Our product team has been busy this week and we’re excited to share some of the updates we’ve shipped. We thank you for your continued support and collaboration, since it directly helps us continue to ship great products for our customers.

Product Updates

Creating and leveraging custom tags for endpoints

• You can now create custom tags to group endpoints by user group, workflow name, or anything else. 

Visualizing the model environment per user or per endpoint

• Users can now visualize routing and governance policies on a per-user basis.

  

• Users can now visualize routing and governance policies on a per-endpoint basis.

New governance capabilities for the Workbench

• Administrators can now set policies around model access and spend in the Workbench on a per-user basis

New Workbench UX for model comparison and experimentation

• Radiant’s Workbench now makes it easier to compare multiple models side by side to evaluate response quality, performance, and more

More GenAI model integrations

• Radiant now supports Perplexity AI’s API

• You can now connect any OpenAI API-specification compatible provider to Radiant, regardless of where it is hosted

More logging targets

• Model and audit logs can now be sunk into Google BigQuery.

About Radiant

Radiant is the Enterprise AI platform to take you from idea to production deployment. From security and governance to scaling and resiliency, we make it simple to make AI a critical part of your business. 

Try out a demo here, sign up here to get your own instance, or reach out to our founders directly at [email protected].

We’re also hiring. If you know of someone great that is interested in helping every company build AI into their products and operations, we'd love an introduction.