Glossary · Core Concepts

NL2SQL

NL2SQL is the task of automatically translating a natural language question into an executable SQL query.

NL2SQL (natural language to SQL) is the technical name–common in AI research–for converting plain-English questions into SQL. It is the same problem as text-to-SQL: given a question like "which customers spent the most last quarter?" and a database schema, produce a correct query. The hard parts are mapping everyday words to actual table and column names, inferring the right joins, and handling ambiguity. NL2SQL matters because it removes the single biggest barrier between business people and their data: knowing SQL. Modern systems built on large language models reach accuracy levels that make this practical for everyday business questions, not just demos.

In practice

How AI for Database applies it

AI for Database is an NL2SQL system end to end: you type a question, it generates the SQL, runs it against your connected database, and returns a table or chart.
Core Concepts · aifordatabase glossaryRead-only ✓

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

See it on your own database

Connect read-only in minutes. Free models included.

Start free