Skip to content
Writing · Topic

AI agents

Agents take actions inside real systems. We write about keeping them bounded by a human review gate and an audit trail, and about where an agent earns its place in production and where it does not.

  • What we check before an AI agent touches a real system

    Before an agent we build gets access to a real system, it passes a fixed preflight: bounded scope, a human approval gate, an eval set it must clear, a kill switch, an audit trail, a cost ceiling, and a tested rollback path.

All writing