TrufflePig AI vs Excel for Finance Teams from Building Models to Real-Time DCFs with Ian Schnoor

In this episode of Financial Modeler’s Corner, hosts Paul Barnhurst and Ian Schnoor continue their exploration of AI tools for financial modeling. This time, they test Trufflepig, a tool designed to help financial analysts automate spreadsheet tasks while still allowing them to focus on the insights. The hosts test Trufflepig on various financial modeling tasks, discussing its performance and how it compares to other tools they've used. They cover tasks such as building a DCF model for Nvidia, generating executive summaries, and creating a financial forecast. While Trufflepig performs well in some areas, there are still challenges that need to be addressed, particularly with certain financial concepts like working capital and net income.

Expect to Learn

• A review of Trufflepig, an AI-powered spreadsheet tool.

• How Trufflepig performs on real-world financial tasks.

• The benefits and limitations of AI tools in financial modeling.

• Insights into how Trufflepig compares with other financial modeling tools.

Here are a few quotes from the episode:

• “The biggest advantage of using Trufflepig is that it helps you with the repetitive tasks, so you can focus on higher-level analysis.” - Ian Schnoor

• “Trufflepig is an interesting tool, but as with any new software, there’s a learning curve. But if it delivers value, it’s worth it.” - Ian Schnoor
  
  

Trufflepig is a promising tool for financial professionals, particularly those looking to automate repetitive spreadsheet tasks. While it performs well on basic tasks like building DCF models and creating executive summaries, there are areas for improvement, especially around financial concepts like working capital and the handling of complex formulas.

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

Trufflepig: https://Trufflepig.ai/

In today’s episode:
[01:40] – Review of Previously Tested AI Tools
[05:15] – Trufflepig’s Positioning and Messaging
[12:00] – Trufflepig Attempts the eSports Modeling Case
[22:00] – Challenges with TEXTSPLIT and Modern Excel Functions
[30:50] – Executive Summary Generation
[40:01] – Data Sourcing and Web Pulling Behavior
[49:26] – Reasons for DCF and Market Price Differences
[59:45] – Exporting to Excel and Formatting Issues
[1:12:26] – Final Review and Closing Thoughts

Full Show Transcript

(00:00:02):

Welcome back to another episode of the Financial Modeler’s Corner. The ModSquad. Unfortunately, once again, I think the third week in a row, we're missing one of our three core members.

(00:00:13):

Giles unfortunately wasn't able to join us this week, last week in and Giles went without me and the week before it was Giles and I. So we're running at two thirds capacity today, but we're super excited to have you. I'll do a quick intro of myself and then I'll introduce my cohost, Dan and we'll jump into things. So my name's Paul Barnhurst. Obviously this is the Financial Modeler Corner. Thrilled to have you here on the show. We're testing AI tools so you don't have to, and helping you give an understanding of what they're capable of doing. So why don't we take a minute and let you introduce yourself.

Ian Schnoor  (00:00:46):

Sure. Thanks Paul. I was going to say thanks to Giles because he and I did it. As you know, last week we tested another tool, but yeah, we had a great time last week and you and I are going to have a good time this week. I am the Nuer Executive Director of Financial modeling Institute, FMI, the world's only financial modeling accreditation organisation and community and we are thrilled. I'm thrilled to be working with you on testing all these different AI modeling tools. Modelers all over the world have been really curious to know what's going on in the world of modeling and AI these days. And my entire career has been focused on modeling from my time as an investment banker to working to running a training firm and building, being, having the honour of building the financial modeling that's part of the CFA programme. So I've been really focused on modeling for many, many years.

Paul Barnhurst (00:01:40):

Yeah, no, I know you have, you've built many models and we've tested them now, I think today is tool number seven, so I'm just going to run through what we've done. You can find all the episodes on YouTube under Financial modelers Corner at the end. They're the last seven episodes I think that we've done so far, seven or eight. But we've tested Excel agent, Rosie ai, trace Light.

Ian Schnoor  (00:02:03):

Yep.

Paul Barnhurst (00:02:05):

Tabs, AI

Ian Schnoor  (00:02:06):

Tabs

Paul Barnhurst (00:02:08):

Shortcut. Yep. LAL

Ian Schnoor  (00:02:11):

Car six.

Paul Barnhurst (00:02:12):

And today we're going to be testing a kind of unique name truffle pig. What do you think of that name for a spreadsheet?

Ian Schnoor  (00:02:19):

Well, truffle pig, there is a meaning behind it for a spreadsheet. Gosh. I mean naming anything, it is memorable, so I don't mind that. I like it. It's certainly unique. It's easier for me to remember that than some of the other names that might've been made up names, but yeah,

Paul Barnhurst (00:02:40):

For sure. I mean, I'm trying to decide if I like it or not, but I totally agree as far as the marketing of being unique and remembering it, seeing the big pig and truffle pig is really easy for me to remember versus some of these others that are words I've never heard of. Right. They've made up a word as their business. So they do have that going for 'em

Ian Schnoor  (00:03:04):

And we'd have to ask them why they named it that way. As you know, there must be some connection we can figure out. I mean it comes from the origin I guess. A truffle pig, which I remember reading about once, is a type of pig that is used to dig up truffles, right?

Paul Barnhurst (00:03:27):

And I know they're focused on trying to find insights or trying to get the work done so you can find the insights. So I don't know if the idea is, hey, let us take care of all the drudgery so you can focus on finding that insider, that thing of value.

Ian Schnoor  (00:03:41):

Yeah, that's probably right. That's probably right and it certainly is memorable. So we'll give it a shot here today, won't we?

Paul Barnhurst (00:03:48):

Alright, so why don't we start, we'll show their website, we'll go through the little one pager we have with them and then we'll jump into testing. One of the first things is this will be the first tool we've tested that's 100% a new spreadsheet experience.

Speaker 3 (00:04:04):

When

Paul Barnhurst (00:04:04):

We tested shortcuts, we did test shortcuts for at least one problem in their spreadsheet. Then we went and did the rest in their Excel add in here, 100% spreadsheet. They like to call themselves the AI first spreadsheet. Initial thoughts on new spreadsheet versus Excel add in. And I know you're a career long Excel user, so I'd imagine me, you probably have some strong feelings here.

Ian Schnoor  (00:04:33):

Well, I mean I've done some initial preliminary testing and it's certainly been working well from our preliminary tests as a tool. I don't love having to learn a new sort of quasi spreadsheet software. We'll demonstrate it does some funny things, but listen, if it's ultimately the best and the right tool, then I guess people will be fine using it this way. But they've decided to have it in its own app as opposed to an Excel add-in. And I'm not sure if you know why they did it that way.

Paul Barnhurst (00:05:15):

My understanding from the, I had a conversation with one of the founders back when, and I believe it was this one, I've talked to a few, but usually what I hear when they build their own spreadsheet is they're not confined by Microsoft. Microsoft rules. The older tech, it opens up opportunities that are easier for development.

Speaker 3 (00:05:34):

That's

Paul Barnhurst (00:05:34):

Generally the argument for its own spreadsheet, which makes total sense. And then the counter argument to everybody is Excel. Everybody's so used to Excel, why do I want to fight against it?

Ian Schnoor  (00:05:42):

Exactly. No, I could see that you have your own, you could export it into any spreadsheet tool and there are not hundreds, but there are a handful that are used of course. And so this allows you to work with anybody, I suppose.

Paul Barnhurst (00:06:00):

Yeah, that's kind of my thinking is it's really being able to control all the UI and UX and having ownership of everything, but that also creates more work versus just being the agent. So we'll see how it works. I mean at the end of the day, like I said, I can tell you if it performs way better than all the other tools, I'd be open to using it more.

Ian Schnoor  (00:06:19):

Totally. Yeah,

Paul Barnhurst (00:06:20):

No, you'd get used to it. I mean a spreadsheet is a spreadsheet at the end of the day. They're not that different,

Ian Schnoor  (00:06:25):

Right? No, that's exactly right.

Paul Barnhurst (00:06:27):

Alright, so let's just jump through. We'll do a quick look at the website. Pretty lightweight. They're still on an open beta, but they do charge during the beta, which I think is kind of interesting. Usually you see kind of a free period, which they did have. So we got the AI first spreadsheet, finally a spreadsheet to speak your language, describe it and it's done. And they show an example of a DCF model. Pretty typical. Skip the busy work, focus on the insight. So get great answers, fast build presentation ready workbooks, work in one contextual workspace, understand your workflow. To me, what it feels like is their marketing here is what you can do. Some of the sites, it's hype, we're going to save you a bunch of money. We're better than everybody else here basically. It feels to me very basic to saying, look, we're here to help you.

Ian Schnoor  (00:07:17):

Yep.

Paul Barnhurst (00:07:18):

I don't know what your thoughts are. Work at the speed of thought.

