Allow to add guardrails to agents

Created on 28 August 2025, 17 days ago

Problem/Motivation

Right now, any content written by the user in a chat is sent to the chosen LLM, and every content produced by the LLM is sent back to the user. This can lead to a series of issues, like sharing personal information with external providers, hallucinations, policy violations, and so on.

Create the concept of Guardrail agents Active introduces the concepts of guardrails and guardrails set; we can also use them on agents to make sure no unwanted contents are sent to an LLM or back to the user.

Proposed resolution

Add a new select to the agent configuration form to choose which guardrail set to apply.

User interface changes

A new select in the agent configuration form.

API changes

None.

Data model changes

None.

Feature request
Status

Active

Version

1.2

Component

Code

Created by

🇮🇹Italy lussoluca Italy

Live updates comments and jobs are added and updated live.
Sign in to follow issues

Merge Requests

Comments & Activities

Production build 0.71.5 2024