Skip to main content

Automatic Agent Protection

Automatic protection can freeze an agent when its payment behavior reaches one of your configured safety thresholds. A frozen agent cannot start new payments until a team member restores it. When an automatic freeze occurs, associated wallets are frozen as well. Use this control as a backstop alongside payment policies and approval rules. Policies decide whether an individual payment is allowed; automatic protection can stop the agent when a pattern of activity needs review.

Protection settings

Read the current settings with GET /api/agents/{id}/freeze-config:
New agents may not have enough payment history for relative activity thresholds to produce a meaningful comparison. Consecutive failures and policy violations can still provide protection while history develops.

Update settings

Send only the values you want to change. Omitted values retain their current setting.
The API key needs the agents:write scope. In the dashboard, owners, admins, and managers can manage this setting.

Freeze or restore an agent manually

Add an optional customer note so other team members can understand the decision later.

Review status history

Use GET /api/agents/{id}/freeze-history to reconcile when and why access changed:
Use each event id as a stable reconciliation or support reference. Automatic events use stable, customer-readable explanations. Team actions include the optional note supplied with the freeze or restore request.