Ian Schnoor  (00:07:22):

Yeah, listen, like it. I like their vibe, I like their messaging and their articulation. I like the layout. I mean somehow Giles and I were talking about this last week. A lot of the AI finance tools that we've looked at have a similar look and feel like if you scroll up, I mean a lot of nice white space and a bit of a demo. And there seems to be a more similar than not look and feel, but agreed.

Paul Barnhurst (00:07:50):

Sorry, I agree with you. They're more of a similar look and feel than not,

Ian Schnoor  (00:07:55):

But I certainly like their messaging and their vibe so far. Totally.

Paul Barnhurst (00:08:01):

One thing I think is interesting, and this speaks to the AI advantage web search, AI intelligently pulls facts into the grid as you work, ask questions and compare sources without tab hopping. So a little easier to do the ai, pull it in, pull in from another source and compare it. That might be a little tougher to do in Excel. It probably could do it with copilot and some of those things. But I'm going to guess just looking at that, that to me strikes me as probably something that was easier to do in a dedicated way, the way they built it, but I don't know. And then obviously everyone we have, we secure your data, it's encrypted, it's going to be safe. I don't see the SOC compliance yet. That's probably why they're still in beta. I imagine. We'll see all those logos like the others when they're done and then get started for free. So very lightweight pricing. Pretty similar to the others. They have a free version if you do an annual, it's 21 a month. If you do monthly, it's 30 for the pro and 200 for their super. And if you want a team plan call,

Ian Schnoor  (00:09:08):

Can you go back up to the description? So Giles and I were unsure last week on the pricing, whether you could get for the pro plan, it says you get unlimited default mode messages and 15 max mode messages per month. Again, it's not totally clear what determines and what differentiates between

Paul Barnhurst (00:09:34):

You select, it doesn't show it here. I've played with the tool enough. There's a place where you select default or max mode and then,

Ian Schnoor  (00:09:41):

Right. But I guess it might not be clear when you're doing that, whether you need one version.

Paul Barnhurst (00:09:46):

Oh yeah, I get it. Yeah, that makes

Ian Schnoor  (00:09:47):

Sense. Right. And should I be using this particular request, should I be using the default or should I be using one of my 15 max credits kind of thing, so Right.

Paul Barnhurst (00:09:59):

No, I think that's a great point. It's hard to tell from there. You don't know for sure.

Ian Schnoor  (00:10:02):

Anyway, let's take a look and

Paul Barnhurst (00:10:05):

I'll show one other thing real quick. Let me just pull up here. So we've done some of these on the other beta, it's a new product. Launch date was April, so they're not even eight months in yet. They kind of focus saying, Hey, we're focused on doing the spreadsheet busy work. So not specifically modeling, they're broader than some of the other tools. They say their ideal customer is finance operations and sales team. So they're just going after the hardcore spreadsheet so to speak. And then something I thought was really unique, this is their claim is they say, Hey look, some of these other tools demo real well. We may not demo as well, but we believe we do a much better job of the real work. Couldn't validate the claim. That's what they say. It makes 'em unique. We'll put it to the test here in a minute. Sure. Alright, let's jump into the tool. I think what I'll do here is I'm going to log in and just show the basic spreadsheet. So let's see, can I get a blank sheet? I should be able to go here again. And so this is what a blank spreadsheet looks like for them. Maybe I'll make this a little larger. You can import your Excel or whatever you want here up to 30 megabytes. So they're not going to let you import that 50 megabyte Excel file?

Ian Schnoor  (00:11:34):

No, no.

Paul Barnhurst (00:11:37):

You can download 'em as an Excel S or A CSV, duplicate something. And then they have just a very basic spreadsheet. They have their chart thing, some filtering grid lines. I'm not sure if I see a pivot table here. So it looks pretty lightweight, but I think the real point is to see how it does with its AI tool. So any other thoughts on this before we jump in?

Ian Schnoor  (00:12:03):

No, it is pretty accessible for anyone looking at it. It seems pretty usable.

Paul Barnhurst (00:12:09):

All right. So I have the first case here and what I want to do, just so people can see is I'm going to pull up the actual case in Excel real quick. I'll do that while we test it and I'll come back to that. Take me a minute. I don't want to spend the time but notice the images aren't here. Anyone who's followed the episode, you can see the name is kind of when it was pulled in.

Ian Schnoor  (00:12:32):

Yeah, when you open the file. When you opened it, it sort of deleted all the, it

Paul Barnhurst (00:12:36):

Stripped out a lot of the images.

Ian Schnoor  (00:12:38):

Yeah.

Paul Barnhurst (00:12:39):

And so we'll show you what it looked like in Excel. So that was one of the first things that jumped out to me. But what I've done is I've put the same prompt that Giles always puts in here, go ahead and analyse this case. This is a basic eSports case. Notice that it's going to give you an example at the start of each of 'em and you need to solve the problem. There's five bonus questions, seven levels. I've said please solve level one first before completing the other steps so I can review it. And what I'm going to do is I'm going to go ahead and use their most powerful model. I figure since we have access we might as well.

Speaker 3 (00:13:17):

Sure.

Paul Barnhurst (00:13:19):

And let's go ahead and kick it off and see how it's doing.

Ian Schnoor  (00:13:21):

Yeah, and let's give it a second here before we pause because let's see what it's doing and what it's thinking about. Last week when Giles and I were on our own, we were just about to pause recording and it was done. It finished. So let's see how quickly this takes, but it's so

Paul Barnhurst (00:13:39):

Level one's done that looks right, updated 10 cells, it's stinking. So pretty quick. I only do level one. Perfect. The formulas have been applied. The results, it's giving me the solutions, it tells me the formula you used.

Ian Schnoor  (00:14:00):

Can you click on the green cells?

Paul Barnhurst (00:14:02):

Do you want to keep these changes? So what it does first is notice I like this. It puts a box around it saying, Hey, here's all the area we're working on. Do you want to keep these changes? So I can click in and see, oh, it did the left. That looks right. I 53. What surprises me is I would expect that this to be red over here. Kind of like Excel. You can see the blue around it and you can see that, oh, there we go. If I click in up here, it gives me all the colours. Okay, so that all makes sense. I'm going to go ahead and say yes. And then what I'll do is I'll ask you to solve the rest of the, please solve the remaining levels and bonus questions. And while it's doing that, let's keep talking and I'm going to pull up just so people can see what the case looks like in Excel so they can kind of see how it's different.

Ian Schnoor  (00:14:54):

Sure, sure.

Paul Barnhurst (00:14:57):

So I'm doing that here now as it looks like it's going pretty quick, it's doing level two. It's analysed that. So we got all right, have the case here and we'll bring that up in Excel while it's stinking. So it's done level two, that's done. It's on the level three it looks like.

Ian Schnoor  (00:15:24):

Yeah. We'll have to see if it's done correctly and we'll have to take a look at the nature of the functions. But there you go.

Paul Barnhurst (00:15:29):

So here's what that case looked like. You can see something quite different. All the colour and stuff was really stripped out so you could see, compare. If I split my screen here, let's come up to the top. Well it's working and we'll minimize this for a minute. So if I just scroll up to the top, all blank there, you can't even see. So you can see the wording here, but even that, the spacing, so definitely pulls it in differently. That's something that I imagine will get better with time to be more on parody with what you'd see in Excel. Why don't we pause it for a minute. It looks like it's still working. Let's see, is

Ian Schnoor  (00:16:12):

Is it working or is it done? Let's do it, well why don't you, before you pause, just click on level three. Let's just see what the formula looks like in that.

Paul Barnhurst (00:16:20):

Alright, let's take a look at level two first. Let's see the formula. The formula. I just hard coded the numbers

Ian Schnoor  (00:16:26):

Well. Oh wow. Okay, so it's not, can you click on the rest?

Paul Barnhurst (00:16:30):

It did the formula here, so if I click here, it has a hard code.

Ian Schnoor  (00:16:36):

That's very interesting.

Paul Barnhurst (00:16:37):

Level three. It did what you would expect to call an indirect. That's fine. But the

Ian Schnoor  (00:16:44):

Column

Paul Barnhurst (00:16:44):

Around it, I think all those answers are right.

Ian Schnoor  (00:16:47):

Do you have the answers? Do you know if those are the correct answers? It does concern me with the previous one. Hardcore

Paul Barnhurst (00:16:51):

I do. Yeah, those answers are all right. From what I can see, they all look correct.

Ian Schnoor  (00:16:55):

Okay,

Paul Barnhurst (00:16:55):

Let's look at the level. Level four looks all right and they did a formula again, which makes sense. So I don't know why they didn't do one for level two. I'll have to ask. That all looks good. Level five. Let's see how it all looks right. It did the formula again.

