What Happens When the AI Tools Fail Basic Math and More with Ian and Giles

Foreign. The Mod Squad featuring Ian Schnorr, Executive Director of Financial Modeling Institute. Giles Mail, Humble MVP and co founder.

Of Full Stack Modeler and Paul Barnhurst.

The FP and a guy. The tool we had scheduled for today is subset. What you'll notice first is there's no pricing. You can try it 100% free.

This is not built into Excel. This is its own separate piece of cloud based software that we need to look at by going in and opening a new tab right. In a browser.

I had to import the file and it's certainly put the tab names in, but the form formatting is. It just doesn't look like my spreadsheets. What is interesting that it says build a dcf. So I appreciate it's in beta, but if it can build a dcf, that's quite a thing.

It was able to build something when you clicked on a made up manufacturing company model. But let's see if it has the ability to pull historical data.

All right, we're back. This is our next episode. We've decided to be the beanie and glasses people. Giles, what's with the outfits today?

Well, we didn't want people to realize that we may or may not, it's unconfirmed, be recording two episodes back to back. So we've. I mean, I've told them now, but we've. We've changed. We're in disguise. We. We are so professional, it's unreal.

We would never, ever record multiple episodes back to back. So obviously we just happen to be randomly wearing different outfits.

I think we fooled everyone. I think we will fool everyone.

Nobody would ever think this is happening right after a prior episode. Good job.

Yeah.

All righty. We fooled them all. Take off my glasses so I can see. But I got. I'll keep the beanie. We got to, you know, got to have that going.

It's cold.

And I just want to say, mine was made by my wife, so, you know, I got a. I gotta make for me. She would.

Can I get her to make one.

For me around here? Just let me know.

It's getting cold in Canada, but I'm gonna de hat.

All right. I'm gonna stick with it. Are you gonna. Are you gonna be brave and go with the hat throughout? Giles?

Yeah, I don't know how brave it is. I'm just a bit chilly, so I'm. I'm keeping it up. I'll keep it on.

Why don't we get started? We'll do quick intros here. Welcome to another episode of the Mod Squad. We're a minute and a half in and now we're introducing ourselves because we're having a little fun. This is what, episode nine or so I think we're getting up there. We're nearing the end of testing all these tools and so we'll we have one more we're going to look at. We'll talk a little bit about different tools we've considered testing and what's next with the mod squad. So why don't we start with intros of everybody. My name is Paul Barnhurst. I'm known as the FP and a guy been hosting Financial Modelers Corner for a couple years and thrilled to have with me Giles. And in his co hosts, I run my own business. I do a lot of podcasting and we're going to have another fun episode today. Ian, why don't we go to you next?

Sure. Thanks, Paul. Great to see you both again for another episode. Yeah. Ian Schnorr, Executive director of Financial Modeling Institute. My life and career have been focused on financial modeling and it's a real pleasure and thrill to be doing these episodes with the two of you as we really learn a lot and test and hopefully share some interesting insights and knowledge with people all over the world around where we're heading and what's going on in the world of AI.

Alrighty.

Giles, hello. Yeah, Giles Mail, amateur XL gangster rapper, as you sort of found out last episode and in my spare time, co founder of Full Stack Modeler. And we help individuals and teams get better at Excel and financial modeling. Really happy to be here. It's been. Been a hell of a journey. Yeah, it feels like we've been doing this for ages. Nine episodes doesn't actually sound like that much, but I feel like I've learned a huge amount over the course of those.

I totally agree. We've learned some. So let's do a quick recap what we've tested so far and then what's on cap for today. So Excel Agent, we've done, we've done Trace Light, Rosie. AI. Rest in peace, Tabs. AI Shortcut. Yeah, can't forget Shortcut. That's Giles favorite truffle pig, Melder.

And today, El Car.

