Testing The New Microsoft Excel Agent for Finance Pros with Ian and Giles

Foreign.

The Mod Squad, featuring Ian Schnorr.

Executive director of Financial Modeling Institute.

Giles, male, humble MVP and co founder of Full Stack Modeler. And Paul Barnhurst, the FP and a guy.

This week we're going to dig into Excel Agent. If you're not a good modeler, don't start with AI prompts. Go take a course, build a strong foundation, then use AI to help you.

Extremely impressive. I have a forecast of the income statement. Just eyeballing it, I can see that the revenue directionally is moving in the right direction. Done a great job building that.

They all put actual formulas in in.

The financial modeling task. It's done really well mechanically.

I'm really impressed with this one. It calculated the change in working capital, which is correct. It's the actual change.

What does this mean for the other tools if Microsoft's agent is that many steps ahead of where they're at?

Welcome to another episode of the Mod Squad Pod. I'm your host, Paul Barnhurst, AKA the FPA guy. And I have here with me my other two hosts. Really excited to do another episode. So why don't we start with Ian. Why don't you give a real quick introduction to our audience.

Thank you, Paul. It's great to be back here with you and Giles and nice to see the rest of you watching. I'm Ian Schnur, executive director of the Financial Modeling Institute. I'm running our tests on three statement modeling, corporate finance modeling, and we'll get into some other tests like that applicable to those working in sort of accounting and finance, corporate finance fields. My whole career has been in financial modeling and I'm excited to be working with the two of you on this great podcast.

Over to you, Giles. Why don't you do a quick introduction of the humble mvp?

Sure. Well, it's a pleasure to be back again and I'm particularly excited about this episode, actually, with all the stuff that's gone on in the last week online. So, yeah, Founder of co founder of Full Stack Modeler, Microsoft mvp. Lifelong modeler and esports, I should mention that. More XLE sports player this year. Very, very average player.

No, you are above average. You are above average. You are scoring well.

He is above average.

He's humble.

That's why he's the humble mvp. He won't knit his drill score.

An outstanding competitor. Yes.

So this week we're going to dig into Excel Agent. About a week ago, maybe a week and a half ago, it wasn't very long, they released the beta version of the Excel Agent, which you have to have Copilot to access. It's an online tool only, but it does many of the things similar to these other tools and so it's got a ton of publicity online. I know Giles, you've had many conversations, seen some things, kind of maybe share a little bit of your thoughts so far with what's going on as far as Excel Agent.

I asked a question on the Unpivot podcast months ago saying I wonder what's going to happen if Microsoft, like catches up. So the Excel Agent for me, I'm really excited about. I think it's fantastic. Like if Microsoft could lead the way but have pressure from good competitors, I'm happy. What I'm not happy about, which I may have expressed once or twice, is where people get a little bit carried away with the language and say, oh, you just click a button, get a coffee and your model's built. And I think we need to really unpick whether that's true or not. If it is awesome. But. But let's see.

So what are your initial thoughts in I know you've seen some things online. We've talked a little bit about this. Where are you at now that you've had a little time to think about this? I know we touched on it last.

Week, but I don't tend to spend as much time maybe as some other people on online getting involved in some.

Of the so in has more of a life than you and I do.

He's just a mature. You're a mature adult. That's why I get it. I get it.

I'm not sure that's true. I'm not sure that everyone would agree with that statement, but maybe I'm just lucky that I don't have quite the time. But that's fine. I just spent some time online. Listen, I've seen what's going on. I don't love the. You know me. I think we're all in a similar boat. We were all excited about all of these tools. The Excel Agent, while it was frustrating to get launched and installed for me and I couldn't get it working easily and of course right now it's only in the online cloud version of Excel and you seem to need a Copilot license. So it's not the most straightforward path to get it, but I finally managed to get it working. It's impressive. I mean, listen, I will always be impressed when I can, you know, write an English sentence, or presumably someone can write a sentence in any language and then you just watch it building things in a spreadsheet I mean that's still pretty mind blowing. It performed very, very well. But as you said Giles, we're not talking about where you enter a sentence. It does a whole day of work for you and you go home. I mean we'll see that in the test especially when it comes to model building. So but really impressive start and I'm excited about what, what we're seeing here.

One thing I said over the weekend is we saw you know, a lot of people getting really excited about it and maybe over promising on what it could do is my conclusion and it hasn't changed. I think it really was at the start. It's, I'm more convinced of this now is if you're not a good modeler, don't start with AI prompts. Go take a course, go build some models, build a strong foundation, then use AI to help you. If you're using it for assumptions, like to help validate assumptions to give you ideas of inflation, maybe some ideas for scenarios, how to write a formula, all those things great. But don't just think I'm going to become a modeler today and write your prompt and turn it into somebody that's just a disaster waiting to happen.

Well, I'm going to show in my testing. I am going to show. I mean I agree with you 100%. People need better modeling skills than ever. I believe take a course with one of you, get your AFM certification, right? That proves that you have incredible modeling skills because it is only at that point, I mean I was able to find errors in some of these, some of these AI generated models that others might not find unless they were also really strong modelers. And so, so it is important you do not want to be caught off guard with a mistake that you couldn't catch.

And that was the message from so many from my posts is you know, Lance Rubin and many others were saying, I fully agree with you that it's going to make the, the best modelers are going to get benefit out of it. If you don't know what you're doing, then learn what you're doing. Giles, you're going to say something. I saw that.

Look, I was just going to try and pre counter the accusation that like for me personally as the co founder of a trading business for Excel and modeling it would be like oh, of course you would say that. I don't care where you get training. If what you just said Ian, is spot on. Like if you want to go and train with anyone that's reputable, please do that. Rather than do what you just suggested, which would be to just go, oh, AI, I'm a modeler. Hit a prompt, go and get a coffee. Like, just get the training, you know.

