Artem Keydunov: evaluation

Transcript context

…We heard the same from Harrison and LangChain that most people just use OpenAI. We did a OpenAI has no moat emergency podcast, and it was funny to like just see the reaction that people had to that and how hard it actually is to break down some of the monopoly. What else should people keep in mind, Artem? You're kind of like at the cutting edge of this. You know, if I'm looking to build a data-driven AI application, I'm trying to build data into my AI workflows. Any mistakes people should avoid? Any tips on the best stack to use? What tools to use? I would just recommend going through to warehouse as soon as possible. I think a lot of people feel that MySQL can be a warehouse, which can be maybe on like a lower scale, but definitely not from a performance perspective. So just kind of starting with a good warehouse, a query engine, Lakehouse, that's probably like something I would recommend starting from a day zero. And there are good ways to do it, very cheap, with open source technologies too, especially in the Lakehouse architecture. I think, you know, I'm biased, obviously, but using a semantic layer, preferably Cube, and for, you know, like a context. And other than that, I just feel it's a very interesting space in terms of AI ecosystem. I see a lot of people using link chain right now, which is great, you know, like, and we build an integration. But I'm sure the space will continue to evolve and, you know, like we'll see a lot of interesting tools and maybe, you know, like some tools would be a better fit for a job. I'm not aware of any right now, but it's always interesting to see how it evolves. Also it's a little unclear, you know, like how all the infrastructure around actually developing, testing, documenting, all that stuff will kind of evolve too. But yeah, again, it's just like really interesting to see and observe, you know, what's happening in this space. So before we go to the lightning round, I wanted to ask you on your thoughts on embedded analytics and in a sense, the kind of chatbots that people are inserting on their websites and building with LLMs is very much sort of end user programming or end user interaction with their own data. I love seeing embedded analytics, and for those who don't know, embedded analytics is basically user facing dashboards where you can see your own data, right? Instead of the company seeing data across all their customers, it's an individual user seeing their own data as a slice of the overall data that is owned by the platform that they're using. So I love embedded analytics. Well, actually, overwhelmingly, the observation that I've had is that people who try to build in this market fail to monetize. And I was wondering your insights on why.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.