We Tested 7 AI Tools in Excel for Financial Modeling, and None Could Build a Reliable Model
In this episode of The ModSquad, hosts Paul Barnhurst, Ian Schnoor, and Giles Male are joined by Tea Kuseva, Community Manager at the Financial Modeling Institute, for a detailed discussion on the state of AI tools in financial modeling. The group continues its hands-on testing of seven tools, including TabAI, Excel Agent, Shortcut, and TrufflePig, evaluating how these platforms perform on real-world financial modeling tasks
Tea Kuseva is the Community Manager at the Financial Modeling Institute (FMI), the only global accreditation body dedicated to financial modeling. With her deep involvement in the modeling community and her role supporting professionals worldwide, Tea Kuseva brings thoughtful questions and provides structure to the discussion, helping translate technical insights into practical takeaways for finance professionals.
Expect to Learn
How leading AI tools perform on real financial modeling tasks
Common issues like unbalanced sheets and flawed formulas
Key differences between Excel-based and standalone tools
Practical ways AI can assist with analysis and reportingWhy Excel and modeling expertise still matter in an AI-driven workflow
Here are a few quotes from the episode:
“Even five years from now, you’ll still need to understand every cell if you're handing in a model.” – Ian Schnoor
“Fast, consistent outputs are still better achieved by experienced humans than by today’s AI tools.” – Giles Male
AI tools show promise in assisting with financial modeling, but they are not yet reliable enough to replace human expertise. Strong Excel skills and sound judgment remain essential. Used wisely, AI can enhance productivity, but it should complement, not replace, technical understanding. The future of modeling is human-led, AI-assisted.
Follow Ian:
LinkedIn - https://www.linkedin.com/in/ianschnoor/?originalSubdomain=ca
Follow Giles Male:
LinkedIn - https://www.linkedin.com/in/giles-male-30643b15/
Follow Tea:
LinkedIn: https://www.linkedin.com/in/tkuseva/
In today’s episode:
[01:16] - Guest Intro
[06:07] - Tools Under the Microscope
[07:59] - The Testing Framework
[13:43] - Lessons from the Esports Challenges
[19:33] - Real Examples from the Tools
[25:54] - Practical Use Cases for AI Today
[33:56] - Variability in AI Outputs
[39:40] - Looking Ahead: The Next Five Years
[44:58] - Final Comments
[46:13] - Final Thoughts and Key Takeaways
Full Show Transcript
Guest: Tea Kuseva (01:11):
Thank you everybody for joining. If you don't know me, my name is Tea the community manager, the Financial Modelling Institute. If this is the first FMI session, you're joining and you don't know who we are. FMI is the only financial modelling accreditation organisation in the world. We have our executive director, Ian Snow with us today, and I'll let him say a few more words about what we do in a second. But before I do that, just a couple of quick admin items to go through today. We'll be talking about AI tools in financial modelling. We are recording this session and recording will be available to all of our FMI community members within 24 hours. And I will let Paul tell you a little bit more about the podcast in a second, as we will be able to see that episode on there too. There is a q and a feature on the bottom of your screens, so feel free that should be visible to you. Feel free to leave your questions in there. You can also use the chat if that's easier. We do like to keep the conversation going. Don't be shy. And with that, and I would like to pass it over to you maybe to say a few more words about what to expect from this session and introduce our guests today.
Co-host `1: Ian Schnoor (02:13):
Thanks tea. I'm still just amazed that more people have entered where they're coming from. We've got Roberto in Peru, we've got Cameroon, Ghana, and someone in Hamburg, Germany. So our colleague Laura, Laura is on the call. So Laura, can I wonder if you can keep track of how many different countries are being represented so far? It's amazing. I think we're close to 20. It's truly global, so I love seeing that. Anyway, hi everyone. I'm Executive Director of the Financial Modelling Institute. As Tea mentioned, we're the only financial modelling accreditation organisation in the world. And one of our goals and mandates is to offer regular webinars, which we offer to our FMI community, but to the broader financial model and community all over the world. This is one of them. So we bring in expert guest speakers all the time on various topics. And today we thought it'd be nice as part of our community programme to get the Mod squad together.
(03:05):
I'm also honoured to be working with these two very, very professional and esteemed and very accomplished professionals that are joining me today. Become good friends, Paul and Giles. And earlier this year we were saying there's a lot going on in the world of ai. Maybe we should get together and run some testing and guys will tell you about what we're doing. So it's taught us, all of us, a lot about what's happening in the world of AI and financial modelling. Very, very hot topic. And so we're having a lot of fun with that. And so we're going to talk to you today. We want to keep it interactive. Today's session. We've got some things we want to share with you about what we're seeing and experiencing in the world of AI and financial modelling, but we'd also love to see your questions. This session can go up to an hour and if there's less, we'll go probably somewhere. This session will probably go somewhere between 45 minutes and an hour. So Tea back to you and maybe you can help introduce our other. Yeah,
Guest: Tea Kuseva (03:53):
I would love to do that. I would like to have everybody say maybe a few more words about themselves. First, you probably already know them, but JS one of our master financial modellers, also known as the combo MVP co-founder of Full Stack Modeller. Welcome js. And then Paul, if you can also say a couple of words about yourself, we know you as the fp NA guy and host Financial Monitor Corners podcast. And so over to you guys.
Co-Host 2: Giles Male (04:17):
Who wants to go first? Paul, do you want to go? Oh, you going to let me. Hello everybody. I'm a bit ill by the way, so I apologise for the way I sound. We've just had quite an extreme week in Las Vegas for the XL World Championship finals. So yeah, co-founder of Full Stack, we train people in Excel financial modelling. We do a lot to support people through the A FM now as well. And I've really enjoyed this series, the podcast series that the three of us have been on. I think it's been an amazing journey for us learning about these tools and similarities and the differences and hopefully we can share a lot of that with you today as well.
