AI Financial Modeling Test for Finance Pros to Understand the Limitations Using Real Tool Comparison

Speaker A: Foreign.

Speaker B: The Mod Squad, featuring Ian Schnorr, Executive director of Financial Modeling Institute.

Speaker C: Giles, male, humble MVP and co founder

Speaker B: of Full Stack Modeler, and Paul Barnhurst,

Speaker C: the FP and a guy. We're having a bake off today. Giles, in and I are all going to run the case and then we're going to come back at the end and score them on the structure. How did they look aesthetically? Were there any critical errors? And all kinds of things.

Speaker A: I'll be leaning into Anthropic. Uh, I've been a big Claude fan for a long time. I'll be using 4.8 and I'll be doing ChatGPT.

Speaker C: And they don't give you the model in. In Excel.

Speaker B: Which model do I use? I ran a webinar and I said, how many of you here are finding yourself running one model and then using a second one to check the first one to kind of validate?

Speaker C: Go ahead and build the model in five minutes, get fired and hit. Welcome to another episode of Financial Modelers Corner. This week we have the Mod Squad with us, so I'm thrilled to be joined once again by Giles, Mel and Insh.

Speaker B: Nor.

Speaker C: Giles, how you been?

Speaker A: Good. Uh, I feel like I'm in a beard competition with you now. I've got a little bit of a way to go, but, you know, be scared.

Speaker C: Is your goal to see how long you can get it? Is that the plan?

Speaker A: I've hit this phase where it doesn't actually feel like it's growing. I just feel like I look like I'm homeless, but it's uncontrollable at times.

Speaker C: So. Yeah. And how have you been?

Speaker B: Great. Great. Missing you guys. But I did get a chance to see and catch up with Giles recently at the Global Excel Summer Summit in London in exactly a month ago. And that was a lot of fun and a lot of great learning and nice to catch up with. Um, the Global Excel and modeling communities. Life is busy. How could it not be? I mean, everybody that I know who's working in business, accounting and finance right now is still kind of inundated, overwhelmed, tired with, excited with this world of AI. Right? I mean, it's all of the above. We're trying to do our jobs, run our businesses, run our organizations, manage our lives and learn and keep up with. Right? It'd be one thing if we just had to learn AI, but it's not about learning AI. Uh, we have to keep up with it because it's changing so fast. It's like whatever skill you learn. And Giles you're probably the best dog with whatever you skill you learned last month. Well, now there's a whole set of new things and so now you're trying to keep up and figure out what you, what you should invest your time in and learning like it's exhausting. No, Giles.

Speaker A: Yeah, I agree. Well, we've talked about it before. Uh, I'm kind of uh, almost a fully fledged co pilot trainer now and I think it'll extend to Claude. I know Paul, you're doing stuff as well and just trying to keep up with what changed in the last seven days. I mean there were huge announcements from Microsoft two days ago that change a whole bunch of stuff. So yeah, it is a non stop battle just to stay broadly up to date. It's crazy.

Speaker B: And a different, it's a different level of like exhaustion, isn't it?

Speaker A: Sort of.

Speaker B: It's a. Ah, yeah, I read.

Speaker A: What was the term you used? Maybe it was exhaustion, like AI fatigue or fatigue.

Speaker B: Yeah, fatigue you. That's right. It's like a fatigue you feel. Right, like.

Speaker A: Yeah, but I. And again, I know we're repeating old ground. I wasn't over the XL fatigue. Regex has been on my list for years and now I've just got to park all of that and become an xi, an AI guru.

Speaker C: Agreed. So we'll continue this discussion around AI a little bit more in some different areas. But in the meantime what we want to do is we're having a bake off today. So we're really excited about it, what we're going to do and then I'll turn it over to IN to explain the case and we'll kick it off is we've selected a case from fmi. Giles, M in and I are all going to run the case. We'll each share what tool we're going to use in a minute and then we're going to come back at the end and we're going to look at how they did and we're going to score them on some things like how good was the structure, how did they look aesthetically, you know, were there any critical errors where it's like this just, you know, fell because the balance sheet doesn't balance and all kinds of things. So that's the basic idea. So what I'm going to do is I'm going to turn it over to in. But before we do that, we're gonna have each person say what tool they're going to be testing today. So Giles, what are you testing with?

Speaker A: I'll be leaning into Anthropic. So, uh, I've been a big Claude fan for a long time. I'll be using 4.8. I really wanted to be able to join you today and use Fable, but for, uh, for well known reasons. Thank you, US Government.