Building a model, as we all know, is a. It's a discipline and it's a skill. It requires judgment. It requires thinking and asking good questions. It's no different than any other skill like playing a sport or flying an airplane. I mean, in theory. In theory, I could be, you know, chosen to be a pilot of an airplane. And 99% of the chance that if, even though I know nothing about flying a plane, I could become a pilot tomorrow and, you know, the plane could take off and land and. And I'll get lucky because there are AI tools built in to airplanes and autopilots that it'll work. But you don't want me there in the odd chance that something goes wrong, right? That I need to troubleshoot. You want to make sure that whoever is driving this engine, driving this machine, knows how to troubleshoot, knows how to look you in the eye and assure you that it's all working, that they're all set. Because things do go wrong a lot, and you need to make sure that you can step in when needed.

It's a really good analogy. You think, right, commercial pilots to fly those big planes, I think they have to have, what, like a thousand, two thousand, so many thousands of hours before they can even get that job. And it's not because the tool doesn't do 80% of the flying. It does. A lot of it's on autopilot in the machine. When those landing gear doesn't work, when turbulence hits, when the wind goes on fire, I want that experience, pilot.

And by the way, I mean, you don't even need AI for airplanes. I mean, airplanes have had autopilot mode for a long time. Sometimes when I run webinars all over the world at times, I'll start and I'll, you know, ask, you know, the group or the class. Hey, who here would get on an airplane with no pilot? Imagine one day walking onto an airplane, and they said proudly, look at this. You're gonna fly. You're gonna go up in the sky. There's no pilot. Now, there are taxis doing that, of course, and there are cars. And maybe it's just a mindset and we will get there. But right now, I can promise you, most people I speak to would not be comfortable being on an airplane, flying it if there was no pilot at the front. Even though if they thought about it, they'd Realize that when there is a pilot, that pilot may not be doing that much on their own anyway, but they're there. Right. And I don't know if you have a thought about that analogy, Giles, but that sort of feels relevant to me and what we're talking about.

I do not want you flying any plane home on anytime soon, so.

So would you rather have nobody flying it? Is that what you're saying, Giles?

Oh, that. Well, that's different. I think I'd rather have Ian there than nobody. Just. Just as a backup. Yeah, I take you over nobody. There you go. There's a compliment.

And you know what? You probably would because you'd probably take a human because, you know, presumably you could speak to air traffic control and they could try and give you some instructions. Right. But what you're saying is you want someone there who can help troubleshoot important.

All right, so I think we. We've covered that. Made some great points there. I want to share one other thing. I did some testing over the weekend. I showed this to you guys earlier and we thought we it on the show for a minute. So I'm going to share it. So let me just level set what I did and we'll bring it back again after we've done some more. But I took the easy Excel Esports case that we've tested the last few weeks that the Excel Athlete case, and I ran it through Rosie AI, and I ran it through the Excel Agent, and I ran it through each of them twice. And so what. What we have here is say, what.

Model do they use?

This one's using Copilot. This one's using Chat GPT. Very similar. What's the level? Max score, how they scored. Each of them got the exact same score. They each got 1210 out of 1250. They missed the bonus question 5, which there's a very easy reason why they did. They both took roughly the same time to run it within a second of each other. They all use formulas each time. All of them were formula based. And in some cases, they use the exact same formula between the tools. So let me sort this by level because I think it will be kind of interesting. So. Right. I could see.

Oh, hey.

They used the exact same method for level one.

So you are. This is Excel in the cloud that you're showing us, I believe. Correct.

I'm using Google Sheets right now, so shame on.

Oh, my goodness. Giles, close your ears.

It's fine. I'm relaxed about things when. When people do things that are slightly different to me, it's Fine.

All right, so question one, they both answered it the exact same way. Question two, similar, but different approaches, right? One put a value in the front, one used the double negative in the front to convert it from a text string. And I think one did a sum here, like you mentioned before. One did a plus and did an array constant.

Can you just remind us, can you go left for one second just to show everyone one more time? You're talking about these. Each of these rows, just so we. Just so everyone can see it.

Each row here is. First row is Rosie, second is Excel Agent level one. In fact. Let me hide.

Let me hide this. So that's right. So just a reminder, you're showing how you ran it under Rosie AI, which is the tool we looked at last week versus the new Excel agent, and you're saying question one, they did a very similar. The same. The same thing, didn't they?

You're saying for question, exact same thing. There's really kind of one simple answer for that. So they did the same thing. If we go to level two, they each took a slightly different approach, but very similar. They each used the lat, they each used text split, substitute and large.

So I think they're both good answers. I think the fact the XL agent has used the array as part of large to pull both the first and the second largest is impressive. So. But, yeah, both good, you know, but.

What'S interesting is over here, try number two. They each used a different answer, so they may have both used lead again, but it wasn't the same formula. Something was different in it. Either they, you know, like the first one may have done some. The other one may have done a plus instead of the array constant. So they changed up the formula a little bit. I thought that was interesting. Now, if we go to question three, very different approaches and not surprising. Rosie took a really complex method. I would never do it this way. It works, but. Right. Putting an array constant for the numbers one to nine and a fine, when all you need to do is a simple indirect.

Yes.

And then the next time it did the simple indirect. So three of the four times it used the same formula. But this gets back to what we've said before and we'll continue to see this. If I'm getting a different answer every time, what if I'm adding a new year? Am I confident it's going to use the same formula as it did in the prior column, or is it going to try a new way of solving it, or am I going to be smart enough to prompt it? To say, hey, you need to use the same formula as you add the new year.

