Perancangan Arsitektur Conversational Decision Support System Berbasis Agentic AI dan Large Language Models
DOI:
https://doi.org/10.47065/bulletincsr.v6i2.997Keywords:
Decision Support Systems; Conversational AI; Natural Language Processing; Business Intelligence; Artificial IntelligenceAbstract
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.
Downloads
References
M. Soori, F. K. G. Jough, R. Dastres, and B. Arezoo, “AI-based decision support systems in Industry 4.0, A review,” Journal of Economy and Technology, 2024.
T. Maaitah, “The Role of Business Intelligence Tools in the Decision Making Process and Performance.,” Journal of intelligence studies in business, vol. 13, no. 1, 2023.
S. Syed, “Towards Autonomous Analytics: The Evolution of Self-Service BI Platforms with Machine Learning Integration,” Available at SSRN 5028517, 2022.
A. Alparslan and D. Chernenko, “Ai-powered opportunities for business analytics–self-service analytics goes conversational,” 2023, BI-Spektrum.
M. Abou Ali, F. Dornaika, and J. Charafeddine, “Agentic AI: a comprehensive survey of architectures, applications, and future directions,” Artif. Intell. Rev., vol. 59, no. 1, p. 11, 2025.
A. K. Ghosh, S. Fattahi, and S. Ura, “Towards Developing Big Data Analytics for Machining Decision-Making,” Journal of Manufacturing and Materials Processing, vol. 7, no. 5, Oct. 2023, doi: 10.3390/jmmp7050159.
R. Sharda, D. Delen, and E. Turban, Analytics, data science, & artificial intelligence: Systems for decision support. Pearson London, 2021.
J. G. Fernando and M. Baldelovar, “Decision support system: Overview, different types and elements,” Technoarete Trans. Intell. Data Min. Knowl. Discov.(TTIDMKD), vol. 2, pp. 13–18, 2022.
Venkat Sanka, “Conversational AI for Enterprise Data Analytics and Governance: A Comprehensive Framework for Natural Language-Driven Business Intelligence,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 11, no. 2, pp. 3922–3928, Apr. 2025, doi: 10.32628/cseit25111329.
C. Schröer, F. Kruse, and J. M. Gómez, “A systematic literature review on applying CRISP-DM process model,” Procedia Comput. Sci., vol. 181, pp. 526–534, 2021.
J. B. Magdaong, A. B. Culaba, A. T. Ubando, and N. S. Lopez, “Generating synthetic building electrical load profiles using machine learning based on the CRISP-ML (Q) framework,” in IOP Conference Series: Earth and Environmental Science, IOP Publishing, 2024, p. 012082.
S. Studer et al., “Towards CRISP-ML (Q): a machine learning process model with quality assurance methodology,” Mach. Learn. Knowl. Extr., vol. 3, no. 2, pp. 392–413, 2021.
A. Handijono and Z. Suhatman, “Optimisasi Hybrid Recommendation System dengan Clustering menggunakan Machine Learning,” Sainstech: Jurnal Penelitian Dan Pengkajian Sains Dan Teknologi, vol. 34, no. 4, pp. 1–11, 2024.
S. Narne, T. Adedoja, M. Mohan, and T. Ayyalasomayajula, “AI-driven decision support systems in management: enhancing strategic planning and execution,” International journal on recent and innovation trends in computing and communication, vol. 12, no. 1, pp. 268–276, 2024.
M. M. Mariani, N. Hashemi, and J. Wirtz, “Artificial intelligence empowered conversational agents: A systematic literature review and research agenda,” J. Bus. Res., vol. 161, p. 113838, 2023.
F. T. Awamleh, A. N. Bustami, Y. A. Alarabiat, and A. Sultan, “Data-Driven decision-making under uncertainty: Investigating OLAP? s mediating role to leverage business intelligence analytics for entrepreneurship,” Journal of System and Management Sciences, vol. 14, no. 8, pp. 350–365, 2024.
M. N. H. Mamun, “Role of AI and Data Science in Data-Driven DecisionMaking for it Business Intelligence: A Systematic Literature Review,” Available at SSRN 5402976, 2025.
A. de Araujo, P. M. Papadopoulos, S. McKenney, and T. de Jong, “A learning analytics?based collaborative conversational agent to foster productive dialogue in inquiry learning,” J. Comput. Assist. Learn., vol. 40, no. 6, pp. 2700–2714, 2024.
H. Gong, L. Ma, D. Liu, and D. Zhang, “AI-driven discovery of high-performance corrosion inhibitors using a BERT-GPT framework for molecular generation,” Corros. Sci., p. 113327, 2025.
F. James, “The Integration of Conversational AI with Data Lakes and Warehouses”.
C.-C. Lin, A. Y. Q. Huang, and S. J. H. Yang, “A review of ai-driven conversational chatbots implementation methodologies and challenges (1999–2022),” Sustainability, vol. 15, no. 5, p. 4012, 2023.
Y. Song, R. C.-W. Wong, and X. Zhao, “Speech-to-SQL: toward speech-driven SQL query generation from natural language question,” The VLDB Journal, vol. 33, no. 4, pp. 1179–1201, 2024.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Perancangan Arsitektur Conversational Decision Support System Berbasis Agentic AI dan Large Language Models
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2026 Ardijan Hadijono
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
