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

# Simulation Overview

> Test your AI agents with Netra's simulation framework. Run goal-oriented conversations with simulated users—over text or voice—to validate agent behavior before deploying.

AI agents don't just answer questions—they engage in complex, multi-turn conversations to achieve goals. Netra's Simulation framework lets you test these interactions systematically, simulating realistic users to validate your agent's performance before deployment.

<Card title="Quick Start: Simulation" icon="rocket" href="/quick-start/QuickStart_Simulation">
  New to simulations? Get your first simulation running in minutes.
</Card>

## Why Simulation Matters

Traditional testing falls short for conversational agents. Simulations provide a comprehensive way to test multi-turn interactions with realistic user behaviors:

| Question                                                     | What Netra Simulates                                  |
| ------------------------------------------------------------ | ----------------------------------------------------- |
| Does my agent handle multi-turn conversations correctly?     | Full conversation flows with simulated user responses |
| Can my agent achieve specific goals?                         | Goal-oriented scenarios with success/failure tracking |
| How does my agent perform with different user personas?      | Frustrated, confused, friendly, or neutral users      |
| Does my voice agent sound natural and transcribe accurately? | Full audio calls with configurable STT/TTS pipelines  |

## Text and Voice Simulations

Netra supports simulation of multiple types of AI agents, including **[text agents](/Simulations/text-simulations/Simulations)** and **[voice agents](/Simulations/voice-simulations/Simulations)**. Simulations come in two modalities. You choose the modality when creating a multi-turn simulation:

<CardGroup cols={2}>
  <Card title="Text Simulations" icon="font" href="/Simulations/text-simulations/Simulations">
    A simulated user chats with your agent over text. You define the scenario goal, behavior instructions, a persona, and facts the agent must communicate.
  </Card>

  <Card title="Voice Simulations" icon="microphone" href="/Simulations/voice-simulations/Simulations">
    A persona calls your agent over a real audio channel. Configure the STT, reasoning LLM, and TTS pipeline, add background noise, and evaluate how the call actually sounded.
  </Card>
</CardGroup>

Both modalities share the same building blocks—evaluators, simulations, and test runs—and produce the same transcripts-with-scores workflow.

## Core Building Blocks

The Simulation suite is built on three interconnected pillars:

### Evaluators

[Evaluators](/Evaluators/overview) assess the conversation after it completes. Library evaluators are organized by category:

| Category           | Scope          | Evaluators                                                                                                 |
| ------------------ | -------------- | ---------------------------------------------------------------------------------------------------------- |
| **Agentic**        | Session        | Goal Fulfillment, Information Elicitation                                                                  |
| **Quality**        | Session        | Guideline Adherence, Conversation Completeness, Conversation Memory, Conversational Flow, Factual Accuracy |
| **TTS**            | Turn & Session | Humanness, Pronunciation Accuracy, Language Accuracy, Speaking Rate / Pace                                 |
| **STT**            | Turn           | Word Error Rate, Transcription Correctness, Time to First Transcript                                       |
| **Conversational** | Session        | Backchannelling Naturalness, Expressiveness, Speaking Percentage                                           |

Session-level Quality and Agentic evaluators apply to both modalities with a default pass threshold of >= 0.6. The TTS, STT, and Conversational categories score voice-specific qualities such as [voice naturalness and transcription accuracy](/Evaluators/voice-evaluators).

### Simulations

[Simulations](/Simulations/text-simulations/Simulations) are collections of simulation scenarios that define multi-turn conversation goals.

| Feature                  | Description                                                                                                       |
| ------------------------ | ----------------------------------------------------------------------------------------------------------------- |
| **Multi-Turn Scenarios** | Define conversation goals with simulated user interactions                                                        |
| **User Personas**        | Choose from neutral, friendly, frustrated, confused, custom personas—or reuse saved personas in voice simulations |
| **User Data & Facts**    | Provide context data the simulated user can reference during the conversation                                     |
| **Voice Pipelines**      | Voice simulations configure per-stage providers, call duration limits, and background noise                       |

### Test Runs

[Test Runs](/Simulations/TestRuns) execute your simulation scenarios, providing detailed transcripts and evaluation results.

| Feature                     | Description                                                                                         |
| --------------------------- | --------------------------------------------------------------------------------------------------- |
| **Conversation Transcript** | Full multi-turn dialogue between simulated user and agent—with synced audio playback for voice runs |
| **Scenario Details**        | View goal, persona, user data, and provider configuration                                           |
| **Trace Integration**       | Link directly to execution traces to debug issues                                                   |
| **Run Comparison**          | Compare multiple runs side-by-side with pass rate, score, cost, duration, and latency deltas        |
| **Aggregated Metrics**      | View total cost, average latency, and pass/fail rates across the simulation                         |

## Getting Started

<Steps>
  <Step title="Configure Evaluators">
    Set up [evaluators](/Evaluators/overview) to define your scoring criteria — choose from the library or create custom ones.
  </Step>

  <Step title="Create a Simulation">
    Build a [multi-turn simulation](/Simulations/text-simulations/Simulations) with simulation scenarios, personas, and context data—for text or voice.
  </Step>

  <Step title="Run Simulations">
    Execute your simulation from the dashboard or SDK and review transcripts and results in [Test Runs](/Simulations/TestRuns).
  </Step>

  <Step title="Analyze and Improve">
    Use insights from simulations to refine your agent's behavior.
  </Step>
</Steps>

## Related

* [Text Simulations](/Simulations/text-simulations/Simulations) - Create multi-turn simulation scenarios
* [Text Simulation Test Runs](/Simulations/TestRuns) - Analyze results and conversation transcripts
* [Voice Simulations](/Simulations/voice-simulations/Simulations) - Create voice simulation scenarios
* [Evaluators Overview](/Evaluators/overview) - Understand the evaluator framework
* [Text Evaluators](/Evaluators/text-evaluators) - Configure scoring logic and criteria
* [Voice Evaluators](/Evaluators/voice-evaluators) - Score audio quality, transcription, and delivery
* [Traces](/Observability/Traces/overview) - Understand how simulations connect to trace data