Safety evaluation models
Models and tools for evaluating safety properties of other AI systems — reasoning integrity, intent, and behavior risk.
Model Services
Model Services
Model safety evaluation and safety-enhanced capabilities for agent systems.
Join the waitlistSafety-enhanced models
Lightweight models for reasoning alignment, intent checking, and runtime protection in agent systems.
Service scope
Safety evaluation and enhancement
Whitzard's model services translate NUWA research on frontier AI risk into model capabilities for evaluating safety and strengthening runtime safeguards in agent systems.
Safety evaluation models
Models and tools for evaluating safety properties of other AI systems — reasoning integrity, intent, and behavior risk.
Safety-enhanced models
Lightweight models for reasoning alignment, intent checking, and runtime protection in agent systems.
Model development
Model provenance
Model documentation distinguishes original development, fine-tuning, and third-party hosting.
Self-developed
Models built by Whitzard and NUWA from research on frontier AI risk and safety.
Fine-tuned
Open or partner models adapted with Whitzard's safety data and methods. The base model and fine-tuning approach will be documented.
Hosted
Third-party models offered through Whitzard's infrastructure, with clear attribution to the original provider.
Access
Request access
Share your use case, agent environment, and deployment requirements. Our team will help identify the right evaluation or safety model for your workflow.
Join the waitlistUpdates
Research and product updates
Follow NUWA's research or join the waitlist for model service updates.
Research updates
Subscribe to research updates from NUWA on Substack.
Subscribe on Substack ↗Model service updates
Join the waitlist with your use case and deployment requirements.
Join the waitlistDocumentation
Documentation & resources
Explore Whitzard's open-source projects on GitHub and Hugging Face, including evaluation tools and safety models.