Skip to content
~/reflective_data

analytics-dictionary / term / ai

Text-to-SQL

Text-to-SQL is using AI to turn a plain-language question into a SQL query.

Written by Reflective Data experts · updated Oct 5, 2026

It makes data accessible to non-analysts, but unguided models can pick the wrong tables or invent metric logic. Grounding the model in a semantic layer, with approved metrics and joins, greatly improves accuracy.

Always show the generated query and the data sources.

related

Large language model (LLM)Self-service BISemantic layer

// how we can help

We build company brains, agent harnesses and AI bots on top of data you can trust. AI services → · The data platform behind it

more in ai

embeddings.md

Embeddings

Embeddings are numerical representations of text or other data that capture meaning, so similar things are…
agent-harness.md

Agent harness

An agent harness is everything around a model that makes an agent useful and safe: tools,…
gemini.md

Gemini

Gemini is Google family of AI models and assistant, available across Google products and through APIs.
context-window.md

Context window

The context window is the amount of text a language model can consider at once, including…
reranking.md

Reranking

Reranking reorders retrieved results with a more precise model, so the best passages go to the…
token.md

Token

A token is a small piece of text, often part of a word, that language models…

← full analytics dictionary