Sanjana Yeddula

app.arize.com/auth/phoenix...

Missed the news from Arize Observe 2025? Phoenix Cloud just got Spaces & Access Management!

✨ Create tailored Spaces
🔑 Manage user permissions
👥 Easy team collaboration

More than a feature, it’s Phoenix adapting to you.

Spin up a new Phoenix project & test it out!
@arize-phoenix.bsky.social

Google GenAI | Phoenix Instrument LLM calls made using the Google Gen AI Python SDK

Docs: docs.arize.com/phoenix/trac...

Notebook: colab.research.google.com/github/Arize...

🆕 New in OpenInference: Python auto-instrumentation for the Google GenAI SDK!

Add GenAI tracing to your @arize-phoenix.bsky.social applications in just a few lines. Works great with Span Replay so you can debug, tweak, and explore agent behavior in prompt playground.

Check Notebook + docs below!👇

Learn to prompt better

Google Colab

Cookbook: colab.research.google.com/github/Arize...

YouTube video by Arize AI Tracing and Evaluating OpenAI Agents

Check out the full video: youtu.be/iOGu7-HYm6s?...

Just dropped a tutorial on using the OpenAI Agents SDK + @arize-phoenix.bsky.social to go from building to evaluating agents.

✔️ Trace agent decisions at every step
✔️ Offline and Online Evals using LLM as a Judge

If you're building agents, measuring them is essential.

Full vid and cookbook below

We've added GPT-4.1 models to the @arize-phoenix.bsky.social Prompt Playground.

My go-to way to test out these new models: grab a failed trace from a previous run, pull it into playground, switch the model and see if 4.1 can succeed where 4o failed.

Early signs are promising!

good point - the focus of the tutorial was on general prompt optimization techniques. textgrad is awesome for gradient-based optimization, but this approach aimed to keep things more widely applicable. definitely worth exploring in a future video for more fine tuning

phoenix/tutorials/evals/optimizing_llm_as_a_judge_prompts.ipynb at main · Arize-ai/phoenix AI Observability & Evaluation. Contribute to Arize-ai/phoenix development by creating an account on GitHub.

Notebook: github.com/Arize-ai/pho...

YouTube video by Arize AI LLM as a Judge Prompt Optimization

Full video: youtu.be/pvef59pEmvo

LLM as a Judge allows models to evaluate outputs in a single prompt—but a good judging needs a good prompt

In my new tutorial, learn techniques on how to optimize your prompt so your judge can improve accuracy, cost, fairness, and robustness

better prompts ➡️ better evals

Notebook: github.com/Arize-ai/pho...

Notebook: github.com/Arize-ai/pho...

YouTube video by Arize AI ReAct Prompting

Think + Act — all within your prompt

In this tutorial, I apply ReAct principles to prompt LLMs to Reason + Act like humans. By specifying these steps, the LLM generates reasoning and interacts with tools for greater accuracy.

Full Video Tutorial: youtu.be/PB7hrp0mz54?...

Hey! No particular reason for sticking with 3.5 in these demos, just what I've been rolling with. phoenix prompts and these notebooks let you swap out models easily if you are interested in testing that out

I'll switch it up in some upcoming notebooks. thanks for the feedback!

Chain-of-Thought Prompting YouTube video by Arize AI

Video: www.youtube.com/watch?si=yHW...
Notebook: github.com/Arize-ai/pho...
#LLM #prompts #observability

How much LLM reasoning can you drive through your prompt itself?

I’ve been using Chain of Thought (CoT) prompting to help LLMs replicate logical step-by-step thinking.

For the next segment in my prompting series, I use @arize-phoenix.bsky.social to test the performance of various CoT methods

YouTube video by Arize AI Arize Phoenix – 5,000 Stars on GitHub!

🎉 5000 Stars and Counting... 🎉

We're celebrating Phoenix reaching 5000 stars on GitHub! This milestone underscores the growing demand for robust, open-source tools that tackle the complexities of AI and LLM development

Check it out: github.com/Arize-ai/pho...

www.youtube.com/watch?v=bW5Z...

phoenix/tutorials/prompts/few_shot_prompting.ipynb at main · Arize-ai/phoenix AI Observability & Evaluation. Contribute to Arize-ai/phoenix development by creating an account on GitHub.

Notebook: github.com/Arize-ai/pho...
Video: www.youtube.com/watch?v=ggXc...

How much more data does an LLM app really need?

In my latest tutorial, I explore how few-shot prompting boosts accuracy without massive datasets or retraining—using @arize-phoenix.bsky.social prompts and experiments to break it down.

This kicks off my prompting series... more to come!

🧠 Phoenix now supports Anthropic Sonnet 3.7 & Thinking Budgets!

This makes Prompt Playground ideal for side-by-side reasoning tests: o3 vs. Anthropic vs. R1.

Plus, GPT-4.5 support keeps it up to date with the latest from OpenAI & Anthropic - test them all out in the playground! ⚡️

Some updates for Projects! Gain more flexibility and control with:

📌 Persistent column selection for consistent views
🔍 Filter data directly from tables with metadata and quick metadata filters
⏳ Set custom time ranges for traces & spans
🌳 Option to filter spans by root spans

Check out the demo👇

Prompt Optimization Techniques Explore different prompt optimization techniques and learn how Arize Phoenix and DSPy can be used to automate and enhance the process.

Prompt optimization is essential, and automating it with frameworks like DSPy gives you scalable and data-driven improvements.

There's also a tutorial linked in here where you can use Phoenix to compare the performance of different techniques. 👇

arize.com/blog/prompt-...