00:00:00 | Announcer: Welcome to the Analytics Power Hour: analytics topics covered conversationally and sometimes with explicit language.

00:00:13 | Michael Helbling: Hi everybody, welcome to the Analytics Power Hour. This is episode 300. This is Analytics Power Hour. Okay, sorry, that was just a dumb joke on the movie. Okay. Every time you turn around. I think you’re hearing about the semantic layer. We even did a show on the topic recently. It’s what AI needs to be successful. Well, that’s at least what we keep hearing from the vendors. And well, honestly, that was right around the time we ran across an article that grabbed our attention. What if we didn’t need semantic layers? Then we read an article by OpenAI. They published about how they’re using AI to analyze data and took a closer look at a couple of vendor websites. We started seeing the context for AI isn’t only a semantic layer thing. And well, we wanted to talk about that. So let me introduce my co-hosts, Moe Kiss of Canva. How you going? I’m going great. Thanks for asking, Michael. I see you’re down a remote on the wall there. So that’s… Oh jeez.

00:01:14 | Moe Kiss: I love when we give a visual in-joke that no one else can follow.

00:01:18 | Michael Helbling: Yeah, for an audio podcast. It’s okay. We’ll make a clip out of it. Julie Hoyer of Further. Welcome.

00:01:27 | Moe Kiss: Glad to see you.

00:01:28 | Julie Hoyer: Hello. Hello.

00:01:30 | Michael Helbling: Glad to be here. Awesome. And go Browns. And I’m Michael Helbling. So naturally, we reached out to the author of one of those articles. And I’m excited that he is our guest. Jacob Matson is a developer advocate at MotherDuck, the cloud data warehouse built for answers. He has also held senior data and accounting roles at firms like Simetrics, Funko, and Verimatrix. And today he is our guest. Welcome to the show, Jacob. Hey, Michael and Julie and Moe. It’s great to be here. I’m super pumped. Awesome. Well, we’re excited to have you. So I think, Jacob, maybe to kick off the conversation, I think it would be great for us to understand a little bit more both about your background and exposure to this and sort of what started formulating for you that led to you kind of digging in and doing research in this area around sort of semantic layer or not or other alternatives to semantic layers.

00:02:24 | Jacob Matson: Yeah. That’s such a good question. I guess I’ll start with a little bit of biography that got us here. I’ll try not to be too self-indulgent. So when I graduated from college, I worked in accounting, in public accounting. I sat for the exams, did all that stuff, and worked in public accounting and then had a

00:02:43 | Moe Kiss: company called Verimatrix that was called out there, doing all of the normal accounting

00:02:47 | Jacob Matson: things, climbing the ladder in a very specific kind of governed way, working for people with titles like Controller or CFO, and eventually taking some moves on myself. I think one of the things that we always talked about was especially on the financial side was like, how do we know what numbers are right for this definition of this thing? And at the time, the tools we had were much, much worse than we have now. I remember it being a big deal when we got the Excel that could handle 1 million rows and not just 65,000 rows. That’s why I think it was Excel 2003, maybe, which of course, actually, what it all did was train everyone to just have a horrible experience in Excel all the time and just be totally fine with it. It’s just too much information, it can’t handle it, and then we all dealt with saving issues and crashing and all these things all the time.

00:03:34 | Michael Helbling: Yeah. Don’t calculate your metrics until you’re really ready.

00:03:38 | Jacob Matson: Yeah, exactly. Turn that automatic calculation off. That’s right. Yeah. Step one. And then you can do that as a binary format Excel file. So did all those things and had the pleasure of working on things like MDX and DAX along the way, which are both the modeling languages that are built into the Microsoft stack. And along the way through that journey, really found my way towards using SQL for a lot of the work I was doing, and that just naturally came out of the data that I had that was too big for Excel and it was too complicated. And there was lots of really, I was just driven 100% on just the business need for solving these problems and I needed to get more robust tooling and we had SQL server and it had more, it was running on a server that had more compute than my laptop and all these things. And so it was very natural to kind of progress up there and so I’ve done lots of fun things kind of in that space. I kind of like the joke that I always worked in data from the beginning of my career. It’s just my pipelines ran like once a month, right? It was a month in close process for those of you at home. And it was just kind of how I got there. And so you do a lot of things along the way and you see lots of errors along the way too. Some material, some not, right? And I worked on the IT side at a public company and you see lots of interesting things produced internally that never make their way into the filing documents, for example, sent to the SEC. So I think for me, kind of some of the genesis that led to this notion of like, do we need semantic layers anymore? It was like two things, A, working in accounting for a long time and like understanding the quality that goes into those numbers, which is very high, but also not as high as you’d like. That’s what I would say. And the second part of that is that like we often, at least what I would see on accounting, the accounting side was like, we would get too precious about the exact accuracy and precision of a number instead of instead of actually moving the business forward, right? And so what actually happened in my career, at least, is that like it seemed like I, you know, I wasn’t that close to it early in my career, but like what it felt like is that like CFOs in particular, completely abdicated the realm of analytics to like some other domain. Like, you know what, we can’t get accurate enough, you know, it’s not good enough for whatever reporting we’re building, we’re just going to let some other part of the org like handle that. In fact, I remember even seeing like job descriptions that were like, director of analytics, non-finance, like type of roles. I experienced that when I was at a company room really fast and was trying to build all of these things. And I built, you know, our first day to warehouse from very much, you know, accounting principles first, and eventually just got to the point where we had to break that apart because it was just, we didn’t have the right primitives to answer the questions in a way that we were, we were comfortable with. And we tried all the things and it was just really hard to manage and to update. So a little bit of this idea is me manifesting like, what if I just took away all the pain that I experienced when I was like building these analytics cubes back in the day? Like what if we could just like ask AI those questions and it would like reformulate those on the fly? And so that was kind of like what led me to exploring the idea and then beginning to do like research around it.

00:06:44 | Moe Kiss: Can you tell me a little bit about the tension that you just, you kind of touched on, but we didn’t go date the tension. So I mean, we talked about this with Cindy a little while back about semantic layers and just like, it’s been sold at the moment is like the holy grail as every new, not actually new idea in analytics is that all will solve all of our problems. But that like, that core tension that you touched on on how hard it is to maintain the like inflexibility perhaps that then makes you not able to answer your business questions like what were some of your lived experiences?

