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

This week our product team released several new features to meet the needs of our growing customer base. Radiant now supports OTEL open telemetry format, making it easier to migrate from existing telemetry platforms. We also added a new data sensitivity function to restrict who can see the contents of model interactions in a specific project. We’re excited to show your our latest features now available in Radiant.

Product Updates

Data Sensitivity in Projects

Radiant customers are increasingly using the platform to handle sensitive data such as proprietary data from company databases or sensitive data generated by employee or customer interactions. In order to protect privacy and the principles of least privilege in data access, we have now added a data sensitivity label that can optionally be turned on all projects.

This new label restricts the ability to see the contents of messages to specified users our groups of given project. This way, project managers and engineers can administer a generative AI project and analyze metadata without the need to have access to potentially sensitive details in each transaction.

Open Telemetry Integration

This week we added support for the Open Telemetry standard for LLM traces, making it easier for our users to ingest their data into Radiant from their existing telemetry tools such as Arize Phoenix. Radiant will automatically ingest logs and display trace information in one place.

In addition users can now use the Radiant API to submit requests and responses separately.

Docs Refresh

Over the past few months we’ve made substantial changes to the Radiant platform, adding metrics, evaluations and better access controls. We’ve now released updated documentation and will continue to write new guides for our tools.

New Filter Options

This week we added several filter options to our dashboard and traces. Users can now filter by User ID, Model or Group ID to identify specific patterns of usage from these groups over a time window. In addition, users can now search across trace groups or individual interactions.

Support for Open AI structured outputs API

This past week Open AI introduced a new structured outputs setting to their API. This new feature will allow developers to build more reliable AI applications as it guarantees outputs will always match the JSON schemas provided by developers. We have added support for this new model version gpt-4o-2024-08-06 in our latest releasee.

About Radiant

Radiant is the Enterprise AI platform to take you from idea to production deployment. From security and governance to scaling and anomaly detection, 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.