Skip to main content
Agent guide: CLI and SDK instructions →

1. Have your context ready

You need Monitor access, a signal scope, and an intended workspace. Not every external event is available as a Monitor.

2. Ask your agent

Paste this into your agent, then provide your task and example inputs when it asks:
Complete any requested sign-in yourself. Give the agent the missing information before approving execution. Provider-backed work can incur usage.

3. Review the result

The deployed Monitor has the intended scope and observed state. The downstream Play receives the correct event, and suspension or removal is confirmed before assuming work has stopped. Ask your agent:
Approve a larger job, recurring work, or external changes only after reviewing that decision.

Check your understanding

Does filtering unwanted rows inside the Play prevent the Monitor from accepting those events?
No. Narrow the supported Monitor payload scope. The Play filter operates after ingestion and may not reduce accepted-event usage.