Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs

TL;DR

This paper introduces Analytic Agent, an LLM-based system that securely translates natural language into enterprise analytics API interactions, ensuring compliance and reliability in organizational data access.

Contribution

It presents a novel agentic LLM system tailored for enterprise analytics APIs, addressing reliability, security, and governance challenges in natural language data access.

Findings

Successfully interpreted 90 real enterprise use cases

Validated permissions and executed governed queries reliably

Generated compliant visualizations through multi-step reasoning

Abstract

Enterprise analytics aims to make organizational data accessible for decision-making, yet non-technical users still face barriers when using traditional business intelligence tools or Text-to-SQL systems. While recent Text-to-SQL approaches based on Large Language Models (LLMs) promise natural language access to structured data, they fall short in enterprise settings where analytics pipelines rely on governed APIs rather than raw databases. In practice, these APIs encapsulate complex business logic to ensure consistency, auditability, and security. However, delegating mathematical or aggregation logic to an LLM introduces reliability and compliance risks. To this end, we present Analytic Agent, an LLM-based agentic system that translates natural language intents into secure interactions with enterprise analytics APIs. Evaluated on 90 real enterprise use cases constructed by domain experts, it reliably interprets user goals, validates permissions, executes governed queries, and generates compliant visualizations through multi-step reasoning and policy-aware orchestration.