Work with a coding agent

1. Have your context ready

Use an agent with shell access, such as Codex, Claude Code, or Cursor. Have one representative input ready.

2. Ask your agent

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

/deepline-gtm Follow https://code.deepline.com/INSTALL.md in this environment. Complete the supported setup and verify the selected Deepline workspace. Then ask me for one business outcome, a representative input, and an acceptance rule. Inspect matching tools or Plays and explain the proposed pilot. If this environment cannot run the supported setup, explain the missing capability instead of assuming it worked.

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 setup works where the agent actually runs. The pilot preserves source identity and has a result you can review before expanding the job. 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

Deepline works on your laptop. Does that prove it works inside your remote agent?

Show the answer

No. Ask the agent to verify installation and workspace access where it actually runs.

​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