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

1. Have your context ready

State which database you mean, the business question, and whether this is read-only work. Deepline-managed views and your own tables have different write rules.

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 answer comes from the intended database and population. An empty successful query differs from a permission failure. Approve writes to your own permitted objects separately. Ask your agent:
Approve a larger job, recurring work, or external changes only after reviewing that decision.

Check your understanding

Does a successful empty query mean Database access failed?
No. The query completed without returned matches. A permission or execution error is a different outcome.