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

# Quickstart

> Set up your dazense agent project in minutes with the CLI.

## Step 0: Choose your operating mode

Before setup, decide which user experience you want:

* **Direct Analytics**: fastest, minimal guardrails
* **Trusted Analytics V1**: contracts + policies + bundles + semantic metrics
* **Trusted Analytics V2**: V1 runtime with OpenMetadata-fed governance signals

<Card title="Compare operating modes" icon="sliders" href="/dazense-agent/trusted-analytics/operating-modes">
  Pick the right trust level for your users
</Card>

## Step 1: Install dazense-core package

```bash theme={null}
pip install dazense-core
```

## Step 2: Initialize a dazense project

```bash theme={null}
dazense init
```

This command will ask you:

* To name your project
* If you want to connect a database *(optional)*
* If you want to add a repo in agent context *(optional)*
* To add an LLM key *(optional)*
* If you want to setup a Slack connection *(optional)*

<Note>
  You can skip any optional question and configure them later in your `dazense_config.yaml` file.
</Note>

This will create:

* A new folder with your project name
* An architecture for your context files
* A `dazense_config.yaml` configuration file
* A `RULES.md` file

## Step 3: Verify your setup

cd to the project folder and run:

```bash theme={null}
dazense debug
```

This command checks your configuration and displays any issues.

## Step 4: Synchronize your context

```bash theme={null}
dazense sync
```

This will populate your context folder with your context files (data, metadata, repos, etc.).

## Step 5 (recommended): Validate governance configuration

```bash theme={null}
dazense validate
```

If you're using Trusted Analytics V1/V2, this checks bundle/policy/semantic consistency before chat usage.

## Step 6: Launch the chat and ask questions

You have two options to access the chat UI:

### Option 1: Using dazense chat command

```bash theme={null}
dazense chat
```

This will start the dazense chat UI. It will open the chat interface in your browser at `http://localhost:5005`.

### Option 2: Using Docker

Instead of `dazense chat`, you can use Docker to run the UI:

**With built-in example:**

```bash theme={null}
docker run -d \
  --name dazense \
  -p 5005:5005 \
  -e BETTER_AUTH_URL=http://localhost:5005 \
  metazense/dazense:latest
```

**With your project:**

```bash theme={null}
docker run -d \
  --name dazense \
  -p 5005:5005 \
  -e BETTER_AUTH_URL=http://localhost:5005 \
  -v /path/to/your/project:/app/project \
  -e DAZENSE_DEFAULT_PROJECT_PATH=/app/project \
  metazense/dazense:latest
```

Access the UI at `http://localhost:5005` and add your LLM API key in the settings.

From there, you can start asking questions to your agent!

## Step 7: Evaluate your agent

First, create a folder tests/ with questions and expected SQL in yaml.
Then, measure agent's performance on examples with dazense test command:

```bash theme={null}
dazense test
```

View results in tests panel:

```bash theme={null}
dazense test server
```

If you're using Trusted Analytics V1/V2, also run:

```bash theme={null}
dazense eval
dazense eval --engine
```

These commands validate governance behavior, not only answer correctness.

<Card title="Evaluation Guide" icon="flask" href="/dazense-agent/context-engineering/evaluation">
  Learn how to build comprehensive test suites and evaluate your agent
</Card>

## What's Next?

<Card title="Context Builder" icon="cube" href="/dazense-agent/context-builder/overview">
  Learn how to build and customize your agent's context
</Card>

<Card title="Self-Hosting" icon="server" href="/dazense-agent/self-hosting/deployment-guide">
  Deploy your agent in production
</Card>

<Card title="Chat Interface" icon="comments" href="/dazense-agent/chat/overview">
  Explore the chat interface features
</Card>

<Card title="dazense Cloud" icon="cloud" href="/dazense-agent/cloud/overview">
  Use our managed cloud service
</Card>