Capabilities

Human-in-the-Loop Escalation Gating

Holding a routed-for-review prompt or a proposed tool call for explicit human sign-off before it executes, with the reviewer given enough context — what data, what action, what triggered the flag — to make a real decision rather than rubber-stamp a queue.

Features2
  • Escalation review inbox
  • One-click approve/block
Capability entities1
Agent pattern capabilities1