Speaker B: You're welcome. Yeah, I can't because I'm the only

Speaker C: US citizen here, so I'll take the blame. The other thing I'll say is you train people on Co Pilot, but you're doing Claude. Okay, we'll leave that for later. What tool are you testing?

Speaker B: I think, uh, we talked about it. I'm going to use Co Pilot, but I'm going to use the um. Did we say that? Oh, no. Uh, Giles, you said that you want me. Right. Pod four. Eight within Copilot, though, because we expect that it's going to generate a different model. We're going to look at the Henderson model again to keep it consistent with what we've been testing over the last six months. But we're going to try three current modern tools. So, Giles, you're going to use, uh, which anthropic tool are you going to use?

Speaker A: So I'll be in the Claude app in Excel and I'll use Opus 4.8 as the model. That'll be that one. And um, if you can do the same through the app. I think that was what we said, wasn't it? So you're going to use Copilot in Excel. Choose 4.8. Yeah, perfect.

Speaker B: Yes.

Speaker A: Yep.

Speaker B: And I'll do it that way.

Speaker C: I'll be doing Chat GPT and they don't give you the model in Excel, they just allow you to select. Do you want it to do fast standard or heavy reasoning? So I'll be doing heavy. Well, why don't you take us through the case here? Sure.

Speaker B: You want to share this screen?

Speaker C: Then we'll. I'll kick them up. So I'll bring it up on the screen and you can walk us through this thing. Right.

Speaker B: So again, we're keeping it consistent. Anyone who's watching before, we're going to use the Henderson I Manufacturing Company model again. And this is what we all have. We all have the same file. We're all of this exact same file and we're all going to give it the exact same prompt. So in our Excel we have a sheet called model. And on this sheet we simply have the last three years of historical financial statements. We have the income statement, we have the cash flow statement, and then we have the balance sheet. That's it. That's all that we have on this sheet, um, and then the rest is blank. And then what I did is there's a case study. Where's the case study? Here's the case study. The case study is what an exam is candidate would have been given. And it's a two page PDF case study that talks about the company. It talks about their, their history. It provides information about the company's sales, about their operating costs around their fixed assets and depreciation, their working capital, their income tax, their debt, their equity. And what I did is I took this case study and I copied it into a separate sheet. I just find it works a little easier typically. I copied the case study historic, uh, into one sheet as text. It's not nicely formatted. It's not numbers, it's just, it's just gobbledygook strings of text in cells. And then there are instructions at the bottom just like this. I just copied the full case. And then what we're all going to do and I'll show you and I, I think I was told I am going to be testing right here. This is where you want me to go write giles into Opus 4.8. So I am going to run Opus 4.8, you can see and literally I'm going to put in this prompt and we all have the same prompt. It says on the case tab you have been provided with information about a company called Henderson. You have also been provided with three years of historicals. On the model tab, build a five year forecast model with all the required schedules, revenues, cost, depreciation, tax, working capital, debt, equity. And there are Instructions in cells B60 to B66 here, right at. And so there are some. So we'll see how well it incorporates these additional instructions. Over the last month or two, it's done a pretty good job building scenarios, adding an assumption page, etc. That's what we're all going to do. So I'll stop my share now, but we're going to do that and then at the end of the episode we will see how each of these tools performed. Right, Paul?

Speaker C: Yep. So what going to happen? We're going to pause here for a minute. We're all going to get it kicked off, answer any questions our AI asks us, let it start running, we'll come back and have the conversation. So we'll be back here in a minute, but we're going to go ahead and pause it for a second while we do that. So you can see right now. And this is something I actually did with Copilot's new personalization. One of the instructions I put it is please auto fit the width of each column when you're done because it

Speaker B: does this all the time.

Speaker C: I don't know if you guys have noticed this, but. Yeah, right. So tiny thing. Let's let me just expand it out.

Speaker B: That's a beauty. I, I, I encourage you to hand that into your boss that way with

Speaker C: all those, you know, you could see it said. But it did mention it fixed the print ranges.

Speaker A: Nice.

Speaker C: So supposedly it will print. You can't read it, but it will print.

Speaker B: So, uh, first of all, some decent points for formatting. Not bad. I mean it's, it's try, it's made an effort, right, to try and do something presentable.

Speaker C: Let me make it not quite that big. Let's go there. So what, what how they laid it out. We can see 26, 27, 28. It did a summary. It didn't do it on the model sheet. I would have liked to see. Well did it did bring it in here as well. It looks like very interesting that it,

Speaker B: that it kind of collapsed the columns

Speaker C: and made them so it looks like interesting enough. It did it here. This is its summary. Okay, so let's go. I don't like the order. It's model assumptions, summary.

