We're excited to be headed to @databricksinc.bsky.social Data + AI Summit next week! Aparna has a session on building & evaluating self-improving agents with Arize, Databricks MLFlow, & Mosaic AI. Info here: www.databricks.com/dataaisummit...

🐳 @arize.bsky.social OSS Prompt Playground @arize-phoenix.bsky.social gets Deepseek support! Now you can compare outputs of all the top tier reasoning models. Which LLM provider would you like to see next? Let us know on GitHub! github.com/Arize-ai/pho...

🚀 Get ready to learn from a powerhouse group of speakers at Shack15 in SF on June 25. Builders, researchers, and leaders from @anthropic.com @microsoft.com @llamaindex.bsky.social (+ many more). Get tickets: arize.com/observe-2025

Learn to prompt better

Chicago event alert: We’re bringing Chicago’s AI builders together at Google’s office for hands-on sessions focused on advancing LLM-powered agents. 🚀 Join us May 19. Space is limited! Register: lu.ma/d6mo5zxs

I'll be speaking at Arize:Observe at SHACK15 on June 25! Looking forward to exploring what’s next for AI agents & assistants. More details on my session to come. @arize.bsky.social arize.com/observe-2025

Join us 6/25 in SF for a full-day event focused on agent reliability and evaluation. Hear from the people building the next generation of AI systems—it's conference by engineers, for engineers. Most of our speakers on the site. 👀 Register: arize.com/observe-2025/

Demo your app at this year's Observe! Fill out a short application by 4.30 to be considered for our Demo Den. Great opportunity to showcase your work to the AI community in SF. Apply here: docs.google.com/forms/d/e/1F...

Automate LLM performance with Arize and NVIDIA NeMo. 😎 More on that here: arize.com/blog/arize-n...

For all my NYC friends! 🗽🍎 We're hosting an in-person office hours tomorrow all around LLM and Agent Evals. Join for the free snacks/drinks, stay for the heated discussions about the validity of Pokemon-based model evaluations ⚡️🐀

🤖 Building agents, but not sure how to measure their performance? Our newest blog post on @hf.co has you covered! This post shows you how to use @arize-phoenix.bsky.social to trace and evaluate your smolagents. Credit to @srichavali.bsky.social and @aymeric-roucher.bsky.social

Managing state and memory in LLM applications is one of the biggest challenges in AI development. From conversation history to semantic switching, choosing the right approach can make or break user experience, cost, and performance. Our latest: arize.com/blog/memory-...

Join us in SF on June 25 for the must-attend AI observability and evaluation event of the year! Past speakers have included top builders and researchers driving AI innovation and tackling its most important challenges. Be a part of the conversation shaping AI’s future. arize.com/observe-2025/

Another full house at GitHub with @arize.bsky.social!

Quick guide to the EU AI Act for AI teams. A few things we break down in here are the risk categories (the core of the Act), navigating transparency requirements, newly drafted guidelines for general purpose AI, and more. 👇 arize.com/blog/quick-g...

New tutorial out on agentic RAG, using @arize-phoenix.bsky.social to help you understand what's happening under the hood. In this example, we also use @llamaindex.bsky.social to simplify query engine creation for structured and unstructured data. www.youtube.com/watch?v=1_73...

Integrating LLM evaluations into CI/CD pipelines can ensure reliable, consistent AI + also help you automate experimental results. Here's a tutorial with an example using @arize-phoenix.bsky.social arize.com/blog/how-to-...

If you're in the Bay Area, come out next month to our agents bootcamp @github.com HQ in SF. Hosting with @llamaindex.bsky.social + @groqinc.bsky.social 🙂 For anyone working on chatbots, virtual assistants, or complex decision-making systems. lu.ma/agent-tracing