Hey everyone 👋 If you're interested in experimenting with image classification, I just released a blog post that walks through setting up and running an experiment in Phoenix. For those who might not be familiar, Phoenix is a platform that helps teams monitor, evaluate, and improve the performance of LLMs and ML models in production. This guide covers some of our latest features: 🧪 Experiments: Easily set up and manage LLM experiments without needing to track versions manually. 🎨 Multimodal Tracing: Our new feature allows you to visualize and debug models across different data types like text and images. 🚤 Register Ergonomics: Launch Phoenix with a single line of code, thanks to our updated OTEL register function. Here's the link to the post: https://arize.com/blog/evaluate-image-classifier/ Would love to hear any thoughts or feedback!