Tursio for Credit Unions: Structured Data Search with Automated Context Graphs

TL;DR

Tursio is a secure, on-premises platform that enables credit union business users to query structured databases using natural language by automatically inferring context graphs and generating accurate queries with LLM assistance.

Contribution

Tursio introduces automated context graph inference and LLM-assisted query generation for natural language database querying in regulated environments, reducing manual effort.

Findings

Successfully applied in credit union scenarios

Automates schema understanding and query generation

Operates entirely on-premises for security

Abstract

Extracting actionable insights from structured databases in regulated industries, such as credit unions, is often hindered by complex schemas, legacy systems, and stringent data governance requirements. We present Tursio, a secure, on-premises, database search platform that enables business users to query enterprise databases using natural language. Tursio automatically infers a context graph -- a schema-level metadata structure that captures join paths, column semantics, and domain annotations -- and uses it to systematically generate accurate query plans through LLM-assisted compilation, grounding, and rewriting. Unlike existing AI/BI tools that require extensive manual context curation, Tursio automates this end-to-end and deploys entirely on-premises. We demonstrate Tursio through realistic scenarios in the credit union domain, and discuss its applicability to other regulated settings.