THE FUTURE OF BUSINESS INTELLIGENCE: INTEGRATING AI ASSISTANTS LIKE DAX COPILOT INTO ANALYTICAL WORKFLOWS
DOI:
https://doi.org/10.15662/IJRAI.2025.0801004Keywords:
Business Intelligence (BI), DAX Copilot, Ambient AI, Clinical Documentation, AI Integration, Analytical Workflow AutomationAbstract
Artificial intelligence (AI), particularly Nuance's DAX Copilot, is revolutionizing business intelligence (BI) solutions. This AI assistant passively records information by transcribing doctor-patient discussions into structured summaries. A study applied Nuance's domain-aware AI technology to a corporate BI environment, enhancing data quality, reducing effort, and improving decision-making processes. A mixed-methods approach was used, with 20 business analysts using a DAX-enabled BI simulation for 30 days, while a control group used traditional tools. Performance parameters such as report creation time, documentation completeness, and user satisfaction were assessed. “In our business, we pride ourselves on handling reports as efficiently as possible, regardless of market conditions — and the addition of an AI assistant like DAX Copilot directly accelerates our workflow while improving both quality and user experience”. Results showed significant improvements, with report creation time reduced by 34%, documentation completeness increased by 28%, and analyst satisfaction increased by 41%. The study recommends adaptable integration strategies and strong privacy controls for promoting AI adoption in BI ecosystems.
References
1. J. Jiang, et al., "SiriusBI: Building End-to-End Business Intelligence Enhanced by Large Language Models," arXiv preprint arXiv:2411.06102, Nov. 2024. [Online]. Available: https://arxiv.org/abs/2411.06102
2. E. Y. Lai, Y. He, and S. Chaudhuri, "Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-service Business Intelligence," arXiv preprint arXiv:2504.11627, Apr. 2025. [Online]. Available at: https://arxiv.org/abs/2504.11627arxiv.org
3. Brown, T. et al., 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems 33. NeurIPS . Available at: https://papers.nips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64aAbstract. html.
4. Marcus, G. & Davis, E., 2020. GPT-3, bloviator: OpenAI’s language generator has no idea what it’s talking about. MIT Technology Review. Available at: https://www.technologyreview.com/2020/08/22/1007539/gpt3-openai languagegenerator-artificial-intelligence-ai-opinion/.
5. A.Vertsel and M. Rumiantsau, "Hybrid LLM/Rule-Based Approaches to Business Insights Generation from Structured Data," arXiv:2404.15604, Apr. 2024. [Online]. Available: https://arxiv.org/abs/2404.15604
6. N. Busany et al., "Automating Business Intelligence Requirements with Generative AI and Semantic Search," arXiv:2412.07668 [q-bio], Dec. 2024. [Online]. Available: https://arxiv.org/abs/2412.07668
7. Microsoft, 2024a. Excel for Microsoft 365: Copilot for Microsoft 365. Available at: https://support.microsoft.com/en-us/office/identify-insights-with-copilot-in excel52d97339-86c0-431c-b46c-e7b07b2898dd.
8. Microsoft, 2024b. Copilot Lab. Available at: https://copilot.cloud.microsoft/enUS/prompts/all?products%2Fname=Excel&createdB y=CreatedByAll.
9. P. Rajkumar, J. Gruska and B. Neubig, "Evaluating Large Language Models for SQL Generation from Natural Language Queries," arXiv preprint arXiv:2204.00498, 2022.
10. Naveed, H., Khan, A.U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Akhtar, N., Barnes, N. and Mian, A., 2023. A comprehensive overview of large language models. arXiv preprint arXiv:2307.06435.
11. Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q.V. and Zhou, D., 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35, pp.24824-24837.
12. E. Amershi et al., "Guidelines for Human-AI Interaction," Proc. In: ACM CHI Conference on Human Factors in Computing Systems, Glasgow, UK (2019) 1–13.
13. Zhang, H., Dong, Y., Xiao, C. and Oyamada, M., 2023. Large language models as data preprocessors. arXiv preprint arXiv:2308.16361.
14. Zhou, X., Zhao, X. and Li, G., 2024b. LLM-Enhanced Data Management. arXiv preprint arXiv:2402.02643.
