Our product team has been busy this week deploying significant changes to developer user experiences, model administration and brand new alerting capability. Here are some of the updates we’ve shipped to our front end. We thank you for your continued support and collaboration, since it directly helps us continue to ship great products for our customers.

Product Updates

Introducing Alerting on Log Events

This week we introduced a new alerting capability to give users more tools to identify and resolve issues with models or applications. Radiant highlights specific categories of logs on the provider or endpoint level such as error codes, response lengths and more.

Users can see alerts for all resources they have access to on the home page and quickly drill down to logs to further investigate and take action by resolving model provider connections and updating model routing rules.

Radiant natively integrates with services like DataDog, Slack, and Pagerduty to connect to your team’s existing setup and centralize your logging.

Powerful new model routing configuration

The ability to send requests to different models is critical for maintaining Generative AI application reliability, performance and compliance. This week we introduced a completely redesigned model routing configuration designed to provide more control over routing strategies.

Easy Client Defined Routing

Users can use the select a model when calling the Radiant API through an endpoint using Client Defined Routing. This allows for programmatic model selection through the API. As part of Client Defined Routing, users can specify all models accessible to the user or select which specific models should be available.

More Intuitive Radiant-Defined Routing

This week we introduced a completely redesigned UI for Radiant-Defined, allowing users to more intuitively set load balancing, fallbacks and rule-based routing. Routing options now include:

• Setting Load Balancing across the main model

• Defining multiple fallbacks for models

• Using a webhook to route to a specific model 

• User-group metadata to route to a model (e.g. geography)

• Using content of a prompt

Redesigned Developer Connection Experience + Microsoft Semantic Kernel

This week we made it even easier for developers to embed Radiant in their applications. We’ve redesigned the connection interface to make it easier to select the endpoint URL based on the client your app uses. We by default hide the API key. We also provide code examples for common languages and this week introduced an integration with Microsoft Semantic Kernel. 

Enhanced Provider Management

This week we refined the provider management experience to give administrators more visibility and control over provider settings. Providers now list their active connection status and usage based on-user defined limits within the UI. Administrators can easily set and store API keys for each provider and jump to provider-specific logs if they detect issues.

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.