> ## Documentation Index
> Fetch the complete documentation index at: https://docs.usenash.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Guardrails & confirmations

> How Nash Agent decides which actions run automatically and which require your approval.

Nash Agent can only do what you could do yourself in the Portal — your role and permissions are the hard boundary. On top of that, **guardrails** decide *how* an action runs: automatically, or only after you approve it.

## Action tiers

Everything the agent can do falls into one of two tiers:

* **Auto** — safe, reversible, or read-only actions (looking up a delivery, summarizing performance, drafting a message) run automatically.
* **Confirm** — destructive or customer-facing actions (canceling, refunding, reassigning a provider, rescheduling, sending notifications) surface a **confirmation card** first. Nothing happens until you approve it.

<Note>
  Confirmation always wins. Even when an agent runs in **auto-execute** mode (see [Scheduling & execution](/nash-agent/scheduling-and-execution) and the [Entity monitor](/nash-agent/entity-monitor)), actions in the **Confirm** tier still pause for human approval before anything is applied.
</Note>

## The confirmation flow

When the agent proposes a Confirm-tier action, it shows a card describing exactly what it will do — the entity affected, the action, and the parameters. You can **approve** it to run, or **decline** it. Approving runs the action with the same audited permissions you have in the Portal.

## Per-organization overrides

The defaults are sensible, but admins can tune which actions sit in **Auto** vs **Confirm** for their organization — tightening guardrails for sensitive operations, or loosening them for trusted, high-volume workflows. One exception: reaching a customer or driver by text or voice call always requires confirmation and can't be moved to Auto.

Individual [custom agents](/nash-agent/custom-agents) can be tightened further: an agent's **confirm-first actions** list forces confirmation for specific actions on top of whatever your organization already requires — tightening, never loosening, the org default. See the [Custom agent configuration reference](/nash-agent/custom-agent-configuration) for the recognized action keys.

## Related

<CardGroup cols={2}>
  <Card title="Scheduling & execution" icon="clock" href="/nash-agent/scheduling-and-execution">
    Run agents on a schedule or trigger in report-only or auto-execute mode.
  </Card>

  <Card title="Entity monitor" icon="radar" href="/nash-agent/entity-monitor">
    Watch deliveries and act on changes — within your guardrails.
  </Card>

  <Card title="Custom agents" icon="robot" href="/nash-agent/custom-agents">
    Define reusable, scoped agents — and force confirmation for specific actions per agent.
  </Card>

  <Card title="Channels: Slack, SMS & voice" icon="phone" href="/nash-agent/channels">
    Work with Nash from Slack, and reach customers or drivers by text or voice — always with your approval.
  </Card>
</CardGroup>