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

# AI coworker

> What the in-app coworker can do, and a record of what it did — Settings → AI coworker.

**Settings → AI coworker** governs the assistant inside the workspace — not the voice agents that call patients.

Connector read/write gates for HubSpot and the rest live under each connector. See [Permissions](/connectors/permissions). This page is the coworker's own tool catalog.

## Permissions

Every action runs at one of four **approval levels**. The model cannot bypass them.

* **Auto-run** — happens without asking (reads, memory updates, and any quiet change still at this level).
* **Draft, then you approve** — prepares a change; you sign off in the conversation before it commits.
* **Propose only** — shows a plan; you have to ask it to execute.
* **Never runs** — describes what to do. You do it yourself.

Admins can override a single tool. Writes that still auto-run are named on the page so that is visible.

## Activity

The **Activity** tab is an audit log of what the coworker did.

## Next

<CardGroup cols={2}>
  <Card title="How to talk to Rivvi" icon="messages" href="/workspace/chatting-with-the-agent" />

  <Card title="Connector permissions" icon="sliders" href="/connectors/permissions" />
</CardGroup>