Host: Paul Barnhurst (04:49):
Amazing. And I'm Paul Barnhurst. I am not a humble MVPI am an MVP, but I'm not humble like Giles, so I'm known as the fp and a guy. I've been running my own business for about four years. I spent most of my career working in fp and a within corporate finance. This series has been great. Really excited to have this conversation. We'll release this as a podcast episode as part of the Mod Squad financial modellers corner. I'm lucky enough to talk to people who really know how to model. I mean obviously I know my way around a spreadsheet, but I love talking to people that know it so well and it's been great to test all these AI tools. So I'm super excited to share some of our learnings. There's a lot of information out there and some is good and some is nothing but marketing hype
Guest: Tea Kuseva (05:30):
And I think
Host: Paul Barnhurst (05:30):
That's
Co-host `1: Ian Schnoor (05:31):
Check out Paul's podcast, financial Modellers Corner. He runs a few podcasts including Financial Models Corner where he brings in really great guests from all over the world every month. So
Guest: Tea Kuseva (05:40):
Yeah, I just wanted to say, I think what you guys are doing is super important and just saving everybody a lot of time, testing all of those different tools, reviewing them and really seeing the ones that can add benefit to what the financial modelling profession is doing right now. So I would like to just know a little bit more about what are the tools that you have tested so far and how did you pick those particular ones?
Host: Paul Barnhurst (06:05):
Yeah, I'll talk to that. I kind of put together a lot of the list and then in Giles and I would discuss it, but the episodes we've tested seven tools so far that we've released Microsoft's Excel agent, which kind of threw a bomb into all of this as we started testing and then we released within its release two tools went out. One we were scheduled to test and one we had already tested.
Co-host `1: Ian Schnoor (06:27):
When you say went out, they shut down, you mean
Host: Paul Barnhurst (06:28):
Which Yeah, they shut down. They went out of business. Excel agent, like I said, totally kind of turned the market upside down or a lot of concern with it coming out. So we did Rosie ai, Excel Agent Trace Light tab, AI L Car,
Co-Host 2: Giles Male (06:46):
My favourite
Host: Paul Barnhurst (06:47):
Shortcut, which is Giles favourite and Melder. And so those are the seven tools. We also have a couple more episodes coming where we looked at what else is out there. We have some tools on our list that we still want to test in the future. Index is one that is sponsored by OpenAI. They've raised about 15 million, but they're still in wait list. And so those are the tools we've tested.
Co-host `1: Ian Schnoor (07:10):
And I would say Paul has a great relationship. Paul has relationships with so many fp and a companies and software companies and he's got relationships with all the founders of the new AI tools. And so he's kind of our access point and the gateway to all these and getting us access to try all these tools, which has been great. That's
Host: Paul Barnhurst (07:27):
Been a fascinating thing in itself. And I'll just say for talking to all those founders and seeing how they think about the tools as we've talked about, is it just the LLMs or is there something the tools are doing? And the answer is somewhere in the middle. The tools can definitely make a difference. There's a heavy part of the LLM and so it was always interesting talking to the founders, trying to understand what makes you unique, how is this nothing more than just LM plugged into Excel in testing. We've seen some areas where they're different. We've definitely seen a lot of similarity where it's kind of a wrapper and we'll talk more about that.
Guest: Tea Kuseva (07:59):
Yeah, I was going to ask, how do you guys approach that testing process? Do you fit it with the same type of information? Do you have different approaches? Ja, if you want to.
Co-Host 2: Giles Male (08:10):
Yeah, sure. Well, we took a very structured approach. I think it's interesting looking back at whether we would change it if we were to do it again, but I took some eSports cases. Paul had some fp and a challenges and then Ian did the kind of financial modelling stuff. So we tried to be fair in the sense that we wanted to give them the same challenges. Yeah, and also I think it was important that we didn't come at it as experienced prompting pros or anything like that. And I think we all felt that that was the right thing to do to try and be a normal person coming at this going, how do we get the best results from this? So yeah, pretty similar prompts. Sometimes if a tool did something that we felt that was sort of close to the right answer, we gave it a little bit of leeway and said, oh, you've done this wrong, give this a go. But in general, no. We gave it exactly the same challenges.
Guest: Tea Kuseva (08:58):
And I guess the question that everybody's wondering about, what's the best tool out there? Which one did you like the most so far out of the ones you
Host: Paul Barnhurst (09:07):
Tested?
Guest: Tea Kuseva (09:07):
And I would love to hear everybody's perspective.
Host: Paul Barnhurst (09:10):
I think we all have a little bit of a different opinion on this. I agree. Yeah,
Co-host `1: Ian Schnoor (09:13):
I think we do.
Host: Paul Barnhurst (09:13):
That's good.
Co-host `1: Ian Schnoor (09:14):
Did you guys take provide a thought on that at all at this point or Go ahead.
Host: Paul Barnhurst (09:19):
So I think the tool that was most, there's probably two that I'd list. I really like cab AI and one of the reasons it was my favourite wasn't even so much that it did the best on everything. It was also, I thought it was the most complete tool in the fact the workflow, it's starting to bring in things like your QuickBooks data or zero data and building more of a platform than just an agent. So I really liked that about it. I thought it really did a really good job with the executive summary, some of the Excel cases. Another one I really liked was Truffle Pig. What I didn't like is the fact it wasn't in Excel, just I'm so familiar with that. But I loved the way it brought things in from the web. I really liked when we did the model, I think it was the closest to a complete model. I think we just had to change the working capital, if I remember right in, I think that was the one where they had the working capital wrong.
Co-host `1: Ian Schnoor (10:13):
Was that the only tool or was there two tools We tested? They were own basically their own software platform.
Host: Paul Barnhurst (10:18):
There was a second one we tried. That didn't work very well. This was the only one Foley, and this is when Giles wasn't there. So this is the one we did the Nvidia DCF with.
Co-host `1: Ian Schnoor (10:26):
Right, exactly. That was so again, truffle pig was great. As a guy myself that likes using the keyboard and staying on the keyboard, I found it challenging and frustrating that the user experience was a little different and I couldn't, I didn't have the fast keyboard shortcuts and it expanded columns and it did things that it was forcing me to use my mouse and it changed the formatting and presentation. But you're right, Paul, it was a very, so this is truffle pig we're still talking about, right? It was a very powerful tool. Again, I would prefer to be staying in the Excel environment, but I agree that did perform well.
Host: Paul Barnhurst (11:00):
Agree. I like that you could easily see all the changes it was making the way it did the web. I think it did really good on answering some of the things, but it drove us crazy. We brought in the eSports cases, wouldn't even bring in the images. Formatting wasn't the same keyboard shortcuts. So it would be a long learning curve if I decided that was my AI tool. But those were probably the two I enjoyed.