Right.

These are little things that I think can confuse people. Exact same answer here and then, you know, same answer here, but different here. And so the more complex. It used a different answer each time. Right. Because you would agree with this is you got to think more through the solution than this one. There's really kind of one way 90% of people do it.

Yeah, but. But what? Neither tool has spotted that the answer for level 5 is one very small tweak to the solution that they had at level four with Len and Substitute. So, so they both answered it. Right. But they've both taken quite an overly complex route to get there. But it's still right.

Yeah. I mean again, and this continues to. Is very impressive. It's. It's mind boggling actually that, you know, they can read English instructions, figure out which are the green cells or the colored cells that need to have the answer put in. It understands that and it puts in an answer. Brilliant. At the same time, I continue to believe that any, that if you are using this in your work to try to, you know, take an instruction and build a solution, you sure want to make sure that you understand what it has generated as a response to know if it's reasonable, to know what the tool's doing, to know if there's a better way. And so there's a lot of people in, in the Excel world that don't use the indirect function or the sum product and don't understand what they do. But you know, the, the, the flip side is it's a great learning opportunity to try and take a solution and say, hey, I'm going to learn something by what it's done here.

Yep. So I think the highlight is great. They all put actual formulas in.

Yep.

The only place they hard coded.

Sorry. Bless you.

Let them edit that out or we'll just. Bless me.

Leave it in. Leave it in. I agree.

We're leaving it in. The only place they used text was really around array constants or you know, setting it to a one or two so it makes sense. It's not like in some of the others where we've seen a lot of manual.

Yeah. None of these, none of these has typed in dead numbers into which it could do instantly but a human couldn't do. So they have all generated formulaic answers for the solutions. But fascinating to me, as you said that they've used and used which. Which makes sense. Two different people would choose two approaches to solve the same problem. And two versions of AI have chosen different ways each time, though half the.

Time they've chosen something different. Five minutes later getting the exact same question. That's a little. Could be concerning.

They are both very impressive sets of solutions. I know they're not perfect, but they've understood the.

On the whole solutions here.

Yeah, right.

They got 1210 out of 1250. That's a great score. The. The answers clearly show that they've been trained well on Excel formulas. They're able to reason through complex formulas. And let's just show a quick example. So I think we'll move into testing the agent mode. So this is the same case I just showed you. What we're going to do is I'm not going to do level one and then ask it to do the rest. We're going to have it do all seven.

Paul is. I'm just conscious. Like we really want to give Ian as much time as possible on this one. Do we even need to show this?

No, I think we should go to the. Let's go to the next one because.

You'Ve basically just shown it. Basically got it right with formulas.

Yep, I'm with you. All right, so we're. We've been recording that whole time. We're providing our humor. You get to hear us unscripted. We might let him edit, but we'll probably leave it all in. All right, so I asked it to open the new case. Is it going to open it? Error installing functions. All right, I'm going to pause it for one second. We'll be back with the case up. After some internal discussion, we've decided to skip the Excel athlete case because we just showed you it can solve it. In the interest of time. If you've watched the other episodes, you've seen it twice. And so where we want to focus on is the humble mvp, the greatest MVP in the world, the musical. It will be coming to Broadway soon. You'll be able to watch it. It's a two hour long production. But in the meantime, until Giles gets the funding to build that, he's had an Excel case built all about it. And so this is our complex Excel case. This is a lot harder than the other one. It has things like the humble closet where we can see Giles has all his fur coats and outfits. It has dance formations. So if you're a dancer, you might recognize some of these. If you're not, you might be like, what the heck? But they have to figure out different moves and positions and you can see the dancer and the formation and here's the lyrics to his awesome song. So, basically there are the bonus questions in the different levels of the actual case. This is the main stage here. And so what we're going to do is we're going to feed it all this information and we're going to ask it to solve level one. If it does that right, we're going to solve the other levels. So I put in the same prompt we've used before. We're going to go ahead and hit play, and then I'll give Giles 30 seconds to see if he wants to add any color to the case before we just let it run. So we're going to go ahead and kick off level one. Go ahead, Giles. Any color you want to add.

Only that level one can trip people out, or we've seen it trip tools out before, where you've got to look at the closet. So if you go back to the Humble closet tab, you've got to go over to the right hand side. You showed the picture. But what you're actually going to have to do, the tool is going to have to do is look here and it's looking at counting the number of items in each of these vertical fur coat stacks. So this can be quite tricky. And then it ramps up. So there's other questions about the fur coats, then the dancers spatial logic that you've got to deal with. So, yeah, this is tricky.

The reclusive, recursive. Let's check out some of these names for a second before we pause here. We got the Glow stick, Arctic Rave, the one I'm really curious about. Do you really have the Pimp as one of your shelves in your closet, Giles?

100%, yeah. Every one of these fur coats I own and handmade, they're great.

The Queen of Narnia. And that, folks, explains his humbleness. So in the meantime, we'll be back here in a moment. All right, we're back. And we're experiencing what others have shared on LinkedIn and other social media. That right, Excel Agent is in beta. And sometimes what we find is things just hang up forever. And we're experiencing potentially that now. It's hard to know. One of our problems with Agent is it doesn't tell you where it's at in the process. All you get is, hey, here's this little moving thing at the bottom. I guess it's still working, but you just have no idea how close it is. If it's really working, is it going to stay there forever? So we've made the choice to kill it Any. Any thoughts on that, Giles?

We've been going. How long did you say we've been.

We've been going now 11 and a.

