⚡️ Ship AI recap: Agents, Workflows, and Python — w/ Vercel CTO Malte Ubl

**SPEAKER_1** (0:03)
All right, we are here in the remote studio. Thanks again to F.ink for Lanyas' space with Malte Ubl, who is CTO of Vercel. Welcome.

**Malte Ubl** (0:11)
Hey, how's it going? Glad to be here.

**SPEAKER_1** (0:12)
Did I get it right, Ubl? I've actually never pronounced it out loud until like just now.

**Malte Ubl** (0:15)
That was completely perfect. It rhymes with Google.

**SPEAKER_1** (0:17)
Ah, okay. So perfect that you worked on search at Google and AMP and Wizz, which I think still people don't know enough about Wizz.

**Malte Ubl** (0:26)
It is like no longer a secret, but yeah, you can use it. So like unless you work at Google, in which case you probably know what it is. Otherwise, there's no reason to really know.

**SPEAKER_1** (0:34)
Anyway, suffice to say that you are responsible for a lot of the web as it is today. So thank you for spending some time with us. You're also obviously now building the next web, as we say, with Vercel. And we can cover framework defined infrastructure. I think you probably saw I have a lot of interest in self-provisioning runtimes. We can cover V0, but here really, this part is recorded right after you did Ship AI, which we're trying to recap for the general Latent Space audience who may not be watching Vercel as closely as I do or you do.
So basically just generally, what I guess is your message to the broader AI engineer audience on what Vercel is doing with AI?

**Malte Ubl** (1:16)
Yeah, I think the super high level view is that what we're really trying to do is we're the biggest fan of the AI engineering movement and we are also fans of, we're not just going super hard on hype and the big ideas and talking about things, but being very concrete about agents are very exciting and you can actually build them. So I think our entire conference was about both making that easier and discovering the right abstractions as we're kind of figuring out what the people actually want to do, which is emerging as we speak. Then the way Vercel always does these things is by building things ourselves. And so that is both in terms of products, so agents that are products that you can purchase from Vercel and stuff that we do basically in our back office to make our own operations more efficient. And so this kind of building of apps, that's as ground kind of what we do in that reality. And then kind of extract the abstractions that we feel are really helpful to then put that on the road. And I think the probably most talked about thing that we shipped at the conference was on a new workflow development kit, which really, really is just a way to make writing workflows very idiomatic. It's something that just becomes kind of first class. It's something you do every day. You think about it, you write 15 design docs just because you want one of them. It's just something you do literally every day. I think since your audience is more generally in the thing, probably listening to what people talk about, I think that's a lot of talk about our workflow development kit, but also more generally, what are workflows? What are agents? How are they related? Do you use one or the other? I would actually love to talk about that as well, but obviously in our conference, basically introduce just what we hope is by far the easiest way to make your agents something that is easily embeddable into complex workflows and to make those workflows durable, zoomable, and so forth.

**SPEAKER_1** (3:19)
Yeah.
As listeners might know, I have a long history of workflows at Temporal. I think what's weird is a lot of people are discovering this for the first time. You don't really learn about this in CS classes. You don't really learn about this in bootcamps or anything like that, because it's not really a unit of compute and storage that is taught. It's kind of emergent from Uber and Stripe and everyone else. I don't know if there's a version of this at Google.

**Malte Ubl** (3:46)
I mean, there is. There's a version of this at every single company that has been doing anything in computer since 1950 But what's not necessarily the case is that it has been abstracted in any way. But when I run a bank transaction system in 1975, then I invent this. Maybe I'm in pure batch processing world and I kind of avoided it.
But the reality is that I built this. So either I use something very productized, which obviously Temporal innovated on that being a thing, or I use something that's ad hoc. So I go and say, well, I need some kind of queue that tracks the work. And I need a database to store the state at any given point. And I know, maybe I write a con job that makes sure that the stuff on the queue doesn't get stuck. And so I think what's extremely common in essentially every transaction processing system that has ever created is that there either is an explicit abstraction for workflows in it or someone made one ad hoc because otherwise the thing just doesn't work.