Blocks

## Heading 2

### Heading 3

#### Heading 4

paragraph

- list
  - nested list

1. ordered list
2. ordered list

**strong**

_italic_

<ins>underline</ins>

[link](https://judgmentlabs.ai)

<Callout type="info">This is an info callout</Callout>

<Callout type="warn">This is a warn callout</Callout>

<Callout type="error">This is an error callout</Callout>

<Callout type="success">This is a success callout</Callout>

<Callout type="tip">This is a tip callout</Callout>

<Cards>
  <Card href="/documentation/tracing/introduction">
    <MDXImage
      src="/images/monitoring.png"
      alt="Tracing Example"
      className="h-60 w-full rounded-t-lg object-cover"
    />
    <div>
      <h4 className="mb-1 text-xl font-medium">Tracing</h4>
      <span>
        Observe your agent's inputs/outputs, tool calls, and LLM calls to debug
        your agent runs.{" "}
      </span>
    </div>
  </Card>
  <Card href="/documentation/evaluation/unit_testing">
    <MDXImage
      src="/images/dark_unit_testing.png"
      alt="Unit Testing Card"
      className="h-60 w-full rounded-t-lg object-cover"
    />
    <div>
      <h4 className="mb-1 text-xl font-medium">Unit Testing</h4>
      <span>
        Test your agent's tool calls, routing paths, and output quality at every
        step to catch regressions before they hit production.
      </span>
    </div>
  </Card>
  <Card href="/documentation/evaluation/introduction">
    <MDXImage
      src="/images/experiments.png"
      alt="Evaluation Example"
      className="h-60 w-full rounded-t-lg object-cover"
    />
    <div>
      <h4 className="mb-1 text-xl font-medium">Evaluation</h4>
      <span>
        Measure and optimize your agent along any quality metric, from
        hallucinations to tool-calling accuracy.Flag quality degradation in
        production and take automated actions to fix issues.
      </span>
    </div>
  </Card>
  <Card href="/documentation/data-primitives/dataset">
    <MDXImage
      src="/images/insights_ss.png"
      alt="Datasets"
      className="h-60 w-full rounded-t-lg object-cover"
    />
    <div>
      <h4 className="mb-1 text-xl font-medium">Datasets</h4>
      <span>
        Construct datasets from your agent interactions to test and evaluate
        your agent's performance.
      </span>
    </div>
  </Card>
</Cards>

<Card
  title="Get your free API key"
  href="https://judgmentlabs.ai"
  icon={<KeyRound className="text-amber-400" />}
  external
>
  Adipisicing proident culpa Lorem culpa ut pariatur ullamco
</Card>

<Steps>
    <Step>
        ### Clone the repository
        
        ```bash
        git clone https://github.com/JudgmentLabs/judgment-cli.git
        ```
    </Step>
    <Step>
        ### Navigate to the project directory
        
        ```bash
        cd judgment-cli
        ```
    </Step>
    <Step>
        ### Set up a fresh Python virtual environment

        Choose one of the following methods to set up your virtual environment:

        <Tabs items={['pip', 'pipenv', 'uv']}>
            <Tab value="pip">
                ```bash
                python -m venv venv
                source venv/bin/activate  # On Windows, use: venv\Scripts\activate
                ```
            </Tab>
            <Tab value="pipenv">
                ```bash
                pipenv shell
                ```
            </Tab>
            <Tab value="uv">
                ```bash
                uv venv
                source .venv/bin/activate  # On Windows, use: .venv\Scripts\activate
                ```
            </Tab>
        </Tabs>
    </Step>

    <Step>
        ### Install the package

        <Tabs items={['pip', 'pipenv', 'uv']}>
            <Tab value="pip">
                ```bash
                pip install -e .
                ```
            </Tab>
            <Tab value="pipenv">
                ```bash
                pipenv install -e .
                ```
            </Tab>
            <Tab value="uv">
                ```bash
                uv pip install -e .
                ```
            </Tab>
        </Tabs>
    </Step>

</Steps>

import { Card } from "@components/ui";

```ts
import { Card } from "@components/ui";
```

from components.ui import Card

```py title="main.py"
from components.ui import Card
```

<Tabs items={["Python", "TypeScript"]}>
  <Tab value="Python">```py from components.ui import Card ```</Tab>
  <Tab value="TypeScript">```ts import {Card} from '@components/ui' ```</Tab>
</Tabs>

One fish, Two fish, Red fish, Blue fish,

Black fish, Blue fish, Old fish, New fish.

This one has a `console.log("hello world"){:ts}` car.

This one has a `print("hello world"){:py}` star.

Say! What a lot of fish there are.

<Accordions type="single">
  <Accordion title="Tracing">
    Observe your agent's inputs/outputs, tool calls, and LLM calls to debug your
    agent runs.
  </Accordion>
  <Accordion title="Unit Testing">
    Test your agent's tool calls, routing paths, and output quality at every
    step to catch regressions before they hit production.
  </Accordion>
</Accordions>

<Accordions type="multiple">
  <Accordion title="Tracing">
    Observe your agent's inputs/outputs, tool calls, and LLM calls to debug your
    agent runs.
  </Accordion>
  <Accordion title="Unit Testing">
    Test your agent's tool calls, routing paths, and output quality at every
    step to catch regressions before they hit production.
  </Accordion>
</Accordions>