TechPrufer
Sign inGet started

Blogs›Together AI›AI Security and Safety Guardrails

AI Security and Safety Guardrails

AI Security and Safety Guardrails

1
posts
2025

Together AI now offers VirtueGuard, an enterprise-grade AI security and safety model, integrated directly into its platform. This guardrail model provides comprehensive protection against harmful outputs, compliance violations, and reputational damage. It boasts an 8ms response time, significantly faster than alternatives, with a high F1 score and low false positive rate. VirtueGuard covers 12 risk categories across text, images, and audio. The integration is seamless, requiring only a single API parameter, and benefits from Together AI's 99.9% uptime SLA, automatic scaling, and continuous improvement from Virtue AI's research team. It is proven at scale with organizations like Uber, Anthropic, NVIDIA, and Glean.

2025

VirtueGuard: Enterprise-Grade AI Security and Safety Now on Together AI

7/29/2025

Introduces VirtueGuard, an AI security and safety guardrail model, as a new capability on Together AI. The post details its technical performance metrics (8ms response time, 89% F1 score, 0.058 false positive rate) and the 12 risk categories it covers. It highlights the seamless integration via a single API parameter, leveraging Together AI's existing infrastructure for enterprise reliability (99.9% uptime SLA) and automatic scaling. The post also mentions continuous improvement of threat models and policy frameworks by Virtue AI's research team.