Episode
Building Alyx: How Arize AI Dogfooded Its Way to an Agentic Future
- Podcast
- Just Now Possible
- Published
- Oct 9, 2025
- Duration seconds
- 2967
- Processing state
not_requested- Canonical source
- https://justnowpossible.podigee.io/5-building-alyx-at-arize
Actions
POST https://stenobird.com/v1/public/podcasts/just-now-possible-7481489/episodes/building-alyx-how-arize-ai-dogfooded-its-way-to-an-agentic-future/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/just-now-possible-7481489/building-alyx-how-arize-ai-dogfooded-its-way-to-an-agentic-future.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
What does it really take to build an AI agent inside an AI platform—especially when you’re using that same platform to build the agent? In this episode of Just Now Possible, Teresa Torres talks with SallyAnn DeLucia (Director of Product at Arize) and Jack Zhou (Staff Engineer at Arize) about the journey of building Alyx, their AI agent designed to help teams debug, optimize, and evaluate AI applications. They share the scrappy beginnings—Jupyter notebooks, hacked-together web apps, and weekly dogfooding sessions with their customer success team—and the hard-earned lessons about evals, tool design, and how to prioritize early skills. Along the way, you’ll hear how cross-functional experience, intuition-building, and customer insight shaped Alyx into a product that’s now central to the Arize platform. If you’ve ever wondered how to move from vibe checks and one-off prototypes to systematic improvement in your AI product, this episode is for you.