Natural-language query engine

Ask in plain English.
Watch it compile to a query.

A live demo of the natural-language search pattern I designed and shipped in production. Your prompt is translated into a typed, structured query, which then runs against a dataset. Every result shows the compiled query underneath — that translation is the engineering on display.

  1. 1Plain English

    You ask a question the way you'd ask a colleague — no filters, no syntax.

  2. 2Compiled to a DSL

    An LLM parses it into a typed query — filters, sorts, limits — validated against a schema.

  3. 3Runs live

    The structured query executes over the dataset and returns matching rows in milliseconds.

Behind the demo

This mirrors a search engine I designed and shipped in production.

What you just used is a scaled-down version. The real one I owned end-to-end ran over a large financial dataset — a query DSL that unified the stack, a compiler to optimized SQL, a vector layer for similarity search, and an LLM layer that turns a prompt into a structured query and refines it when ambiguous.

50–75%faster queries — from isolating filter edits and bounding the vector search