Governed Support Ops Agent
AI agents your security team will actually approve.
For US tech companies past Series A that need agents, not chatbots.
Scoped access
Least-privilege by default. Every agent only sees what it needs.
Full audit trail
Every action logged. Tool calls, inputs, outputs, approvers.
Human in the loop
Approval gates on anything risky. Your team approves. Always.
Two artifacts, one repo
A runnable Governed Support Ops Agent, and @sarthak/agent-shield: the governance layer (Cedar policies, audit log, kill-switch, MCP scope check, circuit breaker) extracted as a drop-in library.