Chat with your database in plain English
and check every answer against the query that produced it
Datarelix lets you ask a database a question in plain English. It reads your schema, turns the question into a read-only query and shows the executed SQL, source tables, returned rows and runtime alongside the answer. Business users can build reports without writing the first query; analysts can inspect the calculation and investigate further. Useful charts can be saved to a dashboard and refreshed on demand.
What you can ask, and what comes back
You ask the question the way you would ask a colleague. What comes back is a table or a chart, and underneath it, the evidence: the query, its sources, and how long it took.
- the query
- the exact SQL that ran, not a paraphrase of it
- the tables
- which sources it read, so you can spot a staging copy
- the row count
- how many rows came back
- the runtime
- how long the query took on your database
The mechanism behind the translation — schema context, a structured plan, validation, then execution — is set out in how a plain-English question becomes SQL.
SELECT c.name, SUM(o.total) AS paid_order_value_usd
FROM customers c
JOIN orders o ON c.id = o.customer_id
WHERE o.status = 'paid'
AND o.created_at >= DATE_TRUNC('quarter', CURRENT_DATE)
AND o.created_at < DATE_TRUNC('quarter', CURRENT_DATE) + INTERVAL '3 months'
GROUP BY c.id, c.name
ORDER BY paid_order_value_usd DESC, c.id
LIMIT 10;| Customer | USD |
|---|---|
| Enterprise Plus | 352,940 |
| Acme Corp | 284,110 |
| Globex | 219,803 |
| Initech | 201,442 |
Enterprise Plus: 352,940 USD; Acme Corp: 284,110 USD; Globex: 219,803 USD; Initech: 201,442 USD; Northstar: 169,000 USD; River: 148,000 USD; Oak: 127,000 USD; Cedar: 106,000 USD; Pine: 91,000 USD; Maple: 78,000 USD
Read-only by design
Every query Datarelix generates is validated as read-only before it runs. Your database credentials are encrypted and never reach the AI model, and generated Python analysis runs with its network access blocked.
See how each control works on the security page, in how read-only access is enforced and in how credentials stay out of the model. Comparing tools? Use the AI analytics security checklist.
See how every answer was calculated
Each answer arrives with the query that produced it, so you can see how your question was read — which table, which filter, which period — before a number goes into a report.
Describe your tables and business terms once — what counts as a completed order, which amount is net — and every later question starts from that meaning. More on schema context and business definitions and on how to verify AI-generated SQL and results.
Turn answers into charts and dashboards
When an answer is worth keeping, ask for a chart in the same conversation and pin it to a dashboard you refresh whenever you need current numbers.
-
Ask for the chart you want
“Make this a line chart by month.” The chart fits the result, and you can restyle it without code.
-
Pin it by asking
“Add this to my Sales dashboard” puts the chart on that dashboard.
-
Refresh one card or all of them
A refresh re-runs the saved query and redraws the chart with current data.
-
Take it with you
Download charts as PNG or SVG and results as CSV, ready for a deck or a doc.
Step by step: build a dashboard from database questions.
Revenue by customer
Bar · 10 rows
Revenue by month
Line · 12 rows
Build your first dashboard from a question.
Connect your database, ask in plain English and pin the chart.
14 days free · no credit card required
Works with the database you already run
Datarelix queries your databases, warehouses and cloud files where they live. See every supported source, or add your first connection with the quickstart.
Start with the guide for your engine: PostgreSQL, MySQL, BigQuery or Snowflake.
Alongside your BI tool
Keep your BI dashboards for the metrics everyone reads every week. Datarelix answers the questions in between — the ones that would otherwise wait in a ticket queue.
Compare AI analytics and traditional BI, or see how self-service analytics fits the stack you already run.
Answers you can check
Datarelix belongs to a category we call verifiable conversational analytics: you ask in plain words, and every answer comes with the query that ran and the tables it read.
Read the category explanation or browse the guides by task.
Common questions
- Do I need to know SQL?
- No. You ask in plain English, and the SQL behind each answer is there if you want to see it.
- What do I need to connect?
- The connection details for your database and a user that can read the tables you want to ask about.
- Can it change my data?
- No. Every query Datarelix generates is validated as read-only before it runs.
- Does the AI model see my database password?
- No. Credentials are encrypted and used only to connect to your database; they never reach the model.
- Can I keep charts and dashboards?
- Yes. Pin a chart to a dashboard by asking, refresh it whenever you need current numbers, and export charts as PNG or SVG.
- Does this replace our BI tool?
- No. Keep your BI tool for the metrics everyone reads every week; Datarelix answers the questions in between.
Ask one question you already know the answer to.
Connect your database, ask, and check the answer against the query that produced it.
14 days at Pro limits · no credit card required