Radiant is a product analytics platform for teams building with Generative AI.

Radiant allows product teams to: 

• Quickly see and characterize what users are sending to models and what models give back using evaluators, filters and clustering. 

• Be able to see model interactions how the user seems them, with detailed visibility into complex usage patterns

• Understand how well AI is actually reaching business objectives by integrating with external business metrics

Product Updates

Radiant is now SOC 2 Compliant

We are excited to announce that Radiant is now SOC 2 Type 1 compliant. This new certification reflects our commitment to a robust information security program and will allow current and future customers to deploy Radiant with confidence.

We partnered with Modern Assurance to evaluate the suitability of our processes and controls and worked with Secureframe to get and stay compliant.

Read more about this ongoing commitment on our blog.

Revised Project Navigation

When performing investigations its useful to be able to quickly characterize LLM interactions with custom evaluations. Do the sample messages meet a certain criteria? Do messages contain specific phrases or score a certain way? This week we added several features to make it even easier to find content that matters.

Filter by categories

Product teams often want to categories interactions into specific buckets to better filter responses based on a given topic, product or event. Radiant makes it easy to deploy on the fly categorization and now users can filter product categories in our redesigned filter interface.

Tracking critical events using metrics

Radiant users can now create investigations that combine multiple filter criteria into a metric. For example users can now combine categorization results, tone evaluators and external data about refunds to track how many unhappy customers had a poor experience dealing with a customer service chat bot. This combination of signals provides a high degree of flexibility in defining key metrics that can be used to steer model performance and measure application impact.

Investigations now appear as cards

Once an investigation is saved, users can get a quick glance to see how their desired metrics are performing over time, a useful way to track if changes are impacting the metrics that matter.

Other News

Generative AI Summit Austin 2024

This week the Radiant team will be in Austin, Texas to participate in the MLOps World/Generative AI World summit. Our CTO Jakob Frick will be delivering a talk on Finding the hidden drivers of AI business value and our team is co-hosting a happy hour with MongoDB. If you’re in Austin and would like to join us for a drink on November 7 feel free to RSVP: https://lu.ma/yx8wnkrb 

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.