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.
How to Access Guardrails
To configure an agent’s guardrails:- Open the agent from Devic’s sidebar panel.
- Select the options menu (⋮) in the upper-right corner.
- Click Guardrails.
- Press Add guardrail to create a new one.
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. |
Next: Mask PII
Learn how to protect personal and sensitive data through the automatic masking guardrail.