When Snowflake acquired the TruEra AI Observability platform, we committed to keeping TruLens open source. We’re not only keeping that promise; we’re emphasizing it. Our goal remains to support LLM app developers in creating trustworthy generative AI applications. In the weeks since the acquisition, we have already added ecosystem-friendly enhancements including: We plan to continue making enhancements and improvements that benefit the community at large, whether on Snowflake or not.

Struggling with API issues? API observability may have the solution. It reveals the critical insights that hide within API metrics, logs, and traces, offering you the power to diagnose and fix problems swiftly. In this article, we detail what API observability is, how it benefits your systems, and the ways it supersedes traditional monitoring to keep your digital services operating at peak performance.

In the fast-evolving landscape of data science and machine learning, efficiency is not just desirable—it’s essential. Imagine a world where every data practitioner, from seasoned data scientists to budding developers, has an intelligent assistant at their fingertips. This assistant doesn’t just automate mundane tasks but understands the intricacies of your workflows, anticipates your needs, and dramatically enhances your productivity at every turn.

If you think workflow orchestration sounds like tech jargon, check out this simple explanation and consider practical advice for how to apply it to your business processes. Let’s start with the basics: what is workflow orchestration? Put simply, workflow orchestration is the end-to-end management of people, digital workers, systems, and data in a process.

In this post, we demonstrate how a robust and scalable generative artificial intelligence (GenAI) chatbot is built using Amazon Bedrock and Confluent Cloud. We walk through the architecture and implementation of this generative AI chatbot, and see how it uses Confluent's real-time event streaming capabilities along with Amazon's infrastructure to continually stay up to date with the latest advances from the AI landscape.

If you’re one of the cool kids building AI-based products you’ve probably heard of — or are already doing — RAG. If you’re not, let me tell you what RAG is before telling you one weird fact about it. “Retrieval-Augmented Generation” is nothing more than a fancy way of saying “including helpful information in your LLM prompt.” Still, there are many ways to do it and many questions to answer when building a RAG pipeline.