- Radiant AI
- Posts
- Radiant Update | Feb 4
Radiant Update | Feb 4
Product updates from Radiant
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
Marking and securing production workflows
Application administrators can now mark workflows as being in production mode.
Applications in production mode are clearly marked visually to avoid accidental changes
You can restrict permissions to modify configuration for applications in production mode
Issue and manage API keys for applications
Application administrators can now issue API keys to developers to provide access to models.
Tokens can be issued and revoked. Radiant can also surface analytics per token
When a token is used with Radiant, the platform will route requests to the associated Radiant endpoint
New Dynamic Routing Panel
Our new routing panel makes it more clear how requests are processed with Radiant.
Model routing can be based on request payload (such as model prompts), or request metadata (such as users/groups, incoming IP address)
Routing logic is always executed deterministically, from top to bottom, so you have confidence in how models are being selected
Reflect your organization’s groups and manage permissions based on them
We now reflect your organization’s groups when logged into Radiant using SSO and you can manage roles and permissions based on them.
Other Updates
Menlo Ventures called Radiant out as a key part of the modern enterprise AI stack
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.