00:07:19 | Jacob Matson: Yeah, this is such a good question. I mean, I think like the first one was, I think we, so I was working on an ERP system and we were like, hey, we want to implement like better reporting analytics on it. We’re going to buy this software package that will just like automatically build out all the OLAP cubes for us and then we can like tie them into our BI tool. I think this was even like pre-Tablo maybe and well, Tableau existed, but it didn’t exist for the company I worked at, I think that’s what I would say, it was certainly not something I was tracking at the time, you know, we bought the software and then I was like, okay, now let’s like implement it. And it was like, it had to fit in a very narrow box for us to actually take advantage of it. And that was a pattern I saw repeated a lot kind of in the ERP space too, which was like, hey, just like, you know, make your business fit into this template of how we run our systems. And then you get all of these awesome synergies or whatever, right? Like now you don’t need people to do your buying. You just like run this report and it tells you what to buy. And so what I kind of came to believe, I think like, I definitely wanted to say, all right, let’s just like apply this system, let’s apply these SAP primitives that are, you know, very old and well tested, let’s just apply this like blindly to our business. Like why are we over complicating it? Like our business is not this hard.

00:08:35 | Moe Kiss: But then what I kind of discovered is that the interesting parts of your business are

00:08:39 | Jacob Matson: really hard to define in someone else’s model, right? They end up being, unless you’re like a pure commodities trader, like the magic happens kind of in the margins. And so like defining those systematically is super hard. I really struggled with that. And so like when I kind of realized that that’s or like that was the mental model that I was bringing to these problems, I started being like, hang on, how do I design this ERP system that we’re working on that was my accountability? How do I make it so that like we can do the thing that we need to do, you know, to make the system work? Also, we allow kind of space in the way that we interact with this so that like the magic of the company would differentiate the organization can still happen too. And so like once I started thinking about it that way, that really kind of unlocked for me kind of a way for us to move forward. And it was much less difficult to kind of get people on board because it wasn’t like, hey, we’re going to change your totally change your job and make it so that like it just fits into this box. It was more like, okay, how do we meet in the middle? And so, you know, I think there’s like a, I think there’s a little bit of a paradox in that, right? Which is like the paradox is that you need some level of conformity across the organization for like everyone to be able to communicate well. But also if you have too much conformity, you have a commodity and you need space for your, you know, to have some sort of differentiation. And so I think like that’s kind of the perspective I brought there, you know, I think figuring out which constraints, I kind of like think about it sometimes like, like this game Jenga, I don’t know if you, if you all played that, but you have like a stack of blocks, right? Some of them you touch them and you’re like, okay, I’m not, I can’t pull that one out. That one has to stay there. It’s like, but like you only figure that out like kind of existentially, right? Like you don’t. So like for me, I spent a lot of time just like trying stuff and like, okay, you know what, that didn’t work. The CFO just got really mad at me, like we won’t do that, but like, let’s, let’s just, let’s just, let’s try this other, other path. And I think a lot of it just became like, and then at the end you have this beautiful tower, right? Hopefully you don’t knock it over, but you have this beautiful tower and that tower is unique shape that like hopefully fits what the actual, what, you know, actually represents what the business is.

00:10:56 | Moe Kiss: And so that’s kind of what I think about it. Hey, Tim.

00:11:04 | Michael Helbling: Have you ever opened GTM preview mode and immediately thought, well, there goes my afternoon.

00:11:09 | Tim Wilson: Absolutely. Nothing says fun like hunting through a giant pile of tags, trying to figure out which one

00:11:13 | Michael Helbling: broke. Yeah. That’s why state built, state GTM helper, a free Chrome extension for debugging Google tag manager.

00:11:21 | Tim Wilson: And free means actually, well, free, no sign up, no subscription. Just install it from the Chrome web store and start debugging.

00:11:28 | Michael Helbling: Yeah. And it works with both web and server side GTM. It helps you focus on what matters by filtering down to the specific tags you’re testing.

00:11:37 | Tim Wilson: Your tags from Google, Meta and Microsoft are color coded, so they’re easy to spot. And it makes JSON payloads readable instead of whatever they normally are.

00:11:46 | Michael Helbling: Yeah. And for server side GTM, it gives you better visibility into consent status and it can help with Shopify checkout debugging too.

00:11:54 | Tim Wilson: There’s even a Website Tracking Checker that gives you a web and server side tracking report with actionable fixes.

00:12:00 | Michael Helbling: The state GTM helper is a must have for anyone deploying our managing tags in GTM, search for state GTM helper in the Chrome web store, or use the link in the show notes page on our site. It’s free, installs fast, and might just save your afternoon.

00:12:17 | Tim Wilson: Michael, where does your best AI analysis live right now?

00:12:22 | Michael Helbling: Oh, I’ve got this Claude conversation called GA4 help for this meeting I’ve got coming up. I’m buried between a lunch recommendation and me asking it to explain regex to me like

00:12:34 | Moe Kiss: I’m a fifth grader.

00:12:36 | Tim Wilson: Exactly, that’s the problem. Your AI work gets trapped in one chat with one person in one thread. Ah, yes, the modern knowledge base. I swear Claude told me this somewhere. And that’s why I ask why I built Prism with memory and shared context across users. So the useful stuff doesn’t vanish into my private little AI cave? Exactly, it’s out of the cave into the sun. Prism keeps the context, your metric definitions, source of truth tables, business rules, prior analyses and makes it usable across the entire team.

00:13:12 | Michael Helbling: I like this. So if I teach it that active user means three sessions in 30 days, Julie doesn’t have to teach it again tomorrow.

00:13:19 | Tim Wilson: Exactly. And if Val runs a GA4 cohort analysis, that knowledge can live in Prism, organized and traceable, not locked inside her chat history like a tiny little analytics hostage.

00:13:30 | Michael Helbling: I am starting to like this team memory, not ask Michael because he remembers the cursed dashboard lore.

00:13:39 | Tim Wilson: Plus, with Claude co-work in Prism, your analysis becomes shareable, auditable and ready to build on.

00:13:45 | Michael Helbling: I like this. So the AI becomes company knowledge, not just some vibes I had with the chatbot at 11.42

00:13:52 | Tim Wilson: p.m. That’s right, because that’s way after my bedtime. So go to ask-y.ai and join the wait list.

00:13:59 | Michael Helbling: And you can use the code APH and I’ll take you to the top of the list. That’s ask-y.ai code APH because your team’s brain should not be trapped in one person’s chat tab.

