Approvals & safety

The approvals inbox

Every agent that sends to a customer, spends money, or changes production data queues a proposal in your Approvals inbox instead of acting silently. You review, edit, and approve — nothing sensitive ships without a human tap.

Read-only agents (analysis, monitoring, drafting) don't need approvals; they publish results and let you decide what to do next.

What lives behind approvals

PostPilot's proposed posts. AdMiral's budget changes. ColdReach's outbound sends. ShopOps's price changes. RingPilot's outbound calls. WarrantyBot's refunds beyond a threshold. Every agent's manual lists exactly what it will and won't do unattended.

Auto-approve rules

You can turn on rule-based auto-approval per agent (e.g. 'auto-post if the AI confidence is > 0.9 and it's a template we've approved before'). Auto-approval is off by default.

Safety-critical agents

GuideFlow, PropertyCine, and any agent producing customer-facing safety instructions run through a citation and hallucination check before you see the output. If a claim can't be cited, the agent flags it instead of publishing.