# Human-Gated Approvals

> Human-gated approvals are a governance control where an AI agent's consequential actions, a payment, an outbound email, a record update, are held in a queue until a person approves them. The agent prepares the action; a human authorises it; an audit trail records who approved what.

- Part of: [The Sentry AI Transformation Glossary](https://sentrysolutions.ai/glossary)
- Canonical: https://sentrysolutions.ai/glossary/human-gated-approvals

The gate is placed at the action, not the conversation. Agents can read, reason and draft freely, because none of that changes the business. The moment an action would cross into consequence, it waits.

Done well, this is not a brake on automation but the thing that makes automation deployable: leadership can say yes to agents precisely because nothing irreversible happens without a person in the loop. Which actions gate, and which run free, becomes an explicit policy rather than an accident of vendor defaults. No agent acts alone.

## Related terms

- [Kill Switch](https://sentrysolutions.ai/glossary/ai-agent-kill-switch)
- [AI Agent Governance](https://sentrysolutions.ai/glossary/ai-governance)
- [Agent Management Platform](https://sentrysolutions.ai/glossary/agent-management-platform)