Co-host `1: Ian Schnoor (11:23):
And for anyone looking at or considering or contemplating adding an AI tool into your spreadsheet, keep that in mind. That's a huge decision. Do you want a tool? And at some point maybe in the webinar I'll show my screen, do you want a tool that just adds a button into your Excel and it's in Excel and you're searching and you're running your promising Excel? Or do you want a separate tool that effectively is a new tab in your browser, right? It's going to be on your Chrome browser, whichever browser you're using. It's a separate tab as a separate piece of software and then you can download it as an Excel file. But it's a different experience and that's a big decision you need to make right off the bat.
Host: Paul Barnhurst (11:58):
Totally agree. And the one other thing I'll say, and then I'll let the others talk more about that, but of all seven tools, I think there were strengths and weaknesses in pretty much all of them. It wasn't like TAB AI was superior everywhere or truffle pig or Excel agent. I think all of us would agree there was no one tool that clearly performed best on everything.
Co-Host 2: Giles Male (12:21):
Totally agree.
Co-host `1: Ian Schnoor (12:22):
Giles, did you ever,
Co-Host 2: Giles Male (12:23):
Yeah, I think it was a close one for me, but I think because I just love their marketing so much, it's got to be shortcut. I'm joking. It's probably agent, I think for me, agent surprised me the most. I didn't love that it was in the web, but I can only imagine that's going to change soon. I think although it didn't do perfectly on the financial modelling stuff, I think it was close to being, they
Host: Paul Barnhurst (12:45):
Have announced publicly that it's coming to desktop. I don't think it
Co-Host 2: Giles Male (12:48):
Have they? Okay, great.
Host: Paul Barnhurst (12:49):
But I've heard they've announced publicly.
Co-Host 2: Giles Male (12:51):
Yeah, so I was really impressed by agent obviously. I think again, some of the hype was a little bit too early for some of the statements that were being made publicly by others, but I thought it was good tab ai, I definitely liked things about tab, tab ai and again, shortcut like being serious. There were some things that shortcut did that I was like, yeah, it's pretty good. But I agree with you Paul. I think every tool showed some really interesting strengths. A lot of them had really similar weaknesses and the one that I kept noticing was sometimes a reference or a formula would just point to the wrong cell. It would be a column off. And to me that's such a weird technical bug that's similar where it's just, I dunno, it just loses the logic link somehow and it's a bit off. But for financial model, that is absolutely devastating. So it's a big flaw.
Co-host `1: Ian Schnoor (13:38):
I think we would agree that you're right. While the tools performed differently, I think we would agree that they all did better. Actually, maybe not all, maybe except for one, right? Paul, most of them did better with a structured set. If you provided it with a structured set of instructions and a structured set of where they had to build the solution and the more guidance, the better they would perform better. So as an example, they all tended to do maybe with the exception of one, most of them did better on the eSports challenges. The eSports challenges say, here's a paragraph, super impressive that it can read a paragraph in English. And then it says, go look at these green cells in column G and build a formula in column G. And oh, there's an example as well. Read the paragraph, put a formula in With that sort of a structure, they did pretty well, right?
(14:24):
I mean the easier ones, they would do pretty well. The harder ones they would struggle with, but better. When you just said, Hey, here's a set of historical financial statements. Can you build a five-year forecast model either by using an A FM case or by just asking it to make its own assumptions? That's becomes much more mind blowing, that's more mind numbing than it is. Some of them said, what do I do now? I have all the flexibility in the world. How do I build it? Where do I go? And if you like, I can show the outputs of a couple of examples maybe in the webinar of what a couple different tools did when asked, and there's more work that needs to be done, I think. Would you both agree?
Host: Paul Barnhurst (14:58):
Agreed
Co-host `1: Ian Schnoor (14:59):
Completely.
Host: Paul Barnhurst (14:59):
The tool you're referring to that didn't do as well on the eSports was interesting was truffle pig
Co-host `1: Ian Schnoor (15:03):
It's own software, right? Paul? Yeah,
Host: Paul Barnhurst (15:05):
They mentioned they go, we don't demo well, but we do real finance work well, and we could kind of see what they were talking about in the sense they really struggled with the structured cases. They did better when we asked about A DC, F or put together analysis, which how many of us when we're doing our day-to-day work are going to have a case like that laid out for us. So it was really interesting to see that.
Co-Host 2: Giles Male (15:25):
I noticed there's a question in the chat about auditing. So Rich has just said, did you find any of them had auditing features and which one did you find most helpful? I'd be interested in the two of you and your thoughts on this, but I think one or two certainly had as guidance prompts like check this model for me. I don't think any of the tools did what I would call a really reliable job at auditing. But again, I think if you thought of these tools as a peer, as a buddy, as somebody that can help you and offer more input, I'm sure almost any one of them would be quite useful to pick a model and say, check this. I'm looking for logical errors or whatever you want to say. But I just wouldn't rely on it to find all of them.
Host: Paul Barnhurst (16:06):
I think of it as a cheaper version of the humble MVP.
Co-Host 2: Giles Male (16:09):
Yeah, really shortcut. I was going to say
Co-host `1: Ian Schnoor (16:13):
They're very confident. These tools are often very confident. It's funny, Richard, it's an excellent question, Richard, as part of the financial modelling testing, and you can check some of the actual episodes on as part of the financial modeler's corner, the mod squad series, but I always start my testing by asking it to do some simple checks and it was hit and miss. I would ask it to check for hidden sheets. I would ask them to check models if there were any white cells, these are things I would ask it to check. I would put hard coded values in formulas and ask it to check for any inconsistent formulas within rows that we need to check for. And they were hit and miss. Sometimes they found them, sometimes they just wouldn't. And it was a little bit scary to think, oh, to realise that if you were relying on that, it might not catch it.
(16:58):
I've led number of webinars all over the world where I deliver talks for an hour on skills to check a model. Here's the funny thing about checking a model. If you know the right skills, it's not very time consuming. So sometimes I would run AI to do a test and then I would do it using just a default Excel tool and it would be faster to do it with a default tool than to ask AI to kind of get it working. So where I think the checking, I think that as these tools get better, Richard, I think the checking, again, I like to think of the AI as a buddy sitting on my shoulder that I can talk to as well. I actually think that the checking might be in a different way. It might become less about formula construction and logic because there are pretty simple ways in Excel to do that on your own.
