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

# Get Started

> Get started with Kubiya in 5 minutes. Open the Meta Agent, connect your infrastructure, and execute your first task.

## What You'll Do

Open the Meta Agent, explore your infrastructure, and execute your first task through natural language.

**Time:** \~5 minutes

## Before You Begin

* Sign in to [compose.kubiya.ai](https://compose.kubiya.ai)
* Keep **Kubiya Hosted** selected (default control plane)

***

## Step 1: Open the Meta Agent

The Meta Agent is your primary interface for exploring and interacting with Kubiya.

**Two ways to access:**

1. **Compose Workspace** - Click **Compose** in the sidebar for the full-screen workspace at `/chat`
2. **Quick Panel** - Press `Cmd+J` (Mac) or `Ctrl+J` (Windows/Linux) from any page

<img src="https://mintcdn.com/kubiya/U0odlsTjA-eJHMTE/assets/screenshots/composer/meta-agent-workspace-initial.png?fit=max&auto=format&n=U0odlsTjA-eJHMTE&q=85&s=26274626ce6c0df7c1bd7856f0e25c0f" alt="Compose Workspace" width="2582" height="1480" data-path="assets/screenshots/composer/meta-agent-workspace-initial.png" />

The Compose workspace provides a dedicated space for conversations with conversation history in the sidebar. Use the Quick Panel for fast queries without leaving your current page.

<Tip>
  For detailed UI navigation, see the [Web Interface Guide](/web-interface/overview).
</Tip>

On first use, select the categories most relevant to your role (Security, Infrastructure, Cost Optimization, etc.).

***

## Step 2: Try Your First Query

Ask the Meta Agent a simple question:

```
"What environments are available?"
```

```
"List all connected data sources"
```

```
"Show me the status of my task queues"
```

The Meta Agent has access to all Kubiya platform capabilities through MCP tools.

***

## Step 3: Set Up a Connector

**Connectors** enable agents to **act** on external systems.

Go to **Infrastructure → Connectors** and add your first connection:

| Connector      | Description               |
| -------------- | ------------------------- |
| **AWS**        | Cloud resource management |
| **GitHub**     | Repository access, CI/CD  |
| **Slack**      | Team messaging            |
| **Jira**       | Issue tracking            |
| **Kubernetes** | Container orchestration   |

<Note>
  Without connectors, agents can explore and analyze but cannot take actions on external systems.
</Note>

***

## Step 4: Add an Ingestion Source

**Ingestion Sources** populate the Context Graph with data about your infrastructure.

Go to **Context Graph → Data Ingestion** and add your first source:

* **Cloud Providers:** AWS, Azure, GCP
* **Identity:** Okta, Microsoft Entra ID
* **DevOps:** GitHub, Kubernetes, CircleCI
* **Custom:** Upload CSV/JSON files

<Note>
  The Context Graph starts empty. Add ingestion sources so the Meta Agent can explore your infrastructure.
</Note>

***

## Step 5: Execute a Task

Back in the Meta Agent, try more advanced queries:

```
"What EC2 instances are running in production?"
```

```
"Show me all IAM roles with admin access"
```

```
"What services depend on the auth database?"
```

Use the **Remote Task Queues** button in the chat to route execution to specific workers.

***

## What You Used

| Component                | Purpose                                             |
| ------------------------ | --------------------------------------------------- |
| **Meta Agent**           | Unified interface for exploration and orchestration |
| **Connectors**           | Credentials for agents to act on external systems   |
| **Ingestion Sources**    | Data that populates the Context Graph               |
| **Hosted Control Plane** | Zero-setup coordination layer                       |
| **Hosted Workers**       | Isolated execution for your tasks                   |

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Meta Agent" icon="brain" href="/core-concepts/meta-agent">
    Deep dive into natural language orchestration
  </Card>

  <Card title="Connectors" icon="plug" href="/infrastructure/integrations">
    Enable agents to act on external systems
  </Card>

  <Card title="Data Ingestion" icon="database" href="/core-concepts/data-sources">
    Populate your Context Graph with infrastructure data
  </Card>

  <Card title="Task Queues" icon="server" href="/core-concepts/execution-infrastructure/task-queues">
    Distributed execution with remote workers
  </Card>
</CardGroup>

***

## Advanced: Specialized Agents & Teams

When you need domain-specific automation beyond the Meta Agent:

* **[Agents](/core-concepts/agents)** - Create specialized AI agents for specific domains (DevOps, Security, FinOps)
* **[Teams](/core-concepts/teams)** - Coordinate multiple agents for complex multi-domain operations

<Note>
  Most users interact through the Meta Agent for general orchestration. Create custom agents only when you need specialized, reusable automation.
</Note>