Half, 12 minutes now, believe it or not, but that's actually not the same as forever. I know in our day, our current brains, we think that 10 seconds is forever, but it's still to your point. I'm just bugging you. It's a long time, isn't it? And it's a long time and I agree with you. What I liked about the other tools we looked at is they gave us some sense that they were working, processing, thinking. So this we're not sure. We're just seeing that moving dotted line at the bottom. Maybe it's hung up, maybe it's working, but it's hard for us to know. Giles.

Yeah. To add to that, I think the measure that's always in my head is, could I have done it faster? And that's been my frustration with ChatGPT and Claude at times where you go, oh, God, I could have just done this myself. The first question, once you understand it, albeit there are some tricky areas to it, you could have done that within five minutes, I would have thought, if you knew what you were doing, you get what, 30.

They got 30 minutes for this case.

30 minutes for the case. Yeah.

You, you, you, you.

We would have done this quicker manually.

Yeah. So level one, you need to be finishing in probably three to five minutes. If you're doing seven levels. And bonus questions, definitely. If not less. Ideally, a lot of them are doing 12 minutes for level one. Right. Especially depends on the case. But I mean, your more advanced, experienced people are one, two, three minutes for level one.

Yeah. Maximum.

Yeah, yeah.

It's a really easy one.

It's the easiest one in the whole question, of course, isn't it, Giles?

This question, this is the easiest level, I think. Yeah. So we. And we asked it to just solve level one. So there you go, we have killed it.

So it did not perform nearly as. It didn't perform at all, but it didn't perform. I mean, whereas the other tools we looked at did solve this level, didn't it? Fairly quickly.

Yeah.

You know what could be interesting, and we'll just give it a minute or two, is just say, review level one and let me know if you have any questions. Just see how quick it comes back and reads it, how it thinks about it in the interest of time. Review.

Okay.

Please review the question and let me know if you have any questions and how you would think about solving it. So not asking it to solve it, just see if it will come back quickly. We'll give it a couple minutes here and then we'll just kill it if it doesn't give us anything. Yeah, and that's the biggest thing. Agent mode. You know, I think the. The biggest issues we're all experiencing from when we online, different things. One, it's online, it's not in desktop. Two, you just have no idea is it hanging up or is it working? And, you know, I think the. The third thing, which I think is a good thing, but you're seeing is one, it picks what it's doing. You don't have to select through a bunch of different models, which at times can be a problem. But for, I'd say the average user, that's a good thing. Right. Not having to try to figure out.

What model to use. I think we kind of sat on that after the last episode, which is probably still. My position is, I think having the tool choose which is the best LLM would be great. It doesn't feel like. Well, none of them that we've tested so far do that. Having the choice manually sounds great, but actually might add a layer of even more stress and confusion. But I do think the big drawback at the moment. Well, they're all drawbacks, it being online, massive drawback. But it's. It's a first stab and I'm sure it will end up with a desktop. Not seeing the thought process, I think, is a really big drawback at the moment. But again, maybe that will update as well in a future version.

All right, well, we'll give this about another 30 seconds, then we'll just go ahead and kill it and move on.

Interesting though, isn't it? Because all you asked it to do this time was just say, you know, what are your thoughts on level one? And it seems to be just hanging.

Part of it could be. The day we're testing that now has been out a week. Are a ton more people on it and that, you know, the bandwidth isn't quite there yet. Maybe hard to know, but we definitely, you know, people complained about it hanging and we're now experiencing it. This is the first time I've really had this particular experience. All right, we're gonna kill it. Gonna close this. And we'll be back in a minute with the FPNA use case. We'll run through a couple of those and see if we can get them to work. With any luck, you won't be listening to us just ramble with nothing happening on the screen. So we'll be back here in a moment. All right, we're back. And now we're going to cover some FPNA use cases. We're going to start the first one with what we call a PVM price Volume mix can be done on gross margin. It can be done on price on a number of different things. This is a case we do with our FPA students in our courses. It's called Paul's Getting Spicy. It's an inside joke because every so often I get a little grumpy and my co partner says depending on how many peppers he calls, that I tell him I am decides whether he'll come to the meeting or not. So he labeled that to have fun. But let's get to the real point. Basically, it's a smoothie business. There's three types of smoothies. There's B.B. barnhurst Bake 6PMP, Polly's Mango Punch, and the Boss Barnhurst Organic Superfood Smoothie. So we'll see here we have units or volume of what was sold. You can see the percentage. So this is what we budgeted. You can see BB was supposed to be 25%. These other 38, we could see what the gross margin was supposed to be. The gross margin per unit, how much margin we get on each unit, the overall. Then we can see the actuals. In actuality, we sold more units, different mix, different gross margin per unit. So what we're going to ask the tool to do, and we can see we have the formulas in here. So this is fairly straightforward. We're going to ask it to calculate what was the price amount, how much was due to volume in total, and then how much was driven by mix for each product, how much was the miss of the volume for each individual project. So we can understand the mix. It should come back with an answer of 220. For the first one, we're going to ask it to just solve price. Then we'll ask it to solve the next two. So this should be a fairly quick return, but let's go ahead and kick it off and see how long it takes. All right, we'll be back in a moment. After several minutes of discussing things like famous parents and singing and videos and all kinds of other stuff, as we waited, we decided to come back in. And you can see agent mode is still spinning. What we don't know is, is this due to agent in general not working? Is this something with my account? But these are the type of things you're going to deal with in real life, especially if you're trying to use a tool in beta and so it's just something you have to be aware of. You know Excel Labs has worked great many times for me so I'm still a proponent of agent mode. I think it can do great things but at the moment it's not working well and that's always a challenge of live testing. So what we're going to do, we're going to get in set up and we're going to do his testing here in a minute. But before we do that in or Giles, anything you want to add to this section of our testing? Anything you want to tell the the audience?

