Short answer: Sam Nadler says he researched Arya Health, got a PRD from ChatGPT and built the demo in Google AI Studio with Gemini Pro in about thirty minutes and four or five tweaks, but real world use takes many more steps.
Watch this answer from Episode 24 (starts at 7:27) · Episode 24 notes and transcript
From Episode 24: This AI Fills Healthcare Shifts in Minutes, starting at 7:27.
Jordan Metzner [7:27]: That's cool. Well, Sam, tell them your workflow. Like, I mean, I think that that'd be cool because, I mean, you entered a work you know, we talk about AI. You don't really this space that well. It'd be cool to talk about your workflow just a little bit on, like, how you build something like this without your domain expertise.
Sam Nadler [7:40]: Yeah. I mean, it's not you know, I'm a little embarrassed how simple it was, but basically did a little research on Arya Health with the context that we were looking to build a feature for start of care. Got a PRD from ChatGPT, went to the Google AI studio using Gemini Pro, put the PRD, and then within four or five different tweaks, probably in the span of thirty minutes, I had kind of what we're seeing now. And then I just went just small refinements to add additional features, but at the end of the day, it was really fast from just a conceptual perspective. And obviously, that's what we see is AI is so powerful, is you can go from, like, zero to one so fast. Now, actually, in as you guys and I would love to better understand how Arya is is working today. But, a, taking this from a concept to actual real world use cases is there's a million steps in between. Like, it's not in real time, as you mentioned. The discharge notes, I don't even know how those come in. Maybe it's phone call.
Sam Nadler [8:57]: Yeah. I don't even know.
