Learn to prompt better

🚀 Phoenix now supports MCP (Model Context Protocol)

This lets tools like Claude query prompts, datasets, and experiment results directly from a Phoenix instance (cloud or self-hosted).

Check out our docs to learn more about how to spin it up 👇

Here’s how it works:
www.youtube.com/watch?v=mHeZ...

🤖 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