> ## 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. # Evals and Guardrails > Evaluations and guardrails are the core of Tuner’s monitoring capabilities. This guide explains what they are, how they work, and how to use them to improve your voice agent’s quality. ## What Are Evaluations? An **evaluation** is the process of analyzing a call against a set of criteria. Think of it as an automated report card for every conversation. Instead of manually listening to calls, you define what matters and let Tuner do the monitoring at scale. **Why Evaluations Matter:** Without evaluations, you’re flying blind. You might know that a call “failed,” but you won’t know why. Evaluations give you the “why” by checking for specific behaviors, metrics, and outcomes. ## What Are Guardrails? A **guardrail** is a set of rules that define what “bad” looks like for your agent. They allow you to catch issues early by automatically flagging calls that exhibit problematic behavior. When a guardrail is breached, it can trigger a **red flag** or an **alert**. **Why Guardrails Matter:** Guardrails are your safety net. They ensure that even if you’re not actively monitoring, you’ll be notified when something goes wrong. ## How They Work Together The evaluation pipeline analyzes every call based on your criteria. Guardrails monitor the results, looking for breaches. When a guardrail is breached, a red flag is created and an alert is sent. The same evaluations and guardrails run on every production call **and** every [**Call Simulation**](/docs/simulation/overview) call. What you configure here powers both monitoring and testing. ## Types of Evaluations in Tuner Evals are evaluations that verify whether your agent performed specific actions or followed certain guidelines during a call. Tuner automatically evaluates every call against them. **Predefined evals** — Tuner ships with 21 ready-to-use evals across Accuracy, Actions & Tools, Conversation Quality, and Safety & Compliance. Each one is backed by an AI judge optimized on real voice AI deployments. Enable any combination with a single click. **Custom evals** — Define your own criteria in plain language and Tuner runs them as first-class judges alongside the predefined ones. **Example:** Use the built-in "Confirmation accuracy" eval to automatically verify that the agent's final confirmation matched the action it completed — or create your own "Appointment Confirmed" eval for your specific workflow. See [Predefined evals](/docs/evaluation/predefined-evals) or [Create evals](/docs/evaluation/custom-evals). Voice metrics are pre-defined, quantitative measurements that Tuner computes automatically for every call. These metrics give you objective data about the conversation without requiring any setup. **Example**: The "Longest agent monologue" metric shows the longest uninterrupted stretch of agent speech in a call. A long monologue increases the chance the customer disengages. See [Call latency & voice metrics](/docs/observability/voice-metrics). The Rule Builder allows you to create custom labels and red flags based on a combination of evals, voice metrics, and other conditions. This gives you fine-grained control over how calls are categorized and flagged. **Example:** Create a red flag called "High-Risk Call" that triggers when the call duration exceeds 10 minutes AND the user sentiment is negative AND the "Identity Verified" eval fails. See [Configuring Red Flags](/docs/evaluation/red-flags). ## Common Use Cases Create a guardrail that flags calls where the agent provides incorrect information. Create an eval that verifies the agent always reads a required disclaimer. Create a guardrail that alerts you when user sentiment is consistently negative. *** ### Next Steps Learn about the pre-defined metrics that Tuner computes for every call. An explanation of all out-of-the-box metrics and what they measure.