> ## 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.

# Key Concepts Overview

> This guide introduces the core concepts that power the Tuner platform. Understanding these will help you get the most out of Tuner and effectively monitor your voice AI agent.

## The Core Loop: Simulate, Observe, Monitor, Optimize

Tuner is built around a continuous improvement loop:

<Steps>
  <Step title="Simulate">
    Stress-test your agent with [**Call Simulation**](/user-guide/simulation/introduction-to-call-simulation) before launch and after every change. The same Evals that score production calls score every simulated call.
  </Step>

  <Step title="Observe">
    Perform deep dives into specific calls in **Call Logs** to understand the root cause of issues.
  </Step>

  <Step title="Monitor">
    Track your agent's performance in real time using the **Overview** dashboard and get notified of critical issues with **Real-Time Alerts**.
  </Step>

  <Step title="Optimize">
    Make changes to your agent, validate improvements with production data, and re-simulate to confirm the fix.
  </Step>
</Steps>

## Key Concepts at a Glance

| Concept                      | Description                                                                                                                                                                                                  | Learn More                                                                                                                 |
| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------- |
| **Evaluations & Guardrails** | Evaluations analyze a call against a set of criteria to determine its quality. Guardrails are rules that define what "bad" looks like—when breached, they trigger red flags or alerts.                       | [Introduction to Evaluations & Guardrails](/docs/getting-started/core-concepts/introduction-to-evaluations-and-guardrails) |
| **Metrics**                  | Quantitative measurements for every call, like talk time, silence duration, and sentiment.                                                                                                                   | [Introduction to Pre-defined Metrics](/docs/getting-started/core-concepts/Introduction-to-pre-defined-metrics)             |
| **Red Flags**                | Tags applied when a rule you define matches, like a hallucination eval failure or a negative-sentiment call.                                                                                                 | [Configure Red Flags & Labels](/docs/agent-configurations/configuring-red-flags)                                           |
| **Alerts**                   | Proactive notifications sent when a specific event occurs, like a spike in red flags.                                                                                                                        | [Introduction to Real-Time Alerts](/docs/getting-started/core-concepts/introduction-to-real-time-alerts)                   |
| **Call Simulation**          | AI-powered test calls with your agent, dialing inbound agents over SIP or triggering your outbound call flow, scored against your production Evals. Use before launch, after changes, and to validate fixes. | [Introduction to Call Simulation](/user-guide/simulation/introduction-to-call-simulation)                                  |

***

### Next Steps

Dive deeper into the terminology used throughout the Tuner platform.

<Card title="Glossary of Key Terms" icon="book-open" iconType="solid" href="/docs/core-concepts/glossary-of-key-terms">
  A comprehensive glossary defining all key terms used in Tuner.
</Card>