I'm still reeling from the news that Giles comes from famous progeny. I'm but you know what? Everything makes so much more sense now. It all comes together. The, the, the, the, the white fur coat, the, the singing, dancing, the performance art I I, I, I it's like it clicked for me Paul, what about for you?

It did knowing he has you know parents that are quite musical and in the music that makes sense of his videos and his productions and we could see where he gets data incredible talent from.

Well I have none of it I, I just know luckily my sister, my brother in law are very talented so I'm just using their talent.

Ah well I, I, I don't agree with that part but it, it all comes to hangs together now as for the tool. Yeah I mean listen you're right Paul. Maybe this is just your account or your system acting up however this is what people potential experience let's see if I have any better luck with Again I said this before I wish though unlike the other tools I wish that agent was giving me some sense that it was processing, thinking, working refining an answer. It gets frustrating when you just see it the dots and bars moving without any sense for whether you're hung up or whether it's going to generate an.

Answer and it's clearly it's not working not just hung up I just ask it you there and it hasn't responded.

Yet is deep oh it's deep in thought deep in thought that that should.

Not take long to respond to.

Well can I just add one thing and again it's just an observation because I've actually seen some posts from Microsoft people sometimes resharing other things from other people. The difference between the message you get or the assumption you might make about its performance from what you read versus this we don't know what the cause is is night and day and that and again that is the thing that gets me triggered a little bit. It's like, God, we just need to be objective and honest about this stuff. It's not perfect. It's beta and I don't know why. The messaging isn't just that. Try it. Let's help it get better.

All righty, I'm going to pause, we're going to switch to end screen and we'll see how this works. Back in a moment. We are back with Excel Agent mode set up on another person's computer.

It didn't like you, Paul didn't like you. Let's see if it likes me any better. I mean, this is now my screen you're seeing in the cloud and not my favorite environment, but for spreadsheets. But in the cloud we've got the Henderson AFM model. The model that people a full three statement model of a company with a cover and executive summary, an assumption sheet, the scenarios and then the. The actual model. This is exactly. This is a classic three statement model. It's exactly what people need to build on the AFM exam. And so I am going to get the. I'm going to get see if AI Agent, if agent mode can answer some questions. Let's start with the same simple one I've been asking. Are there any hidden sheets in this file? And I sure hope my version works better than yours. You can see though, just like oh, here though look, within a few seconds it likes you.

I guess Microsoft knows who to treat.

Well, it was verified and if I recall, I think I'm so Giles can't even get the software. If I recall, yours is hanging up on you. I might be the only non Microsoft MVP in this room. And mine is working, isn't it? What do you make of that?

Yeah, well, I'm being thrifty because I should be able to download Copilot for free as an MVP and I couldn't work how to do it, so I haven't done it yet.

Giles and I are just being blackballed by Microsoft.

No, we say too much. We're too vocal on LinkedIn. We're being blackballed.

Don't revoke our status. We love you, Microsoft.

But look at that. It did work, right? So there are hidden sheets. It knows that the COVID sheet is hidden. The clandestine sheet is very hidden.

And.

And it cannot be unhidden via the Excel user interface. Very nice. So. And it even tells us how it checked. So it says there were two hidden sheets. One hidden, one very hidden. How I checked it queried each worksheet's visibility and listed any that aren't visible. Okay, nice. Well, it passed that test. What about again, are there any white values on this sheet? We discovered sometimes finding cells that were painted white worked and sometimes it did not work with the agents we were looking at. So let's see if this does it. Now, this one is not. Let me just double check. There should be here. I don't know where they are, but this file should have some. There we go. Yeah. So I do have some hidden sheets here. We can see in my formula bar that there are some cells that have been painted white. And let's see if. If it can. It's. It's reasoning now it tells it. It sort of stopped for a second and it's checking and it's reasoning. It says checking for hidden values. Although I looked. I asked it to look for white values and it's sort of understood that white means hidden. So it's doing that. But it's. Again, we don't have a good sense for how close it is. Again, Giles, to your point, to your great point earlier. Again, I do the same thing. I like to say. Could I have done this myself faster? And again, control A control and the letter A selects all. So that doing this manually takes no more than 10 seconds. Control a selects the whole sheet and then going to home and then to the, you know, shading color. If I was to shade the entire background gray, I can instantly see. And all I have to do is scroll down. I can, I can zoom down, I can scroll down and I will see them so clearly. Much, much faster to do this right now on my own. But it's exploring different approaches. Well, we might just stop this one because it's not giving me much guidance, is it? Oh, wow. Okay. This one, it took 72nd seconds. This one says no white font values were found. Look at that.

Tells you what range it checked. Those fonts were right outside your range. Weren't that range it checked? Which is really weird. Weren't they like in here?

No, they're inside the range, I believe. Let's see.

There they are.

They are.

Okay. I just.

S. Okay. Yeah, they're inside the range. They're here. They're stu. And it says it checked B1 to U340. So that's fascinating because again, I'm using this. So to me we use these sorts of tests. This is a general. As a general check on, you know, capabilities. Right. So other other were able to do that. Now let me see again, if I can find any inconsistencies, we know that this formula has a dead hard coded value at the end which is a bad thing in the world of modeling. As does this cell here. Let's just see then if I can ask it to look for. For. Are there any inconsistent formulas on this sheet and you know, it might take a few minutes but we. But we know that it's working right? We know that it's. Here we go so we know that it like you.

So that's good.

