Elkar AI Put to the Test in Live Financial Modeling with Honest Results for Modellers - Ian & Giles

In this episode of The ModSquad on Financial Modeler’s Corner, Giles Male and Ian Schnoor put Elkar to the test, a financial modeling tool that's been getting attention for its speed and slick design. From solving structured Excel challenges to building full forecast models, they push the tool to its limits. What follows is a revealing look at how Elkar performs when accuracy, logic, and professional modeling standards are on the line. Along the way, they uncover surprising strengths, critical flaws, and even moments of unexpected comedy. Whether you’re curious about automation or cautious about AI in finance, this episode offers plenty to think about.

Expect to Learn

• What Elkar gets right: speed, formatting, and a sleek interface

• Where it breaks down: logic errors, disconnected assumptions, and unreliable outputs

• How Elkar stacks up against other AI tools like TabAI and Agent

• Why using AI without understanding modeling fundamentals can be dangerous

• What it takes to turn a promising AI output into a reliable financial model

Here are a few quotes from the episode:

• "Right now, Elkar is like a junior analyst, you see potential, but you can't let them run unsupervised." - Giles Male

• "AI tools like this might build something that looks like a model, but without logic, it’s a house of cards." - Ian Schnoor
  
  

In this episode, Elkar proves to be a fast and visually polished AI tool with clear potential, especially in formatting and task execution speed. However, when it comes to financial logic, assumption structuring, and balance sheet integrity, it consistently misses the mark. The tool even resorts to shortcuts like hardcoding values and plugging imbalances.

Follow Giles Male:
LinkedIn -  https://www.linkedin.com/in/giles-male-30643b15/

Follow Ian:
LinkedIn - https://www.linkedin.com/in/ianschnoor/?originalSubdomain=ca

Elkar: https://elkar.co

In today’s episode:
[06:48] - Exploring Elkar: Website, Pricing, and Features
[10:34] - Elkar Takes on the Esports Excel Challenge
[20:14] - Elkar Gets Caught Cheating
[24:18] - Elkar Struggles with Complex Logic
[35:45] - Cash Flow Logic & Balance Sheet Errors
[46:38] - From Hardcoding to Dynamic Assumptions
[53:45] - Balance Sheet Plugging and Logical Failure
[57:34] - Reviewing Elkar’s Working Capital Assumptions
[1:04:20] - Wrap up & Final Thoughts

Full Show Transcript

[00:01:11] Host: Giles Male: Hello and welcome to another episode of The Mod Squad with me, Giles Male. And I'm joined by just one special guest this time. Ian. Ian, where's our third musketeer?

[00:01:23] Co-Host: Ian Schnoor : He had an appointment. Where? I was not at the last one. And Paul can't join us today, so we're gonna take over his hosting duties. It's not going to be the same without him. I bet it was more joyful without me. But it will be less, uh, less joyful without Paul, that's for sure. So we'll do our best to make him proud.

[00:01:43] Host: Giles Male: We'll do our best. I mean, he's actually left us in control of a recording that will be going on his YouTube channel. His podcast channel? He knows how much I like to swear on recordings.

[00:01:55] Co-Host: Ian Schnoor : Possibly one of the least intelligent, riskiest things he's done in his career. But.

[00:02:02] Host: Giles Male: You can trust us. You can trust us. All right. So I think, um, we're going to be testing a tool called Elkar today. Before we do that, I'll act as host for you. Where's your head at? We've obviously gone through quite a few rounds now. We've looked at the agent. We've looked at a fair few tools. What's your kind of general sense of where we're at in this series?

[00:02:22] Co-Host: Ian Schnoor : Well, I mean, it feels like we've, uh. I hate to use the word plateau, but it feels like we're hitting a bit of a consistency. Right? We're continuously impressed with what the tools are doing. We'll see. What if today is any different? I mean, overall, their performance has been, would you agree, like on some of the tests you've been putting at it, more similar than not? Um, they're various degrees of, of being able to get some of the questions done that you're providing into it and, you know, challenges in modeling, in building a full model. They have not been great to date at building from scratch, would you say? And, uh, we'll test this one. So I feel like we may have hit sort of a common, consistent spot where we're at a bit of a hump and see if we can get over that. What do you think?

[00:03:08] Host: Giles Male: Yeah, probably the same. I mean, obviously, you missed the excitement of testing shortcuts, uh, in the last episode, which was interesting because I agree, I think it's there or thereabouts. It's probably towards the better end of the third party tools that didn't live up to its crazy claims. But, you know, I think Tab AI has probably been one of the most impressive, did some really great things, but wasn't perfect. The agent has done the best so far from a sort of financial modeling perspective, I think. But again, I don't think any of us would say perfect or ready to rely upon, you know, in completeness. Yeah, I agree. I think coming into this episode, I was a bit like, oh, you know, I feel like we kind of know what we're going to get there or thereabouts. Uh, so I wonder whether that's going to change.

[00:03:54] Co-Host: Ian Schnoor : And, you know, I've been traveling, I've been on the road for the last couple of weeks, which is why I missed you the last time. And talking to a lot of modelers traveling throughout the US and, and in, in London last week. And there seems to be a consistent feeling that it's aligned with our own views, that nobody's ready to have a tool, build a model from scratch, have it done, package it up, send it in. People are looking forward to using it as a collaborator, as a partner to help find errors, to help with the design process, to help improve models, um, and to get ideas. I don't think anyone's expecting or looking for a button, a magic button to push to get your model and saves you all that time and energy. Everyone wants to understand what they're doing, so that is.

[00:04:43] Host: Giles Male: What I would say. I am hearing more and more stories of people in teams leveraging copilot, mainly copilot. I'm hearing and getting some value from it. So yeah, sure. Certainly not getting it to build models, but getting it to help look at data or to answer a query about how do I do this in code? How do I do this in VBA? So I'm hearing more of those stories and that I mean that's a testament to the progress of copilot, I guess.

[00:05:09] Co-Host: Ian Schnoor : Yeah. And I think we're hoping that in the modeling world we'll be able to say, use these tools to give me a suggestion. And is there a better way I can think about modeling revenue? And do you have any ideas on what I can do with this depreciation calculation? And can you help me out with an idea? Right. I think we would love to see the same on the modeling side as well.

[00:05:27] Host: Giles Male: All right. Good. I think we're still aligned, which is good. So should we have a look at Elkar. We'll bring up the website first and we'll just have a scan through. So this is alcohol's website. I'll hand it over to you again Ian. Anything that sort of jumps out at you as I scroll down here.

[00:05:46] Co-Host: Ian Schnoor : No, I mean, you know, again, I'm feeling like, um, I'm feeling like there's a consistency in the websites. I don't know if you would agree. Different colors, but they all tend to have the same similar look and feel. I'm looking at it now with some, you know, animations to them, some screenshots. They're clean, they're simple. So I like them. You think it's ElKar. They all have a tagline and a and a and a logo. There is what you think Elkar builds it. Their pricing plans seem to be in. Would you want to talk about that in line?

[00:06:19] Host: Giles Male: I think so. So 4040 and again like I'm I'm just not clued in enough to know when it says $40 and 250 requests a month. Like exactly what does that mean? Is that 250 prompts? It might be something slightly different. If you are planning to use this heavily, maybe you'd start to, you know, step into the $200 a month territory. And once you're there, it is a lot, isn't it? When you, you know, you can get Claude Pro or ChatGPT Pro subscriptions for $2,030, so it is a lot of money.

[00:06:52] Co-Host: Ian Schnoor : What does it say there? If you go down, it says under the pricing for max. So I have a feeling you're right. I mean you could probably fly through 250 requests pretty quickly. I mean, it's not it's not if you're working intensely, if you're working intensely in a spreadsheet, it's not hard to imagine going through, you know, 1020 if that truly means each individual prompt is a request, then you could go through 20, 30, 40, 50 a day. I would think pretty quickly, if you're working on something, iterate like iterating through it. So the max plan says 50. So everything unlimited requests, but 50 monthly requests in agent Max mode. So I don't know what that means either. Does that mean that the best tool agent, which is powered by opus, in the best tool, you still only get 50 requests per month? I'm not sure.

