Notebooks = Chat++ and RAG = RecSys! — with Bryan Bischof of Hex Magic

**Alessio** (0:06)
Hey, everyone. Welcome to the Latent Space Podcast. This is Alessio, a partner in CTO and resident of Decibel Partners, and today I'm joining my Brian.

**Bryan Bischof** (0:15)
Hey, nice to meet you.

**Alessio** (0:16)
So Brian has one of the most thorough and impressive backgrounds we had on the show so far. Lead software engineer, Blue Bottle Coffee, which if you live in San Francisco, you know a lot about, and maybe you'll tell us 30 seconds on what that actually means. You worked as a data scientist at StitchFix, which used to be one of the premier data science teams out there.

**Bryan Bischof** (0:38)
Ouch.

**Alessio** (0:39)
Well, you left, so how good can you still be? Then head of data science at Weights & Biases. You're also a joint professor at Rutgers, and you're just wrapping up a new O'Reilly book as well, so a lot going on.

**Bryan Bischof** (0:51)
Yeah, and currently head of AI at Hex.

**Alessio** (0:54)
Let's do the Blue Bottle thing, because I definitely want to hear. What's that like?

**Bryan Bischof** (0:58)
So I was leading data at Blue Bottle. I was the first data hire. I came in to kind of get the data warehouse in order and then see what we could build on top of it. But ultimately, I mostly focused on demand forecasting, a little bit of REXIS, a little bit of sort of like website optimization and analytics.
But ultimately, anything that you could imagine sort of like a retail company needing to do with their data, we had to do. I sort of like led that team, hired a few people, expanded it out. One interesting thing was I was part of the Nestle acquisition, and so there was a period of time where we were sort of preparing for that and didn't know, which was a really interesting dynamic. Being acquired is a very not necessarily fun experience for the data team.

**Alessio** (1:37)
I build a lot of internal tools for sourcing at the firm, and we have a small VCs and data community of like other people doing it. And I feel like if you had a data feed into like the Blue Bottle in South Park, the Blue Bottle at the Hanna House in Palo Alto, you could get a lot of secondhand information on the state of VC funding.

**Bryan Bischof** (1:53)
Oh yeah. Well, the real source of alpha is just bugging a Blue Bottle.

**Alessio** (1:58)
Exactly. And what's your latest book about?

**Bryan Bischof** (2:01)
Yes. I just wrapped up a book with co-author Hector Yee called Building Production Recommendation Systems. I'll give you the rest of the title, cause it's fun. It's in Python and Jax.
And so for those of you that are like eagerly awaiting the first O'Reilly book that focuses on Jax, here you go.

**Alessio** (2:18)
And we'll chat about that later on, but let's maybe talk about hacks and magic before. You know, I've known X for a while. I've used it as a notebook provider and you've been working on a lot of amazing AI-enabled experiences. So maybe run us through that.

**Bryan Bischof** (2:33)
Yeah. So I too, before I sort of like joined Hex, was saw it as this like really incredible notebook platform, sort of a great place to do data science workflows, quite complicated, quite ad hoc, interactive ones.
And before I joined, I thought this is the best place to do data science workflows.
And so when I heard about the possibility of building AI tools on top of that platform, that seemed like a huge opportunity. In particular, I lead the product called Magic. Magic is really like a suite of sort of capabilities as opposed to its own independent product. What I mean by that is they are sort of AI enhancements to the existing product. And that's a really important difference from sort of building something totally new that just uses AI. It's really important to us to enhance the already incredible platform with AI capabilities. So these are things like the sort of obvious, like copilot-esque vibes, but also more interesting and dynamic ways of integrating AI into the product. And ultimately the goal is just to make people even more effective with the platform.

**Alessio** (3:37)
How do you think about the evolution of the product and the AI component? Even if you think about 10 months ago, some of these models were not really good, very math based tasks. Now they're getting a lot better. I'm guessing a lot of your workloads and use cases is that analysis and what not.

**Bryan Bischof** (3:53)
When I joined, it was pre-4 and it was pre-the sort of like new chat API and all that. But when I joined, it was already clear that GPT was pretty good at writing code.