One product, and the fourteen different questions people arrive with. Pick the one that sounds like yours.
What the category is, what current systems can and cannot do, and how to tell two of them apart.
The category, explained
An assistant that reads your schema, writes the query, runs it read-only and shows you exactly what it did — with no rows leaving your network.
Read moreThe landscape
Four jobs are genuinely solved, two are getting there, and one is oversold. Knowing which is which saves a quarter.
Read moreEvaluation
They all demo identically — a question goes in, SQL comes out. The differences show up in week three, on your schema, and they are all architectural.
Read moreThe two engines it speaks, each covered twice: the workflow, and the depth a DBA asks about.
PostgreSQL
Connect once, ask in English, get rows and the query that produced them. Follow-ups keep the context, so "and only the ones from last quarter" works.
Read morePostgreSQL, in depth
Generic SQL generation writes ANSI SQL and stops. Postgres has thirty years of features past that, and the query you want usually needs one of them.
Read moreMySQL
Ask a question, get rows and the query behind them. It reads your real schema first, so the answer references your tables rather than plausible-sounding ones.
Read moreMySQL, in depth
Most generated MySQL fails for reasons that have nothing to do with the question: a mode, a collation, or a feature the server version does not have.
Read moreWriting SQL, exploring data, or living in a schema somebody else designed.
For people who already write SQL
Generate the query, explain the one you inherited, and find out why the other one takes forty seconds — without leaving the schema you are working in.
Read moreThe technique
The gap between a query that parses and a query that is right is your schema. Here is how that gap gets closed.
Read moreThe interface
Nobody gets the question right first time. A chat holds what has already been established, so refining an answer costs a sentence rather than a rewrite.
Read moreFor analysis
Dashboards answer the questions you knew you would have. This is for the other ones — the ad-hoc, one-off, needed-in-ten-minutes kind.
Read moreFor engineering teams
The word implies a second pair of hands on the controls. This one deliberately has none — it reads, suggests and explains, and every write stays yours.
Read moreLocal models, and the fully offline configuration that makes privacy an observation rather than a promise.
Local models
Local retrieval over your schema and a local model to write the SQL. Nothing about your database reaches anyone else’s server.
Read moreAir-gapped & regulated
In a regulated environment "we do not store your data" is a policy. "The process makes no outbound connections" is an observation, and only one of them survives an audit.
Read moreComparing SQLore against something specific? The comparison pages cover the alternatives, and features is the full capability list.
Start free, upgrade when you are asking enough questions for it to matter.
