What it does
- Identifies the target dataset from your natural language description
- Determines the appropriate validation type
- Generates validation configurations with a description and confidence score
- Waits for your approval before making tests available to run
Create an agent
- Go to the Agents tab in the left sidebar.
- Click Create Agent.
- Select Validation Generation as the agent type.
- Select the data source, and add a name and description for the agent.
- Optionally, add additional instructions to guide the agent’s behavior (for example, focus areas or validation preferences).
- Click Create to save.
Run an agent
- Go to the Agents tab and click the agent you created.
- Select the table you want the agent to run on.
- Click Run. You can create multiple runs for the same agent, each targeting a different table.
- Once the run completes, the agent generates a list of validations — each with a description and a confidence score.
- Review each validation and approve the ones you want. Only approved validations become tests that are ready to run.
Supported validation types
The agent can configure the following validation types:
For a full list of supported validation types and their configuration options, see Validation Types.