Model Roles and Responsibilities

This guide provides a detailed overview of our different AI judges, categorized by their roles in reliability and safety control. Each judge is designed to ensure that your AI systems operate safely and reliably in diverse environments.

Key Features:

  • Preventative Control: Detects and prevents potential issues pre production
  • Detective Control: Identifies and flags errors post-occurrence
  • Monitoring: Offers general oversight and diagnostics of system performance

Model Judges Overview

Judge TypeModel NameDescription
ReliabilityVeritas Nano 1.0Preventative control judge for reliability
ReliabilityVeritas 1.0Detective control judge for reliability
ReliabilityLynx 8B
SafetyCollinear Guard Nano v2.0Preventative control judge for safety
SafetyCollinear Guard v1.0Detective control judge for safety
SafetyLlama-guard-3
SafetyCollinear Guard Nano v1.0Preventative control judge for safety