00:14:13 | Moe Kiss: Exactly. Everyone can see my face, obviously not our lovely listeners, but everyone in the podcast. I love an analogy. My company loves an analogy. And I feel like this Jenga one is going to take away too far because at some point you do knock it down. That’s the reality of when we build data architecture and systems, at some point you do end up rebuilding. But I think the exact tension that I feel right now, and I keep banging on about 80-90%, we do need standardization. We do need some conformity because otherwise, if one person over here calculates it this way and one person don’t, we can’t ever have a mature conversation. But I think the really challenging part is how we get that 10 to 15 or 20% that should be bespoke or is actually a unique situation. And I’m thinking about those are the Jenga blocks that you push through and you can move. But you just have such a wealth of experience here. It sounds like for you a bit of that was trial and error. If I want to learn from all your trialing and the erroring, how do you figure out what the standardization bit is and where the flexibility needs to be?

00:15:27 | Jacob Matson: Oh, that’s such a good question. I think some of it is being able to zoom out and understand what the engine is of the company. How does it function? What’s differentiating about your competitors? But then also how does that build the feedback loop that ultimately increases the cash on the balance sheet, hopefully? I always felt like that was an advantage for me as someone coming from an accounting background where I’m just like, it’s very easy for me to visualize, okay, if this business is great at X, they will increase their cash flow. And so I think a little bit is developing good intuition around that and I’m very thankful to have grown up and working for CFOs who are very excellent mentors as it related to that. But I think the second part of that is your model for reality is imperfect. And so you need to be able to test that model in a way that is sort of safe. And what I mean by that is you don’t get fired if you’re wrong, you might get reprimanded. That’s okay. That’s the threshold. Yeah, exactly. You can take some risk, but you want it to be the right risk. And so I think a lot of the trial and error part was just how do we take some risk here that is not too drastic, but is opinionated in a way that if we’re correct, we win more.

00:16:46 | Julie Hoyer: Do you have an example of what that risk is? I don’t know why. I’m having a hard time conceptualizing the risky metric. In the previous episode that we talked about semantic layers, I think you had thrown out the example of monthly average users when we were talking about semantic layers. Is that a risky metric? Is that a metric that moves the business forward? Can we talk through a metric like that for a business like Canva?

00:17:12 | Moe Kiss: I think monthly active users is one that I wouldn’t take a risk on. And that’s because it’s one of our company foundational goals. So we have long historical reporting, but actually where it does get complicated, right? And I’m going to give you a specific example is we often will look at monthly active users by different products. And sometimes different people have different interpretations of what that product monthly active user is. And that’s why there’s so much devil in the detail, right? Like it’s such a gray zone because someone might be like, oh, anyone that used any kind of like video or social media and some people might be like, well, it’s only video if you did X, Y and Z, like you were in our video editor and you used advanced video features. And that’s why it’s like, it’s just messy, our jobs are messy. Totally agree.

00:18:04 | Jacob Matson: When I think about risk, I guess like I would put it in a slightly different, I would not necessarily frame it as like analytics first, but I would just say that like I left a job and then like a month later, someone on the team who was still there sent me a message and was like, man, it has been rough since you’ve been gone. And I was like, why? And I’m like, everyone knows all the things that was nothing interesting happening. He’s like, well, no one’s making any decisions. And I was just like, oh, yeah, okay, I could see that. And so I think like some of it, like when I talk about risk, I just honestly, I’m just like, make a decision, right? Like be opinionated on what it means to have a monthly active user by product X, Y, X, Y and Z, not said, sorry, you know, and like, you know, maybe that there’s lots of interesting things that happen when you start breaking those things apart, right? And you know, one thing that I think I was well trained on because I was in accounting is you get really good at like delivering bad news, like, you know, and so you’re always in the, you’re always, you know, one of the first objectives in accounting is like, you want this to be true. You want it to be the numbers you’re showing are a reflection of reality as you understand it, right? In a way that is defensible. And like sometimes when you’re dealing with metrics, especially with product teams, like, you know, they want to show that their thing is working, right? And like what you’re, you know, it’s a tension, right? Between the domain team and like a central team, which is, okay, like what is truth to that, you know, you know, to the company and like what moves the business forward. And I would almost always say that like, we want to be measuring things in a way that when they’re tested against reality, they, they’re proven to be right, right? And so when people are bringing agendas into things like, hey, like I want to define something in a way that says, you know, I get more monthly active users, well, if that’s not moving the company forward, that metric when it’s tested is going to fail, right? And so how do we, how do we do that? How do we test them more closely against reality is a really interesting question. And the reason the way we do that is by like, you know, potentially taking, taking bets and like making decisions on them, right?

00:19:59 | Moe Kiss: Can I, can I, I’m taking us completely down off topic as per usual. And I just want to push on this a little bit because I do see this happen and I’m curious if your experience in accounting has perhaps given you confidence or like you’ve built the confidence to sometimes have an opinionated decision. Whereas I feel like often in data lands, sometimes there is this like desire to debate every which way something can be cut and like maybe like make a proposal, but like not often enough be like, you know what, I’m going to have an opinion here of like, we’re going to calculate it this way. Let’s do this. Let’s move the business forward. Like, do you think sometimes like that, is that your accounting background? Do you think that helps you have that perspective because you’re more willing to have a position knowing it’s the best, the best of where you can get to, or do you think that’s like you personally, like what do you think’s driven that willingness to take a gamble and have an opinion?

00:20:58 | Jacob Matson: I mean, I think it’s a little bit of self selection. Like part of why I liked accounting was because it let me do things like that or like gave me a framework to reason about those things, right? I think I’m probably a little contrarian by nature. And so, you know, when I see people getting like too precious about metrics, I’m definitely just like, let’s make a decision, let’s, let’s figure it out and we will test it. And if it’s wrong, we can fix it, right? One of the things that’s great about, you know, analytics in general, compared to, I don’t know, financial numbers that you’re publishing to your board or whatever is that you have a lot more degrees of freedom in terms of what it looks like to go back and make something better. You gnow, one of the biggest challenges, right? And analytics is like, hey, that number got put into, you know, our regulatory filings. So that’s how we do that now. You cannot change that anymore. So like, obviously, like, you know, you don’t want to take, you could, I don’t know if this happened to me specifically, but I’m sure, well, actually, yes, it has. Or we made up some, some way to bin some set of data and then suddenly it was in, you know, annual reports. And now it’s like, okay, now we’re always presenting that. And if we had known, if I’d known, I think from experience would have been like, hey, let’s be a little more precious about this. And I think like, it’s definitely a tough balance, but we don’t need to be perfect. Right. We can be, we, as long as we kind of know, you know, and it’s justifiable and we can defend it, I think we can go pretty far. But like, you know, there’s risk, right? There’s risk that you could be wrong.

