Agents & tools · Glossary term

What is Human-in-the-Loop (HITL)?

A workflow design in which a person supplies judgment, correction, approval, or escalation at defined points in an AI-driven process.

Also called Human oversight and human review.

Why does Human-in-the-Loop (HITL) matter?

Human involvement is most useful at high-impact, ambiguous, or irreversible boundaries, not as an undefined fallback after every step.

Let the agent classify routine requests automatically, but route uncertain or high-value cases to a reviewer with the evidence and proposed action.

HITL does not automatically make a system safe. Reviewers need time, context, authority, and a clear decision standard.

Lessons that name Human-in-the-Loop (HITL) in a title or section

Human-in-the-Loop: Propose-Then-Commit
The 2026 consensus on HITL is specific. It is not "the agent asks, the user clicks Approve." It is propose-then-commit: the proposed action is persisted to a durable store with an idempotency key;…
Phase 15: Autonomous Systems
Agent State Machines — Graphs, Nodes, Checkpoints
A ReAct loop written by hand is a while True. The same loop written as an explicit graph is something you can checkpoint, interrupt, branch, and time-travel through. The agent hasn't changed.
Phase 11: LLM Engineering
Stateful Graph Orchestration — Durable Execution and Checkpoints
Agent is a state machine; nodes are functions; edges are transitions; state is checkpointed after each node. Resume from any failure at the last successful checkpoint.
Phase 14: Agent Engineering

Approval GateA control point that blocks a consequential action until an authorized person or policy grants permission.
Verification GateA control point that blocks progress until defined evidence satisfies a correctness or quality criterion.
AgentA software system that lets a model select actions toward a goal, observe tool or environment results, and continue under an orchestration…
GuardrailsSystem controls that constrain inputs, tool use, outputs, permissions, and escalation.
AI Risk AssessmentA documented analysis of how an AI system can affect people, organizations, and environments, including context, hazards, likelihood,…
AlignmentThe effort to make a model or AI system behave in ways that match intended goals, constraints, and human preferences across both expected…
Multi Round-Trip Request (MRTR)An MCP request pattern in which an operation returns `resultType: input_required` with one or more `inputRequests`, then the client…
Test OracleThe mechanism, specification, reference, invariant, or human judgment used to decide whether observed program behavior is correct.