Skip to main content
Company knowledge and data · Database queries

Ask about business data in natural language
and get tables and charts back

Connect any of 10 databases, including PostgreSQL, Oracle, SQL Server, Snowflake and BigQuery. Ask in natural language, get the answer as a chart, and verify it with the SQL that ran. Queries that succeed are reused for later questions.

Contact sales
An answer to a database query, returned as a table and a chart
An answer to a database query, returned as a table and a chartReal product screen
Knowledge bases · Databases

Ask documents and data
in natural language

Use policy documents as knowledge bases and business data through database connections. Agents draw on both to answer.

Real product screen

Knowledge bases and grounded answers

PDF and DOCX files are indexed on upload, and a search test lets you check the retrieved chunks first. Every sentence of an answer carries a source number.

A source number on every sentence
Real product screen

Natural-language database queries

Connect 10 databases including PostgreSQL, Oracle, Snowflake and BigQuery. Ask in natural language, get a chart, and verify with the executed SQL.

SQL execution and chart answers
What changes

Before and after adoption

Before

Even a simple aggregate means asking the data team and waiting.

After

Business users ask directly and get the results together with the SQL that ran.

Before

It is hard to trust that SQL written by AI is correct.

After

The SQL that ran is shown with the answer, and the system learns from successful queries and uses them in later answers.

Before

Columns that hold personal data can end up in answers.

After

Column policies mask those values or leave them out.

How it works

Four steps

01Connect a database

Choose the database type, enter the connection details and check that the connection works.

Database connection details screen
Key features

Database queries in detail

10 databases

Connects PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, Synapse, Fabric, Snowflake, Databricks and BigQuery.

SQL and charts

Shows the SQL that ran and a chart alongside the answer.

Learning from successful queries

Remembers successful queries and reuses them for similar questions.

Suggestions

Finds and suggests default exclusions, counting rules, joins and execution limits.

Execution limits

Sets execution limits for each connection type.

Column policies

Mark a column as personal data, and its values are masked or excluded in every query.

Admin settings

Settings each company configures

  • Set up the connection and the tables that queries can use.
  • Apply column policies to personal data columns.
  • Review execution limits and suggestions.
10Databases
Executed SQL and charts
Column policies

Figures reflect the product as of October 2026.

Related features

Related pages

GlossaryTells the AI what your company's terms meanKnowledge graphAnswers based on the relations between data and policiesGuardrailsMasks personal data and blocks risky requestsHarnessesWork environments your team shares, taking each task through to result files
FAQ

Frequently asked questions about database queries

Does it also run queries that change data?

Queries are for reading data, and execution limits are set for each connection type. You can see the limits in effect on the Execution limits tab.

What if column names are English abbreviations the AI does not understand?

Write down the column's meaning and synonyms in a glossary, and that meaning is passed to the model before it answers.

Which databases can we connect?

You can connect 10 databases: PostgreSQL, MySQL, MariaDB, SQL Server, Oracle, Synapse, Fabric, Snowflake, Databricks and BigQuery.

See it with
your own documents

In a consultation, we connect a few of your documents so you can check the answer quality for yourself. Send us your questions and our team will get back to you.

Contact salesRequest security documentation
Product videosReal product screens · Example company ACME Logistics · 16 videos