00:22:23 | Julie Hoyer: Do you feel like of all the context in a business, what percentage of it that people use day to day, like when creating metrics, defining metrics, like doing their analysis, making decisions, what percentage of it is actually captured in a formal, like static

00:22:41 | Moe Kiss: semantic layer for like broad knowledge compared to they’re just doing it, like adding

00:22:47 | Julie Hoyer: in their own context and their own SQL queries and their own, you know, the way they’re pulling the data.

00:22:51 | Jacob Matson: I mean, now that I work in marketing, it’s a lot less than it was when I worked in finance. So it’s contextual, I think.

00:22:59 | Julie Hoyer: Yeah.

00:22:59 | Michael Helbling: There are no generally, there are no generally accepted analytics principles, if you will. Yeah. Yeah, sure.

00:23:06 | Julie Hoyer: Yeah. I feel like it’s a small percentage, smaller than maybe people want it to be. And do you feel like people are always fighting to like make it as close to a hundred as possible?

00:23:16 | Jacob Matson: Or I think like the tension is that like, everyone wants the risk to be low. Like, hey, if I’m going to use data to make this decision, well, then it better be right. The data better be right. And therefore, I’m not going to use the data because I don’t want to take someone accountability for someone else, you know, something produced by someone else. I want to take my own accountability. You know, I think that’s a core, definitely a challenge. Do I see it moving towards a hundred percent?

00:23:40 | Moe Kiss: I mean, I think like, if you’re moving toward a hundred percent, like you just

00:23:44 | Jacob Matson: automating the entire function, right? I mean, I guess that’s like Google AdWords bidding, right? Like, okay, the whole thing’s automated. The price is the price. Um, in some ways, that’s like the fully actualized form of analytics, right? Like auction pricing. Um, do I think that’s the right way to do it? Like, I don’t think, you know, most, most jobs don’t are not that, not that straightforward. I think that it’s probably a smaller percentage than, than most analytics people would, would want it to be and probably, you know, roughly around the right number for where, where things are today.

00:24:19 | Michael Helbling: All right. I want to start to pivot into what we actually need to talk about, which was sure, let’s say you’ve been struggling with the semantic layer and you’re running into all the problems that semantic layers kind of introduce, you

00:24:33 | Moe Kiss: know, they’re inflexible, uh, not easy to pull together.

00:24:40 | Michael Helbling: Don’t work well across different departments and teams. Like there’s lots of reasons why a semantic layer is a challenge and, and lots of people spend a lot of time on it. But like, what are the alternatives? What are people doing to lower their dependency on the so-called semantic

00:24:55 | Moe Kiss: layer that is sort of like the, uh, favorite of the AI world right now in

00:25:01 | Michael Helbling: data?

00:25:02 | Jacob Matson: I mean, I think like, you know, ultimately what we’re seeing a lot of right now is that everything is kind of going into the notion of like skills, right? Which is just marked down, marked down on your laptop or in a GitHub repo or somewhere. And I think people are capturing a lot of context that way, that they are ultimately using either personally or sharing inside their company. I think there’s a lot of new service area here for products. Um, I know like, for example, inside of, uh, Claude, they have some of this notion called projects and projects that you kind of put marked down in there and then link, link it to other things. Um, and then whenever you ask a question, you can select a project and then you’ll, you bring context along, you know, with it. So I think we’re seeing that. I think we’re, we’re definitely seeing like vendors coming along in the space. You know, we’re seeing, we’re seeing a lot of like, we’re also seeing like the perspective from the labs, right? The labs who haven’t limited tokens are just like, Oh yeah, we just like, you know, use AI to do, do everything. Like we’re just like, you know, maximizing our tokens, spend, solve these problems. I think the one that I saw that was, was killing me was like, open AI has like a analytics agent and they basically say, all right, well, we’re just going to ask every question twice. So basically we’ll ask, you know, the user will ask and then we’re going to reformulate it and then have our, you know, our background agent, just see if it gets the same answer. And if they’re too far apart, we’re going to, we’re going to escalate it. And I think like, you know, certainly that’s one approach. Uh, I, I can’t imagine it’s cost effective for anyone at reasonable scale who’s not a lab at the moment. We’re seeing lots of ways that people do it. I mean, from, from what we have been working on, you know, at mother duck, we’ve started to do is just, um, put context in a database because of course we’re a database vendor. So like put it in database database or AI is really good at writing SQL. It’s really good at retrieving the right thing. Um, and so when you do that, then you can start, you know, um, treating it in a more structured way, right? Whether that’s, uh, you know, more of like a graph that has like nodes and edges that you can use to like navigate across, or if it’s just like, you know, straight up comments on columns or whatever, which is a, you know, old, old part of the SQL spec.

00:27:05 | Moe Kiss: I am very much feeling the semantic world bubbling at the moment and the pressure of it and the perception that it’s going to solve a lot of our problems or the perception that it’s required to do AI and data well. I think the thing, one of the points that you made that really resonated with me in the article was about semantic layers being static and how challenging that is, but I think the real like thing that’s keeping me up at night, right? Is if, if we don’t go down that semantic layer path, it’s the validation, right? Which, which you just touched on, right? So the bit that’s challenging that I, I see pop up constantly is if we don’t have somewhere for people to self validate, I find that’s, that’s a hard thing that we, I want to solve for because I don’t, my job to be, to QA other people’s shitty outputs and AI hallucinations with data, which it feels like I spend some time doing now. And so like, and I guess, I guess what I’m trying to say is like at the moment, I feel like it’s binary that you either have some type of semantic layer thing where people can validate or you go down the evaluation framework. Am I, am I totally off here? Like, is it one of those binary options? Or is there just like a range of options? And I haven’t thought deeply enough about it yet.

