Topics / Tag

#Guardrails

1 article

AI delivery19 Oct 2026Human-in-the-loop is not a security boundaryTwo AI agents deleted production databases. Neither was stopped by its instructions. Approval improves an agent's decisions; it doesn't limit what the agent can do. Why agent safety is a permissions and architecture problem first, how to size the risk of an action, and what humans are actually for.8 min read