Speaker B: Not at all.

Speaker C: It's summary, assumptions, model.

Speaker B: Exactly. It went opposite for some reason.

Speaker C: Okay, so I'm just to switch that around real quick just as we read through this and I'll put the case at the back. All right, so let's go ahead. It provided a summary clear enough. It did. I would say decent. Okay, EBITDA margin, ebit, Netcom ending cash, total debt, net capacity utilization.

Speaker B: Let's see. Can you click on one of the best case numbers? Go down and click on some of the best. I wonder what it did click.

Speaker C: It looks like all the numbers are coming from below. So it put a summary up here.

Speaker B: Well, I'm very curious to know how it's linking to that.

Speaker C: That's what I'm trying to get.

Speaker B: The best and a worst at the same. It was in row 80.

Speaker C: So let me take one.

Speaker B: Let's just oh, 41 and then 81. B41 bracket.

Speaker C: Give me a second. All right, so like net revenue here. So did the what? That doesn't make any sense. Am I okay, uh, so hold on. B41. Let's go to B41. And yeah, so it did a calculation here for net revenue, B38. So units sold times gross price minus freight divided by a thousand.

Speaker B: Yeah, you don't really want to see any calculations like this on a summary.

Speaker C: Correct. And so then this one. So it looks like where is that coming from? Here is it did the calculate. So this says capacity utilization, but it's where it did the calculations for the base case. Then it did the calculations for the best case here.

Speaker B: So it's.

Speaker C: But it did them off the assumption.

Speaker B: It's basically built three separate models. It didn't know how to run a base best and worst off one model with scenario management or sensitivity tables or switches. It basically reran all the calculations three different ways to get a base best.

Speaker C: That's what it looks like it did here, but it linked into the model.

Speaker A: Okay, so it's given you a switch on the model, has it?

Speaker C: No, no, no, not a switch. What I'm talking. So like this beginning revolver links to the model. The model doesn't have switches. It's decided all three of them. The bank debt. Well that makes sense. The bank debt revolver from 25. Your beginning is always going to be the same because it's an actual.

Speaker A: But what's it done on the forecast?

Speaker C: Terrible way to try to trace it out.

Speaker A: But what's it done on the forecast? How is it picking one of the three models with the three ampers?

Speaker C: Um, it just linked it to the schedules. It's built on this page. So it did the work on this page of one model. Then it recreated three for each of the cases. Are they consistent? Not sure yet. Okay, your look.

Speaker B: Done a decent job on the formatting, I guess. Present. Right.

Speaker C: So what, so if we go through this, let's just run through its main model and kind of flow. Okay.

Speaker A: Do you mind zooming in a little bit just for my eyes?

Speaker C: Yeah, yeah, I'll zoom in a little bit. How's that?

Speaker A: Yeah, great.

Speaker C: Okay, so what we have is we got our income statement. That's all linked below. That all seems to make sense. I'm not going to go through numbers.

Speaker B: Right.

Speaker C: I just want to see. It all appears to be linked.

Speaker A: Well, you got some interesting current tax numbers going on there.

Speaker C: Yeah, we'll, we'll, we'll look at the schedules. I think it did this right in the sense of you got your cash flow statement. It's all linked below. You have your balance sheet. It's all linked below.

Speaker B: It's using uh, the wrong color coding, but it's okay.

Speaker C: Balance sheet doesn't balance. I thought it didn't for a minute. I was like, okay, so it balances

Speaker A: just go up a little bit. Going up a little Bit just to the cash. What was the cash line?

Speaker C: Yeah, give me once. Let me go up to that first. You want to see cashier?

Speaker A: I just. It's always the first thing that I used to notice sometimes you had lumbers on cash and the revolver and God knows what else.

Speaker C: So the cash goes to zero and stays there which is a problem for

Speaker A: all five years leaning on the revolver. That's the check that I wanted to see. So. So you never go cash positive. You don't have a minimum balance.

Speaker C: Yeah. I mean you should be able to. You should be paying it off or. But yeah, get it. So what it's done, which I do like is this is one of the few times I've seen where it did not do any calculations on these schedules. Now it did create three calculation details for each scenario, which is bad.

Speaker B: Sorry, it did not. It did not build. Uh.

Speaker C: I don't see any calculations taking place outside of.

Speaker A: Yeah, the structural.

