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

# Creating Scenarios

> Generate realistic test scenarios with AI-powered scenario, evaluation, and persona creation

## AI-Powered Scenario Generation

UserTrace automatically creates comprehensive test scenarios from simple text descriptions or document uploads.

<img src="https://mintcdn.com/usertrace/X_6-cyeqeUu0zcc_/images/scenarios-generation.png?fit=max&auto=format&n=X_6-cyeqeUu0zcc_&q=85&s=2dcf6ba233785b75da2684f01e5f1b82" alt="Scenario generation interface showing text input, advanced settings, and preview of generated scenarios, evals and personas" style={{ borderRadius: '8px', border: '1px solid #e5e7eb', marginBottom: '20px' }} width="890" height="762" data-path="images/scenarios-generation.png" />

## Input Methods

<CardGroup cols={2}>
  <Card title="Text Description" icon="text">
    **Simple Natural Language Input**

    Describe your target user in plain text:

    *"30-year-old professional dealing with work stress and seeking career guidance"*

    UserTrace generates everything automatically.
  </Card>

  <Card title="Document Upload" icon="file-upload">
    **Batch Scenario Import**

    Upload a document containing multiple scenarios you want to test your agent against.

    Perfect for existing test cases or comprehensive scenario libraries.
  </Card>
</CardGroup>

## Advanced Settings

Fine-tune your scenario generation with advanced configuration options.

<AccordionGroup>
  <Accordion icon="scale-balanced" title="Evaluation Strictness">
    **Control Evaluation Criteria Precision**

    • **Lenient**: Broader acceptance criteria, focuses on general success\
    • **Moderate**: Balanced evaluation with reasonable expectations\
    • **Strict**: Precise criteria with high standards for agent performance
  </Accordion>

  <Accordion icon="shield-exclamation" title="Scenario Coverage">
    **Edge Cases and Failure Conditions**

    • **Basic**: Core happy path scenarios\
    • **Comprehensive**: Includes common edge cases\
    • **Extensive**: Maximum coverage with rare failure conditions and stress tests
  </Accordion>
</AccordionGroup>

## Generation Process

### 1. Preview & Review

After initial generation, UserTrace shows a preview of:

• **Scenarios** - Realistic interaction flows\
• **Evaluations** - Success criteria and metrics\
• **Personas** - Detailed user profiles with motivations and characteristics

### 2. Iterate with Feedback

<Card title="Regenerate with Guidance" icon="refresh">
  Not satisfied with the initial generation? Provide feedback and regenerate:

  • "Make scenarios more challenging"
  • "Focus on angry customers"\
  • "Add technical troubleshooting cases"

  UserTrace refines the generation based on your input.
</Card>

### 3. Deep Research Mode

Once you approve the preview, UserTrace enters **deep research mode**:

<Steps>
  <Step title="Agent Purpose Analysis">
    Analyzes your website and knowledge base to understand your agent's role and capabilities.
  </Step>

  <Step title="Production Log Analysis">
    Reviews any production logs you've uploaded to understand real user patterns and pain points.
  </Step>

  <Step title="Historical Feedback Integration">
    Incorporates feedback from past simulations to improve scenario relevance and quality.
  </Step>

  <Step title="Knowledge Graph Creation">
    Builds a personalized knowledge graph tailored to your specific agent and use cases.
  </Step>
</Steps>

<Note>
  **Processing Time**: Deep research mode typically takes a few minutes to complete. You'll receive a notification when your personalized knowledge graph is ready for simulation.
</Note>

## What You Get

The final output includes:

<CardGroup cols={3}>
  <Card title="Detailed Scenarios" icon="file-text">
    Complete conversation flows with realistic user interactions, emotional states, and contextual background.
  </Card>

  <Card title="Comprehensive Evals" icon="clipboard-check">
    Multi-dimensional evaluation criteria covering functionality, safety, user satisfaction, and domain-specific metrics.
  </Card>

  <Card title="Rich Personas" icon="users">
    Detailed user profiles with demographics, motivations, communication styles, and behavioral patterns.
  </Card>
</CardGroup>

## Next Steps

With your scenarios generated, you're ready to:

1. **Review** the detailed scenarios, evals, and personas
2. **Start simulations** using your configured agents
3. **Analyze results** and iterate on improvements

<Note>
  Ready to run your first simulation? Head to [Running Simulations](/running-simulations) to launch realistic testing sessions.
</Note>