Glossary · Core Concepts

Text-to-SQL

The process of converting natural language questions into structured SQL queries that can be executed against a database.

Text-to-SQL is a natural language processing technique that translates human-readable questions into Structured Query Language (SQL) queries. This technology bridges the gap between non-technical users and relational databases, enabling anyone to retrieve insights from data without learning SQL syntax. Modern text-to-SQL systems use large language models (LLMs) that understand database schemas, table relationships, and column semantics to generate accurate, optimized queries. The field has evolved from rule-based pattern matching to sophisticated AI models that handle complex joins, aggregations, subqueries, and window functions.

Fig — every answer ships with the tables, rows and SQL behind it.