Ian Schnoor  (00:17:14):

Yep. It's just fascinating to me the solutions that the different AI tools use are pretty significantly different from one another and I would expect that because different people would solve the questions differently as well, but they're solving them in very different ways. Some of them are much longer, more complex, others are much more manageable. This actually looks like a reasonable

Paul Barnhurst (00:17:37):

Solution. Yeah, this one, if I look at all these, they look short. So far man, I'm not seeing anything long any less.

Speaker 3 (00:17:45):

These

Paul Barnhurst (00:17:45):

All seemed pretty reasonable. I mean I might solve them differently. This one I would do that way. This one here seems pretty straightforward. Layers level six. Hard coded again. Interesting. I don't know the reasoning, it's the right answer. No, some are right, some are wrong. The first two are right.

Ian Schnoor  (00:18:06):

You want to ask it why it chose to do that or do you want to We'll

Paul Barnhurst (00:18:11):

I think we'll do that here in a minute.

Ian Schnoor  (00:18:12):

I mean it's done though, right? It's obviously done. And what about

Paul Barnhurst (00:18:15):

It looks like it's done, it missed some of level seven. So some is right, some is wrong there. First one's right? And then it looks like it got off on most the rest. So interesting. So not quite as good performance there.

Ian Schnoor  (00:18:28):

Can you go to the very bottom,

Paul Barnhurst (00:18:29):

Do the bonus questions. Let's see if it says it's done.

Ian Schnoor  (00:18:32):

Is it done?

Paul Barnhurst (00:18:35):

Oh it's still solving the bonus questions.

Ian Schnoor  (00:18:37):

There you go Paul. It's doing the bonus and there it goes. It's putting them in so it save them.

Paul Barnhurst (00:18:41):

So first two are right, get the formula. I don't know why it did an upper concatenate. Oh because you're looking for a certain letter and assume capitalised because it put the E so that makes sense why it would do that. Okay. Match max. Fairly simple formula. I'm not sure where the hard coded A plus 10. Oh regarding questions 11 to 30. So maybe that's how they started it. I don't know. The 1 0 8 is right, this is wrong here. Slightly off and then this one is way off. But given, I mean the map looks like it came through, right? So I don't know why it got the colours so wrong.

Speaker 3 (00:19:22):

It's

Paul Barnhurst (00:19:22):

Supposed to be 434 and it got 31, so we'll ask it here. It's going to give me a summary, probably another 20 seconds and then we'll ask it. Why did not use formulas on every level? So I'm just going to say yes for now. Why did you hardcode some of the answers? You were supposed to include the formula for every level that you used.

Ian Schnoor  (00:19:58):

You're really scolding it now you're getting to scold it and aren't you? Let's see what it

Paul Barnhurst (00:20:05):

Says. I am. No, so you'll laugh at this and maybe your audience will. We did an interview on one of my other podcasts and we had some guys from NetSuite and one of the guys is like you got to treat it like a junior intern. You just gaslight it and just talk. It's like you'll get better performance from it. He told us we gaslight our air, you'll get better performance. So I need to be meaner actually is what?

Ian Schnoor  (00:20:26):

Okay. Okay,

Paul Barnhurst (00:20:27):

So it said you're absolutely right. I should have used formulas for all levels. Let me fix the levels were hard quoted values with proper formulas saying the formula for level two, which, so let's see what happens now. Got an error. It's thinking.

Ian Schnoor  (00:20:45):

Oh I see. It's thinking about the levels that it put in dead numbers.

Paul Barnhurst (00:20:50):

I will say this one ran faster than most of the Excel ones. It feels like not a lot, I mean not L car, which I know you tested last week but I think probably on par maybe a little faster maybe.

Ian Schnoor  (00:21:01):

Yeah. Other episodes we've definitely had to pause before we could even see anything. But

Paul Barnhurst (00:21:07):

What I do in this one is I do like you can clearly see where it's working and kind of that colour box around it. That's nice.

Ian Schnoor  (00:21:14):

Yes, yes, I would agree with that.

Paul Barnhurst (00:21:18):

Unfortunately parsing to the limited text level two with the singular formula is challenging without modern Excel functions like text split, the formula I attempted aren't supported in this environment.

Ian Schnoor  (00:21:29):

Oh that's fascinating. It's fascinating. It's claiming that it understands how to do it, but the software doesn't have the capacity to use it. You know what, we may have just answered our previous question when we were applauding the simplicity of some of the earlier formulas, which is good. It might've been limited based on That's right. It hadn't occurred to me. Did it occur to you? It hadn't occurred to

Paul Barnhurst (00:21:55):

Me. No. If I tried typing, not all of it shows text split right here as a formula.

Ian Schnoor  (00:22:01):

What's that? Yeah, not all Excel are

Paul Barnhurst (00:22:05):

Interesting because right, it's showing and what I do like is it gives the column split. It's right there. Yeah, it's

Speaker 3 (00:22:13):

There.

Paul Barnhurst (00:22:16):

Sure. Go ahead and make the changes. I'm going to ask about it. Tech split is available as a formula in this spreadsheet. Please use it and then we'll move on. We'll take one last look and move on to the next task In the interest of time for level two I'd say for answering.

Ian Schnoor  (00:22:53):

Sure. Let's see what happens. Thank

Paul Barnhurst (00:22:54):

You. See I'm being nice now.

Ian Schnoor  (00:22:56):

Now you're being nice to it. Yeah. Let's see if that changes.

Paul Barnhurst (00:23:00):

It's interesting, it told us it can't but then it now let's see what it does. Let's look at the others and see now. So yep, that one was good. We expected that one. This one has it. This one now has the formula using an index row directly. Let's see if I got 'em. All right. Now that's level six.

Ian Schnoor  (00:23:32):

Still

Paul Barnhurst (00:23:33):

Got it wrong though.

Ian Schnoor  (00:23:35):

Are they all wrong?

Paul Barnhurst (00:23:37):

No, on level six it's hard to tell if all of 'em are wrong. Most of 'em are wrong for sure. Looks like almost all of 'em are slightly off by trying to see if they're all off by the same number. No they're not. So I don't know what it did. And then level seven, they're mostly wrong so it struggled with the mapping and I don't know if it brought something wrong or a similar formula to the others. It could be the way it brought stuff inside, but alright, so let's see if it fixes number two and then we'll move on here. So it's still thinking on level two. Interesting. It tried to sum the product and now it cleared it. I don't know why it's not using a tech split. Interesting. You're right, of course, right. AI always defers to you that you're right whether you are or not.

Ian Schnoor  (00:24:31):

That's right. That's right.

Paul Barnhurst (00:24:34):

And calculate the sum of the two largest values. So interesting and I want to see what this one fishes. We'll let it work for just one more second and then we'll move on.

Speaker 3 (00:24:46):

Yeah.

Paul Barnhurst (00:24:47):

Thoughts so far as you watch this, what's kind of your take here?

Ian Schnoor  (00:24:52):

Again, listen, I never want to lose sight of the fact that it's impressive that it can do anything. That you can enter an English language prompt and get an answer and it knows how to read it, interpret it, interpret the data, find where it needs to go and populate some sort of a formula. I mean that's still mind boggling. Yeah, I don't love that hardcoded data that seems to have gotten a bunch of things wrong from what you are telling me right from looking at your answer Keith. So I dunno, how about you? I sort of mixed it. What do you think?

Paul Barnhurst (00:25:28):

Yeah, that's kind of my view as well as mixed. It didn't seem to perform quite as well in giving the answers. The one area I was impressed by the answers it did give was formulas, all of 'em were simple. If part of that is how the AI is thinking about the spreadsheet, that could be why.

Ian Schnoor  (00:25:44):

But

Paul Barnhurst (00:25:44):

I always appreciate when you can give me a simpler answer or a more complex answer.

Ian Schnoor  (00:25:49):

Absolutely. So

Paul Barnhurst (00:25:51):

I do appreciate that part. It got that answer right there now and gave me a formula. We'll give it one minute here. Okay, complete it. See it just won't complete level two. Interesting.

Ian Schnoor  (00:26:07):

While the textbook is available, it says using it with large function encounters, compatibility issues in this Excel environment.

Paul Barnhurst (00:26:21):

It's saying this would be an answer but it didn't put that answer in. Alright, interesting. So clearly a little bit of compatibility issue, I think we call it good

Speaker 3 (00:26:31):

Would

Paul Barnhurst (00:26:31):

Say yes. We're going to close that one. Let's just download it so I have it now. You can download is Google sheets. That is nice. I guess they optimise it

Ian Schnoor  (00:26:45):

Totally.

Paul Barnhurst (00:26:48):

I do like that. Alright, so now here's the more complex one. I'm going to shrink this down a little bit. So this is the J case case

Ian Schnoor  (00:26:58):

Again, it's kind of made up. It

Paul Barnhurst (00:27:00):

Came through though, right?

