🧪 📊 The @arize-phoenix.bsky.social TS/JS client now supports Experiments and Datasets!

You can now create datasets, run experiments, and attach evaluations to experiments using the Phoenix TS/JS client.

Shoutout to @anthonypowell.me and @mikeldking.bsky.social for the work here!

Tired of tweaking prompts yourself? Let the machines do it for you! 🤖

This guide is a great primer on common approaches we see towards automated prompt optimization. If you've already read 100 "prompting tips and tricks" blogs but aren't yet a full DSPy contributor, then let this be your bridge!

@pydantic.dev evals 🤝 @arize-phoenix.bsky.social tracing and UI

I’ve been really liking some of the eval tools from Pydantic's evals package.

Wanted to see if I could combine these with Phoenix’s tracing so I could run Pydantic evals on traces captured in Phoenix

Had a fantastic time talking about Self-Improving AI Agents with @arize-phoenix.bsky.social at the AI Camp NYC meetup this past week!

It's amazing to see how fast the discourse has moved from "just agents" to now multi-agent flows, optimized evals, and automated improvement strategies.

We've added new LLM decorators to @arize-phoenix.bsky.social 's OpenInference library 🎁

Tag a function with `@ tracer.llm` to automatically capture it as an @opentelemetry.io span.
- Automatically parses input and output messages
- Comes in decorator or context manager flavors

In case you missed it, Arize AI Phoenix crossed the 5k GitHub star mark last week! ⭐️

Phoenix has changed a TON since its first iteration.

I'm constantly in awe of the execution speed and quality of this team. Here's to the next 5k and beyond!

Shoutout to Aman Khan and the rest of the @arize.bsky.social team for delivering a top-notch talk at @deeplearningai.bsky.social's inaugural AI Dev 25 conference! 📣

Aman combined our recent Agent Evaluation course with the latest prompt optimization techniques to automate the improvement process.

How can you programmatically improve your prompts? 🤔 🤖

Forget manual prompt engineering - there are better (read: "more automatic") ways to improve your prompts.

This video and notebook break down these techniques.

Featuring:
- DSPy
- @arize-phoenix.bsky.social

Separate AI tools for dev and prod aren't just inefficient—they're actively sabotaging your model performance.

Too often, teams are stuck using disconnected tools—one for evaluation, another for monitoring, and yet another for debugging.

So, we built a unified approach.

arize.com/blog/why-ai-...

🤖 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