Human Approval Gates for Irreversible Agent Actions

Description and use

Managing safety of automated agent actions without creating a bottleneck of human approvals.

Problem

Managing safety of automated agent actions without creating a bottleneck of human approvals.

Outcome

Reduced human approval workload from 86 to 2 decisions weekly while maintaining safety for irreversible actions.

Workflow

• Identify irreversible actions in each skill
• Remove capability verbs for read‑only skills
• Add kill gates for actions that must not proceed under any condition
• Reserve human approval gates only for actions that cannot be undone
• Configure kill‑switch checks centrally
• Document capability and kill‑switch rules in frontmatter
• Review and adjust rules based on audit logs

Evidence

I run 47 agent skills against my own accounts … Two of them stop at the moment of action and wait for me. The other 45 do not, and that is deliberate.

Source

Three mechanisms, ranked by human attention per unit of protection… Capability removal, Kill gate, Human approval gate

Source