Design and Implementation of a WhatsApp-Integrated AI Agent for Automated E-Learning Grade Checking at Politeknik Negeri Bali

DOI

10.2991/978-94-6239-805-4_8How to use a DOI?

Keywords

Academic Administration; AI agent; E-Learning; Grade Verification; WhatsApp

Abstract

This study designs and evaluates a WhatsApp-based AI Agent to support automated grade verification through integration with the institutional E-Learning system. The prototype was developed using an Agile Research and Development approach and combines natural language processing, multi-turn dialogue, workflow orchestration, business-rule validation, pre-execution confirmation, access control, and audit trail logging. The evaluation involved 20 lecturers and one student class, using process efficiency measurement, Technology Acceptance Model (TAM) assessment, statistical testing, NLU benchmarking, and basic security testing. The results show that the average processing time decreased from 18.16 minutes using the manual method to 23.36 seconds using the AI Agent. The error rate decreased from 15.0% to 5.0%, while the AI Agent achieved a task success rate of 95.0%. The comparison also showed a statistically significant difference (p = 5.24 × 10⁻²⁰). NLU testing on 100 utterances across four intent categories showed a 100% intent classification success rate in the test dataset. These findings indicate that the WhatsApp-based AI Agent has the potential to support faster and more structured academic administration. However, the results should be interpreted as an initial evaluation because the test was limited to 20 lecturers, one student class, and 100 NLU utterances, while the WhatsApp connection still relied on Baileys as a prototype connector. Further studies should involve broader participants, more classes, more varied command scenarios, and stronger security, privacy, and platform compliance testing before wider implementation.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - I Gede Sugita Aryandana
AU  - Putu Virgananta Nugraha
AU  - Leni Anggraini Susanti
AU  - Muayyad Muayyad
PY  - 2026
DA  - 2026/10/08
TI  - Design and Implementation of a WhatsApp-Integrated AI Agent for Automated E-Learning Grade Checking at Politeknik Negeri Bali
BT  - Proceedings of the International Conference on Sustainable Green Tourism Applied Science - Engineering Applied Science 2026 (ICOSTAS-EAS 2026)
PB  - Atlantis Press
SP  - 63
EP  - 72
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-805-4_8
DO  - 10.2991/978-94-6239-805-4_8
ID  - Aryandana2026
ER  -