Speaker C: On the three statements. It builds.

Speaker B: That's good. Where the schedules are down below.

Speaker C: Now we're into the schedule. So what I was going to do is I'm just going to hide these columns so we can. I can bring this over a little bit and kind of freeze the pain maybe here just as we're moving. All right, so that's done. So. All right. So it went off the assumptions and did. Did the math there for units sold which I think there was a capacity thing. So that seems to you know, look roughly right. The revenue goes down. I think we're. That looks freight and warehousing. I mean as I look at this first part goes up to 100% capacity utilization and stops.

Speaker B: It feels right. That's what I would have expected for this case. Yeah.

Speaker C: So I think the revenue schedule, just a high level without going through every row looks fine. Right. I don't see any. Has any real issues. Now let's go to the cost schedule.

Speaker B: It's doing a nice job.

Speaker C: Raw materials.

Speaker A: Yeah.

Speaker C: What did it do here? All right, assumptions.

Speaker B: It's doing a nice job.

Speaker C: It seems reasonable at a high level. I mean costs are going up as revenue.

Speaker B: Yeah, I think it's fine.

Speaker A: You've got. You've got a single cell inflation assumption somewhere that I think it's just linking everything to.

Speaker C: Yeah, yeah. We can look at. So if we look at assumptions. Let's just take a minute. See what. So they did the assumptions for base, best and worst. They did gross price, multiplier, volume growth, annual growth thereafter. I'm not sure. Okay. They did 20, 26 and then every year after inflation they made assumptions for each case. They made assumptions for dso, DIO and dpo. That's a reasonable set of assumptions to vary. So that all seems fine. You know annual case inputs. These were the inputs that were given mention and it. I like that it gives you the notes. Case B11K gives me the cells that it took it from so I can validate it. So I like the assumption page there. Same with the operating. It says hey, I took them all from there. So it tells me where it. What's the note? You know, assumption based on run rate and it goes through and gives all its assumptions. This page looks fine.

Speaker A: Or you got. I mean you could be pedantic and say it's got calculations on the inputs

Speaker B: but you don't love. Yeah, I mean I don't love that

Speaker C: but historical driver calculations I wouldn't have done.

Speaker B: Okay, that pulls that right out of the case. The 594 was in the case study. It just hard catered it in. That's not very good.

Speaker C: Yeah, so that, that's what we have.

Speaker A: Any.

Speaker C: Anything else? You guys there, you can see that. Do you know what it looks doing an index? Oh it's just pulling it from above.

Speaker A: It looks pretty okay. I mean uh. Probably a bit of an improvement on a lot of. Well actually a lot of improvement on what we saw last year. Still some of the same minor issues I guess the. Some of the formatting, some of the choices to hard code numbers pulled in different directions. Not perfect. I mean you've got a balancing balance sheet and the numbers looked sensible.

Speaker C: Yep. So any other. Just as I was scrolling down how did they do their depreciation?

Speaker A: Oh uh. They've got. So that's interesting. They've got a semi fixed range that's. I mean that's a reasonably intermediate modeling technique to semi fix a range to do depreciation over time.

Speaker C: I would like to see escape it but it's not bad.

Speaker B: Where's the new asset depreciation?

Speaker C: All they did is they basically did a sum of the two years and divided it by an assumption.

Speaker A: Yeah but look at the next column over. Go to the next column over to the right. Now it's years of capex. Yeah. Go over to the right and then hit F2. So it's. That's what I'm saying. Like that's impressive that it. It can do a modeling technique.

Speaker C: Yeah.

Speaker B: Rolling each year it's a very subtle technique to lock the first cell reference and not the second one. So you.

Speaker C: Yeah, yeah, yeah. It was smart Enough. So yeah.

Speaker B: Yeah, that's good. All right, great starting point. Do you wanna.

Speaker A: I can go next. I think Paul, you need to.

Speaker C: I need to stop sharing and share you which I believe is this one here.

Speaker A: I need to bear with me. Uh, I need to share my real quick.

Speaker C: Well, you're going to share overall if you were handed this. I mean we haven't gone through it in detail but just initial thoughts, kind of final thoughts. I think for me, you know a couple things I really like that at least did individual schedules. That's an improvement over a lot of what we saw last year. I hate the way it did scenarios of detailed case calculations and linking them. M. There's linking issues. I would have done a little more detail on the depreciation. So there's some. There's some messy things but overall it's pretty good. Right in the hand of the right modeler. You could take this and finish it up.