Ian Schnoor  (00:27:03):

Is that

Paul Barnhurst (00:27:04):

The image? Look how the image came through to what

Ian Schnoor  (00:27:06):

It

Paul Barnhurst (00:27:06):

Normally looks like. Again, it really struggles with the pictures and stuff right now,

Ian Schnoor  (00:27:10):

Right? Right. Yes.

Paul Barnhurst (00:27:13):

And just for our audience, I'll show you what it looks like in Excel real quick so you can see the difference. It can't bring in the pictures, it struggled with getting the stage quite right. If I compare the two there, you can see that the audience pit the orchestra looks fine but without the rest of it it looks really weird. But we don't really care so much about the look for this. We want to see how it does in the case. So let's go ahead and do the max again. I would expect it to really struggle with this case given it struggled with some of the compatibility and formulas for a simple case.

Speaker 3 (00:27:55):

So

Paul Barnhurst (00:27:57):

Let's go ahead and put it in please. Complete level one before proceeding to the other levels. Thank you. See I'm being nice again. You're

Ian Schnoor  (00:28:13):

Always so polite.

Paul Barnhurst (00:28:15):

You made me a conscientious of whether I'm being nice or not in

Ian Schnoor  (00:28:20):

No, you have nothing to worry

Paul Barnhurst (00:28:22):

About. So now I'm going to be self-conscious.

Ian Schnoor  (00:28:24):

No, please don't.

Paul Barnhurst (00:28:26):

No, it's all good. I'm fine. Alright, why don't we pause it for a minute and we'll come back I imagine for a minute or two here. So we're going to pause

Ian Schnoor  (00:28:37):

Great idea back in a moment and

Paul Barnhurst (00:28:38):

We'll be back with you here in a moment.

Ian Schnoor  (00:28:40):

We'll let you know how.

Paul Barnhurst (00:28:42):

Alright, we're back. We gave it about 12 minutes or so to run. Solved level one. Did that beautifully. Got 'em all right. We can insert those answers if we want. It did level two, it hardcoded them and then it struggled a little.

Ian Schnoor  (00:28:58):

That's not great though, right? Level two, that's not ideal If it's hardcoded the number,

Paul Barnhurst (00:29:05):

No hardcoded it got 'em all right, but it didn't give us the formula we would've liked Level three. It's hung up on what's interesting, what I did notice and I know we've seen it with others, is the answers are in this file and it was able to look at those answers and say, let me redo it, let me redo it, which I appreciate you could see the learning and figuring it out. Also it's a little like cheating If I was in eSports and I had the answers

Ian Schnoor  (00:29:30):

Makes

Paul Barnhurst (00:29:30):

It a lot easier

Ian Schnoor  (00:29:32):

And it obviously knows what it needs to work towards, but it's chugging here. It's chugging, right? It has gotten through a few levels. It's really chugging to work through the rest of them.

Paul Barnhurst (00:29:44):

It definitely is. It's on a little bit of the longer side for the other tools generally been a little quicker. I think the longest we've gone is about 14 minutes and we're right about 14 minutes now. So I'm going to go ahead and kill this one and we'll move on. I mean my take is maybe it would've got there on all of them but took a little longer. I struggled a little bit, but not bad. I mean we can see similar to all the other models, it's getting some of the answers. It's sometimes following instructions. So similar. The thing I like is you always say yes to apply it. You can see that I think it's good and it shows us that. But let's move on to the next one. This is one of the areas I've seen an analysis of before and when they analyse some data and put together a kind of report, it seems to do really well. So I'm hopeful here we get a good result. So we're going to take the same prompt that Giles has used every time. Again, going to use the max model, let it think a little longer and we'll go ahead and kick that off.

Ian Schnoor  (00:30:53):

And what are you asking it to do?

Paul Barnhurst (00:30:55):

So what I'm asking you to do, let me read through it. So we have great points here. So if someone's coming in for the first time, this is just a ledger data. So what we have here is we have a monthly p and l summary for ourselves so we can see it. We have a chart of accounts and then we have a trial balance. So different accounts, product, sales revenue, sales department, and the credit and debit amounts. And we're asking it to analyse the data and I would like you to produce a comprehensive financial summary of the data, the performance of the company on a separate tab, make the summary professional include visuals with a mixture of KPIs and graphs, charts, review your own work before completing this task. The final summary tab must be top quality for a senior board meeting presentation. So we're basically saying give me your presentation, let's kick it off.

Ian Schnoor  (00:31:48):

Great. Do you want to thinking? Let's give it a moment to see. Let's give it a moment to see how it performs here.

Paul Barnhurst (00:31:57):

So if we go through the thinking here and I like that it leaves it and then minimises it. So the user has, here's the data it has, the user wants me to do the following. It breaks it into steps and then it says I should do this. It analyses it and creates the report of the 11 steps and we'll check 'em off so we can see us thinking it's done. It's read the data and now it's working on the exercise. We're going to pause. We'll give it a few minutes to run here and we'll come back.

Speaker 3 (00:32:27):

Great.

Paul Barnhurst (00:32:29):

Welcome back. I wanted to let everybody know we have a third cohost with us today. We've replaced Giles for a few minutes. Do you want to introduce our third cohost?

Ian Schnoor  (00:32:39):

Yeah, this is actually my dog Giles. So we've got another Giles. No, this is Benny. Benny is a Cockapoo and he's a very good financial modeler actually. So he was curious to see what we're doing and so I thought I would bring him along for this part of the demo.

Paul Barnhurst (00:32:56):

Alrighty, so we can see here. I thought for a few minutes. It gave us a summary of what it did. You can see all the key highlights of the complete summary. It had 11 steps. Although it's interesting, it didn't check all of 'em off even though it says it's done.

(00:33:15):

So that's a little weird visualisation created and it says yes. So we could see where it worked. Let me pull this back. You could see all the areas. It worked. I highlighted everything. We're going to go ahead and hit yes and decent formatting. The one thing it didn't do a good job of is I would've liked it to fix the column widths. You can kind of see it's not great there, but as far as I can tell, I did some checking. All the answers appear right. You can see the formulas. It used a sum ifs. It used a sum. If it did hard code the values, which I would've liked to see it link here, but not the worst. It did give us, let's look at it. Did a p and L trend analysis, then it did a revenue breakdown by category, which totals to the revenue up here, which is the right number. And then you can see it showed what percentage of 'em, all of 'em were what the average monthly was. Did something similar for expense analysis. Looked at both cogs and operating expenses.

Ian Schnoor  (00:34:25):

It's doing a good job.

Paul Barnhurst (00:34:27):

Key insights. And then it even did a year end financial position. What's your current assets? What's your fixed assets, what's your liabilities? I don't know if I've seen another tool get into that, but one of the better analyses and the area I think it did the best job on is these graphs for the most part are really easy to read. The only thing is they have to move this out of the way to see all of 'em. I would've liked them to be over a little further so that that's not in the way. But the graphs are relatively

Ian Schnoor  (00:35:02):

Minor. I would say that minor obviously that's not a right. Yeah,

Paul Barnhurst (00:35:06):

Right. If it does all this right, I could move. I can move a graph.

Ian Schnoor  (00:35:10):

You can move them. Yeah, no, I'm impressed.

Paul Barnhurst (00:35:13):

So yeah, I mean I noticed this got cut off a little bit, the gross profit, but again, on the ledger, I don't know why if I enlarge it, but on the whole, one of the better I've seen, I'm impressed. I think I did a really good job here. Any thoughts before we move on to modeling?

Ian Schnoor  (00:35:31):

Nope. I mean again, I agree with you. I think it's understood the ask and put together at least a very, very strong starting point with some visual aids to Yeah,

Paul Barnhurst (00:35:43):

This is something, if you gave me this, I would ask it to get rid of the zeros, but I could either work with it or clean it up in fairly short order. I think I could have something that's presentation ready and that's what we want.

Speaker 3 (00:35:53):

Yeah.

Paul Barnhurst (00:35:54):

Alright. Why don't I pause here, we'll get you set up and then we'll be back in just a minute with you folks. Alright, we're back. We've completed the first three exercises from Giles and struggled a little bit with some of the Excel stuff. Did pretty good on level one. Definitely struggled a little with level two, took a longer run plan and then did a very good job on the executive summary. We asked for one of the best we've seen. Now we're going to put it through some financial modeling basis. So why don't you take it away?

