Configure a data explorer output

Use a data explorer when reviewers need to inspect, filter, and compare a dataset rather than read a single answer.

Choose the output type

Open the Output step in the agent builder and choose the artifact the agent should produce every run.

When to use Data Explorer

• The agent returns many records, observations, sources, or entities.
• Users need filtering, grouping, sorting, or drill-down.
• The output should help analysts explore evidence before making a decision.

Configure Data Explorer

• Choose Data Explorer in the output type menu.
• Define the record type, fields, filters, grouping dimensions, and detail view.
• Use stable field names and allowed values so the explorer remains predictable across runs.

Instruction pattern

Add a short output instruction to the agent instructions or the relevant skill so the agent knows what good looks like.

Create a data explorer with one record per finding, filters for status and severity, grouped evidence, source links, and drill-down notes.

Quality checklist

• The audience and use case are clear.
• The output format is selected before testing.
• The agent instructions describe the expected sections, fields, or scenes.
• Important claims include evidence or source links.
• The output can be reviewed without guessing what each field or section means.
• If another system consumes the result, the schema and allowed values are stable.

Related articles

• Create a Grep agent: build playbook
• Write great Grep skills