Configure a dashboard output

Use a dashboard when the answer needs to be scanned, compared, filtered, or monitored rather than read as a long narrative.

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 Dashboard

• The agent produces metrics, statuses, flags, segments, or comparisons.
• Reviewers need a repeatable operating view for many entities or cases.
• The output should make trends, counts, exceptions, and priorities obvious.

Configure Dashboard

• Choose Dashboard in the output type menu.
• Define the panels the dashboard should contain before running the agent.
• Ask for short labels, metric definitions, and drill-down rows so the dashboard is useful without extra explanation.

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 dashboard with summary metrics, priority flags, grouped findings, comparison tables, and drill-down notes for each high-risk item.

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