Approvals
Preview of the server-side policy gate for outbound agent actions — designed, shown in the dashboard, not yet enforced.
PREVIEW · NOT YET ENFORCEDThis page describes the pinned design; no tool call is gated by it todayThe approval gate will turn plain-English intent into enforceable policy at the same server seam every outbound tool action already crosses.
A user describes what the agent may do, what must be reviewed, and what must never run.
The server-side sandbox combines deterministic rules, organization memory, and an isolated judge before the tool can run.
The decision resolves exactly once. Timeout and expiry fail closed, so no outbound side effect can bypass the gate.
The invariant
Tool names remain clean—there will be no _with_approval variants and no
second execution path around the gate. An action cannot run before approval is
persisted, each approval resolves exactly once, and timeout or expiry fails
closed.
Policy inputs
Policy code can combine:
- deterministic conditions such as recipients, regexes, and budget windows;
- durable memory inside the caller's organization boundary;
- an isolated LLM-as-judge for contextual decisions.
Dashboard → Approvals demonstrates the state machine with example policies today; nothing is enforced yet, and there is no live queue or decision history. Do not build an integration that depends on an approval response until this page says otherwise.