HITL Approvals

Human-in-the-loop approvals, inputs, and selections—agents pause mid-run for a human decision and resume exactly where they left off

Exemplar

How this harness capability fits the Exemplar platform—governed agent operations, not a standalone prompt playground.

Full autonomy is the wrong default for production: deploys, migrations, and spend need a human at the decision point, not after the incident.

HITL makes escalation a first-class harness primitive—no webhook servers, callback queues, or bespoke approval UIs per agent.

Blocking SDK primitive—harness.hitl().ask(...)—that works from LangGraph, CrewAI, Agno, ADK, or any framework that calls Python.

One console inbox where reviewers approve, reject, answer, or pick an option, with agent-supplied context and full audit on every decision.

Gate high-impact actions—production deploys, credential rotation, tier-0 changes—behind an approval the agent requests itself.

Wrap ask(...) as a framework tool so the model escalates to a human when confidence is low; the run resumes with the human's answer.

One SDK call pauses any agent run for approval, free-text input, or a single choice

Unified review inbox for SDK agent requests and workflow approval steps

TTL-bounded requests—expiry, cancellation, and every decision unblock the run

Slack and email notifications when a request needs a reviewer

Official documentation on docs.exemplar.dev for this capability.

Contact sales

Harness Platform is scoped per deployment. Talk to us about this feature.