[00:07:40] Host: Giles Male: Yeah, I know, and it's interesting, isn't it? Because this gets to the conversation that comes up a lot in sort of MVP circles is like, you know, what about the cost of all of this prompting? Um, and I guess there is a significant cost behind the scenes for these companies as well. So I assume you're right. It's probably, uh, to link to the most powerful tools in the back end, and you have to limit that.

[00:08:04] Co-Host: Ian Schnoor : So you're saying that you're talking about the cost incurred by these third party add-ins? Because of course, as you put in a request, they're submitting a request to, you know, some sort of the LLM.

[00:08:17] Host: Giles Male: I think I think that would be my guess as to how it all works. so yeah, I guess $200 a month, you could probably start to eat through that. If you're looking at 50 requests in your kind of high powered mode a month. I don't really know. This is an interesting thing, isn't it? We don't know. Okay. Anything else?

[00:08:36] Co-Host: Ian Schnoor : Looks good. Let's see how it adds. And you want to look at the features, right? I mean, it.

[00:08:43] Host: Giles Male: What I did is quite interesting. So they've got a bunch of videos here. They do actually have one for the Microsoft Excel World Championship. So this is going to take me to their YouTube. Uh, they obviously have an example of uh, the Microsoft Excel World Championship case of some sort being solved. So they go, I'm not the first person to try this with Elkar. They've done it themselves.

[00:09:03] Co-Host: Ian Schnoor : Yeah, absolutely. Well, let's see, uh, let's see how it performs.

[00:09:07] Host: Giles Male: So I think let's get stuck in then we don't have Paul, so we're probably not going to do his, um, test cases. We'll do mine and yours. Um, and we'll see how it gets on. So I will start with great. Start with the same one I have started with for every tool, which is the easier Excel esports battle case. So let me bring it up on screen. We'll just have a look at what we get in the car, kind of, you know, user interface. And then we'll get going from there. So it is another kind of additional button on my home ribbon. I had a whole stack of these. I had to start deleting them because I had about seven tools in there.

[00:09:46] Co-Host: Ian Schnoor : Yes, as do I. So you just, uh, started removing.

[00:09:50] Host: Giles Male: Them. Removing them. All right. So Elkar, and for anyone watching, this is the first episode. This is an Excel E sports case. You have some bonus questions and then you have seven levels typically where you're given a problem to solve. And then you have to fill in the answers in these green cells so they get harder through the levels. This one is essentially saying pick the number of characters from the left from this word. So if you look at the example, three filters would be filled. So we're looking for formulas to be created by the tool like left with the number of characters. We want it to link to these cells ideally. And it gets harder and harder.

[00:10:30] Co-Host: Ian Schnoor : So ideally and ideally, you know, one thing that we've learned in this process is I think I would say ideally we want it to build a solution that is one that could be transferred to a person to use and to copyright and to automate. And what we've discovered with some of the other tools is that they are, of course, lightning fast, but building tools that are incompatible with the way a person would work, like they might drop in a dozen hard coded values in a formula. Now it's okay. It can do that because it can do it instantly. But that doesn't leave it dynamic and modular and able to be copied. So I think we'd love to see it. And we might need to change the prompts then to see. Well let's see what it does. Let's just put the exact same prompts as before and see what it does.

[00:11:14] Host: Giles Male: Hitting into it. So we just get it to do level one first, just to see if it's got the right kind of sense of what we're doing. Uh, so we're already getting some feedback. I'll analyze the case tab. Perfect. I can see the structure level one is about. So again, I think this is quite nice. The only one we haven't really seen give this much feedback. Oh, wow. It's done. That was quick. Uh, well that was probably the quickest I've seen.

[00:11:38] Co-Host: Ian Schnoor : So you asked it. I'm sorry. You asked it just to do level one.

[00:11:41] Host: Giles Male: I also just do level one. But it's. It has done level one. That was very good.

[00:11:46] Co-Host: Ian Schnoor : I.

[00:11:46] Host: Giles Male: Love.

[00:11:47] Co-Host: Ian Schnoor : And so first of all what I like is it gives you can you scroll up for a second and show everyone um go up above it said, uh, where did it stop? Um, right. I need to create a form. I need to create formulas using the left function and like it's explaining what it understands there. It needs to. That's great. Not all the tools were doing that, were they.

[00:12:05] Host: Giles Male: That's what I was I was I was saying before I got shocked by its speed, I think agent was probably the lowest in that kind of measure of you couldn't really see what was what it was thinking. Yeah. Let's continue with the remaining levels.

[00:12:19] Co-Host: Ian Schnoor : And the formula that it has derived is a I would say the perfect simplest formula also is transferable right to a person that is dynamic and modular in it work. So let's see. Let's see what it does for some of the more complex.

[00:12:36] Host: Giles Male: Um, so I'll hit pause. Just because we don't know. It might take a minute. It might take 4 or 5, but I'll hit pause. Oh, wow. Hit pause.

[00:12:43] Co-Host: Ian Schnoor : You might not need you. Josh, this is fast. Let's see here.

[00:12:46] Host: Giles Male: Oh, wow. Okay, okay.

[00:12:48] Co-Host: Ian Schnoor : So so. But again, I'm, uh. Now how many are free? It's flying through. Which question is it on? That's impressive. Okay.

[00:12:57] Host: Giles Male: It's finished.

[00:12:58] Co-Host: Ian Schnoor : Wow. I know we haven't been timing. That's fast. Right. That was fast.

[00:13:03] Host: Giles Male: That was I didn't have time to hit pause. Um, okay. So, uh, there's a few things we obviously have to check. Annoyingly, I should have fixed this ages ago, but I've got one where I don't have the green ticks available, so let me just pull up the answers on a different screen, and I will just do a quick sense check to make sure it's got the right answers. Because obviously that would be nice. Yes. So right answers.

[00:13:30] Co-Host: Ian Schnoor : Looking good. Looking good.

[00:13:32] Host: Giles Male: So far. Yeah.

[00:13:34] Co-Host: Ian Schnoor : And let's see I'm looking as you evaluate them to see the caliber and the quality of the answers. So again, this one I'm looking to see if there's 100%.

[00:13:44] Host: Giles Male: I have to say that is um, that is by far and away the fastest we've seen. Now, if it was just speed, it's one. Uh, let's have a look at what it did. Okay.

[00:13:56] Co-Host: Ian Schnoor : So, you know, you're familiar with these. It's put in some dead numbers. Uh, is that fine? I'm not sure exactly. It's repeating.

[00:14:04] Host: Giles Male: I genuinely have absolutely no idea why it's turned to the Rept function, and it's repeating that a hundred times, right.

[00:14:14] Co-Host: Ian Schnoor : It's repeating this, and it is. Huh? And it's.

[00:14:20] Host: Giles Male: I don't know what it's doing, bro.

[00:14:22] Co-Host: Ian Schnoor : Look what it's done, though. It's. So this is what we're. This is not likely. It's certainly not likely. The simplest way to solve it. And it's using this is what I, you know, also keep talking about is I think that people's skills are going to have to increase just to understand what it's doing. This is a very unconventional degree. It's using an indirect. If you look where your cursor is, it's using an indirect to populate a row function. Now a row function simply says, you know, Excel's row function simply says click on a cell reference and it tells you the number of the row number. What it's doing is it's using an indirect with a range from 1 to 10. You want to highlight that in quotation marks. I'm not quite sure what that's doing in quotation marks. I'd have to test it. And you're the one looking at it. And then it's embedding that into the row function.

[00:15:10] Host: Giles Male: So I have no idea what it's doing. I'll be honest, I have no idea what that is.

