We won the Open Agentic AI Innovation Award at the first AAIF Technical Excellence Awards.We won the Open Agentic AI Innovation Award Read why

Text to SQL agent that answers from your live database

Ask your database a question, see the answer and the query

For a US manufacturer we built an agent that turns plain-language questions into SQL over 473+ columns in 15 views, and checks every query before it runs.

Book a free consultation How we build agents
ops-data

  1. Operations leadYour team

    Which customers ordered stainless parts last quarter and have no open order this month?

  2. SQL agentAgent

    1. schema.get_views orders, customers, products
    2. sql.generate a read-only query
    3. sql.validate columns, joins, select only
    4. db.run_query on the reporting replica

    The answer is ready, with the query behind it. Sending the list to the sales CRM needs a sign-off.

    Needs a personShare a customer list with salesRead-only result, copied to the CRM
    Approved by Operations lead

  3. SQL agentAgent

    1. crm.create_task a follow-up for each account

    Follow-up tasks created in the CRM. The question, query and result are saved together.

Example data. An agent at work in a team channel, with a person approving the step you choose.
Mixam: conversion to a final sale from about 20% to about 40%
Where agents help

Data questions queue up behind the people who know SQL.

An agent writes and checks the query, and analysts keep the hard questions.

  1. 01

    Where it stallsSimple questions wait days for an analyst.

    What we do An agent turns the question into SQL over your schema and returns the answer with the query shown.

  2. 02

    Where it stallsGenerated SQL looks right and returns wrong rows.

    What we do Each query is checked against the schema and fixed before it runs. A failure ends in a clear error.

  3. 03

    Where it stallsNobody wants a model writing to the database.

    What we do The agent runs read-only queries on the views you choose. Anything else goes to a person.

What we build

What we build for data questions

Whatever comes in, every project is built from the same parts below, set up for your files and your systems.

Data we answer from

  • PostgreSQL
  • MySQL
  • SQL Server
  • Snowflake
  • BigQuery
  • Redshift
  • Databricks
  • Your data warehouse

How we build it

  • Schema-aware SQL generation

    Queries written against your views, column names and business terms, with the SQL next to each answer.

  • Validation and retries before execution

    A graph checks columns, joins and query type, fixes errors within set limits, then runs the query.

  • Database and team tool connections

    Read-only access to your warehouse or reporting views, plus your team's chat and CRM.

  • Accuracy tests on real questions

    Your analysts' past questions become the test set, and every live query is traced.

Not seeing your case? Tell us where your data lives and which questions come up most, and we start from those.

Tell us about your workflow
How we build agents

Agents that work as part of your team

They work in the tools your team already uses, take on whole tasks and stop for a person where you decide.

  1. Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
  2. Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
  3. Approvals log: each action that waited for a person, with who asked, who decided and when.
Routines: agents that start on a schedule, on new GitHub issues or on an API delivery.
Connected systems: GitHub, Linear, Notion, Slack, Jira and other tools an agent may call, each connected with its own sign-in.
Approvals log: each action that waited for a person, with who asked, who decided and when.

Screens from the workspace our agents run in, with example data.

Where it runs

Teams and industries that use it

Each page shows where agents fit in that team or industry.

Engineering in the open

We help build what agentic AI runs on

Open standards, open-source tooling and published research, all public, so you can check our engineering before you hire us.

Shaping agentic AI

Agentic AI Foundation

Vstorm was the first agentic AI engineering company to join the Agentic AI Foundation and received its 2026 Open Agentic AI Innovation Award.

Read the announcement

Open source

We build open-source agent tooling that other engineering teams install

10M+ PyPI downloads
4,000+ GitHub stars
33 public repositories

Framework contributors

When the framework breaks, we fix it at the source

We maintain our own open-source agent framework and contribute fixes to the frameworks our agents run on, through official partnerships with their teams. Breaking changes reach us before they reach your codebase.

Research

Our engineers and PhDs publish peer-reviewed research

Peer-reviewed papers on agent architectures, evaluation and AI security, and an open benchmark anyone can rerun against our results.

Track record

Frontier AI teams now build on what we shipped first

Our client agents were in production before most of today's agent frameworks had a stable release. You get a team that already knows what breaks between a promising demo and a system people rely on every day.

Case studies
All case studies
Engagement models

Ways to start

Each path starts with a free call with a founder or senior AI engineer. A build goes ahead only after its Proof of Value meets the agreed threshold.

Start with one workflow

We map one workflow with your experts and agree a success threshold before any build.

Best whenYou want the success test agreed before you commit to a build.

Book a free consultation
  1. Process redesign and build Best whenYou want one team accountable for the outcome.
FAQ

Text to SQL agents, answered

What is a text to SQL agent? +
A text to SQL agent turns a question in plain language into a SQL query, runs it on your database and returns the answer with the query shown. Before it answers, the agent reads the schema, validates the query, fixes errors within set limits and says plainly when it cannot answer. It works on read-only views you choose.
Which data questions suit a text-to-SQL agent first? +
Questions your operations, sales or finance team asks every week and an analyst answers by hand: orders by customer, stock levels, late deliveries, account history. Start with a small set of reporting views, collect the real questions people ask about them and agree an accuracy threshold before the build. Open-ended analysis stays with your analysts.
Have you built a text-to-SQL agent before? +
Yes. A US manufacturer came to us with a chatbot that broke after its first tool call. We rebuilt it as a main agent with a SQL sub-agent and an 8-step graph that validates and fixes each query before it runs. It answers questions over 473+ columns across 15 database views, read-only. For an engraved die manufacturer, decades of client interactions became queryable in plain language.
How do you stop a text-to-SQL agent from running wrong queries? +
The agent only runs SELECT queries on read-only views, so it cannot change data. Every query is checked against the schema for columns, joins and type before execution. Validation and execution failures each get a fixed number of retries, then the agent returns a clear error. Each question, query and result is traced, and wrong answers go back into the test set.
How do you know it works before the full build? +
We agree a success threshold with your team before the build and test the agent on your own cases in a Proof of Value. It measures accuracy and running costs, and the build goes ahead only when the threshold is met. Corrections from your team go back into the test set, so every later version is checked against them.
Who owns the system, and which models does it run on? +
You own the code, prompts, evaluation sets and rules by contract. The agents run in your environment on hosted or open-weight models. The model sits behind an interface in code, so you can change it when accuracy, speed or your hosting rules change, without rebuilding the agent.
Start with one workflow

Test one workflow on your own data

A Proof of Value shows accuracy and running costs before the full build.

Book a free consultationRead case studies
From the blog

Reading on text to SQL agents

All articles
Agentic AI

Single agent vs multi-agent systems: when one agent is not enough

One agent or several? Deterministic orchestration beats both when the flow is predictable. Pros, cons and the architectures, with production examples.
Agentic AI

One Dashboard, Full Visibility: Why We Use Logfire in Our Stack

When people ask us about Logfire, they usually think AI agents. Monitoring PydanticAI workflows, tracking token usage, debugging LLM calls.
Engineering

Prompt injection is not the vulnerability. Your agent’s tools are.

Prompt injection will get through. AI agent security depends on what the agent can do when it does: break the lethal trifecta and enforce limits in code.