Ajith Suresh

From Dashboards to Dialogue: How LLM-Powered Conversational BI Is Redefining Enterprise Decision Intelligence

Abstract:

The business intelligence landscape is undergoing a fundamental shift. For decades, enterprise analytics meant dashboards, static reports that required technical expertise to build and interpret, and that most decision-makers consulted only when they already knew what they were looking for. Large language models are changing that model. For the first time, it is technically feasible to build systems that allow any business user, regardless of SQL proficiency or data literacy, to ask questions of enterprise data in plain language and receive accurate, contextually coherent responses in real time.
This talk draws on the speaker's published IEEE research on LLM-powered conversational BI architecture and his production experience building enterprise AI systems at global scale to examine what it actually takes to deploy these capabilities in high-volume, mission-critical environments. The talk covers the core architectural challenge  of combining intent classification, entity extraction, semantic mapping, SQL generation, query validation, and multi-turn context retention into a unified pipeline that scales reliably under enterprise workloads and presents benchmarked results from a system achieving 97.8% SQL execution accuracy and 94.1% multi-turn context retention evaluated against standard NL-to-SQL benchmarks.
Beyond the architecture, the talk addresses what the speaker identifies as the harder problem: organizational trust. Technical accuracy alone is not sufficient for enterprise AI adoption. Drawing on lessons from deploying production analytics systems across global operations at Amazon, including a case study where a fundamental measurement flaw in a legacy system had gone undetected across six international sites until a ground-up rebuild corrected it the speaker presents a practical framework for enterprise AI deployment that treats data governance, explainability, and stakeholder change management as first-class deliverables alongside model accuracy and system throughput. Attendees will leave with a concrete understanding of production-grade conversational BI architecture, the most common failure modes in enterprise LLM deployment, and a framework for AI adoption that addresses the organizational realities determining whether these systems actually change how decisions get made.

Profile:

Ajith Suresh is a Data Analytics and AI Strategy professional building enterprise AI systems, LLM-powered business intelligence platforms, and operational analytics infrastructure across Amazon, Illumina, Dell Technologies, and McKesson.
At Amazon's Account Health Support organization, he leads analytics for a global operation spanning six sites and over 860 specialists across North America, Europe, and Asia-Pacific. His work includes building the organization's core performance measurement pipeline from scratch, designing LLM-powered reporting systems that generate executive-level insights automatically, and owning the Weekly Business Review framework relied upon by Senior Directors for operational decision-making. His analytics initiatives have contributed to a 90 percent reduction in missed calls and approximately $2 million in annualized cost savings.
His research on LLM-powered conversational business intelligence, explainable AI frameworks, and generative-AI-driven Auto-BI architectures has been published in IEEE conference proceedings. He is the author of Artificial Intelligence, Business Intelligence, and Analytics: Modern Approaches to Organizational Excellence (ScienceTech Xplore, 2026) and a Distinguished Fellow of the Soft Computing Research Society. A German Utility Patent on his AI-driven decision intelligence and LLM-based SQL orchestration architecture is currently in filing. He holds an M.S. in Business Analytics from Wichita State University and serves as a Lifetime Editorial Board Member of the International Journal of Artificial Intelligence, Data Science, and Machine Learning.