[00:15:14] Co-Host: Ian Schnoor : And you can see it's got a little array, uh, with those squiggly brackets. One, two at the end. Would you see that at the very end of the formula?

[00:15:21] Host: Giles Male: Yeah. Yeah.

[00:15:21] Co-Host: Ian Schnoor : That's that's so that's all part of the sum product right. It's all part. This would be I think it's safe to say I think it's safe to say that this would be a hard formula for most Excel users.

[00:15:35] Host: Giles Male: Okay, that would just. I don't know why it's turning to that, but hey, it got the right answers in a really, really weird way.

[00:15:42] Co-Host: Ian Schnoor : Level again. So here's the thing. For those watching, you know that it got the right answer. Because you know what the right answer is, right? Yeah. Um, just a cautionary warning. If you were asking it to solve a problem like this and you did not know what the right answer was, which is which more simulates reality, right? In real life, you have a data problem. You say, can you solve it for me? You're not sure the right answer. If this is what you got, you're going to have to really kick up your Excel skills pretty significantly to be able to interpret and understand that, to make sure that it's actually doing it right and doing it right consistently. So that's pretty, um, pretty amazing.

[00:16:17] Host: Giles Male: Level three. Fine. So it's used indirectly and column or. Yeah that's fine. Okay. So it's done the job okay. They're level four again. Good Len minus Len substitute. It's using the cell references, which is great. I know 1 or.

[00:16:31] Co-Host: Ian Schnoor : 2 that feels like the way that feels like the way most people would solve it, you know, in a, in a in a challenge. Right? That makes sense.

[00:16:37] Host: Giles Male: Uh.

[00:16:38] Co-Host: Ian Schnoor : Good luck with that one.

[00:16:40] Host: Giles Male: Good luck. I tell you, it's so interesting that different tools that have sort of preferred approaches yet again, it has gone for repped and blank and a hundred. I can't get my head around why it's adding 100 Typekit at 100.

[00:16:58] Co-Host: Ian Schnoor : Like why. Yeah I don't know why. It's some maybe because that is again significantly longer than what the total numeric chain is. Uh, within any of them, I'm not sure. Again, I'd have to kind of go back and dissect it.

[00:17:12] Host: Giles Male: You actually, you might have a point there, because if you did do mid and then if that was the second part of the mid, uh, do you know what I don't know. I just.

[00:17:20] Co-Host: Ian Schnoor : Love I just love if you start from the beginning, I just love, you know, for those who really want to elevate theirs, you've got a, a substitute embedded within the Mid. Embedded within a trim, embedded within a value, embedded within a sub product.

[00:17:34] Host: Giles Male: But then just a bunch of hard coded numbers as well. 100 -99. I genuinely have no idea what that's doing.

[00:17:40] Co-Host: Ian Schnoor : So for those of you who have ever had your manager say what the heck is that formula doing? Be prepared. Be prepared. Yeah.

[00:17:47] Host: Giles Male: Um, yeah. Uh, so level six, good indirect on the map and the reference there, that's that's good. And then level seven, it actually looks more reasonable. That's that again.

[00:17:59] Co-Host: Ian Schnoor : Oh yeah. That seems that for anyone for any good Excel user, that's not going to be hard to uh, to figure that out when it's, it's not a.

[00:18:08] Host: Giles Male: Okay. So I think that is really impressive.

[00:18:13] Co-Host: Ian Schnoor : Well, we didn't have to push pause. We didn't have to push pause.

[00:18:16] Host: Giles Male: We didn't.

[00:18:16] Co-Host: Ian Schnoor : And I think it's safe to say that. Right? I mean, in a company, people would have 30 minutes. Is that right to solve all of those? And most people would not get right.

[00:18:25] Host: Giles Male: Sorry for that easy easy case. So I think, you know, uh, that that's a case where the top pros would be finishing fast. They'd be doing that in, you know, ten minutes, maybe less. But that did it in, what, two minutes?

[00:18:37] Co-Host: Ian Schnoor : Maybe less, maybe less, maybe one. But the very top pros that have practiced would get it in ten minutes. There are plenty of people that would not finish that in half an hour. I'm very confident right in, uh, of that one.

[00:18:50] Host: Giles Male: Yeah, I think so, because some people just wouldn't know the functions to use. Uh, so let's let's really test this tool. Uh, let's go to my case. Um, well.

[00:19:01] Co-Host: Ian Schnoor : Let's, uh, let's buckle up here because I did the first one in a, you know, a minute. So let's see. Let's see how it does.

[00:19:08] Host: Giles Male: On if it does this as well, I have to say, and.

[00:19:10] Co-Host: Ian Schnoor : Then we'll test it on whether it can actually build a model. But let's see what it does on this one. This is.

[00:19:16] Host: Giles Male: Okay. Tell you what. For this one because I've asked it to do all seven levels, I'm going to hit pause. I can't imagine I'm going to do it in my 30s. All right, we're back. We? This is probably the funniest thing. I think we've seen any tool do. So as we were going through, I noticed that it was putting the answers in the column here. And in these cases, this is where you get this really nice green tick. You see on level two, it actually put the answers in this column and overwrote the green ticks. So I moved it over. And I also unhide the answers sheet which has the answers. But you hide it in the background. And I thought this was doing really well. And then when you look at the later levels it's spotted that there's a sheet called answers and it's just linking to the answer.

[00:20:04] Co-Host: Ian Schnoor : This is the most clever AI tool.

[00:20:06] Host: Giles Male: That we've looked at. Pretty close to AGI, isn't it? That's exactly what a naughty human would do.

[00:20:12] Co-Host: Ian Schnoor : Didn't realize you had an answer sheet and it just said, heck, I'm not going to hurt myself. Let me just link directly to the answer.

[00:20:18] Host: Giles Male: Is.

[00:20:19] Co-Host: Ian Schnoor : Does it make sense? Does it make sense to, uh, to pause again and go back and say, hey, can you, uh, can you solve it yourself without checking the answer sheet? I mean, you could, but from the ones that it did solve, it looks like it's done quite well. Is that right?

[00:20:34] Host: Giles Male: I mean, I think it cheated most of them.

[00:20:37] Co-Host: Ian Schnoor : Oh, okay.

[00:20:37] Host: Giles Male: So I'm telling you, I'm saying you can't use the answer sheet.

[00:20:41] Co-Host: Ian Schnoor : Oh, like scolding a small child. Right?

[00:20:44] Host: Giles Male: Absolutely right. I apologize for taking that shortcut.

[00:20:50] Co-Host: Ian Schnoor : See, AI can be fun.

[00:20:53] Host: Giles Male: Brilliant. Joking around with.

[00:20:55] Co-Host: Ian Schnoor : With the AI tool. Um, yeah. Okay, we should pause.

[00:21:00] Host: Giles Male: We'll give it another go. If it's just, it's. We're expelling it. It's done.

[00:21:05] Co-Host: Ian Schnoor : Absolutely.

[00:21:06] Host: Giles Male: All right. We'll be back in a minute. Okay. We are back. That was. That was a good 15, 16 minutes. It struggled a bit. So it's. And again, Ian, I find it really interesting because of this one. So we had the little cheating episode which we've forgiven it for. But it also just seems to be struggling with putting things in the right place. Uh, so it kind of got there. What did it do? It got level two correct. That's fine. Level three. A couple are correct. But again, not not exactly a full set of green ticks. Level four. It eventually got corrected apart from one. And actually that looks correct in terms of some of these kinds of characteristics for the coats. Some of them were zeroed out. So up until that point I think it did. Well level five, it just put uh, the same calculation across all the levels, which was wrong. Level six again. That's wrong. And then again, I'm not giving you this because I think it's still trying to cheat. It's just hard coded, almost the right answers.

[00:22:11] Co-Host: Ian Schnoor : You're you're looking for it too. Yeah. Like again it's doing something that it can do as a computer, but it's not a sort of called a human solution. Is that what you mean? Well, I also.

