Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Jurnal Komtekinfo VIDHEAS: Jurnal Nasional Abdimas Multidisiplin Jurnal Inkofar
Adam Puspabhuana
Universitas Cakrawala
Religion Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Building Expert Digital Twins through Retrieval-Augmented AI Personas: A Framework for Preserving and Transferring Human Expertise Andhika; Adam Puspabhuana; Hedy Pamungkas; Yudi Triyana; Reza Fahmi Alviandy
Jurnal KomtekInfo Vol. 13 No. 2 (2026): Komtekinfo
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/komtekinfo.v13i2.696

Abstract

The preservation and transfer of human expertise represent persistent challenges in knowledge management, particularly when tacit knowledge—embedded within individual experience, judgment, and contextual reasoning—is difficult to document, scale, or disseminate. Although Large Language Models (LLMs) have enabled sophisticated conversational AI systems, existing implementations frequently exhibit factual inconsistencies, hallucinations, and inadequate representation of domain-specific expert reasoning. These deficiencies diminish the reliability of AI-mediated knowledge transfer in high-stakes educational, organizational, and professional contexts. This study addresses these limitations by proposing a framework for building Expert Digital Twins through Retrieval-Augmented AI Personas, providing a scalable and reliable mechanism for preserving and transferring human expertise. The proposed framework integrates six interconnected layers: knowledge acquisition from multimodal expert sources, preprocessing and semantic chunking, vector-based knowledge repository construction, retrieval-augmented generation, persona-driven interaction modeling, and multi-dimensional evaluation. Expert knowledge is systematically collected from books, interviews, speeches, academic articles, and digital media, then transformed into a structured semantic repository enabling dynamic, context-sensitive retrieval. Human-centered design principles are applied throughout to ensure authenticity, transparency, and user trust. An experimental evaluation was conducted by constructing an Expert Digital Twin from a domain expert's knowledge corpus and comparing its performance against a conventional LLM-based baseline using metrics including Faithfulness, Response Accuracy, Expert Similarity, Hallucination Rate, and User Trust. Results demonstrate that the retrieval-augmented AI persona substantially improves factual consistency, perceived authenticity, and knowledge transfer effectiveness. This study contributes a theoretically grounded and practically deployable framework that positions Expert Digital Twins as a novel paradigm for sustainable digital intelligence in knowledge-intensive domains.
Edukasi Internet Sehat dan Aman untuk Pencegahan Kejahatan Siber pada Remaja: WORKSHOP DETEKSI DAN VERIFIKASI KONTEN DEEPFAKE BAGI SISWA SMK Dikky Suryadi; Adam Puspabhuana; Arif Siswandi
VIDHEAS: Jurnal Nasional Abdimas Multidisiplin Vol. 4 No. 1 (2026): Juni
Publisher : VINICHO MEDIA PUBLISINDO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61946/vidheas.v4i1.205

Abstract

Perkembangan teknologi kecerdasan artifisial memunculkan ancaman baru berupa kejahatan siber berbasis manipulasi digital, salah satunya deepfake, yang berisiko bagi remaja sebagai pengguna aktif internet. Kegiatan Pengabdian kepada Masyarakat ini bertujuan meningkatkan pemahaman dan keterampilan siswa Sekolah Menengah Kejuruan (SMK) dalam mengenali, memverifikasi, dan menyikapi konten digital yang berpotensi menyesatkan, sekaligus membangun kebiasaan berinternet yang sehat dan aman. Workshop dilaksanakan selama satu hari di Laboratorium Komputer SMK N 2 Cikarang Barat dengan melibatkan 18 siswa (13 laki-laki dan 5 perempuan) dari jurusan Rekayasa Perangkat Lunak, Teknik Komputer dan Jaringan, serta Akuntansi Bisnis. Materi disampaikan secara bertahap, meliputi internet sehat dan literasi digital, pengenalan jenis kejahatan siber seperti phishing, cyberbullying, dan hoaks, keamanan data pribadi, hingga praktik deteksi dan verifikasi konten deepfake menggunakan pendekatan triangulasi dan tools berbasis kecerdasan artifisial. Peserta juga dilatih membuat prototipe alat verifikasi sederhana berbasis JavaScript dan Large Language Model (LLM) API. Evaluasi pemahaman dilakukan melalui pretest dan posttest terhadap 10 peserta yang mengisi kuesioner secara lengkap, menunjukkan peningkatan skor rata-rata dari 29,72 menjadi 43,22 (skala maksimum 50), serta pergeseran proporsi jawaban kategori tinggi dari 34,44% menjadi 86,67%. Hasil ini menunjukkan bahwa pendekatan edukatif berbasis praktik langsung efektif meningkatkan literasi digital dan kesiapan remaja menghadapi ancaman kejahatan siber, serta relevan untuk dikembangkan berkelanjutan di sekolah lain.
Design and Development of a Lecturer Academic Portfolio Platform Based on Serverless JAMstack Architecture with Supabase Backend-as-a-Service Adam Puspabhuana; Yudi Triyana
INKOFAR Vol. 10 No. 1 (2026)
Publisher : Politeknik META Industri Cikarang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Background Digitalizing academic portfolios is an urgent need for lecturers in Indonesia to enhance their scientific visibility and meet accreditation requirements. However, the currently available Content Management System (CMS) platforms are generic and not designed to accommodate the specific needs of academic portfolios for lecturers. Purpose This research aims to design and implement a serverless CMS platform tailored for faculty academic portfolios, using a zero-configuration deployment approach Methodology The research adopts the Design Science Research (DSR) framework comprising six stages. Evaluation was conducted through black-box testing with 20 scenarios derived from the functional requirements specification, comparative analysis using five evaluation criteria (academic features, deployment complexity, infrastructure requirements, security mechanisms, and operational cost), and heuristic evaluation involving five evaluators consisting of usability experts and information systems lecturers based on Nielsen’s ten usability principles. Findings This platform was successfully developed using the Jamstack architecture, with Supabase as the Backend-as-a-Service (BaaS). All 20 functional test scenarios were validated with a 100% success rate. Heuristic evaluation yielded an average score of 4.1 out of 5 Implications The research results contribute to the development of a serverless academic web application architecture and offer practical solutions for digitalizing faculty portfolios in Indonesia Originality Beyond implementing a serverless portfolio platform, this research contributes a reusable architectural model for academic CMS development that integrates Jamstack, Backend-as-a-Service, zero-configuration deployment, and multi-layer security architecture..
Co-Authors Andhika Arif Siswandi Dikky Suryadi Hedy Pamungkas Reza Fahmi Alviandy Yudi Triyana