<![CDATA[The purpose of this study is to design an LLM-powered chatbot that can assist small businesses in their HR business process, specifically to document knowledge. Employing the Design Science Research (DSR) methodology, the research progresses through problem identification, solution design, artifact development, demonstration, and evaluation phases. The proposed chatbot artifact is evaluated using the Retrieval Augmented Generation Assessment (RAGA) framework for technical performance and the Unified Theory of Acceptance and Use of Technology (UTAUT) for user acceptance. RAGA evaluation demonstrates strong performance, with average scores of 0.95 for context recall, 0.98 for response relevancy, and 1.00 for faithfulness, indicating the chatbot successfully maintains conversational focus and adheres to design specifications. UTAUT results reveal positive user acceptance, particularly in effort expectancy (average 3.30) and facilitating conditions (average 4.08), though employees continue preferring human interaction for complex knowledge-sharing tasks. This study uniquely contributes by developing the first LLM-based chatbot specifically designed for knowledge documentation in small IT enterprise HR contexts, combining technical rigor with practical implementation insights. The artifact design can be replicated and enhanced by future researchers exploring LLM applications in organizational knowledge management, with implications for democratizing advanced knowledge management capabilities in resource-constrained environments.]]>
