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

​
1. Have your context ready

Choose the accounts to watch, the roles that count as a signal, and what should happen for each posting, such as finding the leader of the hiring team. You need enough Deepline credits for the Monitor and each Play run.

​
2. Ask your agent

Paste this into your agent, then provide your accounts and roles 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 Monitor is active with the roles you approved in its payload. The Play is published, and its listener names the Monitor’s tool and stream. A test run returns the posting and a contact, or a reason no contact was found. Ask your agent:
A quiet stream is not an error: an account may not have posted a matching role yet. If the workspace runs out of credits, Deepline turns its Monitors off and resumes them after you add credits. Events from the time they were off are not replayed.

​
Check your understanding

Does the Play’s filter reduce what the Monitor charges for?
No. The Monitor charges for the events it accepts. Narrow its payload to reduce accepted events. The Play’s filter only decides which stored rows start a run.