Mahal Systems

Overview › 10Safety › b.Gating risky actions

Gating risky actions

Gate risky actions behind policy or a human. 1 optimization.

  1. i.

    Gate irreversible actions: allow, ask or deny by side effect

    Classify every action the agent can take by its side effect (read, reversible write, irreversible or externally visible: sending email, issuing a refund, deleting a record, posting publicly, pushing code) and gate by class: allow, ask a human or a policy, or deny.

    Slower

    Tier 2 · reliability · changes guardrails · any agent · 9 sources

Before you go...

Build better agents, weekly

Our latest research, performance benchmarks, optimization strategies, and updates around AOT development.

One email a week, nothing else. Unsubscribe anytime.