Elar. Thank you. And El Car. And today we're we're going to show one of the tools that's out there that we had on our list to test. It's still in beta. We'll talk a little bit more about that and then we're going to talk about just some of the tools we've seen out there that, hey, here's why we haven't tested them, their wait list or the different reasons, and then talk about what's next. As we feel like we're near the end of testing these tools for now, we may bring some others back on. We have some potentially on the list when they're ready, but we're talking about some guests and different things. So why don't we start with the tool we had scheduled for today is subset, and I'm going to bring up their website here and we'll talk a little bit about them because I think they're a unique one and I love what they're trying to do. Very difficult to do, but let me just bring them up here. So I, I think the first thing is, you know, subset is one I found when I was searching, is we were trying to find all the tools. It wasn't one. Someone reached out to me. They didn't complete the survey like, okay, an AI spreadsheet editor build to make finance professionals more productive. Generate a P and L from a PDF, build a DCF, or update a returns model. So I thought, all right, this makes sense to test, right? Kind of right up our alley. Or what you'll notice first is there's no pricing. You can try it 100% free. It's its own spreadsheet I do find interesting. It says, you know, it's backed by Merrill and Site Partners, Index Wharton, and very similar to all the other sites. The lot of white space. Generate a P and L from a PDF, build a dcf, update a return model, automate grunt work. And talks about how some things are on the roadmap for these different exercises. Not sure I fully understand receiving a sim, creating a teaser data room access post investment. So it looks like kind of steps in some kind of M and A activity it's showing and what it's building. So thoughts on the website before we jump into the tool, Giles?

Yeah, I mean, so what is interesting that it says build a dcf. So I appreciate it's in beta, but if it can build a dcf, that's quite a thing. Similar to what we've said before, the website looks pretty clean. It's giving some examples of what it could do. Format input in yellow fill. I love it already. That's what I do. That's what I do. Definitely. Right.

They probably were spying on one of your models when they created that part.

Formatting does look unbelievably similar with the dark blue headers and the white. Anyway, I'm sure it's fine. Scraped all of my models off the Internet to build an AI tool. Shocking.

There we go in.

Any thoughts on the website?

Yeah, it feels a little bit more so sort of bootstrapped homegrown at this point. I mean the formatting, the presentation of it. The other ones seem to have embedded GIFs or videos or they're just a little slicker. This feels similar, but it feels like it's a little bit, as I said, homemade, so to speak. I don't know if that's fair or not. I don't know how. If you think it just. Yeah, Paul.

No, I was going to say I think that's fair is all I was going to say.

Yeah, anyway, but we'll see. And we took a look and the one key thing about this tool as we know is the this is not built into Excel. This is its own separate piece of cloud based software that we need to look at by logging, by going in and opening a new tab.

Right.

In a browser.

And I spent a little bit of time looking at the websites. A couple interesting things. Right. If I click here, let's open in a new tab. That brings up the spreadsheet with the chat. We'll get to that here in a minute. We can see it's integrated a bunch of different models. The next thing that I thought was interesting is, you know, it has quite a bit of help docs but it says we're building the best AI spreadsheet. We spent three plus years building our spreadsheet and now we're focused on designing the best user interface for building financial models. So, you know, learn more about how to use subset and it shows what functions it includes, what shortcuts it includes. Because it's its own tool, it doesn't include all the functions. So we'll, we're going to try with some of the Excel files and maybe we'll just try asking it a question and see how it builds on its own. If we have any kind of challenges, as we've seen so far, we had a little bit of challenges loading some Excel stuff. Why don't we start. Do you want to try loading one of your Excel cases here, Giles? And let's see what happens.

My personal preference is to be in Excel, but if you maybe, I mean if you're a Google Sheets user, you obviously don't care what you're using anyway, so maybe you switch.

I caught it loud and clear. You didn't have to worry about. I didn't have to worry about.

Oh, I took you seriously. I was like. Oh, you didn't hear. I'll say it again.

No, I'm never serious. No, I. I got it, Larry. I gave you. I just thought you wanted a chance to repeat it a second time. But I'm actually a fan of Google Sheets. I think there's a place for it. I think it's a. I think it's a great product for the. Right. You know, even with our team when. When we're collaborating together on pretty low. You know, simple files can be great but. But I hear you straight away.

Bit weird because it's kind of broad in. So I had to import the file and it's certainly put the tab names in, but the formatting is. It just doesn't look like my spreadsheet. So the data is a little bit.

Of truffle pig to a lesser extent where it. When you brought in a sheet, it didn't quite bring in everything. Yeah.

