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

# Get started

> Create your first workspace, add a product, and run a security evaluation.

This guide gets you from zero to your first evaluation run with Know Your AI.

<Info>
  **What you'll need**

  * A Know Your AI account (sign up at [knowyourai.hydrox.ai](https://knowyourai.hydrox.ai))
  * Access to the AI product you want to evaluate (website URL or API endpoint)
</Info>

## 1) Create a workspace

Workspaces keep products, datasets, evaluations, and access controls isolated by project.

<Steps>
  <Step title="Name the workspace">
    Choose a clear project name like "Customer Support Copilot".
  </Step>

  <Step title="Add members">
    Invite teammates and assign roles: **owner**, **admin**, **developer**, or **viewer**.
  </Step>
</Steps>

## 2) Create a product

A product represents the AI system you want to evaluate.

<Steps>
  <Step title="Choose a product type">
    Select the type that matches your AI system:

    * **Website** — A web-based chatbot or AI UI (evaluated via browser automation)
    * **API** — A standard REST API endpoint (OpenAI-compatible or custom)
    * **Streaming API** — A streaming API endpoint
  </Step>

  <Step title="Name and configure">
    Give your product a name and follow the onboarding roadmap.
  </Step>
</Steps>

## 3) Select datasets

Choose datasets to evaluate your product against.

<Steps>
  <Step title="Browse the Marketplace">
    In **Dataset Marketplace**, browse public datasets covering attack prompts, safety tests, and benchmarks.
  </Step>

  <Step title="Or upload your own">
    In **Workspace Datasets**, upload your own dataset as JSON or CSV via drag-and-drop.
  </Step>
</Steps>

## 4) Connect your product

<Steps>
  <Step title="Open the Connect modal">
    In your product page, click **Connect** to link your AI system.
  </Step>

  <Step title="Configure the connection">
    * **API products**: Enter your API endpoint and authentication token (OpenAI-compatible or custom format)
    * **Website products**: Enter the URL and let Browser-Use auto-detect input/response selectors
  </Step>
</Steps>

## 5) Run your first evaluation

<Steps>
  <Step title="Compose a test">
    Go to **Compose Evaluation**, select your datasets, configure the prompt count, and start the run.
  </Step>

  <Step title="Watch execution">
    Follow along in the **real-time console** as prompts are sent, responses received, and each is judged.
    For website products, you can watch the browser automation live via VNC.
  </Step>

  <Step title="Review results">
    View the security score, per-prompt pass/fail results, judge analysis, and compliance reports.
  </Step>
</Steps>

## 6) (Optional) Set up monitoring

Integrate the `@know-your-ai` SDK to track production AI usage.

* Install the SDK and configure your **DSN** (Data Source Name) from the product settings
* Track requests, tokens, cost, latency, and errors in the **Monitoring Dashboard**
* Debug individual interactions in the **Tracing** view

## Next steps

<CardGroup cols={2}>
  <Card title="Datasets" icon="database" href="/datasets">
    Learn about attack methods and dataset categories.
  </Card>

  <Card title="Evaluation" icon="check-double" href="/evaluation">
    Deep dive into evaluation methods and scoring.
  </Card>

  <Card title="Monitoring" icon="chart-line" href="/monitoring">
    Set up SDK monitoring and tracing.
  </Card>

  <Card title="Compliance" icon="shield-check" href="/compliance">
    Understand compliance analysis and evidence trails.
  </Card>
</CardGroup>