Ian Schnoor  (00:36:24):

We are, we are. Although the first thing I want to do is something a little different. I'm going to throw a bit of a curve ball. When I was loading up this tool, when I was getting truffle pigs set up, it said, it told me what I can ask for. It said you can ask for a lot of different things and say you can ask it to pull some public company data and build a DCF. And it literally said, it gave me an example. It said, you can tell me to build a comprehensive DCF model for Nvidia using real financial data. So I thought I would take its exact prompt and see what happens. So I'm going to toss in its prompt that it told me I could ask for, and I'm going to put it in there and see what happens. I've got nothing on my screen. I just said, build me a comprehensive model for D. Using real.

Paul Barnhurst (00:37:10):

Do we want to try? Let's see what happens with the default. And then if it doesn't, we can try the max real quick and see if we get a different answer.

Ian Schnoor  (00:37:17):

I use the default. Yeah, I use the default and let's see what it does now. It has stopped exactly. It has stopped here. It says, thinking I'll build a comprehensive ECF model for N Before I start, let me clarify a few key parameters. So this is great. And you know what? I love this. I love this and this is a theme that I keep talking about in all of these tools. For anyone who's of the view that AI tools are going to replace you or that you might want them to replace you, I would say that's probably not the right way to think about it because it hasn't done anything yet. It says it wants me to please provide your preferences. So it needs, it's look for my guidance on the projection horizon. Do you want five years or 10 years revenue growth? Should I use analyst consensus, historical, average WAC components? Should I calculate current market-based wac? How should I calculate the wac? How do you want me to do the terminal growth rate? What kind of long-term growth rate? How much level of detail do you want quarterly or annual sensitivity? So it's asking a lot of you need to know how to answer those questions.

(00:38:31):

Please provide your preference. Or can I proceed with the standard defaults? So standard defaults five year annual projection, market-based wac, 2.5% turnover growth and a sensitivity analysis. So let's just say for now, please proceed with standard defaults. Let's see what happens here. Please proceed with standard defaults and come back.

Paul Barnhurst (00:39:00):

They all seem reasonable. I mean, right, you could question some of 'em, but there's nothing there that I look at those defaults and say, what were you thinking?

Ian Schnoor  (00:39:09):

No, but what I'm curious to know is, so it's a lot, I mean used in my training days, I used to love teaching valuation and DCF F valuation. There's a lot of nuance to doing a DCF. There's a lot to understand. Are you using unlevered cash flows or levered cash flows are using, how are you thinking about the terminal year, the terminal period? How are you taking the terminal value? Or are you using some sort of a perpetuity calculation or some sort of a multiple? How are you thinking about the long-term change in working capital? So there's a lot to think about. What is it?

Paul Barnhurst (00:39:48):

What are all these images? I'm guessing these are links to the different websites. It's gone to

Ian Schnoor  (00:39:54):

What thinking

Paul Barnhurst (00:39:58):

You see all the images after each of the thinking?

Ian Schnoor  (00:40:01):

Yeah, I can see that. I can click on one. I don't know what, click

Paul Barnhurst (00:40:05):

On one. Let's see what happens.

Ian Schnoor  (00:40:07):

Well, it's taking me to something called fin box.com and it's wanting to

Paul Barnhurst (00:40:15):

Verify that. So whatever thinking it does, it allows you to see all the websites. It's searched.

Ian Schnoor  (00:40:20):

Okay, so it's searching.

Paul Barnhurst (00:40:21):

That's helpful. Yeah. Yeah,

Ian Schnoor  (00:40:24):

It's definitely looking at a,

Paul Barnhurst (00:40:25):

Although that's a lot of websites, it makes you a little nervous. Why is it looking at so many for each question?

Ian Schnoor  (00:40:30):

Yeah. Yeah. It's going to a whole bunch of different sites. This is the financial times. I can see this here. It looks like that's Investopedia. Well, it's still thinking. And again, this is interesting. I tried this again earlier and it provided me with a response very, very quickly. In this instance, this particular one, it's looking for what are NVIDIA's current total debt, cash and cash equivalent shares. Outstanding. Here we go. We're finally getting something here. Beta and beta's as of fiscal 2025. So it went to a whole bunch of sites to kind of arrive at, I mean that's fascinating to watch what it did here. So what did it give me?

(00:41:16):

It says it's an Nvidia DCF valuation model. All figures in dollars as of November 21st. That's today. Key assumptions. It's using revenue growth, operating margin tax rate. It's got a bunch of assumptions here. It's got the WAC calculation. So it arrived at a risk free rate. It says 10 year treasuries. It's got an equity beta 2.1, which seems like a reasonable beta for a stock like this type of volatility. I'm not sure how it derived the wack, the beta, I could ask it. It's using a 5.5% market risk premium. It's coming up with a cost of equity of 15% and a cost. Oh, here we go. Oh, look at that formatting on the fly real time. It tells me that the pre-tax cost of debt is only 3%. That's a little interesting. So again, as a modeler, as an evaluator, I need to think about whether this makes sense. The first thing jumping out at me is wanting to use a cost of debt, a long-term cost of debt at 3%. Paul, do you think it's reasonable to assume a long-term cost?

Paul Barnhurst (00:42:25):

So that's not, that's before tax benefit, which means that you'd be like 2% when you figure the tax.

Ian Schnoor  (00:42:31):

Yeah. Do you think it's reasonable to assume a long-term cost of debt pre-tax lower than the risk-free rate?

Paul Barnhurst (00:42:37):

That's what I was just saying. I'm like, okay, if that was post-tax even then it's low.

Ian Schnoor  (00:42:43):

Yeah,

Paul Barnhurst (00:42:44):

Yeah.

Ian Schnoor  (00:42:45):

Let's see. So it arrived at a, it arrived, and again, the keyboard shortcuts are different. I discovered pressing, most people know F two, F two doesn't seem to work, but F two and then the up arrow allows me to see what's going on. It's got a long formula in here. It's got, oh, what is it doing for the weighted average cost of a capital? So it's calculating. That's interesting. It's doing it differently than what it, and a couple of funny things are going on here. So it's showing me the total value of the company on a percentage basis. It's adding up. It

Paul Barnhurst (00:43:24):

Looks like that's a mistake, that it shouldn't be a percentage. It should be why

Ian Schnoor  (00:43:28):

10 percent? Not sure in dollars. Now this company has very, very little debt. This company has very little debt. So of course the vast majority, the total value will be the equity value. So

Paul Barnhurst (00:43:39):

In the bottom line, it's really almost immaterial to the WAC because that's so little debt.

Ian Schnoor  (00:43:43):

That's right. Debt.

Paul Barnhurst (00:43:44):

But 3% is still the wrong number.

Ian Schnoor  (00:43:46):

But let's see here. Now it's done. Do I want to keep these changes? Let's see what it's done. It tells us,

(00:43:57):

It says complete. I built a comprehensive DCF model for Nvidia using the fair value per share is $48 and 55 cents an equity value. Now it tells me where the current stock price is way above that I believe. And again, I just find it interesting that yesterday it did a number of things differently and it showed me some different information. So as an example, and I'm not going to spend too much more time on it, it's doing something here. You better believe that I'm going to have to dive into understanding everything that it's doing because first of all, yesterday was telling me what was the, if I want to keep the changes, yes, let's ask it. So it tells me that the fair value per share is 48 55. Let's just ask it, what is the current stock price? What's the current stock price of this company? Because yesterday it was telling me the premium or discount to the stock price and I don't know why

Paul Barnhurst (00:44:57):

I just searched. It's 180 1 77. Let's see what it comes back with.

Ian Schnoor  (00:45:01):

Yeah, I wanted it to tell me because

Paul Barnhurst (00:45:05):

Yeah, so roughly close that 180. Okay,

Ian Schnoor  (00:45:08):

So it, it's telling me this means the stock is trading at a significant premium, 272% above the DCFS model's. Fair value of 48 55. This is what I wanted to get to. It's generated DCF for Nvidia telling me that the fair value per share is $48. I hope to check that no investment banking analyst or any other analyst goes out there, runs a DCF on Nvidia using a tool like this and gets a value of $48 and comes back and allows the MD to say, what are you talking about? The stock price is $180 per share. So it is not reasonable to derive a DCF that generates a stock price. That's one quarter of the current market price. I mean, as I said, I've been teaching and I used to teach DCF valuation all the time. There are only two reasons. There are only two reasons why a DCF model might generate an answer that's different from the current stock price of a public company.

