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

1. Have your context ready

Use a Bot session with terminal access and a working folder you can keep for later requests.

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 Bot itself can access the intended workspace. A browser session elsewhere is not evidence that its execution environment is authorized. Ask your agent:
Approve a larger job, recurring work, or external changes only after reviewing that decision.

Check your understanding

Your browser is signed in, but the Bot reports no workspace access. Is the Bot ready?
No. Ask the Bot to complete authorization in its own environment and verify the workspace there.