[00:22:23] Host: Giles Male: Mean that I'm not sure I totally trust it. After our little pulling the answers from the answer sheet escapade, I think it might just be looking at the answers and hard coding them in in a formula. So I don't know. So this is a harder case. We knew it. Uh, I almost got the sense if this was a human analyst, after the speed of the first case, I almost feel like I would be saying to this human, just slow down a bit. Just just take your time. You don't need to rush this. Much like it's more important that you get the right solution and you think through the logic than you win this race.

[00:22:57] Co-Host: Ian Schnoor : Well, the other thing too is we all know, um, we all know from any Excel work we've ever done that Excel problems and challenges tend to elevate in complexity, which is what's realistic about the esports challenges. I mean, in life, often the first things you have to do in any spreadsheet are just add up a column of numbers and then you know, and then do some additional, more complex calculations and eventually build in lookups and other. I mean, it just elevates. And what we're seeing is these tools are good at doing that very easily. And then medium complexity. And as you get into more and more complexity they hit a bit of a wall. And this one has as well. It appears right.

[00:23:35] Host: Giles Male: I think so, but it also feels like it's just like it's had a little malfunction in ways that are quite unique. You know, we said put the answers in column E, it stuck them all in column F. And we've seen bits like that on a few tools. There's a very similar characteristic where, you know, I remember one of the tools for the financial modeling challenge that you set it tried to do the balance sheet check, but one of the line items was pointing to the row above the total assets calculation. You're like, okay, that's just linking to the wrong thing. So yeah, I think it's done okay. In a very, very hard challenge. Should we do my other one? Should we do my other one quickly? And then we'll move on to yours.

[00:24:14] Co-Host: Ian Schnoor : Yeah. What was your other one?

[00:24:15] Host: Giles Male: My other one is the trial balance. So I'll tell you what. Why don't we come back to that? Should we just do it? I get bored of my own voice. You wouldn't believe it.

[00:24:23] Co-Host: Ian Schnoor : All right, well, then let's.

[00:24:24] Host: Giles Male: Move over to you.

[00:24:26] Co-Host: Ian Schnoor : Sure. Why don't we do that? Should we warm it up with some, um. With doing some checks and some testing and looking at a model again? Why don't we do that? And then I'm going to. I really want to make sure we have time to see what it will do. I have not, you know, um, full disclosure, I have not asked this tool to build anything from scratch yet. So this is going to be a real time surprise for both of us when we see what it can do. So let's go here first of all. And, I assume that you've got my screen up now, is that correct? So you do. And, let's start, let's start with, uh, and so here is the Elkar tool. I'll get that one up. You can see I've got lots of them here. And it admittedly took a little bit of time to get this one working sometimes. Tools take a little bit of effort to get them loaded up, doesn't it? This one, some people might not have had the patience, but, uh, but we did get it working, right. And it is working now, so it confirmed that it does work. I'm gonna. It's asking me to upgrade. I have a week. I'll just get rid of this. So let's try some again. I have a financial model here, and it's built. As you know, the balance sheet is not balanced. The balance sheet is out of balance on purpose. And it did not watch me.

[00:25:41] Co-Host: Ian Schnoor : So I'm curious to see how it solves that. There are some white values. There are some hidden white values. There are some inconsistent formulas here. Right. There are some hard coded values. There's some other stuff. Let's see. There are some hidden sheets. Let's start to see. Number one, are there any hidden sheets in this file? I think it's going to solve these fairly quickly based on the performance. And I already like it when I say I'll check. And it says wow look at that quick. Yes there are two. So this is a very confident, uh, AI tool which I love. Right. Like it works fast. And when it gets the answer, it says yes, it's got it. So there are two hidden sheets, covert and clandestine. Done. Easy. What about this? Let's see if there are any. Let's ask it if there are any, um, white values on this sheet and it says, are there any white values? I'll check for text values on the model sheet by examining the formatting so it understands that it's going to check the formatting of all cells and lets me try a different approach. Um, it's doing something I'm not sure what it's doing. I tried a few times. Oh okay. Well look at this. This says no white text found on the model sheet. The font color check did not detect any cells with white text in the sample range, which was B one to U50. Now you 50 goes way out here.

[00:27:05] Host: Giles Male: However you do.

[00:27:06] Co-Host: Ian Schnoor : Check it.

[00:27:06] Host: Giles Male: Out. Yeah interesting. So just got that wrong.

[00:27:09] Co-Host: Ian Schnoor : Have I seen the numbers here? These cells were white. And again, I'm not sure why. There are absolutely white cells here. You can see they're white. So I missed that. I'm not again, not sure exactly what it was doing, but obviously needed to be careful about that. Not. But it clearly understood what I asked. Right.

[00:27:33] Host: Giles Male: I think that's what's even more interesting. It very much understood the question and then still didn't spot what was there, which is. Yeah.

[00:27:41] Co-Host: Ian Schnoor : Well, what about this? Are there any inconsistent formulas on the sheet? That's a key one. Are there any inconsistent formulas? And I know I'll check and I like here I'll check for inconsistent formulas on the model sheet by examining um, formulas across similar rows and columns. I like that it's scanning the model for inconsistent formulas and it says, yes, this is great. This is fast. This is very great. Yes. There are 13 columns with inconsistencies. The main issues are Column B is not as worried about column B, because column B is sort of just a helper column A text column not as worried about that. Column C to O. It recognizes some things. Now that's interesting. And again this is something we're finding as well right. Um, and I forget how people refer to this issue. Uh, I'm drawing a blank right now. I should have the word. But the issue being that if you ask the tool the same question multiple times, you might get different responses, because I tried this one earlier and it did, uh, earlier, it did identify that row 13 as an example was a row that had an inconsistent formula. This one is different than the prior one. It knew that, but this time I asked it the exact same question as I did, you know, an hour ago.

[00:28:53] Co-Host: Ian Schnoor : And are there any inconsistent formulas on the sheet? It's saying yes. Uh, last time it actually showed me the rows that were problematic. This time it's not. So that makes me uncomfortable. Generally with AI tools as well that we've seen, I always wonder, okay, it's got it, but will it always get that? And how many times do I have to try running it too. Let me try again. Let's just literally run it again. Are there any inconsistencies? I'm literally deliberately not changing it because I know that that same prompt gave me a different request last time. So, you know, does it learn from itself? Is it going to do the exact same thing? It's checking for actual errors. Wow. Now it says suspicious patterns have been detected. The formulas on this sheet appear to be valid even though there were multiple formula patterns. So this is concerning. So not only did it still not pick up the answer, but now it's telling me that there are no formula errors or suspicious patterns. And we know that there are. I'm going to do it again. I'm going to try it one more time.

[00:29:56] Host: Giles Male: It's interesting though, isn't it?

[00:29:57] Co-Host: Ian Schnoor : I'm not saying that I think I made a mistake. I will do that next time. How about that? The next time I'll say, I think you're missing something because I just want to see what happens if it runs it over and over again with the exact same prompt. Now, because if you ran it once, if you ran it for most people, I think. Right, Charles, if you ran it once and you got this, you'd be like, great, that's awesome. Right? No inconsistent formulas. And then your boss would discover it at midnight.

[00:30:22] Host: Giles Male: Well, exactly. And that's where my head's at with my kind of worries at the moment with this stuff is if I use the tool like oak, which I've used for 15 years, I'd pull up the model map from oak. I'd be able to scan the inconsistencies visually in about five minutes myself across a huge model. And I'd be right.

[00:30:40] Co-Host: Ian Schnoor : Yeah. I mean, let's be clear. You don't need AI to do any of these model checks, but it would be nice to know that it could do it for you here, right now, for the third time, it's given me a third different response. Yes, there are eight columns with significant formula inconsistencies. Again, strange because just one minute ago it said that there were no formulas or errors or suspicious patterns detected. Right. And now.