(17:39):
I'm happy if it wants to help in that way, but I think a good way where they might help you is to say, Hey ai, am I making reasonable assumptions? Am I thinking about this the right way? Do you think the assumptions seem reasonable? Are we using a reasonable this model, this company has assets in Nigeria and Australia and New Zealand and in Brazil? Am I thinking about the right inflation rates or the right growth rates for those kind of different geographic regions? And I think that it can help bounce around ideas in that regard, but I would not be relying on any of the tools yet to check for true mechanical problems or flaws in a model. None of them, I dunno if you guys would agree with that. I
Co-Host 2: Giles Male (18:19):
Agree. If I think further ahead, we kept talking about this idea of verticals and I think maybe in the area of audit, maybe there's a vertical that a third party company could layer onto the LLMs that's specifically looking at audit. I mean I wouldn't be surprised. So I use OG alot from operas. I could imagine an operas type company doing an amazing job if they were decided to layer in AI to what is already a brilliant auditing tool. I don't know that they're doing that, but that might be the area where a specialist in auditing could develop something that's really tailored otherwise. Yeah, I agree with you. Then
Co-host `1: Ian Schnoor (18:57):
Do you think maybe we'll go off on a tiny tangent here. What do I show the group two different models just so they can see? Because I think it gets into Richard's question as well. Maybe I can show the outputs of what a couple different tools built when we ask it to build a model, see if it can't, even if they're not at the point where they even understand optimal model design structure and logic, it's harder to get them to kind of realise that they should be and checking something. So why don't I spend, yeah, why don't I spend just two minutes and I'll show you two different models that we asked to the first one here. This was actually, this was one of the tools that I thought did, are you guys seeing my Excel screen now? Hopefully
Host: Paul Barnhurst (19:33):
It's starting to come up. Yep, there we see it now.
Co-host `1: Ian Schnoor (19:35):
Okay, so this is a tool I really like. This was a tool called ELK R, and it is a tool that Giles and I tested and I'm going to show it to you in a second. Is
Host: Paul Barnhurst (19:43):
This the one where you called it the naughty teenager or whatever
Co-host `1: Ian Schnoor (19:46):
It might have? I don't know. Recall it. So good must remind me. Yeah, so this was a tool where what I gave it is I said, Hey, literally here's three years of historical financial statements. I said, here's the income statement, the cashflow statement and the balance sheet. The blue numbers were just historical input. So that's all I gave it. And I literally gave it a prompt and said, Hey, can you build us a five-year forecast model, make reasonable assumptions and build a bit of a five-year forecast? That's it. And so this is what it did. I'll show you now what it did. So it did a decent job actually. Now the balance sheet was not balanced and it made about seven or eight critical mistakes which Giles and I fixed. So you're seeing now that fixed version of it, but it didn't do a bad job.
(20:27):
It built formulas right in, but it actually did a decent job. Obviously the formatting is not quite right. Now some of the other tools we tested was a holy mess. There was errors all over the place. This is one of the better ones. So it's got a five-year forecast here. The balance sheet's balanced only after I fixed six or seven issues around working capital and dividends and fixed assets. There were a number of formulas that were wrong, which we fixed it put an assumption section at the bottom, it made reasonable assumptions. Originally they were not blue. I asked it to make them blue. So not bad, but you would not have been able to do this without asking it to kind of go through and fix the problems it made. And I don't think it could have fixed its own problems. Most of them cannot fix when the balance sheets are not balanced, they're not able to fix themselves.
(21:14):
It needed a human override. So this was the first tool LA, not bad. I'm going to show you as well what Microsoft's agent tool did. The agent tool did something a little bit different. I actually gave it one of the A FM case studies. I gave it these. So you're seeing here, I put the case study for the, this is our sample model we use at FMI. It's called the Henderson Manufacturing Company. It's a manufacturer of large storage tanks. So I took the PDF case and I dumped it into a sheet and I also gave it three years of historicals. That's it. And they said, read the case and build a five-year forecast and it took about 10 minutes and it did something. So first it created this sheet called assumptions. This is how it built it just like this. I didn't touch it after.
(21:54):
So it's a start. It's a start. I mean the formatting is not right. I'm not sure what everything means, but it's a start in terms of seeing it's tried to take data from the case and put it onto the assumptions here, some errors, and then what it did is it built the model and this is what it did in terms of the model. So I think you would all agree is not exactly client ready yet or client friendly or your boss ready. What it's done is it's violated a key principle of strong model design that it actually tried to build. So it violated what a lot of modellers will do. You talk about keeping simple, avoiding having formulas on a set of financial statements. Well, it didn't do that. It tried to build literally what it's doing for revenue. It's doing prices times volume, so it's got price and it's got volume multiplied within the income statement and it's chosen to use an index function and it's automated.
(22:39):
The index function with a column function, I would've thought that it would. So the reason why the fifth year is a ref is because within the array of the index function, it's gone outside the array. It built the formulas wrong. So it's asked it to go to a column that's outside the range of the index function. So it would need to be fixed and modified. It didn't do a horrible job, but it looks like this. It has an error in the fifth column. So actually the first column is the wrong year. The first column 2022. It's actually the 2023 numbers because it built the index wrong. So you'd have to understand what it did, you'd have to be able to understand the index. And then it kind of got a half cashflow statement and it got a bit of a balance sheet, which is not balanced. And so that's what it did. So again, I think you'd agree it's going to require a decent amount of human override to get that cleaned up.
Host: Paul Barnhurst (23:32):
And we asked the tools to fix its mistakes on the balance sheet, and I don't think we had a single one, if I remember right, that was able to fix it all. None of them were able to figure out what they had done wrong. One even told us close enough, it's only a point what 3%?
Co-host `1: Ian Schnoor (23:47):
It's good enough, right? Paul? It was off by a few million bucks.
Host: Paul Barnhurst (23:50):
It was off like 0.3 million and it basically said, I'm done looking. That's an acceptable variance for finance professionals. And I'm like, last time I checked balance sheet not equaling zero. Anything other than that is not acceptable. So that,
Co-Host 2: Giles Male (24:03):
Yeah, that was shortcut. And then honestly, El car Ian, that was my favourite episode to record when it found the answer sheet in the eSports and just linked to the answers in the answer sheet. That was fantastic. And then I remember you asked it, you got to, the balance sheet doesn't balance. Can you tell me why it doesn't balance? It was like, oh yeah, it doesn't balance because the assets and lia, the assets don't equal the liabilities in XA.
Host: Paul Barnhurst (24:28):
I remember that.