I am a little bit concerned, you know back to yours. You know I'm. I'm a little wondering whether there's something up with your. I mean we. We can't know but at least on mine it's giving me some minor prompting. Right. And it's changing this so. And I'm also noticing on my using.

Edge I'm going to try Google Chrome and see if it works.

You'd think that it would have a more successful time with Microsoft's browser.

That's going to be my ironic moment here.

What a bit like. A bit like. You would think using teams would be easier than using zooms. If you're a Microsoft person you might think that too.

But on mine, Paul, I don't know if this mine is changing colors. The little dancing dotted line is changing colors. I don't know. I think I saw that changing colors on yours.

Was it.

Or am I. I don't think it was. I thought it was just red the whole time but anyway it's.

I think just the fact you've got text coming up shows that you. Maybe pools wasn't quite working the same way but.

Right. Right. Let's see. Yes. Inconsistent formulas were found it well total inconsistent 392 that's a lot. That's a lot. But see here we know that row 13. I'm just gonna. I mean I'm not sure sometimes it's giving me. Some of these could be hallucinations and. And. And actually correct. But the one I'm looking for is row 13 which has a hard coded value and I don't see. Do you guys see. I don't see anything that's pointing out to row 13 that it has the error seeing anything.

Also it's giving you. It's giving you R1 C1 references which is a bit.

That's confusing a little unusual and for those of you who are not familiar with that there are two ways to. To denote cell references. In fact would you. I think 99.99999999% of Excel users use. I don't. I forget what the name of it is. But a cell name is D2. But you can also call it. You know, you can use the rc. I don't even know. I don't even know why. Maybe it's from a. From a programming standpoint, perhaps.

I'm sure it has to be from a programming early.

That must be what it is, right?

I think it is. I've used it a little bit in esports for map cases, but beyond that, I've never used it in modeling, to be honest.

Well, let's see. One here. H109. Yeah, I just. I mean, in typical grid work I have not seen people tend to use it J. Let's just hear J28. I don't know what it's J28. So row 28 is just the gross minus the freight. This formula is the same all the way across and it tells me it was expecting. I'm not even sure how to read this, to be honest. I'm not sure what it means when it was expecting R row 57. I don't know why it was looking to row 57, but that doesn't make any sense to me. So I'm not sure. Giles, do you have a sense for what this is?

No, other than obviously the numbers are going to be a reference from the starting cell, so it kind of makes it even more difficult. So it's actually from.

Okay.

Oh, what's that next bit though? Is that more useful? It's got hotspots. Go up a little bit.

Hot spot row ranges with multiple deviations. Rows 108 to 110. The ratio is 142. But the problem is, even in the first section here, we're not understanding what it's.

Why don't you just ask it to give you traditional references instead of our, you know, CR1C1 notation and see if it. Then we can at least try to understand it. Because how often we use R1C1, like.

Never. Can you please use traditional references as opposed to R1C1 notation? Sure, let's see if it can do that.

I had to google it because I wasn't sure it's A one notation. So interestingly, you're not now getting the text on the side. The color is still changing, but you're not getting that.

I opened mine in Google Chrome and it's still just frozen. I even just said hello. Why do you keep hanging up? It won't even answer that question and.

You might have to scroll down. I think there's more that's been written underneath that. Yes, yes, yes.

I can use traditional A1 stuff. Going forward, I'll show formulas like D22. Okay. So anyway, I think we can agree though that it was not. I mean, even in spite of that, it was not.

It was not finding what we wanted.

Impressive. No. So what I'm going to ask it to you. Why don't we. It did not find it. That was. I thought that was going to be a little bit different. Let's try.

Try.

Why don't we try this? Why don't we try. I'm not even going to ask it. I'm not even going to ask it to tell me why the balance sheet wasn't balanced. I'm not feeling optimistic that it will determine that. But what I am going to do is ask it to build a model. We're probably going to need to pause for this because when I tried this earlier, it did do something and I was pleasantly surprised. But I'm going to ask it to build a five year forecast model on the model.

Where are you doing this by the way? Because I can't. We can't see anything moving on the screen.

You do see it. Okay, so this is the starting point of the model. This is just the three years of historical financial statements for Henderson. This is what the starting point would be of any financial model. Start with the historical financial statements. This is the starting point of the model exam, the AFM exam. So this is how people start their models. A historical set of financial statements and we build from there. I have simply said build a five year forecast model on the model sheet for the years 2025, 2029. Build separate schedules for revenues, cost, depreciation, income tax, working capital, debt and equity. And I've said make reasonable assumptions and I want to see what it can do. So I suspect that we are going to. This is probably going to take a few minutes, but let's just see if we start to get a, a prompt here. And then I know you're, we're timing this one so we can see how long this is going to take. But it already said it's planning, it's organizing. When it does give you feedback. I'm kind of enjoying this feedback. It's not too much, but it's first, like, at least I know it's thinking, right? It was planning, it's doing something here, it's organizing and now it's defining, it's planning, organizing, defining. So it's doing something. So I like that.

We've seen a few versions of this as well, haven't we. So we've seen one where we got quite a lot of information shown and it stayed there and you had to scroll back up I think. Was it Rosie last week where it showed it but then took it away. It was one of the two.

That's right. That's right. It would show it and the.

And then it would go again. Yeah, I found that. I found that frustrating because I wanted to read. Even if it was getting it wrong. I wanted to read it and see what it was getting wrong.

That's right. And we'll see if. Of the two tools we looked at previously, one of them gave us solutions and then said do you want to apply them? And you had to click apply. Apply. Right. Where's the other one?

You.