[00:31:04] Host: Giles Male: It's looking at it at the wrong axis. It's just it's going vertically and saying, oh within a column that there's differences, which is.

[00:31:11] Co-Host: Ian Schnoor : And now let me try and challenge it. I'm going to go off script here. Are you sure? Um, row 13 has a cell with hard coded values. Are there other rows with formulas like that? Okay. I think they don't like to be challenged. Are you sure? But let's see. Uh, I'm asking it if. If it is, sure is. Are you sure? Row 13. We know row 13 has a cell with a hard coded value in it. Are there any other rows with formulas like. Let me check for hard coded values in formulas across a sheet. So it's trying. Yeah okay. It's very proud of itself. It's found in M13. Well I did give it a hint. Um. That's true. That's true with a hard coded value. Let me search for others. Um, okay, so it is obvious I'm being a little bit difficult with it, but this is the kind of thing I would hope one I don't remember off the top of my head if there are others. Well, look here, right here in oh 13 is another value with a number five at the end. I don't think it's pointed out that. Oh 13 did it find both. I don't think it did. Right. No. So I'm not sure how well I'm going to sleep at night if I know that this is the caliber of checking for hard coded values. But you know. Anyway, it was good to see that. Why don't we try moving on to the next one? How are you feeling about this one? I'm going to ask why the balance sheets are not balanced? Are you feeling comfortable about this one or are you a little more nervous about this one?

[00:32:55] Host: Giles Male: Um, mixed, I again, I feel like you talked about this plateau that we've reached. It's kind of aligned to what we're seeing. I think it's done some good things. It's done some really bad things.

[00:33:06] Co-Host: Ian Schnoor : And that's a hard question.

[00:33:08] Host: Giles Male: Yes.

[00:33:09] Co-Host: Ian Schnoor : Exactly. And I don't know. Listen, there are not many modelers out there in the grand scheme of things who could look at an unbalanced balance sheet and very, very quickly, instantly determine you got to be you have to think through a lot of things and understand a lot of system integrations to understand where to look and why a balance sheet might be out of balance. You have to understand a lot about accounting. So but let's see. Let's try. Why doesn't the balance sheet balance? Let's populate that one. It's a simple task. It's a simple ask for a difficult problem. Right. Because of course there could be 20 or 30 reasons like not only right. And again, the balance sheet is out of balance. And just as a reminder. So I fully acknowledge this is hard because my error is in the working capital schedule. And by the way, the change in working capital here, it's not that it's wrong. The change in working capital like this actually is the change in working capital. The change in working capital went from 56 down to 49. And so it dropped. The change in working capital dropped from 56 to 49. It went down 6.9%. So technically that's not the wrong answer. However, any financial modeler knows that when you're talking about change in working capital, the way a set of accounting statements prepares it, this is referring to the change in cash as a result of the working capital changes. So for a financial model, um, we all need to know that you have to change the sign. Um, I don't care about the actual change in the working capital. I care about the cash implication as a result of that change, which means that I have to subtract it the other way. Last year, minus this year, it's got to be positive. Now I'm just talking, as it were.

[00:34:46] Host: Giles Male: Scroll through. Yeah, I think it's done.

[00:34:48] Co-Host: Ian Schnoor : So the balance sheet doesn't balance sheet. Um, I'm just seeing the balance sheet doesn't balance because of discrepancies in the projected years. Look. Okay. Thank you. So it knows in row 188, it realizes here that looking at the projected years in row one, 88 knows balance. Okay, so it has been identified.

[00:35:10] Host: Giles Male: The.

[00:35:10] Co-Host: Ian Schnoor : Root cause. Well, it says the root cause is the hard coded value in M13 and M14. The hard coded value artificially inflates the net sales price, which cascades. It's using big words like cascades. Right. And here it is: it sounds intelligent, very intelligent. Right. But the reality is any good modeler knows that you can hard code revenues till the cows come home. That has nothing to do with an unbalanced balance sheet, right? It would just if the model was working properly, it would lead to inflated revenues and inflated, um, inflated revenues, which would mean higher cash and higher retained earnings on the balance sheet. Right. That should have no impact on unbalanced balance.

[00:35:54] Host: Giles Male: I just think it doesn't know, and I think it's pointed to the thing that you referenced earlier, because you mentioned specifically that there was a hard coded number of 50 something. I think it's almost just gone there because it's the most logical guess to go to, because.

[00:36:09] Co-Host: Ian Schnoor : I mean, let's just prove it of course. I mean, again, a modeler understands that, you know, there are many mistakes in models that lead to an unbalanced balance sheet. There are even more mistakes in models that have nothing to do with the balance sheet, and will not lead to a balance sheet being out of balance, right? I mean, I'll copy this across. This is correct. I'll control R and copy this over. And my revenues. You know we're still going to stay, you know, significantly out of balance. And just even to prove I can double I can triple the revenues. If the balance sheet is working properly it will just lead to higher because of course that makes no sense. If you double count revenues and you're going to have higher revenues, higher net income, higher cash and higher retained earnings. As long as it's built properly, the balance sheet should stay in balance. Yeah, I think.

[00:36:58] Host: Giles Male: I think he's got that wrong. I don't think I appreciate it.

[00:37:01] Co-Host: Ian Schnoor : Are you sure? Are you sure? Don't you think maybe. Let's see if we can. Don't you think the real error might have something to do with the working capital calculations? Are you sure? I like, um. You're right. I love it. You see that? It says you're right.

[00:37:24] Host: Giles Male: But again, to me, if I was to put this in like a human avatar, I would. I just imagine this, like, really hyper teen, like, you know, late teens, early 20s person. That's really clever. It's like, just slow down. Slow down.

[00:37:38] Co-Host: Ian Schnoor : Well, look at that now. Now it's massaging my ego here. It tells me I'm right and then it tells me. Excellent catch. Thank you. But hang on. Aren't you supposed to be the one doing the catching? The IT tool. I feel like my AI tool is supposed to be doing the catching.

[00:37:55] Host: Giles Male: It's got it.

[00:37:56] Co-Host: Ian Schnoor : Wrong. But anyway, I. Yeah, now it tells me I found it, but it does think it found the real issue. The problem is in the working capital calculation. Look at the formulas K2 60 to K2 65. Um use. So it says accounts receivable use the cost of goods sold to calculate which is fine which is normal convention.

[00:38:15] Host: Giles Male: But surely if it's got accounts receivable it would be linked to revenue wouldn't it. In accounts payable.

[00:38:21] Co-Host: Ian Schnoor : Because all the income and then it's here's it, this inconsistency creates a mismatch. The historical years days are calculated as about right. But sending me down uh, it's sending me down a, um, a bit of an incorrect path here. It's sending me down chasing something that's not right. I mean, this is all fine. The days are calculated as historical. And this is a correct formula for days and the projected years balances. It is normal to calculate. Let me show you. Okay. So it says that the working capital balances should be calculated using revenue, not cost of goods sold to maintain consistency with how the historical balances this is causing the change in working capital to be incorrect. I really am allergic. I'm very, very hesitant and it causes me a lot of things I don't know. This causes me a lot of unhappiness when it Overconfidently tells me that yes, it found an answer which is not right, right. So this overconfidence when you're wrong. So it's pointing out that the history look standard convention dictates that most people use the standard convention of calculating receivables off of revenues. And you can see here in the future we've calculated the receivable balance by using net revenue. Because accounts receivable are most closely aligned to revenue, and everything else is typically related to cost of goods sold. That is standard industry convention. You'll notice that in historical days we also used the cost of goods sold. It doesn't need to be. This is just standard convention. You don't need to. But also it has incorrectly said that this inconsistency is what causes a mismatch. That's not true. Right? Um, I could calculate the historical days off of cost of goods sold instead of off of, uh, revenue, and I'd get different numbers. Uh, it's not that's not standard convention, but it would work like it would.

[00:40:20] Host: Giles Male: It wouldn't.

