Human-in-the-loop (HITL)
Human-in-the-loop (HITL) is a control pattern where an AI agent pauses mid-run for a human to approve or deny a sensitive action before it executes. The decision — who, when, what, why — is recorded as an audit entry, keeping people accountable for consequential actions while agents absorb the preparatory work.
In NeoXam Agents
HITL is triggered by a tool's 'ask' policy: an inline approval card in chat, an API response in task mode, with a 30-minute default timeout — shipping in Beta (V1). The pattern also describes human-in-the-loop reconciliation, where the agent proposes root cause and resolution for a break and the analyst decides.
Related terms
See it at work
Reconciliation break investigation
Shipped — V0 pilotOne click on a break: the agent investigates match history and pricing, then returns root cause, evidence and a recommended action — fully traced.
See how these concepts come together in a governed agentic platform for investment operations.
Explore the platform