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

# Guardrails

# Implementing Guardrails

Ensure your AI agent stays helpful, safe, and on-topic using **Guardrails**.

## Why Guardrails?

LLMs are powerful but can sometimes "hallucinate" or be coaxed into discussing inappropriate topics. Guardrails act as a protective layer that monitors the conversation in real-time.

## Types of Guardrails

### 1. Topic Restrictions

Prevent the agent from discussing specific subjects (e.g., "Politics," "Competitors," or "Spiritual Advice").

* **How to Config**: Add a "Topic Restriction" in the **Features** tab and list the forbidden subjects.

### 2. Sentiment Guard

If the customer becomes extremely hostile, the agent can be instructed to automatically transfer the call to a human manager or politely terminate the interaction.

### 3. Sensitive Data Redaction

Automatically detect and redact Social Security Numbers, Credit Card details, or Passwords from the call transcriptions for PCI/HIPAA compliance.

### 4. Hallucination Check

Cross-references the agent's output with your [Knowledge Base](../getting-started/knowledge-base.md). If the agent attempts to answer a question it doesn't have data for, the guardrail can force a "I'm not sure about that, let me find out" response.

## Setting Up Guardrails

1. Open your agent in the **Agent Studio**.
2. Navigate to the **Features > Guardrails** section.
3. Toggle on the specific protections you need.
4. Optionally, specify a "Failure Message" the agent should say if a guardrail is triggered.