This is the challenge of opening up an Excel file into a non Excel environment. Right. Is it. Things get missing. So what happens when you run it?

Please log in to continue. Okay. Okay, we're back hitting go.

Wait, you know what? It lost your. You have to reopen your work.

Oh, good Lord. Okay. Okay.

But it is working to determine the formula requirements.

You see, it's. It's trying to now calculate your request on a.

It says the green cells are there and I assume we're dealing with. Yeah, you might want to kill that one. Why don't you try. Can you go up to the different models? Try Llama. If you had no tool that's Meta's open source one. I'd just be curious why not?

Oh, okay. Proposed change it to identity cries. Please answer. Oh, here is the solution for level one.

Go ahead and hit Accept. Let's see if it brings it in.

I just can't see it. It says here is the solution.

I know, but you have that Accept button. Click Accept and see if it.

I don't understand.

Try again, I guess. Please solve level one. Maybe tell it where to insert it in cell E77 or something.

You didn't ask nicely. Giles, can you. Maybe it wants a. Please. Let's see here.

Accept. Accept. Say. Oh, oh, hang on.

Is it doing something somewhere?

Give it the specific cell and see what. Try a different model. Typical.

Maybe you didn't understand what the green cells again. I think it's helpful and healthy to be able to see us struggling like this. Right. I mean, this struggle is an important part of the process.

All right, so clearly this tool is still like you Said in beta is try for free.

Yeah.

Doesn't seem to struggle bringing in an accelerator.

How. Like, how much. What would be your personal threshold for patients before you get frustrated in and huck it? I mean, hell.

Oh, similar to my patients with people that overuse Vlookup.

Be careful. I'm a big Vlookup opponent here, so.

The Vlookup's my favorite. Giles, what are you talking about?

The point you're not. You're saying you're not going to have a lot of patience to spend a few hours working with this at this point.

Yeah, I don't know what it's doing, so I don't know if it's put the answers somewhere. I can't see anything in the green cells.

Certainly not responding the way the other tools did, is it?

Yeah, so clearly it's. At least it's not ready there. If you're importing Excel files, can you.

Try one of the Opus. One of the Claude Sonnet or Claude Claude, One of the anthropic tools there.

Yep. This is anthropic.

Here. Try again. You. What are you asking?

Oh, an error. I've been. It just said error. Okay, please try again. Error. Okay, I think I'm probably at the point.

Where does it say error? I didn't miss that.

Where it said error at the top. So try. Try again.

See what it says. Error.

I missed. Oh. Oh, an error occurred.

Yeah.

Okay, why don't we. Why don't we scrap bringing in Excel files and just try. Like, it lists examples saying, you know, help us build. Remember when with. I think it was Truffle Pig, we asked it to build an Nvidia dcf.

Yeah, try that. Giles, you got it open. Why don't you try.

I had a three statement button, so I clicked.

Yeah, fine. Okay, so you click that. So let's see what it does when it just builds on its own so we can at least get a bill for the tool.

Okay, so we're. Oh, this is cool. All right. This is some life. We're. We're watching this now, but we didn't tell it which. How does it know what company or it didn't.

It just said it's a manufacturing company. Use the data for the inputs. Forecast five years.

Use, oh, R1, R1, C1 references.

So the magic is happening now. This is nice to see. It's from scratch. It's building something here from scratch. You know what? I almost want you to. I'd almost love you to run it again and pick, you know, Amazon Or Tesla or Microsoft or something. I mean, I don't know what it's building here, but it's. And why is it. I can't quite see, but is it showing us in R1C1 format? Is that what's going.

Yeah, yeah, that's exactly what it's doing. I don't know whether it's going to come.

Is it going to convert all that? I mean, let's see if it does anything with that. It's ABC Manufacturing Company, three statement financial model.

I don't really understand the reference though. If it's just saying, you know, oh.

Yeah, now it's showing numbers. So it looks like. Yeah, we'd have some value errors. Now we are using. We're using Claudo for now. We'll just give it a minute here. Supposedly it's done.

Well, this makes no sense. Revenue is a hard coded number. Cogs is linked to the revenue number. So it's the same number.

Sure.

That's exactly how it works in real life.

