Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{205649,
        author = {Abhisha Ganesh Whaval},
        title = {Agentic AI for Autonomous Data Analytics: A Theoretical Framework with Visualization-Driven Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {7758-7776},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205649},
        abstract = {The growing volume and complexity of enterprise data has exposed a critical gap in existing analytics tooling: no current system autonomously executes the full analytics lifecycle — from natural language goal interpretation to finished report — without continuous human intervention. This paper proposes the Agentic Data Analytics System (ADAS), a technical framework for autonomous end-to-end data analytics powered by Large Language Models, Retrieval-Augmented Generation, and multi-agent orchestration. ADAS comprises five interdependent modules: a Goal Interpreter that formalizes stakeholder intent into a structured Goal Specification Object; a Hierarchical Planning Engine that decomposes goals into executable directed acyclic graphs; a Tool-Use Controller that selects and invokes tools via semantic similarity matching; a Reasoning and Validation Layer that applies three-gate error checking at every tool boundary; and an Autonomous Reporting Engine that synthesizes validated outputs into audience-specific narratives. Each module is specified at sufficient technical depth to serve as a direct blueprint for prototype construction. This paper is positioned as a technical proposal: no working prototype is presented, but a structured, synthetic dataset — calibrated against Gartner and McKinsey industry benchmarks and visualized in Power BI — is used to contextualize design priorities across five industry sectors. A formal evaluation framework comprising ten metrics, including Task Completion Rate, Time-to-Insight, and Hallucination Rate, is proposed for future empirical validation. ADAS addresses a clear and timely research gap, and this paper provides the architectural foundation for its realization.},
        keywords = {Agentic AI, Autonomous Analytics, Large Language Models, Multi-Agent Systems, Power BI, Business Intelligence, Retrieval-Augmented Generation, Data Science Automation.},
        month = {June},
        }