Get started with CLI

Work with Querio from your terminal or coding agent. Create notebooks, run analysis and manage context using your team's Querio access.

The first notebook uses example data. You don't need a database connection.

1. Install and sign in

Follow the installation instructions in the Querio CLI repository, then run:

querio version
querio login

Complete sign-in in your browser. If you don't have an account, choose Sign up and verify your email.

Return to your terminal and check your login:

querio me

If the browser doesn't open, follow the URL printed by the command. The browser must run on the same machine as your terminal, or otherwise be able to reach its local callback.

2. Connect to your workspace

List your workspace:

querio workspace list

Use its ID to connect:

querio workspace use <workspace-id>

Replace <workspace-id> with the ID from the list.

Starting a new team with no workspace yet? Create one instead:

querio init --name 'My team' --json

This creates and selects your workspace. If you're joining an existing team, use its invitation rather than creating another workspace.

You need permission to create notebooks and run code. Your agent uses your access; the CLI doesn't grant additional permissions.

3. Give your agent the Querio instructions

The CLI includes a workflow guide and notebook-authoring reference:

querio code skill
querio code skill --reference notebook-authoring

Your coding agent can run these commands directly. They explain how to create notebooks, execute cells, inspect results and save the work.

Give your agent this task:

Use Querio CLI to create a notebook called "Revenue quickstart"
in my selected workspace.

First read:
querio code skill
querio code skill --reference notebook-authoring

Use this example data:
month,revenue
2026-01,1200
2026-02,1500
2026-03,1800

Create notebook cells containing the data, a monthly revenue
chart, and the total revenue. Run the cells and check the results.

Confirm the notebook saved successfully. Then close only the
session and execution environment you created.

Show me the findings and the saved notebook ID.

Your agent writes the analysis, and Querio executes it. The example data and analysis remain in the saved notebook after its runtime closes.

4. Check the result

The total should be 4,500, with revenue increasing each month.

Ask your agent to show the calculation and chart, then inspect the saved notebook using the ID it returned:

querio notebook get <notebook-id> --json

The saved cells should contain the example data and analysis.

If execution succeeds but saving fails, keep the session open and resolve the save error before closing it. Repeating the creation task could duplicate work.

5. Bring in your own data and workflow

Connect your data

Connect your database or warehouse, then give your agent a question about your business. Datasource access follows your Querio permissions.

Sync with GitHub

Keep Querio context alongside your dbt project and other code, with changes reviewed through Git.

Bring your BI work over

Export existing BI work with unshackle, then use your coding agent and Querio CLI to port and verify it.

For command options, run querio <command> --help or use the CLI reference.