Co-host `1: Ian Schnoor (24:29):
And then it plugged it, and when we asked it to fix it, it plugged brilliant, it put in a plug, it back solved and it put in a plug. So loved it. They're learning. They're getting better and learning. So Tea, do you want to, yeah,
Guest: Tea Kuseva (24:38):
I have a question for Paul. Knowing all the limitations that you guys have been seeing so far, if someone wants to start experimenting with AI in Excel, what tasks would you recommend they use it for currently? Good question.
Host: Paul Barnhurst (24:55):
Yeah, so I think if you're just experimenting, I would start with just trying different things. If you're trying to use it in your actual work, the areas it's good is one, the more guidance and structure you can give it great at, Hey, help me understand what formula might work here. Now the challenge is it will often give you overly complex formulas or it'll give you a different answer every time. I think it's good to validate assumptions like nsaid. I think helping you build a table of contents, price volume mix analysis, which is common if you have all the data to tell you what the difference is if you're doing some kind of variance commentary, preparing those type of things. I think those are areas it's really good at. I think also helping you select a graph, analysing some data and getting that first pass like some charts and some highlights, you're still going to need to clean it up, but what would you say JI think some of the tools probably got 80% of the way there.
Co-Host 2: Giles Male (25:54):
Yeah, I think the other thing I would highlight in Bennett's putting out a really good series at the moment of articles about all of this, which I'm really enjoying and I think he's spot on. I do think the tools are too early to rely on for the model build and everybody's so focused on the model build. And his point in one of his articles was like, there's probably 30% of a project and there's all these other areas in a project life cycle with a model where you could use AI really efficiently now where you're not looking for a single deterministic answer that has to be right, use it in the scoping and the specification, use it in the post model build phase. So I think if you're not already following, Ian can get that article series. I think it's definitely,
Co-host `1: Ian Schnoor (26:35):
Yeah. Where can people find, can you tell 'em where to find Ian Bennett as well? For those of you who are not familiar with him is one of,
Host: Paul Barnhurst (26:43):
If you, I can drop in the chat. His
Co-host `1: Ian Schnoor (26:45):
Great. Yeah, he is the global head of financial modelling at PWC based in Sydney, Australia. A great,
Host: Paul Barnhurst (26:51):
Yeah, I've had him on the podcast before and we're talking about bringing him back on here. We just were kind of working on this series, so we held off a little bit to talk about all this to speak what Giles said. I had a conversation with him where he mentioned they went out and figured there's 150 touchpoint in their work of a model from the scoping to finish. And I think he said roughly half, like 70 of 'em AI could be used. But then the question was, if AI is used, he said it has to do one of three things. Can it allow us to get more business? Can it save time so we can do more models or can it lower our cost? And he said in many of 'em it didn't. And I think that speaks to what you said, Ian, right? When you had to check if there's a hidden or a hidden sheet, the amount of time it took, you could have checked it yourself probably four times over. And so he does a great job of really laying it out and saying, okay, here's all the areas, here's where it's good, here's where it doesn't make sense, and that type of thing. So I agree with Giles, he's a great one to
Co-host `1: Ian Schnoor (27:54):
And got someone joining Mazana joining from pwc South Africa. Welcome. You should absolutely. Well, all of you should take a look at Ian Bennett, but you should take a look what he's doing. Yeah, no, he's definitely a world leader in terms of modelling as a discipline and understanding that modelling is agree is we're testing these tools to see how they perform on the true Excel build capability. But that's probably not the first place where you may want to be using AI in your models. Yeah, thank you. So you got Ian Bennett's link in there. Great. May anybody want to check it? There is a question here from Vlad and what do you guys think to take a look at? You want to read that out Teia the question from Vlad? Yeah,
Guest: Tea Kuseva (28:33):
So VLA has asked, given their experience, what about building her own agent in Chad G, PT Gemini?
Co-Host 2: Giles Male (28:40):
Yeah, I mean I can share an initial thought on that if you like, because discussed this. So I think where we started with the podcast was we wanted to test these third party tools. I think it was becoming very apparent to us that the LLMs and the agents around them themselves were very powerful. I don't think we know exactly where we're going to go next, but we want to go in a few areas. I think that's a really interesting one that there's a guy, Brian Julius, who I follow and really respect in this area because he is on LinkedIn. Again, sharing all of his experimentation with CPS and agents. I guess that's where you've got to go next. If we think agents can do this work reliably and you can set them up yourselves, not that I know how to do that myself yet. That would feel like an obvious next step for me.
Host: Paul Barnhurst (29:25):
Yeah. Paul, what do you think? Two things. I definitely think you can build your own agents. Now the one drawback is I find the best tools, and I'm talking not just modelling and Excel, but in general, like I interviewed one the other day, that's an analyst tool for fp a professionals using ai, the best tools decide what model to use for you. They may give you the ability to select. One thing we found with this is there was one tool that had 12 options and you had to select which one, and it was just overwhelming because who's really going to run the same test 12 times and many of 'em are going to be very similar. So you change a word as one better than the other. So there's something to be said of having a professional go through and fine tune it and decide which model most often is going to give the best answer based on your prompts. Now is it always going to be right now? And so there's some benefit of being able to do that if you're really experienced. So it kind of gives you the best of both worlds as well as some of the instructions things. So I think there's some benefit, but you definitely could build your own and you're going to get good results. It's not like there's going to be a huge difference. There's not,
Co-host `1: Ian Schnoor (30:32):
At least from what I seen by the way, that also as people, for those of you thinking about looking, trying some of the testing tools, and there was a question maybe I'll show you what we tested in a second here. So what some of the AI tools have done is you enter your prompt and it generates a response for you as you would hope. What some of them do, I guess you can imagine from a developer standpoint, they thought, Hey, we're going to give the user the ability to choose which underlying LLM to use to solve it. So some of them said, which one do you want to pick? And they would have a list of six or seven LLMs that you could pick. And Giles, Paul and I all found that a little frustrating, right? We're like, it made us feel like we were going to have to run every prompt six or seven times and we didn't want to have to do that. We wanted it to choose, right? Because every day they're all jockeying and changing and evolving and we didn't want to have to run our testing over and over and over again. And that's my fear about building your own too. I dunno what you guys think about building your own is it's moving so fast that you need to be able to be nimble and modify where you say something, Charles.
Co-Host 2: Giles Male (31:31):
Yeah, well I agree. And one thing I will say, I think I've probably been relatively negative for a long time about things like copilot, which is always you, not you, but I am hearing more and more stories about copilot and I think it would be the same with agent where you're actually hearing people getting good use out of it. Again, probably not going, can you build me a billion dollar valuation model in five minutes and I'll go and grab a coffee? But actually for lots of people in a finance function for simpler tasks, I'm hearing lots of things that sound positive, which I wasn't hearing anything six months ago about co-pilot or anything else. So I think they're definitely improving. I'm getting to the point myself where I will certainly start giving copilot the time of day, especially once agent is out on desktop.
