACT FROM AUTHOR]

Copyright of Grenze International Journal of Engineering & Technology (GIJET) is the property of GRENZE Scientific Society and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)