Instant Control Over Every Agent

Kill-Switch & Approval Gates

Stop any agent instantly with the kill-switch. Require human approval for sensitive actions. Every decision is auditable. You stay in control.

Instantly halt all agent activity. 4 scopes: all traffic, LLM-only, new keys, or agents-only. Propagates in under 5 seconds.

Configure which agent actions require human approval — code changes, deployments, security-sensitive operations.

Define rules: max files per PR, allowed file paths, cost limits, model restrictions. Agents cannot exceed boundaries.

Every action, decision, approval, and rejection is logged with timestamp, user, and context. 365-day retention.

Key Capabilities

Kill-switch with 4 enforcement scopes

Configurable approval gates per agent and action type

Auto-approve conditions (max files, max lines, allowed paths)

4-layer policy hierarchy (Platform → Org → Tenant → User)

Real-time approval notifications via MCP tools and Slack

SOC 2-ready audit trail with 365-day retention

An agent completes its work and proposes an action.

The policy engine checks against org and tenant rules.

If approval is required, the action waits for human review.

Every decision is permanently recorded in the audit trail.

Connect and manage AI agents with kill-switch & approval gates built in.