Speaker B: I'm not surprised. I'm not surprised to see this. It's done an amazing job in 20 minutes or 15 minutes and yet I beg people not to ever hand that into your client or your boss. And people will. You're going to get. You're going to get. It is not going to be a good day when you hand in something like that. Like it's off to a great start. Um, and now you'll probably spend an hour or two hours learning m it understanding what it did so you can answer the questions about what's going on. How is it built? You're going to find issues you want to improve formatting issues. Like you will spend time and you can either iterate with. With uh, with the tool to have the tool do it or you'll just do it yourself. But you need to know what to look for and you need to know where there are challenges. So yeah, I mean I'm not surprised. It looks.

Speaker C: And one last thing. I do like that it's now it has a check section. There's a few more can add but it has a cash roll forward check and a debt schedule tie.

Speaker B: Click on one of the balance sheet checks in the third year, let's say. Is it. Is it? Uh, yeah. Great. Okay.

Speaker A: Charles, were you in all of their uh, defenses in terms of formatting? You know we're not throwing full capabilities at this because you do have custom instructions and skills files and, and all of this stuff that you can add. So we could. I mean 20 minutes like you said

Speaker C: you could m improve this quite a bit with skills.

Speaker A: Do you know what that Would be a really interesting next episode. We go away, we do the same thing, but we. We put everything on it. We. We get. Get our custom kind of skills and instructions in there and better prompting that be.

Speaker C: We should do that at some point. I still got to build out those

Speaker B: skills and that takes. So that takes a lot more learning. Right? Um, correct. It's one thing to know how to just put in, you know, a pretty basic prompt like we did. It's a whole other, you know, skill set to know how to go in and build skills and have a library and a reply like now you're. Anyway, it's, um. That's great. Giles. How did your example for.

Speaker C: I know someone to build 81 skills for a project they're doing and others built 19. That's a lot of time. All right, we're going to turn it over to Giles now.

Speaker A: So I haven't touched it. I haven't changed the order of anything. So we'll just say why don't we start. So I have.

Speaker C: So you got summary last as well?

Speaker A: I got summary last. I actually think the order is okay because it's.

Speaker C: You enlarge it a little bit. For my old eyes, it's treated the

Speaker A: original input, uh, tab as the output essentially. So actually you do have assumptions, schedules, output and summary. I think that's fine. Given me a nice little summary, five year kind of cumulative numbers and then the final year, uh, which. Which is fine. Just at a high level. If you. So this is my five year forecast here. Formatted nicely, I think. I mean this. Let me just go to. Sorry about that. I just wanted to see if you look here on the right, all formula

Speaker C: driven, although it used a let formula in the bottle. That seems a little bit.

Speaker B: Where did you see a lead formula?

Speaker A: Uh, but you know what? It might. It might. That's for the cash. So if you were, uh, going to

Speaker B: see that though, I'm curious. Oh my gosh.

Speaker C: Holy.

Speaker B: That's what it did on your.

Speaker C: Wow.

Speaker B: That's what it did on your.

Speaker C: This just.

Speaker B: Wow.

Speaker C: Honestly, that's not all that bad if you understand it.

Speaker B: No. Well, it just completely proves and makes my point every single time. This is not how you want to build the revolver section on, uh, so many issues with this. First of all, that should not be right on the financing section of a cash flow statement. And second of all, um, really, are you going to use a let function, One of the newer, more complex functions, um, in Excel when. When your client or boss might just want to see a simple step by Step add up of what you're doing, this is going to be hard to audit and understand. I'm not liking it even though it's probably right. Jaws.

Speaker A: Well, I say it's really interesting. I obviously, I agree. This is not how I would model this at all. What we saw almost consistently last year was that a lot of that final cash balance or revolver balance stuff was solved in the financial statements. So you could argue if you're going to go down that route. I mean at least a let is trying to make the formula a bit more readable. But yeah, I mean I wouldn't do this.

Speaker C: Wait, it has a note there. What does the note say? It put a note on that cell. You didn't put that there. Right.

Speaker A: Um, uh, that's a flag.

Speaker C: Oh, you add. Okay. I thought it was like was there an explanation note or something? I was going to be impressed.

Speaker B: You got excited there Paul, for a second you thought hey it's.

Speaker C: I did. I was like wow, it's now giving me explanations.

Speaker A: So other than other than that obviously that is a big um, I think area of concern. It's. It's pulling from the schedules. Uh, I do.

Speaker C: Wait, didn't we just hard code A0 up there instead of pulling from a schedule. Um, pull down where there's all zeros. I thought that was a hard code

Speaker A: balancing for a second.