(00:46:12):

There's only two reasons why the DCF value might be different. Number one is because your DCF you and your DCF are making significantly different assumptions than the market's assumptions. So either our assumptions are much, much more, significantly more mutant, more conservative and conservative and cautious, which is a possibility. So that's the first possible reason. Or the second reason is because you made a mistake because there's an error in the calculations. Now the default DCF is so significantly below the current fair market price of the company that you better believe you're going to have to understand exactly what's going on and is it, so it's very possible that your assumptions are just a lot more conservative, but it's also very possible that there is a calculation error somewhere. And in fact, what I would think, and I noticed this the other day, so it's derived from a weighted average cost to capital. Here it's derived a weighted average cost to capital. Again, I want to crawl through that and see if that is doing that correctly. Here it's taking the equity value divided by the, it's like 99% multiplied by the cost of equity. So basically there's no debt. So this part may as well, it may as well get,

Paul Barnhurst (00:47:41):

You could pretty much delete that out and your answer changes I think by

Ian Schnoor  (00:47:44):

Nothing, a couple pieces points. But the point is this, the point I think is this, is that, is it reasonable? Is it reasonable to assume, I mean, again, in the world of A DCF, when we want to value a company, is NVIDIA going to have exponential extraordinary growth forever? No. Is it going to stay in the equity finance business with no debt forever? No. And if you are building a DCF, the purpose is to think about the long-term sustainable value of a company. So is it reasonable to assume almost no debt in the long term? Right? It's assuming that there is not going to be any debt in the long term of this business. Now I'd have to crawl through to understand what it is, but I need to understand that yes, it's reasonable for a DS, here's why net debt is already, well that's just telling me what it is. Tech sector norm. Yeah, I mean it's true. So it's telling me in the tech sector companies do have minimal debt when they get large and maybe that is a possibility. That's fine. So why do you think I could ask it? Why do you think the DCF value is so much lower than the current stock price, right? I'm curious to know why it thinks the DCF value is so much more?

Paul Barnhurst (00:49:26):

I'd be curious too, if you look at it, it assumed a 25% revenue growth rate. It assumed the same operating income. The WAC doesn't look totally crazy. So I would expect it to be quite a bit closer. Could still be off.

Ian Schnoor  (00:49:44):

Well, it thinks that the WAC is too high. Now let's see. So it's interesting to me that it actually has an idea. So if the WAC is too high, well it's the one that calculated the wac, right? So why did it?

Paul Barnhurst (00:49:58):

But it's saying, look, we use their historical volatility, but given their current dominant position, maybe we should have assumed there's going to be less volatility. Okay, maybe,

Ian Schnoor  (00:50:09):

Right? The point is I need to be able to have a conversation with it and understand what it's doing. It's useful. So of course it's using, I don't know how it arrived at the equity beta. Of course, when you do a forward-looking DC, F, all DCFS are forward-looking. The beta should reflect future thoughts on volatility, not historically observed beta. So it might need to lower the market risk premium. It seems reasonable, the cost. So again, it's got a cost of equity of 15.7%. I don't see anything blatant.

Paul Barnhurst (00:50:52):

The other thing is it looks like, I thought it was interesting, the number two revenue growth is too conservative. It grew last year at 114% and they're assuming immediately it goes down to 25.

Ian Schnoor  (00:51:03):

Yep, that's right.

Paul Barnhurst (00:51:05):

But also they're assuming for the next six years it's 25, 20 5% growth rate year over year. As that number grows. That's really hard to do for five straight years, even for a very difficult fast growing public

Ian Schnoor  (00:51:15):

Company. And listen. So maybe it is what it does for the terminal value, for terminal value. It's used as a perpetuity calculation here. Maybe it's right, maybe the stock is so overly priced, a lot of people think it is and it's going to drop down to a more reasonable level. That's a possibility. I guess I continue to believe that we're going to have to, anyone doing a valuation like this is going to have to understand. So I'm impressed, I'm impressed. I love the fact that it's given me a good start on trying to value this company, but I really believe that we're going to have to understand it extremely well to know whether it makes sense. I mean, is it using a long-term capital structure? Which is reasonable, which is what you would want to do in a DCF F. Is the cost of debt reasonable in the whack? Is the cost of equity reasonable? So we have to be able to go through, ask these questions and challenge it, and that's going to take some time as well. But I certainly like what it is. The other thing I've been

Paul Barnhurst (00:52:25):

Impressed with it, it looks like all the formulas are relatively simple. The numbers look right in the sense that I don't see glaring mistakes here. Nope. This is really one where I could take this and go back and forth with the AI and change assumptions about how I'm comfortable. I would be comfortable using this for a basic DCF as a starting place. Absolutely

Ian Schnoor  (00:52:47):

Right. This is that little helper on my shoulder that I've wanted. This is the helper that says get something going and it's actually giving me some good suggestions on how the terminal value growth rate may be too low. It's telling me that maybe our revenue forecast is too conservative. So right. I mean, ultimately I'm the one that's going to be responsible for this dcf and I'm going to have to go back to my boss, my board, my management team, my client and defend it and explain it. And so listen, I like that it's generated this and I like that it is giving us some thoughts on what we might do to it. It would be very unusual to present a DCF with a value that's so radically different from the stock price. Because the stock price is simply the market's reflection of value, which is thousands and thousands of investors all doing their own dcfs. And so if every investor thought that this was right, then if every single investor thought that this was right, then of course the stock wouldn't be at $180 because it would trade.

Paul Barnhurst (00:53:47):

The stock would be relatively close to $50.

Ian Schnoor  (00:53:50):

Exactly. If that's what the world thought. So why don't we move on? This was an interesting test. I'm actually quite pleased with the starting point that it's given me. And let's go into this. Let's go take a look then at let, let's do this. Let's actually go see how it can build a financial model. Let's go see that one. Let's go see. Okay,

Paul Barnhurst (00:54:12):

Sounds

Ian Schnoor  (00:54:13):

Good. Maybe. We'll,

Paul Barnhurst (00:54:15):

Yeah, I'm really impressed with the DCF. I thought it did a good job.

Ian Schnoor  (00:54:18):

I thought of that as a starting point. Point, yeah. It's not for the faint of heart and it's not for someone who's brand new to valuation, right? You're going to have done and you're going to have to challenge what it did in terms of its choice of every single assumption. But it clearly was able to do that. Now here's the simple reality as well, given the amount of time I think it's going to take for us to crawl through, I don't actually know how much faster that was than, I mean most of the time in that DCF is going to come from massaging it, tweaking it, playing with the assumptions, checking it, right? I mean literally all it did is it took some historicals, built a very simple forecast using revenue growth. So I don't know that that saved me, but if I wanted to get a back of the envelope DCF on 25 companies and I said do the same thing on 25 sheets for 25 companies, it would be a great starting point and give me a chance to play with it. Let's take a look at this.

Paul Barnhurst (00:55:19):

Even ask it, go out and look at the top 50 companies that have grown the most over the last month and bring back that DCF to look and see, hey, do I think there's one over undervalued? And

Ian Schnoor  (00:55:31):

Absolutely

Paul Barnhurst (00:55:31):

Get you started. Kind of like a screener in some ways, but it's built into something you can play with.

Ian Schnoor  (00:55:36):

Totally. Very impressive in that regard. For sure. For sure. Let's see. So this sheet now is, this is just the three year, three years of historical financials. And I'm not sure why I'm not seeing it here. I I'm not,

Paul Barnhurst (00:55:54):

You'll need to expand it out. If you expand out column C. For some reason it expanded out D and not C.

Ian Schnoor  (00:55:59):

Well, look, it's being a little bit, even as I toggle around and scroll around,

Paul Barnhurst (00:56:05):

Yes, it's a little,

Ian Schnoor  (00:56:07):

There

Paul Barnhurst (00:56:08):

Is some work that needs to be done when it brings in an Excel file.

Ian Schnoor  (00:56:11):

Yeah,

Paul Barnhurst (00:56:13):

That's an opportunity.

Ian Schnoor  (00:56:14):

There is no reason why it shouldn't be showing me the company name, but that's okay. So I'm going to say build a five-year forecast model on the model sheet, which is this one for the years 20 25, 20 29. Build separate schedules for revenue costs, et cetera. Make reasonable assumptions. And this is what I've been asking every other tool to do. Let's see how it performs. Let's see how the truffle pig tool performs its thinking and let's see what it does. So it is

Paul Barnhurst (00:56:42):

Definitely thinking. Should we pause it and give it a few minutes to work?

Ian Schnoor  (00:56:46):

Yeah, let's just give it another second. The tool last week actually started.

Paul Barnhurst (00:56:50):

Oh, I may ask you a bunch of questions similar to the others too. Yeah. Away. Lemme use reasonable defaults,

Ian Schnoor  (00:56:57):

Right? I'm not seeing the same granular flexibility to slide left and right. I mean, as I move to the right, I'm very quickly flying away to the side. So it makes it a little bit more awkward to work with. But that's okay. So is it asking me some questions here?

Paul Barnhurst (00:57:15):

Yeah, it's asking you a bunch of questions about revenue costs and saying, Hey, do you want to tell me the assumptions or do you want me to use default?

Ian Schnoor  (00:57:22):

Yeah. It says I need clarity. I need clarity. It says right, it wants clarity. So it's got some really impressive features. What has done is it, it says revenue growth for 20 25, 29 showed a 13.4 showed a

Paul Barnhurst (00:57:43):

Decline.

