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

# Script-Based Datasets

> Full Conversation Control.

## Overview

A script-based dataset is a collection of test cases written as a conversation script. This gives you full control over the conversation flow and user messages.

Each script test case primarily consists of multiple turns of conversation.

At every turn, you can specify the exact user message to be used in that turn and optionally the expected agent behavior.

Quraite provides three ways to define the expected agent response:

<Card title="Exact Match">
  The agent's response must match the expected response exactly.
</Card>

<Card title="Regex Match">
  The agent's response must match the expected response pattern using regex.
</Card>

<Card title="Semantic Match">
  The agent's response must be judged by an LLM to match the expected response.
</Card>

Quraite also supports evaluating tool calls at each turn.

For multiple tool calls, specify the expected order:

<Card title="In Order">
  Tool calls match the specified sequence.
</Card>

<Card title="Any Order">
  Tool calls match regardless of sequence.
</Card>

Quraite offers flexible evaluation options: *check tool names only*, or *both names and arguments*.

## How It Works

Quraite invokes the agent using the exact user messages specified at each turn. If expected behavior is defined, Quraite evaluates the agent's response against it.

## When to Use Script-Based Datasets

Script-based datasets work best when:

* **Replaying production traces.** Test real conversations exactly as they occurred.
* **Debugging issues.** Reproduce specific user problems with precise message sequences.
* **Running validation tests.** Fast, predictable checks with deterministic inputs.

## Create and Run Script-Based Test Cases

<Note>
  This guide uses the **Retail Agent** in the **Default Project**. Quraite creates this project automatically at signup.
</Note>

<Steps>
  <Step title="Navigate to Projects page">
    In the Quraite dashboard, navigate to the **Projects** page.
  </Step>

  <Step title="Navigate to the Default Project">
    Click on the **Default Project** in the list of projects.
  </Step>

  <Step title="Navigate to the Datasets page">
    Click on the **Datasets** in the left sidebar.
  </Step>

  <Step title="Select the Script dataset">
    Click on the **Script-based Dataset** from the list of datasets.
  </Step>

  <Step title="Create a new test case">
    This test case tests retrieving order status.

    Click **+ Test Case**

    **Enter Turn 1 details**

    User message:

    ```text theme={null}
    Hi, I want to check status of my order W3372648
    ```

    Expected agent behavior:

    1. Select **Evaluation Approach** as **LLM**.
    2. Enter **Expected Content**:

    ```text theme={null}
    Agent asks for user authentication details.
    ```

    **Enter Turn 2 details**

    User message:

    ```text theme={null}
    My email address is yara.johansson3155@example.com
    ```

    Expected agent behavior:

    1. Select **Evaluation Approach** as **Regex**.
    2. Enter **Expected Content**:

    ```text theme={null}
    pending
    ```

    3. Click **+ Tool Call**.
    4. Select **Tool Call Evaluation Type** as **In Order**.
    5. Enter tool call name:

    ```text theme={null}
    find_user_id_by_email
    ```

    6. Enter tool call arguments:

    ```text theme={null}
    email: "yara.johansson3155@example.com"
    ```

    7. Click **+ Tool Call**.
    8. Enter tool call name:

    ```text theme={null}
    get_order_details
    ```

    9. Enter tool call arguments:

    ```text theme={null}
    order_id: "#W3372648"
    ```
  </Step>

  <Step title="Run the test case">
    1. Select **Retail Agent** from the **Select Agent** dropdown.
    2. Click **Run**.
  </Step>
</Steps>

<Info>
  Code-based script test case definitions are coming soon.
</Info>

## Next Steps

* Run the remaining sample test cases in the **Script-based Dataset**.
* Create a new project and run test cases against your own agent.