Speaker C: There was a keep going right there. One of those looked like it was all zeros.

Speaker A: There is. Well that's okay.

Speaker C: Maybe I, it's. I think it's the common shares issuance that was all zeros.

Speaker A: I mean if you, if you look at the output this broadly aligns with what Paul's model saw. So you don't have a cash balance. You are drawing on the revolver year after year. Little bits look sensible like the, the common shares don't change. The retained earnings is going up. You can see that the amortization on the senior debt. So that's coming down every period like that looks. That looks good. I think that's good. And then schedules wise. Yeah, good. I mean it's again I'm a fast kind of modelist. I would much rather see flags and blocks, better blocks than this. It's pulling a lot directly from the assumptions which again is very similar to what Paul saw which is not my preference but it looks, I mean on the face of it. Let's go back.

Speaker C: You could with skills give it to use the face stamp the fat not face the fast standards.

Speaker A: Yeah, you absolutely could. But that all looks pretty consistent. And what are my assumptions look like so here's big improvement on your one if this does work I've got a scenario switch I'm assuming if I change that to two goes to best how's it doing that? Exactly how I would do it Index you could use choose index switch whatever you like probably not switch but choose

Speaker C: when yeah you could I wouldn't use switch you could use a nested if Giles

Speaker A: uh but I think that's impressive so it's got a proper scenario tool I haven't got time to check everything it's doing the same sort of thing with inflation here of various things linking back to an inflation rate formatted this is very much in line with how half of the Excel financial modeling world formats always either blue fill or yellow font I think uh. I'm pretty. I'm pretty happy with that it took a lot longer than than the two models you ran but I think that's

Speaker C: looking pretty good I think what I like what I like it did a better job with its base best and worst case no question I think they were both similar on the other one area I do like on the assumptions page that mine did is it told me where it pulled it from the document and I didn't ask it to do that like it came from this cell or we used averages so I could trace it all out. On the whole I think this one followed a little more some best practices although I don't see did they give us a check section like the other one did Like I haven't.

Speaker A: I haven't seen one and. And again I think that that's a huge plus point for yours the fact I mean I do have the balance

Speaker C: sheet check yeah you have the one

Speaker A: I don't have anything else I don't

Speaker C: think I probably maybe lean slightly yours so far but there's plus and minuses

Speaker A: in both of them I think because of the scenario the Exactly. Not. Not that I'm. I'm not trying to defend my tool because it's the tool no no no I I agree with scenario things probably a big thing because that's kind of fundamental to how do you actually build scenarios in. In a financial.

Speaker C: Agree. That's the. If there's a flaw in the one I did it's the way it did the. The scenarios is just a mess.

Speaker B: That's a.

Speaker C: A D minus type work right.

Speaker A: Just bad two out of two balancing balance sheets even that's a step up from when we do you remember when

Speaker B: we started months ago they couldn't even build anything I mean, it was awful. It was horrible. Six months ago.

Speaker C: We remember one time in said, are we really going to show this? I'm embarrassed to show this. That tool has shut down. So we. We could name it now. We won't, but, uh, to where we're at now. So it's a huge improvement. All right. Why don't you show us what you got? We'll spend a few minutes there and we'll. Then we'll wrap up.

Speaker B: So mine is definitely formatted the worst out of the three of yours. But there's something similar. Like again, I used, um, Opus 4:8 right in copilot. And there's something similar feeling about our two. Right. Um, trials. There's a. There's a switch over here. It's going into. Well, it's actually going into. The switch is actually only going into sales prices and sales volumes. So here they are. And it uses shoes function. It's okay. I like that. Very nice. I looked at these formulas. They're mostly fine. I mean, this is 2026. And they're either. They're. They're not using color differences. It's. It's okay. Um, not super clear. If I go to the schedules, then there's a sheet of schedules not very long. It just has some very simple schedules with pricing, some cost assumptions, you know, long formulas. Here, look what it did for depreciation. It. Okay, let's see. I mean, this is all good working capital.

Speaker C: You do a depreciation schedule? You did yours do one? I think that's the first one that actually did a schedule by year. Did your Giles.

Speaker B: Uh, mine built a summary sheet. I don't really understand. It doesn't look very good. It built a summary sheet for five years under these five items. So anyway, it's. Oh, the base best and worst. The best and worst cases are. Are just, you know, dead numbers. So we need to. To realize that. That they're not actually adapting. They're dead numbers. It typed in. I don't know. I mean, I. Listen, I think it's off to a nice. Either the financial statements look fine. They're a little. They're not quite client ready yet, but they seem like they're okay. All these cells are links. I looked at it quickly before. It does look like, you know, as after we ran it, I was looking at it, it does look like it's built some pretty good formulas.

