Use Deepline with an agent

1. Have your context ready

Know which agent you use, where it runs, and which workspace should own the work.

2. Ask your agent

Paste this into your agent, then provide your task and example inputs when it asks:

/deepline-gtm Help me connect this agent to Deepline. Check whether this environment can run shell commands or supports a remote MCP connection. Use the supported installation path for that environment. Tell me which browser authorization or connector settings I must complete myself. Confirm the effective workspace and discover one relevant workflow without executing it.

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 agent can discover Deepline workflows in your intended workspace. A plugin icon or a signed-in browser alone does not establish that the agent can use that workspace. Ask your agent:

/deepline-gtm Compare the result with the acceptance rule we agreed. Show the evidence for accepted and rejected outcomes, unresolved questions, and recorded Deepline usage where work ran. If work is still running or a response is uncertain, inspect the original saved execution before proposing another request. Explain the next decision I need to make.

Approve a larger job, recurring work, or external changes only after reviewing that decision.

Check your understanding

Does installing a skill grant a new workspace permission?

Show the answer

No. Skills provide instructions. Authentication and workspace permissions still control access.

​1. Have your context ready

​2. Ask your agent

​3. Review the result

​Check your understanding

​Related guides

1. Have your context ready

2. Ask your agent

3. Review the result

Check your understanding

Related guides