00:28:28 | Jacob Matson: I mean, I think the first question is about the interface, right? That you let users interact with, right? If they’re interacting with a spreadsheet, there’s different set of constraints than if they’re interacting with a BI tool, than if they’re inner interfacing with like a chat app, right? There’s more engineering freedom, I think on, on obviously a chat application, which is what, you know, people have proven to love, you know, just asking questions to a chat bot, than there is on like a BI tool. I think that one of the biggest challenges on using, you know, even the best BI tool in the world at this moment is that it’s very difficult to interface with something else that someone else built. Like you’re just, I think one of the things that I’ve really found kind of when using AI generally is that like the closer the framework you’re using to answer questions is like a snap fit to your own brain, the easier it is to like use it and use it well. When you’re using someone else’s model, like even a really well-defined model by a really good engineer or really good BI analyst or whatever, it’s like, that’s their model. That’s not your model. That’s not necessarily how you’re thinking about the problem space. And like the biggest challenge that LLMs solve is they’re really good at translating between languages, right? And that really means they’re really good at for me as a, let’s say, someone working at marketing to ask a question and then have the LLM reframe it to be like, oh, I see what this really means is, you know, it means this and, you know, that translates to this language in your current model or whatever. And so I know I’m not really that kind of answering your question. I don’t know, like, I think there is a spectrum. I don’t know if we know if, like, I think the products are not super mature as or outside of the semantic layer because the semantic layer buyer, I think traditionally has been very risk averse. That’s why they’re buy it. The reason you buy a semantic layer in the first place is because some number got somewhere and it was wrong and legal’s pissed. You know, like that’s how you buy a semantic layer. I’m being maybe a little too cynical, but like only maybe. Um, so I think like figuring out how to, like, how do we, again, I keep, I keep saying this word risk, but like, it all comes down to like, how much risk do you accept? And like that determines the spectrum of tools that you can implement. Right. Um, if you can, if you can take on a lot of risk, like in marketing analytics, you can probably take on more, more risk than you can in financial analytics. That’s just true. Right. The cost of being low of wrong is way lower in marketing than it is in finance. That’s just true. Like that’s, that’s a physics problem. Um, so I think like you may not have the same solution across the entire company. It just depends, you know, horses for courses, as they say, I suppose.

00:31:07 | Moe Kiss: Just to be clear, I will keep asking Jacob 50,000 questions.

00:31:10 | Michael Helbling: I’m trying to make space for other people by not speaking. That’s okay. And we, we added out dead air. So don’t, don’t worry about that. That’s fine.

00:31:18 | Julie Hoyer: I wanted to ask actually, Jacob, if you could talk about your proposed solution in your article that you talked about, like using AI, because everybody’s obsessed with having a semantic layer to help with AI, but you kind of flipped in said also AI could help with the semantic layer problem.

00:31:35 | Jacob Matson: So when I wrote the original article, what I was really thinking about at the time was, uh, the notion of skills and using skills kind of locally on your machine to, to kind of codify the, the way to go here. I think I’ve gotten a little more nuanced recently, but like also I think that we’ve seen a lot of mature maturity and development, especially like in the anthropic ecosystem with projects inside of, inside of cloud, for example. I think it’s a very natural way to think about it is like, how do I, how do I make it easier to maintain and, or actually create and maintain and skills are incredibly, incredibly easy to create and maintain, maybe too easy, right? They may not be the right abstraction. But certainly I think skills is the way that I, I thought about it or, you know, at the time, and then I just, you know, and I’ve been doing kind of evals in

00:32:23 | Moe Kiss: that front against, you know, benchmarking data sets.

00:32:27 | Jacob Matson: And, you know, we can debate the, the efficacy of benchmarks versus, you know, real, real life data and all these things. But I think what we do know is true is that if we can find the right context, we can very reliably return the right answer. And so I think like where my, where I think my, where my thinking has gone recently is, is how do we make our data easy to search, right? Which is a different way than maybe we’ve designed it before, as like a Kimball model, which is like, how do we make it easy to retrieve? You know, there’s a whole bunch of really good research that those guys all wrote around how to make a data warehouse and how to make it work and easy to retrieve. And those were written in the constraints of the time, right, which I think probably the original Kimball book is probably going on 25 or 30 years now. We have better technology now, and maybe we can revisit some of those assumptions. And so my, I think my current kind of position on this stuff is that we really have a search problem. And if we can find a way to make our metrics searchable, then the way that we define it may be less important. It might be a semantic layer that’s in YAML. It might be something that’s more, that’s more well defined than that. It might be, you know, something more programmatic than even YAML that is like kind of like a SQL alternative. But like what I, what I have also found is that like LLMs in particular are so good at writing SQL and understanding it, but like adding another language that is new and bespoke is really hard to get good results out of compared to just using the trusted good old thing that is very verbose and like has weird syntax and like has a whole bunch of downsides, but also like there’s 50 years of training data in the, in the training set, right? So if we can figure out how to say, how do we make it search to find the right thing and then write the right SQL, we can get really good results. And I think that’s what I’m seeing is most promising, you know, at this moment. Can we separate search from the context?

00:34:20 | Moe Kiss: Because I feel like those are two very different things and where you struggle with both. So search is more about like, how do I point it in the right place? How do I help find the right table or whatever it is, right? Whereas the context is more, how do I understand this table? And is, okay. And do you think that what you’re proposing, the way you’re thinking about this solves for both equally? Or do you think perhaps like, I feel like we probably need a different approach for each or different thinking? The answer is the devil’s in the details, I think.

00:34:57 | Jacob Matson: So let me, I think where I’m struggling with this question is like, if you assume that there is a natural language interface, right? And then maybe some sort of tooling like an MCP or something that has a search tool. Well, that’s, you$know, someone should solve the search tool problem, right? Which will say, hey, let me search and find this context and return it to you. And the next thing is, you know, writing the SQL based on that understanding. I think the second part is basically solved, which is if you give good context to an agent and say, like, describe a set of tables and then ask a question, you get really good results. And, you know, the challenge we have, of course, is that like, they don’t have good memory. And so like every day, you have to remind them. And so how do we make it so they have good memory? And there’s a whole bunch of people, I’m sure, working on that problem. I’ve read quite a few papers, you know, in the space of like, how do we make it? So when we ask a question, you know, the next time, the next time we ask it, it’s faster to get the answer. Or we already know, you know, we already have some kind of, you know, pathway built out. The metaphor I kind of think about is like, your data is like a jungle, right? Unless you really know where the things are. It’s really hard to find stuff. We can build a semantic layer, but a semantic layer is like a highway. Right? It’s like, we are just like building the thing straight through the jungle. I would almost say like, we can build it a little more progressively, which is, hey, we need like these little paths, right? Maybe these paths are just wide enough for a human to walk on. And maybe this one we can put gravel on. And maybe this one we can put gravel on. And maybe this one we can pave. And then maybe this one we can build a highway. But like, so I kind of think like, I think this actually goes back to the spectrum question you asked earlier, like there’s probably a spectrum of solutions here where a certain set of questions need to be on the highway, right? Like if you’re one of your key metrics as monthly active users, that needs to be right all the time. And there’s a highway for that, right? And so the search problem is like, can my agent find the highway? Okay. And if you can find the highway, then you get the answer. And then, you know, there’s a bunch of, but the interesting stuff, the reality is the interesting stuff is when you start slicing and dicing by all these arbitrary dimensions. And then like, there’s no highway for that. I can’t afford to build that even in the age of AI today. And so, you know, how do you make it easy to do a little bit of off-roading and then still get the right thing, right? And I think like this is where, you know, I think I’m, I’m in particular probably well served by like, you know, accounting principles as in building this stuff out. And I’m just like, well, what if we just made this a ledger and we can just like, you know, walk forward and backwards through time or whatever. Now it becomes very easy to trace it back to the highway. You know, there’s a whole bunch of abstractions like that we can, we can talk about. But I think like the answer is probably, you know, and not, not or in the long term, I do think that there’s probably some set of questions that are so important that you need to always get the right answer. And that might mean maybe a different interface. Like, hey, you know, for our financial reporting interface, we use X for marketing, we use Y. I don’t know.