It just went right in and did it. This one is actually saying finally it seems to be making some good progress here. This is now finalizing the schedule setup. But we can see it's been running only about a minute or so. Right. Paul. I think so far. And it's implement. It's got a lot of good action words here. Right. It was defining. It was. Now it's finalizing and implementing. It's doing something. I haven't seen it. I haven't seen it put anything into my spreadsheet yet. I don't. Right. You know what I've discovered? Sometimes it adds things and you're not even aware it's adding things down below. But it. Outside of the site range. But it is working here. It is. Obviously there's a lot for it to.

Choose from as well, you know because if you just think about the prompt, you said build a five year forecast from 2025 to 2029. So it has to interpret that you've got three, three years of data in there. It's got to find the data in row seven. I think it is to see that those three years are the prior years. If you think of what a modeler might do, you could go truly vertical on the same worksheet like a lot of AFM people do. You could go my sort of fast approach where you. You pull all of it out. You have separate inputs tab. You don't do any of the outputs on the same starting model tab like so how's it going to make those decisions? If it did either one or something in the middle, I'd be pretty impressed.

Agreed. Agreed. Now we formatting and final checks.

Final checks.

Now we. You know the other tools did attempt something not quite ready for prime time. But let's see what should we pause.

And Come back when it's done or keep.

Why don't we pause again? I think it's helpful to see though that there's, there's definitely some waiting but why don't we pause and then we'll let you know how long it took once we come back and we'll show you exactly what it looks like. As soon as we have something on the screen and it has stopped working, we are back.

It's insane. No, in all seriousness, we've been very impressed with the last round of what we got built. But in Ryan, take us through a little bit. The reason for what, 11 and a half minutes and what do we get?

Yeah, yeah, amazing. Just under 12 minutes iterated but it showed me what it was doing and it took about nine or ten minutes until it started to start populating my, my spreadsheet. I always like watching it because it often makes mistakes at the beginning but then corrects them and fixes them. So listen, this is pretty, you know, pretty impressive and extremely impressive. I have a forecast of the income statement. Just eyeballing it, I can see that the revenue directionally is moving in the right direction. We've got cost, it is building links, it is just linking the revenues and costs down below to schedules. I asked it to build schedules. It is got something. It's got nothing for cost adjustments, but it's going down to ebitda. It has a link to a depreciation schedule, a link to an interest schedule and it's got taxes. Now I am wondering, I'm not sure what it did on taxes, but it has, it is assumed all taxes are going to be cash and no deferred taxes. So that's the kind of thing I need to understand as a modeler to know if I'm comfortable. Why did it do that or not? And the total here is also coming from below and net income. So it's not a great job building that. And then the cash flow statement is adding back, it's. It's adding back the depreciation from, from the depreciation schedule. So it's done some impressive work. It's pulling in change in working capital. It made some assumptions on the capital expenditures here. I'm not sure we'll go see where that came from. But the point is it has a fully integrated complete income statement of balance. You look at the cash flow statement. Let's look at the balance sheet. The balance sheet is built and just eyeballing it, it's actually balanced, right? Look at every year the, it has a five year Forecast balance sheet. It's actually balanced. Eyeballing it now a financial modeler, a good financial modeler would know that you don't ever want to see negative cash on a balance sheet. So we'll see what we can do about that. And I think it's giving me a warning about that down below actually. So look what it says it did. It actually says it built a five year forecast. It said it added five years. It tells me all the work that it did here. It built a driver's base model rolling forward gross revenue by year over year of a growth rate. A capex is a percentage of net revenue depreciation show. It tells us how it calculated everything. It tells us the assumptions it used which are what I like.

It also says is the assumptions are editable like like hey go ahead and modify them. We actually built them properly.

And then it even says you look at this ending cash trends negative because we modeled no revolver draws. That's like if you like I can add an automatic revolver to keep cash greater than or equal to zero for a minimum cash target. That's impressive and wanted sensitivity table. I am going to ask it to add a revolver to see what it does on that front. The working capital looks reasonable here the net PPE looks reasonable. Have to see what it did. It did not use a revolver. The deferred income tax is a curiosity. It has just linked it to one single cell. So it it kept the deferred taxes.

But up above didn't it show no.

Deferred income taxes, no deferred income tax expense which would if you had no deferred tax.

Oh gosh. Held it to the last thing you're never.

Yeah that would keep the balance sheet constant. But I'd still prefer to build in a formula. But it's okay it's doing this. It's got the long term debt. So this is quite impressive here. It actually made some very reasonable assumptions about revenue growth. It made some assumptions about freight and warehousing cost of goods sold tax rate etc. Receivable days. It made some. It made working capital days assumptions and it made some assumptions around long term debt and an annual debt repayment. Right. Impressive. And then it has the little schedules down below. So this is pretty, pretty wild. It's assuming a growth rate for revenues and cost. It built in a fixed asset PPE schedule.

It what does it do for cost? Because I noticed the cogs went down but the revenue went up.

So did it.

So for making the cogs are lower.

Than it's Assuming that costs are just a percentage of revenue. So not my favorite way, but I, I told it to just make some.

Yeah, yeah, yeah. I mean, acceptable given what we told.

Totally, totally. It's not, you know, it's not, it's not factoring variable and fixed cost, but that's okay. For this purpose. It built in working capital. I'm really impressed with this one. It calculated the change in working capital, which is correct. It's the actual change in the working capital. This is the working capital, the assets minus liabilities. It did that. Right. The change in working capital is the current year minus the prior year. However, for a financial model, we're usually talking about the change in cash which needs to be the other way. So the sign should be negative. But I'm really impressed because it did that. It actually knew to do that. So on the cash flow statement it flipped the sign and it made that negative. So it is the correct movement of cash here. This is pretty good. I mean this is better than good. This is incredible.