Perfect.

So revenues equals costs and then gross.

Profit is just revenues plus cogs.

Brilliant.

Wow.

Genius. Look at that. I love that. The gross profit is double the revenue. Wow.

So from revenue of 150,000 doll dollars, let's call it, we end up with 2.1 million net income.

That's incredible.

Sorry, that's.

How do I start something like that?

You know what I wonder? Because go to. Go to the list of models for a second. If you do the drop down where it says Clotopus and everything.

Yeah.

Most of these are quite old versions. There's no GPT5. I'm wondering if they just. They left it out here, but kind of stopped development on this thing because they didn't respond to any of the emails. Older models. It feels like somebody spent a long time on it, maybe saw all the AI stuff and. I don't know, I mean, stop there.

But again, I think it's still worthwhile to see it because it just goes to show people that there's. You got to be careful. There's stuff out there. You might find stuff out there that is old or not being supported or is offering to promising to do something. But here's the thing, Paul, that might be true, but I got to tell you. Can you scroll back to the top, please, Giles? I don't care what version of AI you're using. There's no AI on the planet. You know, version one or minus 10. That should tell you that. That gross profit is revenue plus costs.

Right. So I can't. I can't argue with that at all.

That's not a new invention. That's not newly invented with gp, the latest GPT. Right.

So what you're telling me is in no world can I add my cogs to my revenue and accept and use that for my revenue base.

I'm pretty sure that's not a new invention.

I'm sorry for my gross profit.

Yeah, it gets worse the further you go down. So depreciation, sorry SGNA is just equal to the gross profit. Depreciation is equal to the SGA operating income just adds them all together. I think including gross profit interest expense.

Is equal to operating income.

Like it's just linking to the road.

Like this concerns me because clearly you didn't write this prompt. This was a default prompt built in that said hey, click this button and it'll run a model.

So plus income equals net income.

Can you try this? Can you try one more thing? Can you say build a three statement model. Is that button there again? I'd love to say build a three statement model for Tesla. Try that. Try to say build a three statement model for Tesla.

Build.

I want to see build a three statement model for Tesla. Make reasonable assumptions. Let's see what it does. Make reasonable because I want to see again if it doesn't understand the accounting logic and follow as. Sure, great. Let's see what it does. I mean it was able to build something by just when you clicked on a made up manufacturing company model. But let's see if it has. This is connected. Let's see if it has the ability to pull historical data. Makes it's doing something right. Okay. So it's got like I want to see if it buggers up the calculation of revenue cost, profit, you know.

You know what, another key takeaway I'm taking from this so far, right? What's that? Is all the work that these tools are doing on top of the LLM.

Yeah.

Now I, I would expect if we just went the Claude we'd get something better. So it's interesting how much of this is, you know, their instructions, their logic. Right. Versus the LLM. But it does show there is, you know, some value in what each of the tools are doing for sure.

And now look what it's got. It's. Yeah, yeah, they're trying to absolutely add value. So it's got a, it's trying to do 20, 20, 24, 20, 25, 26 forecast.

Looks like it took two years of actuals and four years of estimates. I'm wondering if it's because if it's not going out to the web. If it's one of the. An AI that only has data through 24 or why it didn't.

Let's see if it's getting revenue, cost of revenue, gross profit. Okay, so the ma. So the math, it's showing revenue and then it's showing costs which are negative. And it's. So the gross profit is mathematically working correctly here. Right.

Can you, can you enlarge it a little bit? Giles, your screen. I'm having a hard time reading these numbers. I'm squinting constantly. Thank you. Feel much better now. My old eyes. I mean, I'm not 40 like you, Giles.

Okay. Yeah.

Okay, first stop, real quick. This is just do a simple sniff test to the numbers.

The sniff test.

Automotive revenue is the same as energy and services in 22, and it's bigger in 23. That's not right.

It's the exact same.

Yeah, yeah, exact same in 22. And then energy and services is much larger in 23. These numbers are just.

I mean, that's possible, but what's highly unlikely is that the numbers were identical to each other.

Well, yes, but I also, I mean, just knowing Tesla, 80 to 90% of their revenue comes from automotive. So clearly these numbers are not right.