00:37:46 | Moe Kiss: Do you think it depends on stakeholders too? Like I’m just thinking. So for example, if you’re a data person, the context is something that exists within you. Like you have such good context. So you know how to prompt, you know how to give the right context. And I’m talking as you’re like in the build stage and this is evolving, right? Because if we have essentially, you know, you’re kind of suggesting like an evolving semantic layer or a knowledge-based graph base, at the earlier stage, right, when that context isn’t fully built, what do you think the like the risk is for the business user to be exposed who potentially doesn’t have that same content? Like, do you know what I mean? Like you haven’t built the enough of the highways yet.

00:38:32 | Jacob Matson: Yeah, such a good question. So when we first were, so we launched our MCP server in December at MoetherDuck. And we had our own existing set of dashboards for the sales team. And immediately what started happening is the sales team started like building their own kind of dashboards using our tool, which is really interesting to see, right? We’re, I mean, we’re a small company where our risk threshold is obviously higher. But what everyone was doing was because they already had really good context for the data, because that, you know, they’re sales team. They’re, they, if the data is wrong, you know, everyone’s mad. It doesn’t work. But like it’s, it’s tested against the sales data in particular is tested against reality all the time, right? Because you’re rolling on a call with a customer and you’re like, hey, I saw you used, you know, 10 hours of compute last week, you know, we sell compute. And they’re like, no, we didn’t. You’re going to be like, okay, let me go. Oops, let me go fix my dashboard. So they have the stakes are pretty high for them, right? And for financial teams too, they’re really high, right? They need to be right. They need to be speaking about the right numbers. And so for teams that have developed an intuition for what the data should be, they’re actually pretty good at using LLMs, regardless of language and understanding like being a data person first, because they have a way to test it against reality really quickly, right? They can break down a set of numbers by, you know, like, if you’re a CFO or something, you could probably break down revenue by product and you would with an LLM and be like, that’s right. I can tell that it’s right because I’ve seen this before, right? You already have like the fingertip feel for the data, but if you’re someone else, especially like, this is the hard part for like a data analyst who’s maybe disconnected from the business is they don’t have the fingertip feel. They just have like a question from someone that says, hey, build me this thing. It’s really, you know, in that case, you really have to, you know, rely on the context of others to help build the right thing. You know, I think like that’s, so yes, I think the stakeholder does matter. You know, I think that that certain teams are more well suited to be data driven than others just like out of the box, but like that we can definitely close the gap with like good context, maybe not for everyone, right? If someone asks a totally off the wall question using the wrong words, like

00:40:28 | Moe Kiss: that’s a, you know, we don’t have a crystal ball.

00:40:31 | Jacob Matson: We have, we have, you know, vectors that we’re matching at the end of the day, right?

00:40:36 | Julie Hoyer: With this like approach that you’re talking about, like using AI to kind of bring up the context for somebody who doesn’t have it themselves. I have two questions. One, and I think, well, you were kind of asking this. So it was like, how do you know when it finds context that it’s choosing the right context? Because again, we’ve talked about people are defining and talking about the same metric differently, especially if it’s not one of the highway metrics. The other part is it feels like classically the legwork, right, was on the individual trying to ask the question, make the query. They had to go around and obviously ask and get all that context. But with the new, if we put in the solution that you’re talking about, where does the legwork now live in that process? Do you know what I’m saying? We’ve shifted the hard work of determining what is right for the question you’re asking of where to grab it, how to think about it, how it’s defined, and how to define the metric you’re trying to query. So I’m trying to understand those two pieces.

00:41:44 | Jacob Matson: The first thing that I always think about is like, well, how do we make it visual? This was a video podcast. I could show you a really sweet demo, but maybe I’ll just have to send it to you. I’ll send you a video async that shows you one way that it could look like. So I think the first thing is how do we make it so that interacting with the context is not just typing into a box and then stuff happens and you get an answer. We need to make it like you need to be able to understand what that looks like. And I think for a lot of this, because I spent so much time in the Excel salt mines, I think about it a lot like I think about Excel, which is you have some tab somewhere that says, here’s this metric, right? Here’s our profit for last quarter. And there’s a little button in there that shows trace precedence. Okay, where does that take me? Okay, that takes me upstream. And then I can keep navigating all the way back until I kind of understand how this thing comes from. And then there’s another little button on there that says calculate formula, right? And it just shows me all the little parts. And it shows how they’re adding and subtracting and dividing and multiplying and how it ends up with the final number. I think like we don’t have those traceability pieces yet for agent work flows or semantic layer stuff, really. I mean, we do, but only for the developer, not for the user. And so what I’m really thinking about is, you know, the way for me to like manifest this notion of, hey, you don’t need the semantic layer. It means you need to have something else. And part of it is, yes, you need the context. But you also need a way to visualize it in a way that like people can reason about and understand and like, you know, agree with how it was calculated, right?

00:43:20 | Moe Kiss: But you’re saying visualize the lineage, though, and the way it’s calculated.

