Radiant Updates | May 19

Product updates from Radiant AI: Explorer view for model anomalies, MLOps World Talk

Our product team has been heads down over the past few weeks building out new capabilities to detect and report anomalies in Generative AI model responses. Here are some of the updates we’ve shipped to our front end. We thank you for your continued support and collaboration, it directly helps us continue to ship great products for our customers.

Product Updates

Explorer view: Detect anomalies in real time

This week we introduced a brand new capability to the platform called Explorer. Explorer is designed to support evaluation and detection of anomalies in prompts and responses in real time. Explorer includes more than a dozen metrics and can incorporate external evaluation sources. Use Explorer to monitor AI activity without time consuming set up and respond to issues faster.

Explorer ships with over a dozen metrics including: latency, response tone, prompt leakage, and token length.

Filter prompts across any number of metrics to identify issues, easily switch between aggregated metrics and individual log entries.

Save filters and Create customized alerts by saving filter criteria for specific types of prompts. Radiant integrates with common observability tools.

Jakob spoke at the MLOps World Tools Showcase

Last week Jakob gave a talk at ML Ops World GenAI Infra Demo Days. He touched on some of the challenges of delivering Machine Learning at production scale, including how to consider testing and quality control. Watch the full video:

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.