What It Is

Guardrails are security mechanisms integrated into Devic that allow you to control, filter, and supervise the behavior of AI assistants 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 harmful, toxic, or inappropriate content.
• Model manipulation through jailbreak attempts.
• Out-of-context responses or deviations from business objectives.
• Unsafe instructions that could trigger tools or processes incorrectly.

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

---

​

How to Access Guardrails

To configure an assistant’s guardrails:

1. Open the assistant from the Devic sidebar.
2. Select the options menu (⋮) in the top-right corner.
3. Click Guardrails.
4. Press Add guardrail to create a new one.

This will open the panel where you can choose from different types of guardrails depending on the needs of the project.

---

​

Types of Available Guardrails

Devic currently offers five main categories of guardrails: The following sections provide more details on each guardrail, its purpose, when to use it, and how to configure it properly.

---