Rajesh B.

Hi Arize Team, We're currently developing LLM-based applications and actively evaluating observability and testing platforms like Arize as we prepare for production deployment. I'm exploring this on behalf of one Startup, our AI-powered sports analytics platform specializing in badminton. We're particularly interested in how Arize can help us:

We’re also curious about how Arize can support a feedback loop to improve model performance over time. Looking forward to learning more about how Arize can fit into our workflow. Regards, Rajesh B

Hi Arize Team, We are currently exploring Arize Phoenix for evaluating LLM-based workflows and agentic AI systems, particularly in the context of our AI-powered sports analytics platform focused on video-based insights. To better understand and experiment with Phoenix’s capabilities, I wanted to ask if there are any publicly available: Sample projects or notebooks Example workflows or evaluation pipelines GitHub repositories or tutorials This would help us get up to speed quickly and explore how Phoenix can be applied to trace, evaluate, and iterate on our LLM components effectively. Looking forward to any guidance or references you can share.

👋 Hello, team!