[00:40:21] Co-Host: Ian Schnoor : Matter.

[00:40:21] Host: Giles Male: It would be accurate, but it would still work and give you a result and not create.

[00:40:25] Co-Host: Ian Schnoor : Exactly like, let's prove it right. Um, let's prove it. And again, I will move on. But again, it is really worrisome that it takes people. It will take people without knowledge down. So let's just show again the change in working capital. I have current minus the past year. That is the change in working capital. But what I need is the reflection on cash. So I either have to flip the sign here on the change working capital or um, or I can keep it that way. And on the cash flow statement, flip it. My preference would be to flip it right here. So I am going to take last year minus the current year. And that should oops. That should get me, uh, to flip the balances that now the working capital has gone down. But the cash has gone up because it means that we've sold off some working capital and put that cash into our bank. And of course, now the balance sheet, of course, should be balanced. But it makes me very uncomfortable that on two occasions it's suggested, you know, a course of action that's just not correct. And a modeler has to understand that, or it's going to be a lot of, a lot of painful, uh, nights. Let's try this. Let's go now and use up some of our additional time. I'm curious to see what it does. This one. We might need to.

[00:41:43] Host: Giles Male: Pull this right.

[00:41:44] Co-Host: Ian Schnoor : We might need to pause. Let's try this one here and let's go back into this tool.

[00:41:51] Host: Giles Male: So this is the one you're going to ask it to build a full on forecast, right?

[00:41:56] Co-Host: Ian Schnoor : Exactly. I am just going to say let's see what it does. Again. Build a five year forecast model on the model sheet for the years 2025 to 2029. Build separate schedules for revenues, costs, depreciation, income tax, working capital, debt and equity. Make reasonable assumptions. And I think that's a fair ask. You know, just to make some reasonable assumptions. We saw some tools that did okay. And most are not doing that great. There's a lot to understand, but let's uh, let's just click enter. Um, I do not expect it will be able to generate, you know, a response, instantly. So let's just see what it says and then take a pause. I'll help you build a comprehensive. And then what I'd love to do, because I think we have a few minutes is, um, we'll come back to the other one and we'll see if it can do a valuation. This is my first time. Let's try and be okay. Let's try and get a bit of evaluation. But interestingly look at this though. Do you see?

[00:42:46] Host: Giles Male: What he's doing.

[00:42:48] Co-Host: Ian Schnoor : We should actually keep this going because unlike the other ones it's actually building as it goes. Right. Like look at this. It's doing things and formatting them. Look at that. It's building something and formatting. Um, the revenue is okay. Um, okay. Well look what it's doing here. Wow. I mean, this is impressive in speed, but again, this is the teenager that you want to scold, right? Because it's what it's doing for revenue. And again, I said make reasonable assumptions. Totally fine. So I'm okay with that. But I also asked it to build a separate schedule for revenues cost. And in this case it just applied well and it didn't. So it made an assumption for 5%. But it's not you know, what it could have done very simply is just made one row above at the top that says, you know, growth, revenue growth 5%. I mean I would hope it knew that it's not ideal to type in a dead number like this right in, but okay, it did it. I mean, I guess I could modify that later. What did it do?

[00:43:46] Host: Giles Male: The numbers look broadly reasonable. I mean, albeit, the TAC, the interest expense has dropped a lot. It'd be interesting to see what it's done with.

[00:43:55] Co-Host: Ian Schnoor : Well, look what it did, though. Cost of goods sold. It's growing at 4%. So most modelers would understand and appreciate that there needs to be some connectivity between the cost of goods sold and the revenue. Right. In this case, it's literally just the growing cost of goods sold. I mean, I sometimes joke when I used to teach a lot of modeling that anyone could build a model in literally five minutes. You can build a model of any company for five minutes. If you literally take the last year's numbers and apply growth rates to everything, then you've got a model. It doesn't mean that it's a good model or that it's actually reasonable, but in theory, you've got to forecast.

[00:44:28] Host: Giles Male: That's always been your bugbear about just with the hype, the big statements, if it can build a model in ten minutes, it's like, yeah, but what's the model? What is useful? Can anybody get value from it?

[00:44:39] Co-Host: Ian Schnoor : Right. Remember, we always talk about the fact that a good model has got to tell a story. It's got to get you smart so that I can come back to my boss and my client and my partners and say, this is a really smart forecast. Well, they're going to very quickly realize all I did is I grew revenue at 5%. I grew the cost at 4%, I grew at 3%. Even depreciation is just growing at 2%. I mean, interest is growing at 7%. Oh, no, it is, uh, interest is sorry. I'm sorry. It's not growing interest. It's taking. Oh, look what it did, though. You're gonna love this, right?

[00:45:15] Host: Giles Male: No, no. Uh, so it's hard coding the principal repayments. Um, period by period.

[00:45:24] Co-Host: Ian Schnoor : It's hard coding. No, it's hard coding the debt amount, I believe. What? It's a pity.

[00:45:28] Host: Giles Male: Yeah, that's what I mean, though. It's like.

[00:45:30] Co-Host: Ian Schnoor : 175. It took a dead amount of 175, which it found. Well, it's the end of the same year. Um. It's taken. It's got a balance sheet. We're going to quickly see if this balances. We didn't even have to pause. This is impressive. So the speed is impressive. It's taken. Um. It's taken, but instead of linking to the end of the balance sheet, it typed in a dead number. It's applying 7%. Okay. I mean, that's not crazy. And it's got an interest expense. It. What did it do for taxes? Look at that. It built a little if statement if, um, 21%. This is still very, very impressive. And I'm sure I could write it says if, if the net income, if earnings is greater than zero, then apply a tax rate of 21%. I bet I could ask for the net income. So it's done. Let's see here. It's good. Now let me continue. I wonder if it's done. It's been updating me as it goes. It's been the model. Okay. So first of all, key assumptions, uh, it claims it's that put the assumptions in here. So this is really actually very cool. The net income it's linked that up correctly. The depreciation is linked to the deferred taxes. And that's impressive because these are all historical numbers of dead changes in working capital. It is taken.

[00:46:50] Host: Giles Male: All times 0.11.

[00:46:52] Co-Host: Ian Schnoor : Well I'm wondering what it's doing here. Down here. What did it do J 111 uh what is one J well J one so this is oh it took oh J 11 I'm sorry J 11 minus I 11 it's taken.

[00:47:10] Host: Giles Male: It's taken 2% of revenue. Is the change in um okay.

[00:47:15] Co-Host: Ian Schnoor : As the change in working capital? I would still think though, that logically, if revenue is growing, you'd expect that you need to invest more in working capital. So you'd expect that that would be an outflow, right? That should be an outflow of cash because you're spending cash to keep up your you're needing to you're needing more working capital. You need more inventory, more receivables. Whereas this is a positive number, which means that we're generating cash every year. Okay. Whatever.

[00:47:40] Host: Giles Male: It's a weird way to go about it, but it gets to an answer. I guess it's yeah.

[00:47:45] Co-Host: Ian Schnoor : It's got a CapEx figure. It's taken by CapEx. It's taken a revenue. It's taken 6% of 6% of revenue as the CapEx assumption. okay. I know now that it's hard to enter into long term debt. It just typed in dead numbers. I would have loved to see change in the long term debt from below. But it is amazing that we actually get to audit this model on the fly right now. Let's see here.

[00:48:11] Host: Giles Male: Well, I mean, even the fact that it's got the structure looking right puts it in the top bracket of what we've seen because there's only been 100%. And I think the shortcut did a reasonable job to get the structure right, even if some of the logic wasn't there 100%.

[00:48:24] Co-Host: Ian Schnoor : So what do you think, Giles? The historical balance sheet balances and you read about the future drum roll, please.

[00:48:30] Host: Giles Male: I didn't think it was. No. Oh, Giles.