Ian Schnoor  (00:57:44):

But how

Paul Barnhurst (00:57:49):

It's saying 2024 showed a decline at 13.4%. Is this an anomaly or trend? I was looking at 23, 24,

Ian Schnoor  (00:57:56):

Showed a

Paul Barnhurst (00:57:57):

13 and saying, what should I do going forward? It's worded a little weird there.

Ian Schnoor  (00:58:02):

The forecast for 2024 had a bit of a decline right? Is this an anomaly trend? Should costs remain as a? So I like this asking for clarification, which means I need to know what to ask for. It wants to know what is the annual CapEx amount, what depreciation methods should we use? So I like that it's asking for clarification. That is,

Paul Barnhurst (00:58:27):

I like working capital. Hey, do you want me to take a simple percentage or should I do a story

Ian Schnoor  (00:58:30):

Or let me use reasonable defaults? Okay, please. I'm going to say please use a revenue growth rate of 5% per year and make reasonable assumptions for everything else, right? How about that? Let's see what that does. So, because I don't want it to project a 13% decline in revenue every year, then we'll quickly get down to zero. But let's see. So I wonder how much it's going to be comfortable trying versus, okay, so let's see, why don't we pause? It got zero. It's figured out that it needs to do 11 steps. Let's put this on pause and see. We will wrap up and show people what it comes back with.

Paul Barnhurst (00:59:29):

Alright, it's finished running. It runs for probably seven minutes or so, and we're going to go ahead and take a look live here and see how it performs. So it's asking us if we want to make the changes and take it away. This is your baby, you're our modeler.

Ian Schnoor  (00:59:45):

Sure, I'll do that. So I haven't accepted anything yet. It took about about eight ish minutes or so, seven minutes,

Paul Barnhurst (00:59:54):

Something like that,

Ian Schnoor  (00:59:55):

Right? It slowly went through and crossed off its 11 point to-do list and then it was thinking and then it said done. And then what it says is I've successfully built a comprehensive five-year model on the model sheet with seven supporting schedules. It said I did assumptions, five-year annual growth, which is what I asked for. It said the assumed cost of goods sold 75% of net revenue CapEx. It's made an assumption for CapEx depreciation debt. It assumed an annual repayment. So this is pretty good. It's made some good assumptions here. I like this. 30% effective rate dividends, 20% payout ratio. This is pretty wild so far what it's doing. I'm not going to lie. And then net income is going and then it's got some highlights, it's got some investment, some highlights here. Net income is going to go from 2.2 up to 26. EBITDA is growing debt's coming down. Just giving me a nice summary. It

Paul Barnhurst (01:00:45):

Says the balance sheet remains balanced throughout. Let's see if it really did, but that's not,

Ian Schnoor  (01:00:49):

I see the balance sheet remains balanced through, so I'm fast.

Paul Barnhurst (01:00:53):

I don't know if that's a forecast highlight. I would solve that standard of your work, right?

Ian Schnoor  (01:00:57):

Yeah, I would. Exactly. Now it's put all of these pieces here and it's put a bunch of schedules at the bottom. I am going to say yes, let's accept. So I'm going to accept and I guess that means it's just here now. Now again there now a bit awkward, tiny bit awkward that I can't easily see all my columns formatting,

Paul Barnhurst (01:01:23):

But you have to expand them. It's annoying that it doesn't.

Ian Schnoor  (01:01:25):

Yeah, and you can see the label.

Paul Barnhurst (01:01:27):

The next column,

Ian Schnoor  (01:01:28):

The labels don't go into the blank cell. So I would have to really make one column wider to see another column here. What I could do, we talked, what I could do is I could download this into an Excel file and let's

Paul Barnhurst (01:01:44):

Go and see what it looks like. We could, it leaves it here and it gives us a download separate so you can just open the download. Sure.

Ian Schnoor  (01:01:52):

And you can choose, and this is probably why we talked about, I think we talked about this, right? Why they've built it in a separate tool is it allows you to download it into either Google sheets or Excel, which is nice. Let's export it. Now this might require me to change my screen share because Yeah, it is. I'm going to have to change my screen share quickly.

Paul Barnhurst (01:02:19):

We're going to pause here for a minute as he brings up the Excel file. We'll be back with you in one second. Okay. Alright, we're back. We've opened up the work, it's done in Excel. Let's go ahead and take a look and see how it is. Take

Ian Schnoor  (01:02:32):

A look. So just download straight into Excel. It's linked to schedules, which is nice. It's obviously built a schedule down below. We'll go take a look at it. This is the first time seeing this here and obviously the formatting is not ideal. I would love it, but that's not a big deal at all. I can and

Paul Barnhurst (01:02:53):

We probably could have asked it to format and got a little Absolutely.

Ian Schnoor  (01:02:57):

It's got, let me just deal with some little consistency here on

Paul Barnhurst (01:03:02):

Of course,

Ian Schnoor  (01:03:03):

Decimal so that I can at least read the numbers more

Paul Barnhurst (01:03:05):

And notice how much faster you're working now that you're in the tool you're used to.

Ian Schnoor  (01:03:11):

Yeah, that's funny. No surprise. Now the net income, interestingly, is not coming from where I would expect it to. And this is what we found some of the other tools have struggled with is understanding some of the account when you ask it to build freeform, sometimes they struggle with the accounting ideas and the accounting system. So net income, most people know it's the right number. I'm just not sure what's grabbing it from a,

Paul Barnhurst (01:03:32):

It is linked to the schedule is my guess. You'd link to the schedule. No, it wouldn't be the schedule because net income to common doesn't come from a schedule per se.

Ian Schnoor  (01:03:41):

Net income should just be right off of the income statement. Exactly.

Paul Barnhurst (01:03:45):

Yeah,

Ian Schnoor  (01:03:45):

I was just going to say I like it, so let's see what it did on that front, but I do like the fact that everything is just a straight link so far. So we're going to see what's happening here.

Paul Barnhurst (01:03:53):

Why did it go one second? Why did operating cashflow go so negative? Can you go back?

Ian Schnoor  (01:03:58):

I'm not sure we're going to have to come back to Well, because okay, we

Paul Barnhurst (01:04:01):

Can come back.

Ian Schnoor  (01:04:01):

I just noticed something massive. It's assuming,

Paul Barnhurst (01:04:04):

Oh, okay,

Ian Schnoor  (01:04:05):

A monstrous, a monstrous investment in working capital every year

Paul Barnhurst (01:04:10):

From zero to that is definitely a red

Ian Schnoor  (01:04:13):

Flag. It's not likely that it's going to have an enormous change in working capital. Let's see though, what is going on?

Paul Barnhurst (01:04:25):

And the balance sheet doesn't balance despite it saying it balances, the working capital

Ian Schnoor  (01:04:32):

Does. Obviously the historical balance sheet balances here, right? We can see that. Let's carry it across, right? Drum roll please. And of course it doesn't, so it's off even though as you

Paul Barnhurst (01:04:42):

Just, if you go up, it's almost exactly off by, I know it's not just that, but it's almost exactly off by the working capital.

Ian Schnoor  (01:04:49):

Well that could be a big part of it. And again, the point is in this meeting

Paul Barnhurst (01:04:52):

I'm sure there's more than that, but it's just interesting that that's the rough number

Ian Schnoor  (01:04:57):

In every episode we've been saying. So now the key is to understand what's going on, what's it doing? Some schedules here. It's built in some schedules and wow, this would not be a recommendation for best practice on any formula to have an enormous change. And I have to check and see if this working calculation is actually working correctly. But what it did is it is, so it's kind of right, okay, so it's forecasting the receivables based on days it's forecasting. So I can tell you just instinctively by looking at this, right? If I look here, this is for 2025, I can tell you that if receivables is going down, that should be a slight inflow of cash, right? Inventory is about flat, payables are around flat and the prepaid expenses are approximately flat. Everything is flat. So how is it possible? How is it possible that if everything is flat, the change is so negative, that's an error. It makes no sense and it is. So there's a huge, huge error obviously in what it's built doing when it arrives to change in working capital and is this number actually

Paul Barnhurst (01:06:20):

You look at it, so yeah, it

Ian Schnoor  (01:06:22):

Has. So I like this. I liked that it built it and it linked it. This is better than some other tools. It built a working capital schedule and it linked it in here. This is the correct flow, it's the right linkage, but that is, we'll

Paul Barnhurst (01:06:37):

Know this in 24, it also, it tried to show it's 55 million, but the real thing is zero. So it's formula. Is there a formula in each? What's the formula if you go to g, G 1, 77 is zero, which is what it shows up above. Oh, it just linked that one and then it tried to do its formula and messed up.

