Channel
Interviewed Person
Malte Ubl
Malta, thanks for having the conversation with us today. Um, this time it feels different when it comes to coding agents. I think there have been times in the past where, you know, it it felt like it was uh a little revolutionary, but I think this time we're all trying to figure out how we are supposed to build while the ground underneath us is shifting. And so super
happy to be speaking with you today. I think that with your products uh DZ your internal data agent and then Verscell V0 as well your public facing thing um you've you've been able to roll with the punches and and be able to build and and create products as the world has changed around us. Let's start with DZ your
internal uh data agent. What was your first approach there and why did it turn out to be so flawed? >> Yeah, to give folks a little bit of context like the thing that makes Versell strong is that we always build things with our own technology and like one of our thesis is that like building agents actually extremely easy and you don't need to buy them. You can just build them yourself. And so we build one ourselves and so the the agent that we call DZero internally is a is a text of SQL engine. So you you give it any
question in Slack and it will reply with the answer and it has access to our entire snowflake kind of subject to the to the access rules of the of the user. Right? And so um I I'll share one query which I think is the funniest one. It's a salesperson. You'll hate it all. Um so this early this year they um this person asked the following question. uh which S&P 500 CTOs and VPs of engineering have private Vercel accounts and have deployed over Christmas.
So presumably they got like an email or a call. I don't know. But like I think like that's like if like actually finding that from I mean obviously you have to do a little bit of research. You have to go to LinkedIn etc. The agent does as well but then eventually you kind of figure out the right snowflake query. It's it's very very difficult right? Um, and so the the initial version of this agent was kind of this kind of traditional infrastructure where you have, you know, the agent is a tools in a loop type of thing. Has all kinds of different tools to do all kinds of different things. Um, and it wasn't like
it was working badly, but it was, you know, maybe not as magical. And then we deleted everything and switched to like an agent that looks very similar to a coding agent. Now it's it's it's still kind of custom coded like it doesn't use for example cloud code as a harness uh because again building such a harness is actually really easy and you can just do it. Um but otherwise it kind of looks the same way. So the the the general architecture is that we did the work of
going through our entire snowflake and for every single column in pros explaining the business value, right? And that gets exported to a YAML file. And the the agent essentially gets told, you know, you got post-trained on using GP on tail and and all these things, right, that you need for coding and go to go to town on these YAML files to figure out the business semantics of everything. And then you
make a SQL query. Um, for that it has a completely different custom tool and that's it. So there's just two tools. There's the bash tool and there's the SQL execute SQL tool. and and that's the entire agent. So, it has like 50 lines of code. Um and and it's completely transformational for the business. >> What led you to understand that you needed to throw everything away? Cuz I feel like you go and you build all of this this code and it's it's just so hard to light it on fire and then start from from scratch again.
