Work with Claude Code

1. Have your context ready

Have a known contact, account, or small input file and a definition of an acceptable result.

2. Ask your agent

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

/deepline-gtm Help me complete this task with Deepline in Claude Code. Ask me for the input, desired output, and rules for accepting a result. Inspect the live tools or Plays that fit before choosing a route. Show the proposed pilot, expected evidence, and applicable usage. Do not submit provider work or change a connected system until I approve the plan.

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

Claude explains the inspected route and reports accepted, unresolved, and failed records separately. Ask why a rejected record failed before changing the rule. 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

The agent says the Play passed its structural checks. Does that prove the email belongs to the intended person?

Show the answer

No. Ask it to compare the pilot’s identity evidence and email validation with your acceptance rule.

​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