00:43:25 | Jacob Matson: I think all parts of that, right? Lineage, yes. But like less about like, I mean, I would love to be like, okay, this number comes all the way from this field in your CRM. You know, I would love to be able to do that, right? Okay. Or like, you know, some sort of way to say, you know, hey, like we were talking about one of the active users earlier, like this, here’s all the detailed ways that that’s calculated. I think that’s probably actually too hard to reason about. It’s the wrong, it’s too detailed, right? We need to kind of be able to get the proper level of zoom out, right? We don’t want to be at the 10 foot level. We don’t want to be at the 40,000 foot level. We want to be at like the 10,000 foot level. And I think it probably depends on persona too. But like you need some sort of way to be able to reason about, you know, those numbers and how they were calculated to be confident that they’re correct, right? And like SQL is of course one way to reason about it, right? But like SQL is like verbose and kind of hard to reason about as like a non-technical person and like even, you know, engineers hate using it. And there’s a whole good set of reasons for that. You know, I think like the magic, the magic of Excel continues to be like demystifying how complex some of this stuff is and doing that with really clever UI interactivity. And so, you know, how do we, you know, what tools, what abstractions do we need to build to make that work? And I’ve been working on that. I think the core thing that I’ve been starting with is just like, how do we take something like a set of tables and like interweave context in there to show us how the tables relate to each other, right? In some ways you’d be like, hey, that looks a lot like ERD, right? It’s like, here’s the primary keys, here’s the foreign keys, whatever, right? But we can add a richer level of that that says, okay, we calculate these metrics this way, we use these joins, you know, we use this formula. That stuff can all, that stuff is also, you know, a level of the graph that’s always been missing when we get the ERD, right? We don’t know how it’s actually used. We just have a thing that says, here’s how the database defines the table. What we don’t have is knowledge of how the application actually uses it. And so, that’s I think the next part too, you know, we can mine like query history. In fact, I’ve done a bunch of work around that, like how do people actually query these, how do databases or how do applications query these, how do those patterns differ when it’s a human versus an application. So there’s a whole bunch of stuff we can do there. I’m not trying to be like too abstract or obtuse here, but like, I truly believe that that part of it is just that we have all of the, we have all of like the Lego blocks, but like no one has assembled it into something that is like cohesive in a way that’s like, I totally get this now, right? It’s very much like, even if you’re like, you know, high-ranking executive and you like get some number, there’s no like, you’re trusting that your team built it right. And like there’s not a good way today. And like lineage is part of that, but like just being able to say like, all right, how do all these components fit together and like fitting that in your brain as like, I don’t know, maybe if you’re the CMO, you shouldn’t do that, but like, I don’t know, maybe you should do that sometimes. I don’t know, hopefully that’s helpful. Hopefully that’s helpful. That’s kind of just how I’m thinking about it at the moment, but like make it visual is number one.

00:46:20 | Julie Hoyer: I was going to ask, how do you fight the echo chamber effect too from some of this? Sorry, when you were talking about like using AI to search for queries, like if it’s just always bringing back historical data and you were to like move that into the future. How do you do that?

00:46:37 | Jacob Matson: Okay. So let me just make sure we from this question. So you’re basically, you’re basically saying like, how do you not overfit the history?

00:46:43 | Julie Hoyer: Because they were figuring it out. Some of it’s not right. Some of it is. Or, you know, it’s just the bias of like, what was right at that time and you know, how do you get things in? This was my exact question. You have people that aren’t going for the context, the old fashioned way they’re relying on the tool to give them the context, but it’s old context, you know.

00:47:01 | Jacob Matson: So I think the first thing that I’m thinking about is like, well, if you had a semantic layer, you only have the history. You don’t have anything going forward because someone curated and built that for you. So now we get a new problem to solve, right? Now, if we can just forget the semantic layer exists or maybe we have it and it’s, you know, it’s the highway, right? But we want to detect when there are changes, right? When there’s drift, when there’s drift in our metrics, right? How do we, how do we detect that? I think this is a really good question. I don’t know if there’s like good programmatic ways that I’m like aware of, like I’ll talk my head at the moment, but certainly like there’s probably ways to do it programmatically. And I think like also some of it is like, well, if there’s less humans, you know, doing, doing some of the, some of the work that’s really easy to automate with AI, well, now what do those humans do next? I think part of it is like, yeah, maybe we need like a curator person who’s like handling this context potentially, right? You know, I think I kind of like always jokingly talk about like, hey, we need like more librarians. Like we’re generating all this context all the time. And it’s like, what do we do with it? It’s like, I don’t know. It just like lives in Slack or like teams or our emails or, you know, DMs on WhatsApp or whatever. And like eventually if it’s like, eventually it gets, it makes its way, you know, into the, the canon of the, of the organization, right? But like that, just that time is like really, it can be really long. How do we make that tighter is a really interesting question. I do think it’s like in the other side of that is like, well, what about archival, right? What if a metric is now was right and is now wrong? How do you discard it and like manage the life cycle of it? So I think like all of those pieces in my mind like kind of fit together, which is like life cycle management of this. And it’s like, we never even got there because we just get to like, we get to like semantic layer is published. And then it’s like, it’s such a big lift. It’s like, even get there that it’s just like, okay, like I got promoted. Thank you. I’m going to go to another company and I’ll do this again. This is now your problem. Like, sorry. And I’m being, again, I’m being sort of facetious, but like, these are hard. Like everyone wants to build it. No one wants to maintain it. And I think like how do we, I think we, you know, there’s probably space for companies or multiple companies in the space to build products that help us do this better. But, you know, I don’t have anything on top of my head that’s like, well, here’s how you catch drift and like reimplement it. You know, I wish I had the answer. You know, it would be, it would be more compelling maybe next time, next time.

00:49:19 | Michael Helbling: Right.

00:49:20 | Moe Kiss: Let me do more.

00:49:21 | Michael Helbling: That can do my next set of research.

00:49:23 | Jacob Matson: We’ll see if we can do it. You know, we are, we are fully migrating our internal stuff.

00:49:28 | Michael Helbling: So if we wanted certainty, Jacob, we would have just interviewed Claude, right? So this is great. Yeah, exactly. Exactly. This is awesome. Thank you so much. Really excellent conversation. One of the things we do at the end of every show is go around the horn and share a last call, something that might be of interest to our users. Jacob, you’re our guest.

00:49:46 | Jacob Matson: Do you have a last call you’d like to share? I just read a really awesome paper that I will share a link to you to Michael called skill opt executive strategy for self-evolving agent skills. I saw it on Twitter this morning. It is really interesting. I’ll share it and you can put it in the show notes. Definitely worth the read just to understand, you know, what it looks like to actually apply some of this stuff about what exactly we were talking about. How do we evolve these things as the systems change? That’s awesome. I love it.

00:50:15 | Michael Helbling: Awesome. Julie, what about you?

00:50:17 | Julie Hoyer: Okay. My last call is a little off the wall, but it was just too timely. Okay. So, Moe, this is a little bit, a fun fact about me and a question to you because it has to do with Canva.

00:50:28 | Moe Kiss: Okay.

00:50:29 | Julie Hoyer: Fun fact. I don’t like squirrels. Like, I just, I don’t like them. I don’t think they’re cute. They creep me out. Okay. Yeah. They kind of scare me. They kind of scare me because quick backstory. My dad said, you know, to this little, little girl, if you see possums are at Coons in the daylight, they’re rabid. I thought that meant squirrels. I went around for years thinking squirrels were rabid. You know how they pop around trees when you’re riding your bike. They like hide on the other side. I always thought they were going to pop out and get me. I don’t like squirrels. Okay. Fun fact that I don’t share with lots of people. I get an email from Canva that is squirrel themed and the CTA at the bottom of the email said, if you would like to stop getting squirrel themed content like opt out here. Like has AI personalized too far? Or like, is this, is this a phenomenon out in like the trendy world that I just have not been exposed to like our squirrels a thing or do they know this about me? So it kind of freaked me out. And there’s my fun fact.

