in
Setti touta
April 2026
General Introduction
Computer science has experienced remarkable growth over the past decades,
becoming a fundamental driver in addressing complex problems and enabling
efficient information management. Initially focused on data processing and com-
putational tasks, this field has progressively evolved to encompass the design
of intelligent algorithms and advanced systems capable of learning from data,
adapting to dynamic environments, and optimizing decision-making processes.
This continuous evolution has profoundly transformed the way modern systems
operate and interact with users, giving rise to new paradigms in computing.
Among these paradigms, artificial intelligence (AI) stands out as one of the
most influential and rapidly advancing fields. AI refers to the ability of machines
to simulate human cognitive functions such as learning, reasoning, problem-
solving, and decision-making. Through these capabilities, AI-based systems
are able to operate autonomously, process large volumes of data, and adapt to
changing contexts with a high level of efficiency. Consequently, AI has become
a key driver of innovation across various sectors, including healthcare, finance,
industry, and education.
Despite these technological advancements, many organizations continue to
rely on traditional administrative systems that struggle to cope with the in-
creasing complexity and volume of information. These systems often depend on
manual processes and rigid workflows, which can lead to inefficiencies, delays,
and increased workload for administrative staff. This challenge is particularly
evident in university environments, where administrative services must han-
dle a large number of diverse student requests, such as registration inquiries,
document management, academic tracking, and communication with multiple
departments.
In such contexts, traditional administrative systems are often unable to ef-
ficiently handle growing operational demands, which negatively impacts the
quality, speed, and reliability of services provided to students. The main chal-
lenge is therefore to design intelligent and flexible solutions capable of improving
administrative efficiency while reducing human effort and operational costs.
To address this challenge, it is necessary to revisit recent advancements in ar-
tificial intelligence, particularly large language models (LLMs), which represent
1
one of the most significant developments in the field. These models are de-
signed to understand and generate human language with a high level of fluency
and contextual awareness, enabling more natural and effective human–computer
interaction.
Building upon the capabilities introduced by LLMs, intelligent agents emerge
as a direct evolution of these models within modern AI systems. Unlike tradi-
tional rule-based approaches, intelligent agents are capable of perceiving their
environment, making autonomous decisions, and executing tasks while interact-
ing dynamically with users. By leveraging LLMs as their core component, they
benefit from advanced language understanding and enhanced decision-support
capabilities, enabling more effective performance in real-world scenarios.
Accordingly, this work proposes the design and implementation of an AI-
driven intelligent agent system named “UniMate”, specifically tailored to uni-
versity administrative environments. The system aims to support both students
and administrative staff by automating routine operations, improving commu-
nication, and reducing processing time, thereby contributing to a more efficient
and user-centered ecosystem.
To achieve these objectives, this study adopts a structured methodology
combining theoretical foundations with practical implementation. The work is
organized into three parts: the first covers the state of the art and theoretical
background, including artificial intelligence, intelligent agents, large language
models, and process automation; the second focuses on system analysis and de-
sign, including requirements specification, architecture, and UML modeling; and
the third is dedicated to implementation and evaluation, including technologies,
user interfaces, deployment, testing, and results discussion.
Finally, the work concludes with a synthesis of the main contributions and
outlines future improvements, such as the integration of more advanced AI mod-
els, enhanced personalization, and the extension to additional administrative
processes.