Glossary
What is Text-to-SQL?
Text-to-SQL is a method in which an AI model translates a question in natural language into an SQL query that runs against a database. This lets finance or accounting staff analyse data without knowing SQL. Because the generated query is visible, it is possible to trace how a result was produced.
In simple terms
Picture an interpreter between you and the database. The database only understands its own, very precise language: SQL. You ask "Which suppliers did we pay late most often in the third quarter?", the interpreter translates that into SQL, fetches the answer and also shows you the translation. Anyone who reads SQL can check it; everyone else can at least see which tables were used.
In the enterprise
In the finance department of Muster Handels GmbH, a controller asks the AI assistant: "Show all incoming invoices over EUR 10,000 from 2025 with 20% VAT where the supplier is based in another EU country." The assistant generates the SQL query, runs it with read-only access on the ERP data and lists the results. The controller sees the query and then reviews unusual invoices one by one.
Related terms
Sources
- Yu et al. (2018): Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task (arXiv:1809.08887)
- Li et al. (2023): Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs (BIRD, arXiv:2305.03111)
How we use this: UNID AI Predict · Predictive and analytical AI on your enterprise data
FAQ
Frequently asked questions
Can text-to-SQL change or delete data?
See it working on your own material.
In a 30-minute call we show the products live and work out which use case makes sense for you first. No obligation, in German or English, in Vienna or online.
UNID AI · Leonard-Bernstein-Straße 10 · 1220 Vienna · +43 660 476 30 89