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

# Omni

> Powered by OpenClaw. An AI teammate for every employee that works in Slack, Teams, and voice.

Every employee in your company uses a different set of tools, works on different projects, and has different questions. A Personal AI Agent sits in Slack, Teams, or voice and handles all of that for them. It reasons across your connected systems, delegates to [Custom Agents](/overview/specialized-agents) when it needs governed access, and learns each person's preferences over time. IT deploys it once to a workspace, and every employee gets a personalized agent automatically.

<Frame caption="A Personal AI Agent handling a task: reasoning, delegating, and returning results.">
  <video src="https://mintcdn.com/xpanderai-099931d1/T0THFmEs4MU38lVG/overview/assets/xpander-agent-demo.mp4?fit=max&auto=format&n=T0THFmEs4MU38lVG&q=85&s=e3f725855b8a122beea39b007b7f8194" controls data-path="overview/assets/xpander-agent-demo.mp4" />
</Frame>

## How it works

An employee asks a question in Slack. The agent figures out which systems to query, delegates to the right specialized agent, and returns a coherent answer, all in one thread.

<Frame caption="The personal agent delegates to specialized agents and returns a unified answer.">
  <img src="https://mintcdn.com/xpanderai-099931d1/q5b617qiln7jh1pm/overview/assets/xpander-personal-agent.png?fit=max&auto=format&n=q5b617qiln7jh1pm&q=85&s=c987d33be5645308b6837688df016747" alt="Personal AI Agent delegation flow" width="3600" height="1950" data-path="overview/assets/xpander-personal-agent.png" />
</Frame>

<Tip>
  **Personal Agent ≠ Specialized Agent.** The personal agent handles conversation and reasoning. Specialized agents handle governed access to specific systems. Delegation happens automatically, the user doesn't choose which agent to talk to.
</Tip>

## Example

Here's what this looks like in practice. A compliance deadline is approaching, and the agent proactively flags it:

**Aria** (Personal AI Agent) - 9:02 AM

> Morning, Mike. Your compliance audit deadline is tomorrow. I noticed the PII classification for the Redshift warehouse hasn't been filed yet. Want me to run it now?

**Mike** - 9:03 AM

> Yes please, go ahead.

**Aria** - 9:03 AM

> Delegating to the Data Agent. Scanning 3 schemas across your Redshift warehouse...

**Aria** - 9:06 AM

> Done. 47 tables scanned, PII found in 12 (23 columns flagged). Report added to your audit folder.

The personal agent identified a deadline, delegated a scan to a specialized agent, and reported back, all in a Slack thread. Mike didn't need to open Redshift, write a query, or remember the audit deadline himself.

## Memory

Without memory, every conversation starts from scratch. The agent wouldn't know your projects, your preferences, or what you discussed yesterday. Personal AI Agents solve this by maintaining three levels of memory:

| Level              | What it stores                         | Example                                                         |
| ------------------ | -------------------------------------- | --------------------------------------------------------------- |
| **Session**        | Current conversation context           | "We were discussing the Acme deal"                              |
| **User memories**  | Individual preferences across sessions | "Mike prefers Slack over email", "Works on enterprise pipeline" |
| **Agent memories** | Org-wide knowledge shared across users | "Fiscal year starts in April", "Escalate billing to #finance"   |

After a few weeks of use, the agent knows each person's projects, preferences, and patterns. It stops asking clarifying questions it already knows the answer to.

## Access control

AI with unchecked access to enterprise systems is a liability. Personal AI Agents separate what the agent can reach from what individual employees can delegate, so IT stays in control while employees still get things done.

| Control             | Who sets it | What it governs                              |
| ------------------- | ----------- | -------------------------------------------- |
| **System access**   | IT / Admin  | Which enterprise systems the agent can reach |
| **Operations**      | IT / Admin  | Which actions are allowed per system         |
| **Model selection** | IT / Admin  | Which AI models the agent can use            |
| **Delegation**      | Employee    | Tasks delegated using their own permissions  |

Each specialized agent the personal agent delegates to operates within its own trust boundary, scoped to only approved operations, with full audit trails.

## Model selection

Personal AI Agents are powered by OpenClaw, xpander's multi-model engine. OpenClaw selects the best model for each task automatically across providers (OpenAI, Anthropic, Google, and others), optimizing for cost and quality. For air-gapped deployments, it routes to local models instead. You can also pin a specific model per agent if you prefer.

## What's next

<CardGroup cols={2}>
  <Card title="Specialized Agents" icon="shield-check" href="/overview/specialized-agents">
    The governed agents that Personal AI Agents delegate to.
  </Card>

  <Card title="Quickstart" icon="rocket" href="/guides/quickstart">
    Build and deploy your first agent in 5 minutes.
  </Card>
</CardGroup>