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

# Configuring Your Agent

> This guide covers the agent configuration settings in Tuner. Learn how to define call outcomes, set up evaluations, and configure other settings to get the most out of the platform.

## Accessing Agent Settings

To access the agent configuration settings, navigate to **Agent Settings** in the Tuner sidebar. This will open a page with several tabs, each dedicated to a different aspect of agent configuration.

<Tip>
  The fastest way to set up a new agent is to [start from a template](/docs/agent-configurations/setting-up-an-agent-from-a-template). Pick the template closest to what your agent does. It doesn't have to be an exact match, since a template is a starting point you shape to fit rather than a finished configuration. It fills the tabs below with outcomes, intents, evaluations, and data-extraction fields for that use case, and you refine them from there. To go further, edit any tab by hand or use [MCP](/docs/mcp/set-up-your-agent) to generate and update configuration from your IDE or a chat app.
</Tip>

## Key Configuration Tabs

<Tabs>
  <Tab title="Agent Setup">
    This is where you define the basic details of your agent, including its name, primary goal, and connection settings (language, and call direction). You also provide the system prompt that guides your agent's behavior. If you plan to use [**Call Simulation**](/user-guide/simulation/introduction-to-call-simulation), configure **SIP Settings** here as well for inbound agents; outbound agents are configured in the **Simulation Setup** tab instead.
  </Tab>

  <Tab title="Call Analysis">
    Define what constitutes a "Success" or "Failure" for your agent. This is critical for accurately tracking your success rate. Add common outcomes from the predefined outcome library or create custom ones, enable intent detection, and define custom data extraction fields. See [Classifying Calls](/docs/agent-configurations/classifying-calls-call-analysis-settings) for a detailed guide.
  </Tab>

  <Tab title="Evaluation Rules">
    Add and manage **Evals**, the criteria Tuner uses to judge agent behavior on every call. Pick from the built-in library of 21 predefined evals or create custom ones. See [Create Evals](/docs/agent-configurations/creating-custom-evaluations-evaluation-criteria) for more.
  </Tab>

  <Tab title="Alerts">
    Configure alerts to be notified of critical issues as they happen. See [How to Configure Real-Time Alerts](/docs/agent-configurations/how-to-configure-real-time-alerts) for a step-by-step guide.
  </Tab>
</Tabs>

***

### Next Steps

Learn how to classify your calls to accurately track your agent's success rate.

<CardGroup cols={2}>
  <Card title="Classifying Calls" icon="check-circle" iconType="solid" href="/docs/agent-configurations/classifying-calls-call-analysis-settings">
    A guide to defining what "Success" and "Failure" mean for your agent.
  </Card>

  <Card title="Set Up Your Agent via MCP" icon="plug" iconType="solid" href="/docs/mcp/set-up-your-agent">
    Configure your agent using natural language by connecting the Tuner MCP server to your IDE or chatbot.
  </Card>
</CardGroup>