00:51:30 | Moe Kiss: Also, like is squirrel a cool hip thing that I also don’t know about because I mean that level of personalization.

00:51:38 | Michael Helbling: Well, if the other cohort was getting emails about moose, then you’re something, now you’re getting somewhere, but that’s probably a reference that nobody knew. Did anybody else get the squirrel email?

00:51:48 | Moe Kiss: Julie, I will follow up and we can, I can share an update with you in our next class called really people hang in.

00:51:54 | Michael Helbling: Well, there you go. That’s a good last call. That just shows the range we can have here. Amazing. All right. Moe, what about you? What’s your last call?

00:52:04 | Moe Kiss: Okay. I have been reading a book which Rachel Gerson recommended. It’s called Word Slut, a feminist guide to taking back the English language by Amanda Moentell. And I just like, you know, words are important. Like you do. But when you go through this book and you hear about the evolution of certain words and how they refer to women, it just like, it’s, I don’t want to say delightful. It’s been surprising in a really great way. Like I feel like it’s kind of added to me wanting to be more thoughtful about the word choices that I use, which is entertaining because I don’t give too much thought to what comes out of my mouth. So anyway, go check it out. And Michael, over to you.

00:52:49 | Michael Helbling: Yeah. So mine is from back in May. James Hawkins, the CEO of post hog wrote an article about what he was thinking about as sort of their next chapter of vision of the future. Just so your book, if listeners aren’t aware, post hog is sort of both an analytics tool as well as other tools for digital and website operations. Anyway, it, I don’t know that I agree with everything he wrote in terms of like where products should go, but I thought it was very thought provoking. It definitely worth some time because all of us in analytics and in measurement spaces were facing a lot of change. And it’s good to see like, okay, here’s a company who’s got a lot of customers who’s doing a lot of work, especially with AI. Here’s how they’re looking at the future. So I think it’s kind of a good read just to develop and gain perspective. So that’s why I would recommend that. All right. Once again, Jacob, thank you. Thank you so much for coming on the show. This has actually been a really cool conversation and kind of like we, we, we stayed pretty high, but I feel like there’s also some really amazing kernels for people to pick up on and drill into their orgs with that I think will actually bear a lot of fruit. And also because it relates to songs like so now in my head, I’m like, life is a highway. Okay. Wow. Yeah. See, that’s what, that’s what happens to me when we talk about stuff. Anyways, so thank you again. And obviously to our listeners, yeah, I’m sure you’ve got thoughts and questions and we’d love to hear from you. And there’s a great way for you to do that. You can reach out to us on LinkedIn or on the measure slack chat group or via email contact at analytics hour.io and wherever you listen, you can also leave ratings and reviews and we read all of those as well. And Tim Wilson who’s not here today would like you to know you can also request a sticker for your laptop. Just go to analytics hour.io and there’s a form that you can fill out and we will mail

00:54:52 | Moe Kiss: it to you even internationally.

00:54:55 | Michael Helbling: All right.

00:54:56 | Moe Kiss: This has been great.

00:54:58 | Michael Helbling: I think there’s about three more of these that probably need to be done. AI is changing so fast. But Jacob, thank you once again. And I know I speak for both my co-hosts, Moe and Julie when I say no matter where you are in the jungle, keep analyzing.

00:55:16 | Announcer: Thanks for listening. Let’s keep the conversation going with your comments, suggestions and questions on Twitter at analytics hour, on the web at analytics hour.io, our LinkedIn group and the measure chat slack group. Music for the podcast by Josh Grohurst. Those smart guys wanted to fit in so they made up a term called analytics. Analytics don’t work.

00:55:40 | Charles Barkley: Do the analytics say go for it no matter who’s going for it? So if you and I were on the field, the analytics say go for it. It’s the stupidest, laziest, lamest thing I’ve ever heard for reasoning in competition.

00:55:53 | Jacob Matson: I think actually like, if you moved your cable around, I wonder if the cable was just like giving you some weird feedback or something. Because I was don’t touch it.

00:56:02 | Julie Hoyer: Don’t touch it now.

00:56:04 | Michael Helbling: Don’t touch it. Hands up.

00:56:06 | Julie Hoyer: Tim sent me a mic that he knew made a buzz. That was like an evil trick. Sabotage. Yeah, my toddler now uses it as her microphone.

00:56:18 | Moe Kiss: I was like, sure, you can have this.

00:56:21 | Michael Helbling: Does she do a podcast because you do one? Because that would be the most adorable thing in the entire world. No, but she does like to sing.

00:56:28 | Julie Hoyer: She just breathes into the mic.

00:56:33 | Michael Helbling: So that’s what I do.

00:56:35 | Moe Kiss: I’m going to be triggered a lot with every time the word, the S word is mentioned. You know, usual.

00:56:43 | Michael Helbling: I do the exact same thing, but I look over because a lot of times I leave crap on my chair back here. And so then I look, I’m like, oh, clear. I don’t.

00:56:51 | Moe Kiss: My husband gets dressed in here in the morning and decides to leave whatever pants he didn’t want to wear in the background.

00:56:59 | Julie Hoyer: Trust me. You don’t want to see what you can’t see behind this cover.

00:57:03 | Michael Helbling: All of the mess is my responsibility.

00:57:05 | Moe Kiss: I do get asked very frequently, though, why I have so many remotes on the wall behind me. And I’m like, it’s a fair question. Well, there’s another one that’s missing. So it’s totally fine.

00:57:15 | Michael Helbling: I don’t know. You’re just, you’re just a very successful person.

00:57:22 | Moe Kiss: And if people can’t deal with that, I’m just, I’m afraid to do it.

00:57:27 | Michael Helbling: I’d be afraid of that level of success is what my answer is. Five remotes. I know. I don’t have the lifestyle governance required. All right. Let’s get into it. So I’ll give us a five count and all right. All right. Let’s stop moving our microphone.

00:57:43 | Moe Kiss: It’s the problem with the YOLO one. It like pains everybody.

00:57:45 | Michael Helbling: That’s right.

00:57:46 | Moe Kiss: That’s right. We’re very serious.

00:58:03 | Julie Hoyer: Rock flag.

00:58:04 | Moe Kiss: And if you build it, who will maintain it?