Arize AI’s Post

Really nice to meet our customers, announce new features

We just kicked off Observe with a keynote by Aparna Dhinakaran and Jason Lopatecki who introduced and demoed Copilot—the first AI assistant for AI—and so much more. 🚀 Amazing lineup today, we’re just getting started!!

Another Arize:Observe keynote drop 🎁: LlamaTrace, a hosted version of Arize OSS Phoenix. The new LLM tracing and observability platform works natively with the LlamaIndex and Arize ecosystem. With a foundation based on Phoenix OSS, the hosted version of Phoenix offers the ability to persist application telemetry data generated during AI development in order to better experiment, iterate, and collaborate in development or production. The solution features a fully hosted, online, persistent deployment option for teams that do not want to self host. AI engineers can instantly log traces, persist datasets, run experiments, run evaluations – and share those insights with colleagues. The new offering is available today, and can be accessed through either a LlamaIndex or Arize account.

✨Introducing Arize Copilot, the first AI Assistant for AI ✨ Premiering onstage today at Arize:Observe, Copilot offers high-level model insights, data quality analysis, and LLM-specific functionalities like evaluation summarization and retrieval process troubleshooting. It also identifies issues and patterns in your evaluation results (suggesting pre-built or custom evaluations), optimizes your prompts based on specific concerns or evaluation data, and leverages AI Search to curate data with natural language queries combined with traditional filters. Read more in this blog by Sally-Ann DeLucia https://lnkd.in/gFuHDDcp

Thrilled to have Vivek Gangasani from Amazon Web Services (AWS) speaking tomorrow at Observe on a panel where AI leaders will address metrics and strategies to ensure AI quality. Sessions on the Innovators Track allow attendees to explore the real world use cases, challenges in deploying products, and scaling of AI across organizations. Join us tomorrow SHACK15! Tickets are going fast: https://lnkd.in/gpEitQb5

🚧 Introducing Arize Guardrails 🚧 While offline evaluation is a great tool for in-depth analysis of patterns of failure modes of LLM apps, guardrails can provide immediate correction of inappropriate content. Arize offers an off-the-shelf ArizeDatasetEmbeddings Guard. Given any dataset of "bad" examples, this Guard will protect against similar messages in the LLM chat. Users have the option to instantiate the Guards with off-the-shelf prompts / datasets from Arize, or customize the Guard with their own prompts / datasets. This demo by Julia Gomes (with a big assist from Harrison Chu) covers the Arize dataset embeddings guard.

On Thursday, Kasey Kyungsil Roh will take the stage at Observe to discuss full-stack LLM for enterprise use cases. The Innovators' Track at Arize:Observe allows attendees to explore development, application, and impact of innovative tools and evaluation methodologies in AI observability. Gain pragmatic experience evaluating and measuring the performance and reliability of AI systems using the latest open-source tools available. Join us for one day of pioneering and learning together in the heart of the action SHACK15 on July 11! Register: https://lnkd.in/gpEitQb5

At Observe, Prateek Burman (Sr. DS Manager at CCC Intelligent Solutions) will be speaking on a panel about challenges and strategies for GenAI safety alignment. There's still time to join us! Sessions like this one on the Innovators Track allow attendees to explore the real world use cases, challenges in deploying products, and scaling of AI across organizations. Join us in SF on Thursday: https://lnkd.in/gpEitQb5

This week at Observe: Shobhit Varshney, Lavanya Ramani, Vivek Gangasani & Barak Turovsky will share metrics and strategies to ensure AI quality. There's still time to register! Arize:Observe covers cutting-edge research, emerging techniques, and theoretical advancements in AI observability and LLM evaluation. Join us in San Francisco on Thursday for one day dedicated to evaluating and troubleshooting AI in production. See you at SHACK15 👉 https://lnkd.in/gpEitQb5