So, so there's something that's not right.

I think we just. I mean, that's all we need to know, isn't it? I just think it's just not. As you said, it's not there.

So you're right, Paul. Maybe this is not even being used or supported and it's just up there. But the danger. But I think it's very valuable to recognize the danger of trolling the Internet for AI tools, because there is stuff out there for free and it will do stuff. And maybe you'll find something free that's better than this, but still not good enough and still making mistakes. I think it continues to demonstrate that you have to understand what you're doing, what you're looking at. You can't sacrifice your own knowledge and your own skills. You need to be able to check, validate, and it is still basing itself on the same underlying LLMs. Right. So I think you need strong diligence in all of this. And it was really interesting to see that this is out there. So anyway, and then I want to.

Take a minute, just so our audience sees. You know, we've spent a ton of time trying to make sure we've looked at every tool that's out there. So I'm going to share two things on the screen and I think one is more so people are aware. So let me just share my screen here. As I went through this one thing I looked at is just what are all the alternative kind of spreadsheets out there beyond Google sheets in Excel So Jazz like ah no, don't tell me and we didn't necessarily test these outside we only tested those that really were advertising themselves as AI and for finance but there are several out there. Rose is a really interesting one that I've heard a lot of really good praise about. I've played with it some. It's really good in marketing great at bringing in reports. So we're saying is there's a lot of stuff out there and you'll find some of these paradigm is by a 21 year old, 22 year old college student that's raised millions of dollars. She graduated from like Harvard or you know one of the big Ivy League schools and it's a really interesting one spreadsheet to automate manual data collection and they bring in a ton of agents and so it's kind of an interesting approach as they've delivered said we're not going to try to be Excel. We're going to try try to focus on really automating your data collection like as you can see hey bring in a company and let us bring in the revenue and categories and all kinds of stuff from the web. So not modeling but just to show people equals is one out there. Sheetrocks Quadratic is one that can considered testing but they're not really designed for a finance they started as the data science spreadsheet and then they re pivoted to AI so right. Quadratic makes your spreadsheet work easy with brilliant results. Add data add questions. I've looked at it before. It has 95% of the formulas that Excel does and has some new ones. I'm curious as I just show some of these. Giles, what would it take for you to step away from Excel and use another spreadsheet?

Lots of money. I'm not sure there is anything that would get me out of Excel. You would have to pay me to do that because basically you have to.

Pry it out of your cold dead.

You'd have to be tied up with someone stepping on his back and forcing him. Right. Disabling Excel from your computer. It'd be pretty severe, wouldn't it?

I guess the serious answer to that because there was a period Google Sheets as much as I joke about Google Sheets it's actually pretty good in lots of areas and there's certain features that have been ahead of Excel. Tables now has got features in Google Sheets that's better than Excel. They were way ahead on the array kind of logic and they still are in a sense. They've got array of arrays working. So I think the serious answer is I'd have to see something that was so significantly more advanced than Excel that it was worth the trouble, me learning it and getting familiar with it to warrant stepping away.

How about you, Ian, what would it take for you to. And on a serious. We know Giles, we'd have to give him a buttload of money. But what would it take for you in.

Well, so I mean, in all seriousness, and I will, I will show this on purpose. I mean, I, you know, people talk about why there has not been as, I mean, Excel does have a cloud version of Excel. It's not very, to my knowledge, it's not very widely used. I'm not aware of people that use it. I've played with it. I think that there's, there's a hesitation to move away from a desktop software to a cloud software for spreadsheets. Yeah, some people talk about the security. I'm not sure if that's a real answer or just a made up answer because other types of data people are comfortable in the cloud. You know, I am comfortable with the work environment. And again, I'm gonna show you. I mean, I, when I run my webinars and I taught, I'm a big advocate of using the keyboard. And this is the keyboard that I use and I joke around, but this is my keyboard. It's got no letters on it. And I do that on purpose because I want, you know, people to work quickly and, and efficiently. And I keep my hands on the keyboard, but I don't look at the keyboard. My point is I'm really getting into the tool and working it and playing with column widths and changing visual dynamics and getting really into it. And that's difficult in a cloud environment. Everything is slower and drags and you can't, you don't have the same delicate ability to modify and tweak things when you're working in a cloud environment. That's my experience. And so, you know, a hardcore Excel user modeler wants to work right in the software, in the keyboard, work fast and I don't know that that's easily replaceable in a cloud environment. So I'm not going anywhere anytime soon either. Giles, would you agree with some of that?