Co-host `1: Ian Schnoor (32:19):
Copilot itself is kind of cool right now because copilot doesn't build, it's not an agent. Copilot gives you ideas, copilot says, Hey, try this formula, try that formula. Whereas the agent tool actually goes right in and it builds for you. I think it might be interesting to show people One other thing and maybe you guys can talk about it. There was a question, and thank you Laura for commenting on this. I want to show a couple things that I'd like you guys to chime in on as well. First of all, are you seeing my cell screen now?
Guest: Tea Kuseva (32:43):
Yep. Yep.
Co-host `1: Ian Schnoor (32:44):
A couple comments I wanted. So there was a question about what tools have we used? So I will show you if you want to see here now we'll send out a follow-on list, but the only tool that was worth looking at that's not here, that you're not seeing is the one called Truffle Pig, because that's a separate piece of software, right? That's you're going to get in your Chrome browser, but these are the tools we use tabs AI appears up here. It looks like this, it appears as its own tab. The rest of them just
Host: Paul Barnhurst (33:09):
Added. Sorry, I wasn't seeing it for a minute. You're good. Keep going. Oh,
Co-host `1: Ian Schnoor (33:12):
We're good now. Yeah, sorry. So tab AI is its own tab at the top. The rest of them just add a button on your screen. So you've got copilot, you've got Excel Labs, which is the Excel agent. You've got Trace Light, we had Rosie, which is gone now. There's El A, always Melder. These are all different tools that we had looked at and so we'll send out sort of a summary of these ones. I want to just touch on this other thing that you guys both mentioned as well. I thought that'd be interesting for people to see this. So one of the strong views I'm coming up with one of the strong beliefs that I'm coming up with. I mean, there are people out there that think that you won't need to know Excel skills and you won't have to know Excel or modelling much anymore. I actually think it's going to be the opposite.
(33:56):
I think if you're going to try using an AI tool, you should be prepared to increase. You're going to have to increase your skill level and let me show you why your skill level, because you're going to have to understand what the heck these tools are doing. I'm going to show you a great example from a test Giles ran. So this was an example of one of the test Giles ran in the eSports challenge. He had a whole column that looked like this. Imagine a whole column of the numbers and what this is is a column of numbers. It's a text string that has 1, 2, 3, 4, 5, 6, 7, 8, 9, 10 digits separated by dashes. It's a piece of text. And the question was, what you had to do is you had to find, was it the largest one and the second largest one Giles, and add them together
Co-Host 2: Giles Male (34:36):
And add them together? Exactly.
Co-host `1: Ian Schnoor (34:37):
Yeah.
(34:38):
Okay. So that was the quest, the question. So imagine a whole column like this and off to the side in a green cell you said, find me the largest and the second largest digit in the string and add them together. So in this one here, we can see that 89 is the largest and the second largest is what? 79. Add those together. Okay, well what it did, it got it right, but it did this, it did that. That's how it solved it. And so if you're not comfortable, this is going to force you to grow and elevate your Excel skills. Even Paul and Giles and I were pretty experienced Excel users. I mean we've all taught advanced Excel. We know Excel well. This forced us to scratch our heads and look at this and think what the heck is it doing and why is it putting in hard code digits a hundred and a hundred minus 99 and we got it, but this took us a while to dissect and if you've ever handed in a piece of work to your boss, you know that you have to understand it, but we all had a suspicion that this was not the simplest way.
(35:37):
And so we discovered, look how long that is. This was the agent's solution and we discovered that the same thing could have been done that literally just split this text string into separate cells, take the second largest and add them up. And literally what we did, what we did like that the agent did like that. So you're going to have to understand what these agents are doing and realise, no, that's not what I need. It's not the smartest way to do it. We're going to do that and I don't know if either of you want to talk about that issue. We saw that with every tool.
Co-Host 2: Giles Male (36:08):
Yeah, I can talk about it a little bit and it links to a question somebody else has asked. The tools might use functions we're not aware of. There was a couple of functions that used
Host: Paul Barnhurst (36:17):
Filter. XML was the,
Co-Host 2: Giles Male (36:19):
Yeah. Then as ever with Excel, you go out and you say, oh, I've never seen this. And then a bunch of people go, oh yeah, we use that all the time. And you're like, oh god.
Host: Paul Barnhurst (36:27):
Well, I actually talked to Excel about this. One of the product managers at the world, I mentioned it used filter XML, and he just started laughing. He goes, yes, there's an obscure use case. I had to research it. So there's some articles out there and it must've been trained on them and brought that in. He's like, but nobody would use it that way today. It was, you
Co-Host 2: Giles Male (36:45):
Wouldn't think so. I mean, I don't think it's objectively wrong. If a tool uses a function that we are not familiar with, it might still be very good and the right solution, but I think there's definitely a risk it will do that. But yeah, to your point, Ian, to have a model churn out or an agent churn out, something like that causes as many problems potentially as it does offering solutions.
Host: Paul Barnhurst (37:09):
I think there's one other thing, if I can share my screen kind of to build on this and we'll go forward is
Co-host `1: Ian Schnoor (37:13):
Share your screen because just you're never, you all know this, you're never going to want to go to your boss and shrug your shoulder and say, I don't know. That's what the agent did. That's never going to fly, right Paul to say, I don't know the agent did that.
Host: Paul Barnhurst (37:25):
I definitely wouldn't want to be the one doing that. So I had to build a deferred revenue schedule multiple times and it built it sometimes better than others. But here's an example. I asked the exact same agent, exact same question one time right after the other. So I did it three times. You could see a basic deferred revenue schedule. Here was a contract amount, and then it's figuring out how much should I recognise each month. So version one, use this formula fairly straightforward, probably the cleanest of all of them. Hey, if it's blank, don't do it.
Co-host `1: Ian Schnoor (37:57):
Sorry, same tool. Same tool. Or is it three different tools?