Speaker C: I like the cash available before Revolver. That kind of help or sell. That's right. But it looks.

Speaker B: I haven't found any big errors. I Have only been looking at it for 10 minutes, but I haven't been found any big errors. It's. It's off to a nice start. Uh, uh, here's got the base, best and worst. And it's typed in dead numbers. There's no formulas here. It's just so. I don't know. I don't like that is a base case. So I just have to trust that they're working base, best, worst. I just have to trust that they're working properly. I don't know. I would be happy to start to give it. Use this as my starting point. Sorry, Charles.

Speaker A: Isn't that fascinating though? Which was kind of why we did this deliberately. That you and I have both used the same underlying LLM 4.8. But uh, mine is directly through the CLAUDE add in and yours is through the copilot add in. And yet it must just be the additional context and whatever else is going on in that. In that processing step before and after.

Speaker C: I think more than that, a lot of it also comes back to one, what skills it's using. So what skills does copilot have inside what tools are it's using, how it's pulling the data. But the other, it speaks to the fact that this is probabilistic in nature. And that's why you, you, you. Have you guys heard the term AI harness?

Speaker A: No.

Speaker C: Giving AI a harness is basically. It's everything beyond the prompt, all the context you're giving a files and the clod skills are basically saying. Because right, if you give a harness, if you're climbing or whatever you're doing, a harness restrains you and protects you.

Speaker B: And it's kind of similar to that,

Speaker C: to AI it needs that additional structure and guidance. Or we end up with these three very different versions. I'm sure if we all build a lot of skills, we could get much closer to each other between these three models. There'd still be ones that would be better and differences. Uh, we could close some of that gap.

Speaker B: Yeah, yeah, yeah.

Speaker C: That's a whole new thing. People are expected to learn. Now you got to know how to model really well. But now go ahead and figure out how to do AI really well and

Speaker B: then figure out how to be a good auditor.

Speaker C: Now instead of someone else auditing it, you got it. Audit the whole thing. Not that you didn't audit before, but in a different way.

Speaker B: And you're gonna have to know.

Speaker C: And auditing someone else's is very different.

Speaker B: It's very different.

Speaker C: Right?

Speaker B: Like for our brains, for many of us, that have been building things, uh, or building. It's a very different learning process in your brain to build and to fight that the struggle and the fight is important. Right. When you're creating, that's the creative process. And a lot of people's learning is absorbed and it happens through osmosis, uh, during the struggle, during the fight of figuring it out. And that's important. So I know for me, that's how I often learn things. By fighting and struggling and learning through the wins and the losses to get there. And then I'm very, very smart about a topic at the end of it. For me, if you gave me a fixed model, um, and you just said learn it in the same level of intimacy and just review it. I don't know that my brain can actually get to the same level of confidence with it or that I can have the same level of deep understanding with it by trying to understand something. Now I'm going to have to because that's the way the world's going. And we will. But we all have to find a way. You're right. To look at this and still rip it apart. Understand it, know what it's doing right, what it's doing wrong, and. And be able to defend it as if it's our own. And that's a bit of a big mind shift. I don't know if you agree with that, Giles, but that's a shift for me.

Speaker A: Yeah, I. I do agree. And, um, and the more we look at this. Yeah. I think we've all been on a journey since. Is this like the wrap up session? Is it worth sharing? I feel like we're in the wrap up session, Paul.

Speaker C: We. Yeah.

Speaker A: All right, that's. Let's share our closing thoughts. Um, I think back to when we started and it was longer than six months ago. And at that time I did a year ago now.

Speaker C: Is it really approached this?

Speaker B: Yeah, nine, ten months.

Speaker C: M. We did. Was October really okay? Which means we recorded it in September, which probably means we first discussed it in August. Late August. Yeah.

Speaker A: We were planning, I think back to when we started it and this, this whole concept of agents that you can draw on within an app and like it. It wasn't there. And that's why I think we started with third party tools because they were the only ones that had kind of put that layer on. So the world has completely changed. I think we can see clear improvement. The fact that I think we just all had balancing balance sheets. Awesome.

Speaker C: And.

