Unattended execution

In practice

Unattended is about when the agent runs, not how much it decides. An agent can be unattended and tightly scripted, or attended and highly autonomous, and confusing the two is how people end up granting broad permissions they did not intend. Running unattended needs four things: a host that stays up without a person, credentials scoped to only what the job requires, a hard spend ceiling that stops rather than warns, and actions that are either reversible or gated behind an approval. The useful test is what happens if the agent fires wrongly at 3am and nobody notices until Monday.

Read more

• Unattended AI agents
• Do agents need supervision?

Nearby terms

• Trigger