Ask your data, in Arabic or English

Type a question the way you would ask a colleague. An open-source AI model on your own laptop writes the database query, runs it, draws the chart and explains the result in the language you asked in. Ask about the future and Google's TimesFM model adds a forecast with a likely range.

For teams who hold data they can't send to the cloud, such as beneficiary lists, survey answers or sales, and who want answers without waiting for an analyst.

Try the examples

These are real answers recorded from the app on sample data. The aid figures are made up for the demo. Open a question to see what the AI did.

SELECT region, SUM(households_reached) AS total_households_reached
FROM aid_distributions
GROUP BY region
ORDER BY total_households_reached DESC

SELECT 
    date_trunc('month', CAST(date AS DATE)) AS month,
    region,
    SUM(households_reached) AS total_households_reached
FROM 
    aid_distributions
GROUP BY 
    date_trunc('month', CAST(date AS DATE)),
    region
ORDER BY 
    month, region

SELECT region, SUM(households_reached) AS total_households_reached
FROM aid_distributions
WHERE date_trunc('month', CAST(date AS DATE)) = DATE '2026-03-01'
GROUP BY region
ORDER BY total_households_reached ASC

SELECT 
    date_trunc('month', CAST("date" AS DATE)) AS period,
    SUM("households_reached") AS total_households_reached
FROM 
    aid_distributions
GROUP BY 
    period
ORDER BY 
    period

SELECT 
    date_trunc('month', CAST(date AS DATE)) AS period,
    SUM(households_reached) AS households_reached
FROM 
    aid_distributions
WHERE 
    region = 'Rafah'
GROUP BY 
    period
ORDER BY 
    period

SELECT region, COUNT(*) AS response_count
FROM survey_responses
GROUP BY region
ORDER BY response_count DESC

How it works

1. Ask. Load a spreadsheet or CSV and type a question in Arabic or English.
2. Query. A local AI model reads the table's columns and writes the SQL. If the query fails, it reads the error and fixes it.
3. Answer. The query runs on your computer. You get a table, a chart and a short explanation, with the SQL shown so anyone can check it.
4. Forecast. For questions about the future, Google's TimesFM model predicts the next periods and shows the range they will likely fall in.

What you get

• The analyst set up on your computers, with your own files and your own words for things.
• Open-source models only, so nothing is sent to OpenAI or Google and there are no per-question bills.
• The same questions on Snowflake or BigQuery when your data lives in the cloud.
• The code, open on GitHub, so your team can keep it running without us.

Priced per project, after a free 20-minute call.

Talk to us

See the code on GitHub.