[00:48:35] Co-Host: Ian Schnoor : Giles. What's going on here? Um. Yeah. I mean, it's only off by $37 million. It's really not a big deal, is it? Uh, most people wouldn't care. Yeah. Listen. So it is again. I'd have to dissect this further. It is. Off to a nice start. It is. What is it done, though? It told me the assumptions it has used. So it has used assumptions. It says it puts the assumptions in rows 112 to 130.

[00:49:05] Host: Giles Male: Or is it just. Hey. But. Yeah, well.

[00:49:09] Co-Host: Ian Schnoor : It's funny. It's so interesting. So what it did is it's, um, it put the assumptions in on an assumption, but it's not using them anywhere. Right. Like you can see here. It's not. So it entered 5%. But if I do a trace, it's not going anywhere. Right. So it didn't use that assumption. Let's try one more thing and let's get to do some valuation. This is um, should I compliment it? Should I give it a compliment like it gave me one? This is great. However, can you remove the hard coded values from the formulas and link to the assumption cells instead in rows? What did it say? 112 to 137. So let's ask it to do that. Let's ask it to replace and remove the hard coded values that it put in, and see if it can use these values. I like that it actually has a right. I have no problem with this. I told it to make an assumption and it did for revenue growth 5% freight and warehousing growth. And it's actually describing what it's doing. Like it's this it knows that this is a growth rate. This is a growth rate. These are all growth rates. It's told me that 21% is a tax rate. It's assuming that 10%. So again this is just not how deferred taxes would work. I get it, it made an assumption, but I would also hope that it would know how to make a reasonable assumption. Typically, you would not assume deferred taxes as a percentage of the cash tax and of the current tax, you know, so it is done something I'll see what it's doing here. Now. I'm doing a lot of work here. Let's see.

[00:50:45] Host: Giles Male: But again I just can't get out of my head the fact that it's like if this was a junior analyst, you'd be saying like, hey, look, you've shown some really strong signs that you know, the good signs. You've got a lot to work on. If it was a tool where I knew that the more time I invested, the more it learned and remembered I'd been. I'd be invested in this process. But I'm not even sure we're there yet with these tools. I don't know that they remember everything, so it's kind of dead time if it doesn't get things right, I.

[00:51:13] Co-Host: Ian Schnoor : Yeah, and you know what? While it's while it's looking. While it's looking. So I don't know if let's see if it's doing that. First of all, Let's see. Yeah okay. Look at that. So bang it did it.

[00:51:23] Host: Giles Male: And kudos like it's its one prompt, like you literally just have to say, hey, link to the assumptions and it's done. That's cool.

[00:51:29] Co-Host: Ian Schnoor : And by the way, I'm going to go into the formula just to double check it. I'm going to select the cell reference and press F5. Enter. It'll take me right to that cell reference. Yeah it's good. It's linked up correctly. So I'm happy with that. The model is now fully dynamic right. Let's see. Can you make the assumption values blue? Let's see if it can do that. Let's say I should have said blue font. Well look at that. I didn't even have to do it. Fantastic. So now their assumptions. That's Model Blue which is perfect. So I wasn't even as clear as I would have liked, but it was. So this is good. Now, of course, we still have a situation where the balance sheet is not balanced, the balance sheet is unbalanced. Any ideas? So I'm going to try writing in a more, you know, colloquial slang way. The balance sheet isn't balanced. Any ideas? Why not? Let's see if it can follow that you know along. Obviously prompt writing is important, but it seems to be understood. Okay, let me check the balance sheet to see what's causing the imbalance. So I like that it understands my English.

[00:52:28] Host: Giles Male: I found the issue.

[00:52:29] Co-Host: Ian Schnoor : I found it, found it, found it. Quickly I found it. The balance sheet is in balance because. Total assets. Oh, Giles. It's because the total assets don't equal the total liabilities.

[00:52:46] Host: Giles Male: Oh, this is my favorite tool.

[00:52:50] Co-Host: Ian Schnoor : That's why it doesn't balance Giles. Because the assets don't match the liabilities. Um, the problem is that the cash position is going very negative, which is true. It's creating a mismatch. So what I suspect is happening here, actually. And I didn't want to say okay. So it's actually made a bunch of oh it's.

[00:53:06] Host: Giles Male: Still changing okay.

[00:53:07] Co-Host: Ian Schnoor : Ah look what it's doing though I knew this might be the case.

[00:53:10] Host: Giles Male: So negative revolver balance.

[00:53:12] Co-Host: Ian Schnoor : Giles. Giles. Wow. Giles.

[00:53:14] Host: Giles Male: Wow. Oh yeah. So it did fix it, but I just spotted the revolver line. So if this is the balance sheet, the revolver is negative.

[00:53:23] Co-Host: Ian Schnoor : Well, so, so impressive. So impressive. Now, first of all, it's done. Something. I haven't gone through it. Now look at that. It's getting the last laugh on us now. It's probably laughing at us. It's balanced. That's great. It has. I'd like to see what it did. It's got a revolver. Now it knows that it needs to have a revolver formula, which it did. But the revolver formula is negative. So that does oh oh, 0000 is it, is it just plug Giles. Oh Giles. It plugged the balance sheet. Giles. John, this.

[00:53:58] Host: Giles Male: Is a cheat. This is a cheater.

[00:54:02] Co-Host: Ian Schnoor : It took total assets minus everything else. No, it took the total assets minus everything else.

[00:54:08] Host: Giles Male: Can't have that alcohol. That's not on.

[00:54:11] Co-Host: Ian Schnoor : No. It balanced it by it. Balanced the balance sheet by plugging it. Right. And the funny thing is that it chose to do that on the revolver, which ended up making it negative because the assets are less than liabilities, of course. Now I'm going to eyeball this to see it does appear that the debt is going down. These numbers are reasonable to me. But if we look at the cash change in cash is positive. So there shouldn't be a massive need for a revolver. Now I'm not going to spend it. Why don't we do this? Let's pause it. Let's pause it. And then I'm going to spend a minute trying to figure out why it's out of balance. And then we'll come back and show that and do some. Why don't we pause it now and I'll spend a minute.

[00:54:56] Host: Giles Male: We're back. Ian, how's it done? We're back.

[00:55:00] Co-Host: Ian Schnoor : Well, this might be the most impressive learning. Um, and I think this is a really important part for anyone to watch, to see what's going on here. And this. This causes me concern about, you know, model modeling and the dangers of two things. The dangers of having AI build a model without. There's a lot to understand. And number two, the dangers of a human not understanding what is going on. So Giles and I, we spent literally 8 or 9 or maybe ten minutes, um, going through it and figured out all the real reasons, if you recall, I know we laughed. We had a fun laugh at the fact that it did. So of course the balance sheet is not balanced, its balance is not balanced. And what it did is to balance it. It was stuck in a plug, a classic area, put in a plug. Basically, it took total assets minus everything else, and it ended up with a negative revolver. Uh, that's a disaster. There are some real meaningful errors, and I think it's important to see what these errors are and how it did not understand modeling what a model means and the integration of a company's financial statements. So I'm going to do this very, very fast, um, working exactly off what it gave us and where we got it balanced. And so we noticed that there were a bunch of issues. We found them very, very quickly. One of the things we noticed was this, um, one of So we first of all noticed that it had some links correctly, right? The on the balance sheet cash was linking to cash on the balance sheet.

[00:56:21] Co-Host: Ian Schnoor : That's great receivables. It made an assumption that the receivables were just going to grow. Um, sorry. The receivables were going to be a percentage of revenue okay. Not standard to do it this way, but not the end of the world. It took revenue and it simply said that revenue, uh, would be it said that it would take revenue. And it used an assumption here of 12%. It said 12% of revenue would be outstanding as AR. I'm okay with that. And it did the same thing for inventory. Prepaids that's how it arrived at the working capital. Now, if you look closely here, if you look closely, the receivables went down, the inventory went down, the prepaids went down a lot. When assets go down, cash goes up. So just by these three going down, that should mean that there's a lot of cash coming in. Let's go check the change in working capital on the cash flow statement. Well, to our unfortunate surprise, it didn't appreciate or recognize that there's a connection. It didn't understand that there needs to be connectivity between the balance sheet items and the cash flow statement. So it literally calculated the change in working capital as the difference in revenues multiplied by a percentage. It took the difference in revenue multiplied by 2%, but it's not connected. So what I did when we were offline is I know in real life I would tell people never, ever, ever to do what I just did.