Ian Schnoor  (01:06:57):

Yeah, there's no previous period here. But let's take a look at this one here so we can all agree, right? The change in working capital, if I just make these numbers, again, this is where we're seeing a lot of challenges in these tools. They don't seem to really understand the purpose of these ideas in these concepts. So what I would say is, now first of all, this working capital schedule is not optimal here. But what I would do is I would start by adding up the, let me just add a couple rows here. Let's see what the actual working capital is. We do have our assets, we have our total assets, receivables, inventory payables, our assets, prepaid expense assets and other current assets. And sorry, payables, prepaids,

Paul Barnhurst (01:07:54):

Payables, accounts payables should be a liability, right?

Ian Schnoor  (01:07:56):

Sure, of course. Yeah. I don't like,

Paul Barnhurst (01:07:59):

Okay, I was looking at when you said asset, I'm like you must be right. And I'm like,

Ian Schnoor  (01:08:02):

Yeah, no, no, I don't like that they had an order. So where are the assets? The assets are my receivables, my inventories and my prepaids of course.

Paul Barnhurst (01:08:10):

And other current assets,

Ian Schnoor  (01:08:12):

Liabilities here. So I don't love that it threw me off because it doesn't have them in the right order. And then of course we're going to subtract out the payables, the accounts payable and the other current liability. So this is my networking capital. Would you agree with that?

Paul Barnhurst (01:08:30):

I agree.

Ian Schnoor  (01:08:31):

That's my networking capital and is just the assets minus the liabilities. And then the change should of course be the last year minus the current year, right? It should be in this case. So this is the change in working capital that should be flowing into the cashflow statement. Not, well, I don't even know why this, so this is, I'm going to call this the networking capital. This is my networking capital here. This is correct. Assets minus liabilities. The change should be the difference year over year. Last year minus this year. If the working capital is going down, cash is coming up. So cash is coming up here. So gosh, it appears, well, it appears it's got the sign wrong. It took the negative of this minus that which ended up, look what this little piece of calculation does, and this is just a little bit concerning by taking, I'm just going to put these two in brackets.

(01:09:35):

So what it did here is it took the difference in the receivables, right? Agree with that. And if I do an F nine, just that in itself because it did a minus minus a, a minus, a minus, it flipped them. It used its mathematical operations incorrectly. It ended up with negative 55. So that's a big error. So let's do this. Let's link the cashflow statement to row 180 here and see what that does. But again, you really have to understand modeling and how these calculations should work. So really that should have been, I'm going to copy that over. So now we've linked it correctly to the change in working capital. Let's see now that should be fixed. Let's see now if that did anything to get a look that was the only thing Paul, the balance sheet balances. Now everything else is, that was the only error here. Otherwise I got to tell

Paul Barnhurst (01:10:26):

You, you may, I found that itself. We could go back in real quick and ask it to see if we can find why it didn't balance in the air.

Ian Schnoor  (01:10:32):

Yeah, I want it. Oh sure. I have to go back to the air, otherwise I have to tell you. Otherwise I have to tell you it's doing a really fine job here. Right? Let's look at the depreciation. PP e schedule beginning balance plus CapEx minus depreciation. Excellent job on that. The cost schedule, the revenue schedule, I'm not going to crawl through them all. We're already probably at time here, but other than that one error in the working capital schedule, it feels like it's done some really nice work. And other than the formatting and the presentation of it, let's just see here. Beginning retained earnings, it added in net income.

Paul Barnhurst (01:11:15):

Did it do a revolver?

Ian Schnoor  (01:11:16):

Why is it calculating net income as, oh, did net income as J 1 53 minus J 1 55. It is. Oh interesting. Okay, that's interesting. That's interesting. It's calculating net income on the equity schedule even though net income already exists on the income statement above, but it appears to have gotten the right answer

Paul Barnhurst (01:11:39):

And that's why it was linking wrong above. Remember net income, you're like why is it linked down to the bottom?

Ian Schnoor  (01:11:44):

Yeah, it's coming down here. So it calculated net income. So listen, overall, I think that this is, has done a really nice job. I think with a whole bunch of additional prompts, we could clean it up, we could pull out the assumptions, we could refine the assumptions, we could add a summary page, we could probably add scenarios. It's not take us zero time to find, we had to troubleshoot an error, which we had to understand we had to, and again, would any quickly realise that this was the obvious problem? I'm not sure. I mean to me I was able to hone in on that quickly because it seemed like a huge, because the number was so huge, but yeah,

Paul Barnhurst (01:12:26):

If you have enough experience, you could quickly look at it. Would everybody have that?

Ian Schnoor  (01:12:30):

Overall though, I think it's done a very, very impressive job and I'd be thrilled to use it as a starting point to get a model built. So I think we can stop.

Paul Barnhurst (01:12:39):

That's kind of my take. What I find really interesting, and this gets back to if you remember they said, hey, we may not demo as well demoing showing the Excel eSports, that's kind of sexy. We can solve that.

Speaker 3 (01:12:51):

That's

Paul Barnhurst (01:12:51):

Not real work. What we've done here is a little bit more of the real work and it has performed better. I think what they said is true.

Ian Schnoor  (01:12:57):

Yeah, no, I think I agree with you a hundred percent. This has definitely outperformed probably virtually every other tool I'm noticing here. Things like it's showing negative cash, which nobody would ever want to show on a balance sheet. So we'd have to understand why it was the revolver. So obviously it didn't know to build a revolver on the debt schedule. So again, these are modeling concepts in the accounting concepts. I'd have to go back to the product. I would probably need to re-upload this, go back to the prompt and say, Hey, we're showing negative cash, so can you build in a revolver, give it some instruction so that the revolver starts to kick in and as a result we have zero cash. But its ability to build schedules and mechanically link them all together was great. The only blatant error that we found was the way it treated working capital. Overall though, I give this a very, very high grade and it's done a really, really nice job. So we'll

Paul Barnhurst (01:13:54):

Back to you, I agree with you. It linked a few things like why did the net come down at the bottom. So there's the revolver, there's some quirks in here, there's some things you need to work out. But on the whole, if you know what you're doing, this is a tool I could feel comfortable having to do some stuff and then massage it. It could save me some real time.

Ian Schnoor  (01:14:14):

This would empower an, A good analyst could get better, but you have to know how to challenge it, push it, find the issues. And we keep saying every episode, so obviously your boss would obviously events you want to see that net income is coming right off of the bottom of the income statement. That's more standard convention. But again, if you understand that, then you can do that and clean it up once you get it to work. Same thing like I did here with the working capital. But I think I'll turn it back to you then and I'll stop my screen share because I think that yeah,

Paul Barnhurst (01:14:47):

We're kind of to wrap up points. So why don't we stop, we'll stop your screen share and just final thoughts before we go. I mean I was very impressed with the Truffle pig on the hole. I was a little nervous at first. Like I said, it struggled on the eSport cases, but on the work tasks I give it pretty close to an A. Not quite there, but on the whole it might've been the best one we've seen. It's right up there for sure.

Ian Schnoor  (01:15:11):

A hundred percent definitely up there. Again, maybe it's just getting used to it. They don't love working in a separate platform that way, but I guess you have to get used to working in their own app and then their own spreadsheet and then downloading to Excel. I guess if it's very iterative, if you're going to do that, you're going to work on something, download to Excel and probably make some changes, tweaks, formatting improvements, re-upload it if you want to make more changes. So I don't know if that would be a bit of a pain to be downloading and

Paul Barnhurst (01:15:41):

I think there is a little bit of pain there. So you get a little bit of pain with just learning a new spreadsheet if you're going to go back and forth. I love the fact that you can link out to all the websites and it shows 'em all. That was really nice. I love the way it shows changes that are very easy to see. So impressive on the whole, I mean, something invaded, it's going to get better if you're wanting a third party spreadsheet, AI tool, definitely one I'd consider. No question

Ian Schnoor  (01:16:07):

A hundred percent. Yeah, no, I think it's a great job and I give kudos to them for developing this tool. It's certainly the best one that's been able to integrate the financial statements and actually do it correctly from sort of an accounting standpoint. For the most part.

Paul Barnhurst (01:16:26):

Great job truffle pig. We'll be back again testing another tool next week. We're not done. We have several more to go and a few other exciting things we're thinking about. So please stay tuned with us. We'd love to hear from you. If you've watched an episode and you joined it, reach out to us on LinkedIn or send us an email. We always love to hear from an audience and thanks for joining us. So thank you Ann. It was a pleasure. Giles will be back with us next week or it will involve his dog even more if Giles doesn't return.

Ian Schnoor  (01:16:53):

Yeah, yeah. Benny might be back if Giles wants. He needs to keep skipping off here, but we'll see. Anyway, thanks everyone.

Paul Barnhurst (01:17:00):

All right, thank you. Alright, let me end.