TruEra Launches LLM Evaluation and Observability that Combines Leading Open Source Software and Massive Enterprise Scale

Latest version of TruEra Full Lifecycle AI Observability builds on the success of the TruLens open-source offering by providing massive scale, collaboration, and robust LLM app monitoring. 

REDWOOD CITY, CA – March 13, 2024 – TruEra, the only AI Observability company that covers the full AI lifecycle, announced its latest version of TruEra AI Observability, with major enhancements to its Generative AI Observability capabilities. Multiple innovations include an architecture that scales seamlessly from individual developers to enterprises, greater collaboration capabilities, robust LLM app monitoring, and serious cost benefits against alternatives, allowing companies to deliver high-performance LLM apps faster, and keep them high performing in production for longer. With these enhancements, TruEra becomes the only company with both a leading open source offering for LLM application evaluation and a scalable, enterprise-class evaluation and observability solution for both Generative and Predictive AI.

One of the keys to success in Gen AI is providing critical evaluation and monitoring of LLM applications, which have well known risks for reliability, hallucination, and toxicity, for example. TruEra’s open source solution, TruLens, provides LLM evaluation and tracking for the individual developer.  As TruLens usage grew rapidly – recording an 8x increase in downloads from November 2023 to January 2024 – TruEra heard increasing demands for higher scale, collaboration, and LLM app monitoring in production.

The latest release of TruEra AI Observability brings full Generative AI Observability and LLM Observability capabilities to teams, mid-size organizations, and the enterprise. Individual developers can start with open-source, free TruLens on their individual laptops, then seamlessly transition to the scalability, collaboration, and monitoring capabilities of TruEra. Or, organizations can start with TruEra from the outset, enjoying enterprise-class security, scalability, reliability, and support of the SOC-2 Type II certified SaaS solution.

Key innovations in the latest version of TruEra AI Observability include:

  • Enterprise-class scalability.  In this latest version of TruEra AI Observability, major updates have been made to fit the largest classes of LLM models that customers have in use. TruEra,for example, can now monitor up to hundreds of thousands of events per second. This scalability ensures that TruEra can easily manage the requirements of all of its customers, from the individual developer to the largest enterprises.
  • Seamless transition from individual developer to team or enterprise use. Existing TruLens users only have to add in one line of code to connect their LLM runtime environment to TruEra. When LLM apps mature from being developed and tested by a single developer using TruLens, it can easily transition to TruEra, where it can be managed by the teams that monitor LLM apps to ensure ongoing quality in production. Developers can also start with testing and evaluation in TruEra.
  • Easy-to-use collaboration tools and upgraded UX help apps reach production quality faster. Developing and pushing an LLM app to production requires the coordinated, informed efforts of multiple people across an organization. Now, AI developers can easily share the results of their work using TruEra’s Gen AI dashboards and collaborate using native workflows in a new, easy-to-use UI.
  • Robust monitoring for LLM apps. Previously, users of TruLens had elementary views into app performance in production. This new version of TruEra AI Observability has robust, comprehensive monitoring capabilities. Easily track a portfolio of applications with easy-to-use observability dashboards, and get alerts when apps start experiencing issues, for rapid debugging.

“Over the past few months, we have seen a huge surge in the adoption of TruLens by developers. Tens of thousands of developers have taken my hands-on course on and engaged deeply in our hackathons, workshops, and webinars with major players in the emerging GenAI tech stack. This release of TruEra GenAI Observability responds to key asks from our community of developers to enable enterprise-class scalability, collaboration, and production monitoring, while offering an easy path for individual TruLens developers to transition to team or enterprise use,” said Anupam Datta, Co-Founder, President, and Chief Scientist of TruEra.

To extend the flexibility that makes TruEra a developer favorite, TruEra AI Observability works across apps made with all major LLM foundation models in the Gen AI ecosystem, as well as the major app orchestration frameworks.

Reducing app iteration time from 2 weeks to 2 hours at Equinix

One of the enterprises using TruEra is Equinix, the world’s digital infrastructure company. “We are building out a best-of-breed GenAI tech stack to rapidly build, iterate on, and deploy high quality apps that drive revenue and greatly increase the productivity of teams across Equinix. My team has been working closely with TruEra to bring their tools for evaluation, debugging, and monitoring into this tech stack,” said Ravi Pasula, Head of AI at Equinix. “We are impressed with the results so far. For example, by leveraging TruLens early in the dev cycle, my team has improved app metrics, such as relevance and groundedness, by up to 50% and reduced iteration time from 2 weeks to 2 hours.”

TruLens a part of the development pipeline at KBC Group

Belgian bank insurer KBC Group is leveraging TruLens. “We have been happy to be an early adopter and contributor of the TruLens open source project. We liked its lightweight nature, and the flexibility to add new evaluation functions to an existing library. We have started integrating TruLens into our Generative AI development pipeline,” said Michaël Mariën, Chief Data Scientist, KBC Group.

The latest version of TruEra AI Observability is available today. Learn how to get started and dive deep into the new capabilities in this blog, “LLM Evaluation and LLM Observability – Now at Enterprise Scale.”

About TruEra

TruEra provides the first Full Lifecycle AI Observability software helping enterprises monitor, debug, test, and evaluate both discriminative and generative Artificial Intelligence (AI) applications. Powered by AI Explainability technology based on over nine years of research started at Carnegie Mellon University, TruEra provides AI teams with comprehensive analytics and tools to drive AI performance across the lifecycle. TruEra is a critical part of the AI stack and emerging MLOps and LLMOps stacks.

Want to learn more?

Get in touch with TruEra

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

By submitting this form you agree to the TruEra Privacy Policies