Autonomous (headless)
The agent runs unattended against a goal you defined up front — typically a long-lived monitor, scheduled job, or remediation worker. Budgets (turns, tokens, cost, wallclock) bound the run; the session log is the audit trail.
QuickstartFirst 15 minutes: a working monitor with budgets, headless permission posture, durable session log.
OperationsDepth reference: budgets, lifecycle tool, crash-resume, failure policy, audit log, subagent composition.
Common references
Section titled “Common references”- Sessions and event log — durable session storage + crash-resume
- Context management — compaction + checkpoints make long unattended runs viable
- Attach mode — let an operator drop into an unattended agent mid-run
- Kubernetes event triage — worked multi-agent example
- Autonomous fleets — the general pattern for long-lived unattended workers
- Agent design — prescriptive patterns; goal-following is stricter without an operator in the loop