Host: Paul Barnhurst (37:59):
Same tool all within the same day, just strictly one right after the other. Same exact prompt. So the first time it built it this day with a date diff and an if and an end, pretty clean, similar to what a lot of us would do in end of month. Second time it decided to put it in a table, used an if or okay fine, but then it did an e date with a date and hard coded the dates used the date diff at the end and it used column why it decided to use column. It was because it didn't have a date in the headers, so it got really messy. Third time, oh, let's use a value and an index and let's reference the front sheet and let's hard code the row number. Those are things you don't want to see in your model and you're going to run into, I think this is a key thing to understand. Gen AI is probabilistic. It's guessing what it thinks. The next thing you want is what the best answer is, and that's one of the reasons audit and some of these other areas, it's really going to struggle with till it finds a way to put enough guardrails to make sure it can do something the same way each time versus deterministic. If I give a math problem, if I put the same inputs, I'm getting the same answer every single time. That's not,
Co-host `1: Ian Schnoor (39:16):
I love this. I love this slide poll, and again, it's one of the five things that we identified that these tools do, and this is a lesson for everyone, for us, and for all of you looking at do never ever just run a prompt once if you're going to run it multiple times because you're pretty much guaranteed going to get different ways that it's going to solve it. And that's why you're going to have to have really strong Excel skills to be able to say, I'm not convinced. And there's a problem with that one, and I think it can be done simpler, right? You're going to have to know how to guide it and direct it because you're going to get different views. So I love this slide. Paul Gil.
Co-Host 2: Giles Male (39:50):
Yeah. Well, I mean pivoting slightly. I see a question about where we would ideally see AI helping with financial modelling in five years. And yeah, five years is a long time in AI world. Paul, Ian and I were always talking about the fact that we might get three months down the line and we'd need to retest everything that we've looked at. So my guess is in five years, something's going to be able to build pretty reliable models. I do worry that there's always just going to be an element of it's just going to do something wrong at some point, even if we're five years down the line. But I would've thought it's going to be pretty capable of building and reviewing models effectively. Yeah. What do you think?
Host: Paul Barnhurst (40:31):
I think at least template types like a standard DCF, A lot of things more complex if you're doing multiple tranches of debt or LBO or some kind of buyout model where you have on distressed debt where you're trying to figure out what you're going to pay to 30, 40 people. Those things can be very, very complex. Or maybe it won't get there, but it'll start to do templates and it will get there on the modelling. I mean, it can do some pretty good stuff. Now, I would agree with you. I think in five years we'll be doing more checking and validating assumptions and things. At least 80% of it I would see an AI being able to do with the right prompts and the right structure.
Co-host `1: Ian Schnoor (41:08):
Yeah, I agree with that. And I would just say though, for all of you, and there's a lot of professionals in this room today, again, I can come back to the same thing though. I don't think you, even in five years, I still don't think we're going to be living in a world where someone asks you to run a complex analysis on a new capital structure configuration for a company, and they are okay if you run it in your ai, hand it in without understanding every single sale, you're going to have to understand what it's doing and how does each piece of debt work and how does the sculpting work and why is it to happen that way? I don't think we're yet anywhere near a time where people are going to, so you're going to have to understand it. And so sure, I am excited about the day when it can give you a great draught of medium or complex analysis, but I encourage you to ensure that you still understand exactly every single cell what it's doing because you're going to have to be able to defend it to your client, your board, your boss, et cetera.
(42:01):
And I think you guys are on the same page.
Host: Paul Barnhurst (42:04):
Agreed. The knowledge doesn't go away. And the reality is AI is a magnifier, whether it's Excel agent or anything else. If you know the topic really well, you're able to get more out of AI than somebody who doesn't. And given it uses complex formulas, there's two real benefits of getting better in Excel. One, you're going to be better at using ai. Two, you're going to be better at understanding what AI's done. So anyone who thinks they don't need to learn excel and modelling really well, I would really encourage you to think again because that's not what all the experts are saying. And we're not just saying that because, hey, maybe we train people or we have an incentive. We're saying that because that's what we're seeing in the testing. That's just the reality of where the tools are at.
Co-host `1: Ian Schnoor (42:48):
Paul, did you make that up? Did you just make that up on the fly? AI is,
Host: Paul Barnhurst (42:51):
I did. I don't even know where I got the idea from. I just kind of thought, I'm going to go here.
Co-host `1: Ian Schnoor (42:56):
Paul, you better copyright that and patent that. That was brilliant. I might want to use that. Incredible. Paul Barner says AI is a magnifier. Write that down. That was great. I would agree with that. Gil, you
Co-Host 2: Giles Male (43:06):
Yeah, I agree. I also, I'm intrigued by where it's going to go if you think there's a generation coming through now that will have only known a world with agents and AI and copilot, so I dunno, the pressure's the wrong word, but is this still going to be the drive to learn the hands-on skills? I dunno the answer to that. I agree that I think we should have them. There's been so many times in this series where Ian and I in particular when we were doing the financial modelling bit, you're looking through, the only reason you spot the issues is because we've done this a thousand times before and I am really intrigued a little bit like the generation that's never grown up without a smartphone in their hand. The next generation's only going to know a world where they've got things like copilot and all of these tools to hold their hand to get the answer. So I don't know how that's ourselves.
Co-host `1: Ian Schnoor (43:58):
Yeah, maybe you're right, but you're ab observ Charles, one of the agents built a model and we knew the balance sheet wasn't balanced. It took us seven or eight minutes and we found the eight or nine mistakes it made and we quickly balanced it and got it working. But that wouldn't happen unless we truly intimately knew modelling it. Well, if you had never built a model or only done it once or twice, you wouldn't have found all those mistakes. Certainly would've taken you hours to do that. I still think people want to talk to people and use technology, use the internet, use excel, use software, use other tools to help you do your job. But I just think that we're at an inflexion point where those people who want to elevate their own game, they want to get technically better and smarter and use tools, including AI to make them push themselves higher up the curve and get themselves better, will excel, no pun intended, and they will be perceived as stars. Those who try to rely as a crutch on ai. I guess what you said, Paul, it's a magnifier. If you want to use AI as a crutch and you're not going to be the top of your game, those people will, I think, quickly get replaced. So it's an opportunity, I would think of it that way.
Guest: Tea Kuseva (45:06):
We have one maybe last question to answer Q and a. Yeah, why don't we take one EF and then maybe we can get everybody's final
Co-host `1: Ian Schnoor (45:15):
Comments.
Guest: Tea Kuseva (45:15):
Yeah,
Co-host `1: Ian Schnoor (45:15):
Sure. Go ahead.
