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

# What It Is

> Introduction to Devic’s guardrails: what they are, why they are necessary, and how to configure them in your agents.

**Guardrails** are built-in safety mechanisms in Devic that allow you to control, filter, and monitor the behavior of AI agents before they process user instructions.\
Their purpose is to ensure that models operate within safe, legal, and appropriate boundaries for production environments.

In real-world scenarios—especially in companies handling sensitive data, regulated processes, or critical information—guardrails are essential to prevent risks such as:

* Unintentional exposure of personal or confidential data.
* Generation of toxic, harmful, or inappropriate content.
* Model manipulation through *jailbreak* attempts.
* Out-of-context responses misaligned with business objectives.
* Unsafe instructions that could trigger tools or processes incorrectly.

Devic allows you to add guardrails to each agent, configuring an additional protection layer **before** the user’s message reaches the model (LLM).

<img src="https://mintcdn.com/devic/cVxkg9x2JN5RWih7/guardrails.png?fit=max&auto=format&n=cVxkg9x2JN5RWih7&q=85&s=0cd4dd065c4b66c760b7b29b070262b3" alt="Access to guardrail configuration in the agent" width="1912" height="940" data-path="guardrails.png" />

***

## How to Access Guardrails

To configure an agent’s guardrails:

1. Open the agent from Devic’s sidebar panel.
2. Select the options menu (⋮) in the upper-right corner.
3. Click **Guardrails**.
4. Press **Add guardrail** to create a new one.

This opens the panel where you can choose among different types of guardrails depending on your project needs.

<img src="https://mintcdn.com/devic/cVxkg9x2JN5RWih7/guardrails_agent_add.png?fit=max&auto=format&n=cVxkg9x2JN5RWih7&q=85&s=bc69574a892b8e33bf83517f2f544bad" alt="Guardrail configuration panel" width="1912" height="940" data-path="guardrails_agent_add.png" />

***

## Types of Available Guardrails

Devic currently offers **five main categories** of guardrails:

| Guardrail               | Purpose                                                                            |
| ----------------------- | ---------------------------------------------------------------------------------- |
| **Mask PII**            | Detects and hides personally identifiable information before it reaches the model. |
| **Moderation**          | Blocks sensitive, toxic, or prohibited content using moderation classifiers.       |
| **Jailbreak**           | Detects and stops attempts to break the model’s security boundaries.               |
| **Off Topic Prompts**   | Prevents the agent from responding to topics outside the defined scope.            |
| **Custom Prompt Check** | Allows creating custom natural-language rules to validate or reject instructions.  |

The following sections describe each guardrail, its purpose, when to use it, and how to configure it properly.

***

<Card title="Next: Mask PII" icon="shield" href="./guardrails/pii">
  Learn how to protect personal and sensitive data through the automatic masking guardrail.
</Card>