[00:57:44] Co-Host: Ian Schnoor : Never do this in real life. You should build a working capital schedule, um, line by line, nicely organized, and link them in. Um. In fact, I should just show it here, right? This is the. This is the completed Henderson model. A real good model. Should have a nice working capital schedule. Oops. With all of the lines laid out. Very clean for receivables, inventory payables linked into the balance sheet. And the change goes into the cash flow statement. Well, what I did here just to get it working is I did all of that work in one cell. So I just took the difference in the receivables, the difference in the inventory, the difference in the prepaids, the difference in the other lines. And I'm going to copy that in here. So really the change in working capital should have been 17 million in the first year. Which. Right. That's what the answer should be because the assets went down a lot. So there should be based on what it did to the assets, that should lead to a cash infusion. So that was one big mistake. It did not understand that there needed to be connectivity between them. So I put the proper formula in and I copied it over. Okay, fine. This was good. It also calculated the CapEx. It's got CapEx. It's also taking revenues multiplied by 4%. Okay. To get it CapEx. It has another row here called other, which we're going to come back to.

[00:59:07] Co-Host: Ian Schnoor : It's showing some other cash inflow of 2 million and then a 6.6, -6.6, in investing activities. Fine in the financing activities. It's got some. This is a formula. But whatever it's doing it's simplistic but let's see where the real problems are. Now on the balance sheet. Well, on the balance sheet, what we learned was that the way it did PA is it took last year's fixed assets and it minus the depreciation. Right. J20 is the depreciation. It did that correctly. But what any good modeler would know is that PA has to be the previous year minus the depreciation. But add the CapEx. You also have to add the CapEx. And it didn't do that. It did not realize that every line on the cash flow statement has to hit the balance sheet somewhere. So let's pick that up. So that was a big one. So of course the PE dropped by the depreciation but increased by the amount of the new spend. The CapEx. So again Worrisome that it knew it knew to have a CapEx line, but didn't realize the connectivity of where that needs to go on a balance sheet. And now, since we saw this row as well, it's going to make me wonder, you know, one of the biggest all time mistakes people make on balance sheets is they don't realize that every line on the cash flow statement has to hit the balance sheet, and the change in every line on the balance sheet has to hit the cash flow statement somewhere.

[01:00:31] Co-Host: Ian Schnoor : So there's another row here called another. And let's see, it's not going anywhere. It's only going into the total. This 2 million is not going anywhere. It didn't pick that up. So let's go put it somewhere. Let's just stick it into PPE. If there's a cash infusion coming in in investing activities, it means an asset somewhere was sold off and they got some cash. So I have to reduce one of the asset lines. I'm going to just reduce PPE by that equivalent value on the cash flow statement. If cash is coming in, it means that there was an asset somewhere that was being decreased. Okay. And then I've got the other which is now picking up in my working capital. Let's just see what is now. Now, instead of being off by 31, I'm off by seven. I know that this is another one. Another connectivity issue. Right, Giles? We saw the deferred taxes it took. It calculated the deferred tax liability as just the total assets. This is unusual. You'd never do this. It took total assets multiplied by 3%. That's not how you calculate deferred taxes on a balance sheet. On a balance sheet, it should just be the prior year plus the deferred tax expense, the new deferred tax expense on the income statement. But you need to know that a good modeler needs to know that. So I'll link that in and copy that over. And now there is one more thing here.

[01:01:53] Host: Giles Male: Earnings. Yeah I think there was retained earnings wasn't it.

[01:01:57] Co-Host: Ian Schnoor : Exactly. Remember what it did. It took the prior year. It added to net income. It added to net income. And it subtracted the dividend. In theory. Correct. Remember that. But it subtracted a dividend. That's a negative number that is correct on a cash flow statement the dividend would be negative. But you can't then subtract it in your retained earnings by minusing this dividend we're adding because it is minus a minus. So it made the retained earnings go up when in fact the retained earnings needed to go down. It needed the formula needed to add the net income. But add the dividend because it's already negative. And if we do that and click enter. Now I don't believe this is important. I do not believe that the AI would have been able to yet, maybe in the future, maybe down the road. But you know, I really believe that to be a good modeler, you need to be able to check, audit, understand and be able to really quickly identify what's going on and not simply rely on the AI. So I'm really pleased. Why don't we end it here then? I'm very pleased with what it did. I'm very pleased that it was able to get me started. But as I've been saying, you know, it's got to be my partner on my shoulder that I can bounce things around, not send me down. You know, rabbit holes. And I would hope that it understands the system and the integration. But anyway, we're off. It is a good start, but it needed a lot of us to kind of get it working. Would you agree?

[01:03:24] Host: Giles Male: Yeah. I think from my side to wrap up, you know, we spent what, ten minutes, the two of us very experienced at looking at three statement models. We found it. But we know what we're looking for. And again, I'm in the same place I've been for a long time with this, which is I love where this is going. I think the future is definitely that. These tools will make our lives so much easier. But do not listen to the hype saying it builds financial models. It's gonna it's just it is building something that looks like a financial model and you have to know how to troubleshoot it. Otherwise you're going to get in a world of trouble. That's probably one.

[01:04:00] Co-Host: Ian Schnoor : Of two things for me. Number one, right now it's getting a good start. It's not good enough. The model that it built is what a brand new model would do. It made some classic models.

[01:04:10] Host: Giles Male: Absolutely.

[01:04:11] Co-Host: Ian Schnoor : Will it be able to fix those over time? Yeah, I believe it will. It'll be able to learn. But I also strongly believe that your boss, your client, you know, your colleagues are still going to say, Giles, what did you do? How did you assume CapEx and what did you do and how did you get the deferred tax working and why? Why are we doing this and that? And even if it is at the point where it's going to, I think it's actually going to be a while, a little while until it really understands all the integrations and be able to beautifully forecast. But even then, even then. Right. Giles, you're still going to have to understand what it's doing perfectly. And if it's making a mistake like a plug, be able to troubleshoot. So anyway, fascinating to see that. I hope that was helpful.

[01:04:52] Host: Giles Male: And I mean overall it's still like Elkar. Great job. It's a great tool. We're not just out here being negative about this left, right and center. Obviously there's gaps, but it's still amazing what a tool like this can do. And I feel like we're saying that with all of them at the moment, which is interesting. So sorry Paul, we didn't do anything too dodgy. None of us swore. I think we've held up the reputation of your podcast.

[01:05:14] Co-Host: Ian Schnoor : We even had fun with Elohim, didn't we?

[01:05:16] Host: Giles Male: Oh, yeah. Not. We can't tell him we had too much fun. He won't come back.

[01:05:19] Co-Host: Ian Schnoor : I hope. No, do not tell him we had more fun than if he was here. I mean, we had him.

[01:05:26] Host: Giles Male: Just slightly less fun than if he would have been here. But we still had lots of fun. That's what we'll say.

[01:05:30] Co-Host: Ian Schnoor : But you were rolling over a couple times with the. With things like the plug. But, uh, anyway, it'll be better when he's back. In the meantime, that was a great episode. A lot of fun and really hopefully interesting to see, um, where this is headed.

[01:05:43] Host: Giles Male: All right. Thanks, everyone, for watching, listening. And we'll see you next time. Bye bye.

[01:05:47] Co-Host: Ian Schnoor : Thanks, everyone. See you next time. Bye bye.

[01:05:50] Music: The mod squad. We are the Mod Squad.