Yeah, absolutely.

All right, so back to here. You can see these are you know, some of the others, like I mentioned, that are out there equals has got a little bit of traction. They're kind of an interesting one because they started kind of saying, hey, we're building the next spreadsheet. But a couple years in they found their product Market fit. Right. Go to Market Analytics. You trust insights to drive revenue. Today, even though it's a spreadsheet type solution, they very much focused on, hey, you can do SQL, writing your own data, building the reports right in there versus trying to compete with Excel. And so what it, what it tells me is you have to have unique use cases if you really want to compete. Right. I mean, nobody can just build a spreadsheet and like, all right, I'm good to go. And then here I wanted to show these are all the tools we. This is the list of different tools that basically found out there that are AI in some way. And then I went through all these and said, okay, are they at a point we could test them, you know, are they on a wait list? Several are on a wait list. Some were like, oh, they're their own software or they're just talking about building something. Weren't even in beta yet, still kind of in concept. Some were, you know, different enough to like, oh, all they're doing is helping you write formulas in Excel, even though they say AI. And so we just want you to show, I mean, look at this list. We got 30, 38 things we put on this list. We went out and looked at everything we could find out there.

Right.

You know, I did quite a bit of searching and looking to just kind of get an idea of what's there. And we brought, we've brought you, you know, at this point what we think is a very good list. We may test some others later on as some of them come out a wait list. I think NDEX would be an interesting one since they're backed by OpenAI, you know, Mosaic, we've talked about. So we'll continue. But I think we're coming kind of near the end of going out and testing the tools. Agree Giles, in thoughts on that.

I think certainly the third party ones. I think we've got a collective interest in looking at some of the LLMs to within whatever reason and you know, sensible capacity we can, I think that could be interesting. I suspect we'll come back to agent. I mean we might come back and review all of these tools again in six months. But it's really interesting for me that I had a kind of feeling in my head of what these would be able to do. And I'm not sure actually that's a lie. There's certain things they've done that I have been impressed with, but my position is exactly the same as it was at the start, just with more evidence now, which is that it's really clever, massively flawed at the moment, unreliable in lots of areas, but I love it, I keep supporting it. I want to be using these tools. I use AI in lots of parts of my life already. Yeah, I hope it progresses.

All right, Ian, you're kind of your thoughts there.

Listen, I mean, obviously AI is evolving by the minute. I don't know if either of you have played with the latest release of Nano Banana for or have you tried that at all. I played around with that a little bit yesterday. It seems like, you know, the earliest entree into AI was research. Right. Crawling through the Internet and aggregating and doing and actually generating research results for you so you didn't have to click on various links. It feels like it's a bit of a step up and a leap for them to actually build spreadsheets. Now it's working and they're doing things and I have no doubt that they are going to keep progressing. And I highly encourage everybody, especially young professionals. You don't want to miss this boat. I think now is the time. Here's the thing. I strongly believe now is the time to watch our videos, to start playing around because it's safe. Because I don't think anyone's expecting you to be a world renowned expert at this point because I think generally people know that there's the good, there's the bad, there's the ugly. So I think it's a good, safe time to be learning, trialing, piloting, staying, you know, afloat, making sure you're aware of what's going on. You do not want to get left behind. And there will be a time when these tools get better and better. But I can continue to believe that they will be your partner if you know what you're doing, they will be your partner in the same way that when Excel came around, people either adopted it or didn't. And, and you can't really be working in business these days in finance or accounting if you don't know how to use a spreadsheet. And so I encourage people to kind of roll up their sleeves, try these things out. They're going to get better so that you can continue to use them as they get better in your own work and support you, you know, and something I'll add.

