<![CDATA[A lack of understanding of procedures and administrative complexity are major obstacles for prospective students pursuing the recognition of prior learning (RPL) pathway. This study focuses on the development of a virtual assistant in the form of a natural language processing (NLP)-based chatbot integrated with the Telegram platform and managed through the Replit development environment. The method applied is research and development (R&D) with a waterfall system development model. The evaluation results show that the system obtained a precision score of 0.90, a recall score of 0.94, and an F1-score of 0.92 in intent classification. Usability evaluation using the System Usability Scale (SUS) on 30 respondents resulted in an average score of 75.20 (good category). In addition, the average response time of the system was in the range of 1–2 seconds per request. These results indicate that the integration of artificial intelligence, Replit, and Telegram is effective in improving information accessibility and accelerating RPL services compared to manual procedures, thereby helping students understand and prepare for the process of converting work experience into academic credits.]]>
Copyrights © 2026
