Amtsal, Muh Khairul (2026) Pengembangan Modul-Modul Fungsional Berbasis Artificial Intelligence untuk Customer Service, Pelayanan Perbankan, Manajemen Talenta, dan Sistem Presensi. Project Report. [s.n.], [s.l.]. (Unpublished)
![[thumbnail of 5025231172-Project_Report.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5025231172-Project_Report.pdf - Accepted Version Restricted to Repository staff only Download (1MB) | Request a copy |
Abstract
Evolusi Artificial Intelligence (AI) dalam satu dekade terakhir telah bergeser dari model generatif probabilistik menjadi Agentic AI yang memiliki otonomi dalam perencanaan dan eksekusi tugas transaksional. Penelitian ini mendokumentasikan pengembangan ekosistem AI komprehensif di PT Sakura System Solutions untuk mengatasi keterbatasan sistem petahana pada sektor perbankan dan Human Resource Information System (HRIS). Permasalahan utama yang diidentifikasi meliputi inefisiensi operasional akibat interaksi teks yang rigid, rendahnya akurasi retrival informasi internal, serta kurangnya objektivitas dalam penilaian kinerja talenta. Solusi yang diusulkan mengintegrasikan tiga pilar teknologi utama: (1) arsitektur Retrieval-Augmented Generation (RAG) yang digabungkan dengan agen otonom untuk menangani instruksi perbankan kompleks, (2) penerapan Vision Language Model (VLM) untuk analisis multimodal pada matriks 9-Box Grid dalam manajemen talenta, dan (3) algoritma Face Recognition pada sistem presensi untuk menjamin validitas data secara real-time. Hasil dari kerja praktik ini menunjukkan bahwa integrasi ekosistem AI yang otonom dan multimodal mampu mereduksi latensi interaksi, meningkatkan akurasi retrival informasi, serta menyediakan basis data yang objektif untuk pengambilan keputusan strategis dalam manajemen sumber daya manusia dan layanan perbankan.
===============================================================================================================================
The evolution of Artificial Intelligence (AI) over the past decade has shifted from probabilistic generative models to Agentic AI, which has autonomy in planning and executing transactional tasks. This study documents the development of a comprehensive AI ecosystem at PT Sakura System Solutions to overcome the limitations of existing systems in the banking sector and Human Resource Information System (HRIS). The main problems identified include operational inefficiencies due to rigid text interactions, low accuracy in internal information retrieval, and a lack of objectivity in talent performance assessments. The proposed solution integrates three main technological pillars: (1) Retrieval-Augmented Generation (RAG) architecture combined with autonomous agents to handle complex banking instructions, (2) the application of a Vision Language Model (VLM) for multimodal analysis on a 9-Box Grid matrix in talent management, and (3) a Face Recognition algorithm in the attendance system to ensure real-time data validity. The results of this practicum show that the integration of an autonomous and multimodal AI ecosystem can reduce interaction latency, improve information retrieval accuracy, and provide an objective database for strategic decision-making in human resource management and banking services.
| Item Type: | Monograph (Project Report) |
|---|---|
| Uncontrolled Keywords: | Agentic AI, HRIS, Retrieval-Augmented Generation, Vision Language Model, Face Recognition. |
| Subjects: | T Technology > T Technology (General) > T58.6 Management information systems T Technology > T Technology (General) > T58.64 Information resources management |
| Divisions: | Faculty of Information Technology > Informatics Engineering > 55201-(S1) Undergraduate Thesis |
| Depositing User: | Muh Khairul Amtsal |
| Date Deposited: | 09 Feb 2026 02:46 |
| Last Modified: | 09 Feb 2026 02:46 |
| URI: | http://repository.its.ac.id/id/eprint/132245 |
Actions (login required)
 |
View Item |