An LLM-Powered Virtual Assistant for Authoring Competency-Based Learning Objectives in Basic Education: A Proof-of-Concept Study

Abstract

Thailand's ongoing shift toward Competency-Based Education (CBE) has emphasized the need for practical tools that help teachers translate national policy into classroom practice. However, many educators still face difficulties in developing curriculum-aligned, competency-based learning objectives (CBLOs) due to limited time, training, and pedagogical support. This study addresses that gap by designing and evaluating a proof-of-concept virtual authoring assistant powered by a large language model (LLM). The system was developed using a Rapid Application Development (RAD) framework and fine-tuned using curriculum-derived custom knowledge to align with Thailand's Basic Education Core Curriculum B.E. 2551 (A.D. 2008) across cognitive, affective, and psychomotor domains. A Design and Development Research (DDR) Type I approach guided three phases: system prototyping, expert quality evaluation, and usability testing with in-service teachers. Results revealed a Very Good quality rating from experts (M = 4.85/5.00) and a Good usability score (SUS = 81.2), confirming both pedagogical soundness and practical feasibility. The study demonstrates that an LLM-powered virtual assistant can effectively support teachers in creating high-quality CBLOs while reducing cognitive and temporal workload. This work contributes a model with strong potential for scaling AI-supported competency-based curriculum design, bridging the gap between educational policy and classroom implementation.