<![CDATA[The rapid advancement of information technology and the increasing complexity of organizational data have intensified the need for more adaptive and accessible Decision Support Systems (DSS), particularly for non-technical users. This study aims to examine and propose a Conversational AI–Driven Decision Support System as an evolution of DSS in the modern data era. The research adopts a Conceptual and Architectural Research (CAR) approach grounded in the principles of Design Science Research (DSR), with CRISP(Q) ML employed as the system development methodology. The main contribution of this study lies in the design of a conceptual architecture and an end-to-end process flow that integrates Agentic AI based on Large Language Models (LLM) with Business Intelligence infrastructure to support interactive data exploration. The proposed intelligent agents are capable of understanding user query context, performing step-by-step reasoning, and autonomously generating analytical queries, thereby overcoming the limitations of traditional NLP-based approaches. The findings indicate that conversational approaches have the potential to enhance analytical accessibility and support faster decision-making, while also identifying challenges related to data quality, governance, and user trust.]]>
Copyrights © 2026