Speaker A: And you know, the more we get into this, the more I'm convinced that focusing this is not a criticism of what we've just done, but the focus on, can it build me a financial model so that I don't have to do any of the work just feels so like it's not the pot of gold at the end of the rainbow for me. And that's partly now because I'm looking at that space and going, God, you've got teams up to their eyeballs. And all this other stuff. Do you remember Ian Bennett talking about all the value you could get from all of the other areas of a modeling project? And I think I'm probably even more convinced that that is where the value is at the moment, at least. And you know what? Figure all that stuff out if you're a big company. And then by the time you've done all of that, we'll be on Fable, we'll be on mythos version 9, and you won't have to get out of bed.

Speaker B: Right. You'll think it.

Speaker C: You'll just have Alpha, no name.

Speaker B: You'll think something, and it will develop, and you'll. You know.

Speaker A: Yeah.

Speaker B: Yeah, that's a scary thought.

Speaker C: If they can read my thoughts. Any last thoughts from you on this? And I think we. We got Giles, uh, dissertation. Let's move to you.

Speaker B: No, I agree. I agree with Giles. I think this is a different world than nine months ago, when we started, when. When we didn't even. It was only at the end of the year. Remember, it was at the end of last year when the LLMs announced that they were starting to incorporate. It wasn't even considered in the fall. We were looking at all these other tools, and I. I haven't kept up with how they're all performing, but I suspect it's a challenge for many of them. You know, where they need to differentiate themselves, obviously, if they're going to survive. Now people are desperately learning, going deeper, as you said, into A.I. uh, they're trying to code, they're trying to learn skills. They're trying to kind of get under, you know, and. And think about it in terms of automating their day and their. And their monthly clothes and their life and their emails and connecting it all together. We weren't talking about anything like that six, nine months ago. And from what we're seeing today, obviously, these three models that we built today, I don't know if there's a real winner. I mean, they're all similar, uh, I would say, but they are much better than what we looked at nine months ago. But compared to the models From February, March.

Speaker C: Yeah, a little bit.

Speaker B: The balance sheet's balance, which is nice. But you're still. We're still with all of them. None of these is ready to hand in. And that's even scary if people think that they have a models rated. Because you're going to. You're missing the point of. Of the learning process, I think.

Speaker C: And yeah, uh, I don't think there's a market improvement, like you said, from Opus 4. 7 to what we did today.

Speaker A: But I'd be really intrigued if you two are up for it. I think we should do. Whether it's the next episode, whatever. I think we should do it like, okay, let's give it our best shot. Like, let's actually put all of the custom instructions we would think of and um, um, skills files and whatever else. Because I'd be really intrigued to be like, with our best efforts, how good could we get it straight away?

Speaker B: But that takes a lot of skill on our part to know modeling, to know accounting, and to know how to really be a strong musician, uh, with this tool, to work it, to really work our models and get right. That's going to take a lot of time and effort to get there. And I'm not saying we shouldn't. We should, but that's not free like that. That comes with investment, right? That's a real investment.

Speaker A: We're just invoicing, Paul, for our time, aren't we?

Speaker C: Exactly right. Yeah.

Speaker B: Hours and hours.

Speaker C: I'm going to Anthropic.

Speaker A: Yeah, let's get Nito to pay for it. Uh, what are your closing thoughts, Paul?

Speaker C: I think it's similar to the two of you. One thing I want to say is. Do you remember when we tested Copilot online?

Speaker B: Right.

Speaker A: That was. That was an episode.

Speaker C: Think how far we've come from that. Like a lot of people have bad mouth. Copilot. I've been guilty of it. In general. I think Claude's a better tool right now. And I think most people do. That's pretty clear. But how far it's come, that's what I keep telling people, is you can get value out of it. I don't care which one you're using. I think one message, you can get value out of all of them. Two, none of them on their own are production ready. Could you potentially get there with skills for certain tasks, for certain things? No doubt. Full financial model, maybe, depending on what you're doing. But even if you do, you still have to know how to audit it. You still know I have to check it I. I'm, um. Just like the two of you. I say AI Is a magnifier. The better you know what you're doing, the more you can get out of it. The one thing I'm so sick of is the AI Slop we're seeing all over the place of. Do this in five minutes, and I will repeat what I've been saying all along. Uh, go ahead and build the model in five minutes, get fired in 10. You know, it's just stupid. If that's. That's the way you think these tools work. It's not.

Speaker B: No.

Speaker C: There's not a magic easy answer to anything. And that's true with modeling. But you can get huge benefit if you're willing to pay the price, I think is the message.

Speaker B: Yeah, I agree with that. Gents, always great to see you. We are the master.