Guest: Tea Kuseva (45:16):
So Stefan is asking, do you have an opinion if the tools work well with structured modelling techniques like fast standards? I have the feeling that agent mode, the clouds add in Excel, you have a hard time to work with the structured calculation blocks. Does that have any implications to modelling going forward from your point of view?
Co-Host 2: Giles Male (45:33):
Yeah, I can go first if you want. I think they do struggle and it's really, I've been thinking about this a lot. Why do they struggle? And maybe these tools are looking or leaning on data that is available to them, and maybe there just isn't that much solid data to the same volume that you have in other areas of whatever you might be trying to get support. There's a lot of written text about the fast standard, but are there that many referable models that are consistent that these AI tools can ingest into whatever they look at? So I think they do struggle, but probably everything we've tested given another six months, it'll be utterly useless because the world would've evolved again and we'll have to come back and test them all again. So I think it'll get better.
Guest: Tea Kuseva (46:18):
Amazing. And I guess with that, maybe if you guys want to share some final thoughts,
Co-host `1: Ian Schnoor (46:25):
Parting thought
Guest: Tea Kuseva (46:26):
Before we wrap up thoughts?
Co-host `1: Ian Schnoor (46:28):
Sure. Maybe why don't go and then you guys wrap it up and we'll finish it up. And I would say I've had the opportunity to listen. I've been at a couple of live talks by a professor named AJ Agrawal, one of the top AI academics and researchers in the world. And his comment about AI is that AI is great at prediction and predictability and calculation, but that it's not very good yet at judgement . And judgement is a harder, it is a human concept and modelling requires a lot of judgement . Now, I do think it will get better and I think it will improve over time, but why should the revenue schedule for this particular company be? Should I build a 500 row revenue schedule where I model every product separately or is it sufficient to do it in six rows and aggregate by category? Should I do it multiple tabs on one tab? These are all things that require judgement and discretion. And so I think that they're important components of a good model build and we're not there yet, but I like the direction these are going and I think that again, for those that are excited and keen use it, we're not suggesting don't use it, use it. Stay in the flow for sure and help it allow the tools to make you better. And then I think we're going to be fine. Giles. Paul, do you want to wrap up? Paul,
Co-Host 2: Giles Male (47:46):
Do you want to go?
Host: Paul Barnhurst (47:47):
I mean, the way I think of it is it's human led AI assisted, just like you often lead a project and you have your analysts assist you. A lot of that's the same with ai. You still have to validate it, you still have to check it. And the second thing I'll say is vibe coding, right? We've been hearing about that for 18 months. It was pretty bad when it first came out. Where we're at is where vibe coating was 18 months ago. So I expect us to have made a lot of progress in 18 months. But the bottom line is, and it gets what it in Giles and it's what we've been preaching on pretty much every episode. It doesn't advocate your need to learn. It doesn't advocate your need to own the process. Even if you get to the point where it can build the whole model, you still need to understand really well, there's a human judgement aspect once it figures all that out and it can manage that better than us. I guess we're all sitting at home on a universal basic income and we'll figure that out when it comes, but I don't see that anytime soon. So my biggest advice is you need to be using these tools, whether you're doing it through the ai, whether you're trying it in Excel, whatever, and you need to be developing the skills, but you also need to be developing your Excel and your modelling skills while you're at it. It isn't an either or thing.
Co-host `1: Ian Schnoor (49:07):
Paul, you're cranking at the taglines today.
Host: Paul Barnhurst (49:09):
I'm trying
Co-host `1: Ian Schnoor (49:11):
Human led. I assisted what's going on here. You use this Mr tagline today I'm
Host: Paul Barnhurst (49:16):
Impressed. I've been reading a book about buzzword bingo and I wanted to see if anyone picked up one today.
Co-host `1: Ian Schnoor (49:22):
Phenomenal. All right.
Co-Host 2: Giles Male (49:24):
And then for me, so I agree with everything you've both said. I would just say I'm really positive about ai. It may not come across like this sometimes, but I am genuinely really positive about ai. I'm very negative about people that overhype it and leverage it for their own benefit. I think it can be really reckless, but without question, it's going to transform the way we go about modelling. It probably is starting to already just start using it carefully. Be very careful who you listen to. We've put out a few names today. Ian Bennett, Brian Julius, there are others on LinkedIn, which is an interesting platform, so be careful, but I do think you have to start using it because if you do ignore it completely, you are definitely going to be left behind. Just
Co-host `1: Ian Schnoor (50:10):
Wait, Josh. Should people be leery? Should people be leery of those LinkedIn posts that say learn to build a full complete financial model in four minutes and save eight hours a day
Host: Paul Barnhurst (50:18):
With those type of Well, they should 100%. Trust them in.
Co-Host 2: Giles Male (50:21):
I know what you're doing. You're trying to trigger me with two minutes left and I'm not going to bite. I'm not going to bite. You should be very careful who you listen to and that's all I will say
Co-host `1: Ian Schnoor (50:32):
With that. Why don't we wrap it up. I hope this has been helpful and it's been a lot of fun. There's a lot of free stuff out there too, right guys, you can get free samples. A lot of these tools let you try them for a week or a couple of weeks. You have to sometimes have to give your credit card, but we did that and you can cancel. Try them. Play around, do stuff, right?
Host: Paul Barnhurst (50:48):
Indeed. Yeah.
Co-host `1: Ian Schnoor (50:49):
We were testing. I cancelled it
Host: Paul Barnhurst (50:51):
Real quick when it was $15,000.
Co-host `1: Ian Schnoor (50:54):
Yeah, try stuff. Just get them. You saw the ones I showed you. Just mess around. Just mess around. Try things and you'll find that it helps you. So anyway, great to see all of you. Thank you for joining us and tail over to you to wrap it up.
Guest: Tea Kuseva (51:06):
Yeah, thank you guys very much for being with us today. Thank you Ian Giles, Paul for sharing your insights and thank you for testing all of those tools. I think that's super, super helpful to all financial modellers. The recording will be shared within 24 hours in the community and then very soon Paul will be publishing it as part of the qua podcast series as well. I have shared a link in the chat. So yeah, keep following us on LinkedIn and we will see you guys soon. Have a good day. Happy
Co-host `1: Ian Schnoor (51:35):
Modelling. Thanks everyone. Bye-Bye everybody. Great to see you all from all over the world. Take care everyone. Have a great day.
Host: Paul Barnhurst (51:41):
Take care.
Guest: Tea Kuseva (51:43):
Bye.