That's interesting. I've seen several of these FP&A tools with, they're starting to bring, you know, they bring in the AI and obviously you, you do some modeling there and integrated three statement and they, they do a better job. Like you connect netsuite and it builds out the full three statement. But the difference is that's all structured. There's the chart of accounts all there. They're working within a very detailed tool where they can give very strict instructions and so they can get, you know, templates where hey, we'll do a 3 statement or we'll do a head count or we'll do your CRM data. So the more structured we can make this stuff, the more AI can help with templates and help with use cases. You know, we were really showing a lot of, I don't want to say unstructured, but semi and unstructured. And it also shows the importance of knowing what you're doing regardless.

But the tools, I mean, Paul, we found that, right? Paul, we found that normally in the esports cases, even as they got complex by saying here are the instructions, here.

Are the green cells.

Build a solution. Super impressive, super difficult, but it is structured and sort of programmatic, right? It's able to kind of figure out a solution so sometimes better than others and do it. But when you say, hey, here's three years of historical financial statements, you know, go wild and build me a beautiful three state, three statement, five year forecast model. We're not there yet.

The more instructions you can give it, the closer it will get, the more structure you can give it. I think that's one of the key things if anyone's wanting to, you know, try with AI, the more detail, the more structure, the more framework you can give it, the better the results are going to be. You still have to know what you're doing. Doesn't fundamentally change that. And then as far as what's next, maybe we'll talk a little bit. I know you mentioned LLM Claude. We want to get our hands on Claude for Excel. We've tested Excel Agent, which is basically copilot, you know, and so we've done that. And then I know we've also kind of as a group we've discussed potentially bringing on some guests or things. So maybe talk a little bit of how you're thinking as we, as we continue to go forward here. Giles, any of your thoughts of what people can expect?

Yeah, well, I think just personally I really enjoy it because this is helping me learn so much and obviously you know, I think we, it's nice to kind of share and bounce ideas with the two of you. So I'm not sure how much value there is right now in us just continually going, okay, there's another third party tool. What is really interesting to me is seeing how the LLMs stack up themselves. All of these tools, as far as we're aware, lean on an LLM or multiple LLMs and some of them will have layers of code and additional instructions that may do something. But I just have a gut feeling that when we now look at ChatGPT and Claude that they're going to perform really well. So I'm interested in that and I'm also really interested because I don't think any of the three of us would call ourselves AI experts. You know, coming at this with a decade of AI experience. I would love to speak to people that do have more insight into this technically or maybe people in the industry, you know, that have, have been leading the way themselves actually and have done even more digging than us.

So I think the message there, and we'll get insights, is, you know, this isn't the end of the series. We still have stuff we want to do, maybe pause on the third party tools, but we feel like there's something here long term for us to continue to learn and bring our thoughts on how AI is impacting financial modeling. Because I think we all believe it's going to have a fundamental impact, a big impact. There's no question there. It's just trying to separate hype and reality.

So in thoughts, listen, I think it's been fascinating. I'd love to continue doing the following. I'd love to continue to try new tools that come available that look like they're impressive and worth trying. I'd love to come back to the tools we did test at some point to see how they have evolved and improved over time. I would love to bring in guests, as we talked about that, both on the technical AI side and on. And we know a lot of people or that are bankers, finance professionals, accountants that are using it to talk about their own experiences. I think there's a lot of things we can do to, you know, to support people all over the world as they themselves try to learn about, you know, what's happening in the world of AI and finance and spreadsheets in particular. So, yeah, I look forward to continuing our discussions.

Great. And thank you so much for joining us on this journey. If you've been through all nine episodes, I feel sorry for you. No, I mean, thank you for joining us. We really appreciate it and we're excited to bring you more episodes. So please stay tuned for more from the Mod Squad as we continue to see how AI is changing modeling and spreadsheets and the way we work.

Now, you're going to include a link at the bottom to how people can buy your wife's hats. Or is that they're not quite ready.

For sell yet, but I'll have to talk to her. We'll see.

I think you're gonna get.

I, you never know.

No, you're gonna. We need massive demand. I already want to put an order of five, so, so she's gonna need to get busy. I, I, they're great. I would like.

I'll go talk to her right now and let her know she needs to get busy on.

I hope I can, I hope I can afford them, but I, I would like a few. So anyway, it has been great to be here and I look forward to continuing our conversation.

All right, until next time, thank you for joining us.