How did it, how did it actually work out the balances for all the working capital lines as well? What did it do? Can you see?

It may take in the revenues.

Good assumptions.

It's taken the revenues and then it is calculating the receivable balances.

Assumption.

Yeah. Revenue times. It's made a day's assumption. Yeah, it assumed 47 days receivable. And I'm going to guess it figured out that that's what the historical days were. But not sure. It must be because the working capital balances are reasonable. Right. They are growing at a reasonable pace in the future years. They all look reasonable. The prepaid expenses look reasonable and they.

Use a historical or pretty close to an historical app.

Yeah. So it's using a re. Very reasonable assumption. It made a debt assumption here. So let's go a step further.

So far this is the best we've seen yet in all the times we've run.

So let's go to the bottom and say if you'd like, I can add an automatic revolver. So now I'm going to push this a little bit harder. And please add an automatic revolver to keep cash. Right. I'm going to say greater than or greater than or equal to. Right. Greater than or equal to zero. And I'll say borrow whenever there is a cash shortfall and repay the revolver whenever the company has excess cash. Right. Do you give it some instruction? Let's see what happens then if we ask it to build in a revolver again. I still with you guys. I believe I Mean, the ability, though, to still do this, right. The ability to ask and to challenge and to get it to make, you know, requires that we have an understanding of how this works. I would never want to just hand this in like this because I think there's already an issue on deferred taxes. But this is an incredible start. I'm not going to lie.

Well, and also, I mean, there's two things I would say. Number one, I think it's something we've talked about a few times. What does this mean for the other tools if Microsoft's agent is that many steps ahead of where they're at? The other thing I would say is actually off a comment Hilary Smart from Operis put online the other day where she was saying, you know, there's a very big difference between getting a model mechanically sound, of course, and then right for a project. I'm really impressed by this potential for it to get close to a mechanically sound model. But, but then there's a huge leap between that and what are the exact situations and the assumptions you have to manage on your project. Should interest be calculated on like a 3 over 360 basis or, you know, whatever actuals over 365. So those are two different things. But this is, this is really impressive, especially compared to everything else we've seen.

You can also tell it to do those type of things, right? You could say, hey, now use 360.

I mean, you probably could, but you, but you'd have to. This is my point about you have to then have modeling skill to know the next level. Because if you have no modeling skill and you go, hey, build me a financial model that does X, you need to know the next questions and prompts. But I'm still blown away. I think it's really, yeah, this is.

This is better than any I expected at this point.

Well, and this is why, this is, this is why a lot of financial modelers feel that there's always going to be a part of modeling that that requires. I mean, you know, I can pretty much guarantee that for a long time coming that when you are ready to present your analysis on your infrastructure project or your investment opportunity or your credit assessment, your client, your credit committee, your boss is going to look at you in the eye and ask you, and you are going to need to be able to explain and justify and talk about how you derive the assumptions and great use, you know, use your AI tool to help you with that. And they're going to still want to make sure you understand, you know, every element of it completely agree with you. However, this is still a very impressive mechanical effort, isn't it? In, in terms of its ability to do this work very quickly I think we can agree this, it did this faster in about 12 minutes.

If we, if you got this to start with some tweaking, you could probably with giving it all the instructions. It could get pretty close on an AFM if it continued to be this consistent.

Well, we haven't tried. What we don't know is its ability.

So scenario I asked it to build.

This by just making some reasonable assumptions and it has made some very basic reasonable assumptions around growth rates. On revenue. We, we would all suggest that a good model should be drivers based and that revenues should factor in prices and volumes. But I assume if I gave it some price volume information it, you know, would figure it out. But I would test it for that. What we don't know is if we gave it a two or three page case study and we can try that, you know, next.

If we gave it a two or.

Three page case study that simulates reality, could it then factor all of that information and there's a lot more information? Perhaps it could. We will try that at some point here. Now it is, it has made just some very simple assumptions around margins. It's assumed effectively it has assumed the margin, it's assumed the cost to be goods sold percentage as a percentage of revenue. Now it's still working on the revolver issue. What, what you know, we talked about during our. When we were offline is will that enable. Will that lead to a situation of circularity in this model when, when it builds in the revolver? We will see. Time will tell. So we've been going here. How long has the revolver question been running? A good five minutes. I think at this point.

Yeah, probably about five minutes.

Why don't we take a pause and come back when the revolver is built and see if it is still, if everything is still working well and then we'll show everyone that.

Welcome back. We showed you last time it built the model. We've now asked it to do the revolver. We're going to turn it over to in to show that I unfortunately have to step away for a minute. So Giles is going to close this episode. I'm trusting you with the mic, Giles. Be humble and bring it home. Okay.

All right.

In the meantime in go ahead and cheer what happened here.

So we asked it to build in a automatic revolver. We said borrow whenever there's a shortfall and repay the revolver whenever the company has excess cash. And so what's happening here is I don't see it on the debt schedule. The debt schedule is still just showing the term debt, the long term debt. However when I scroll up we will see and it also. So it tells us what it did. It went through and it put it in, it set the revolver, made sure that there was cache never went below zero. If the pre revolver ending cache was less than zero it drew so that's exactly what it's supposed to do. If the pre revolving cache was less than zero it would borrow and if the pre revolving ending cache was greater than zero it would repay it to the revolver. So very impressive. That's exactly what we want to do. And then it linked it up and then it verified that the ending cash is negative. So very impressive. Now it says minimum cash target was zero. No interest though there was no interest built in and no hard cap on the revolver availability. Great. I mean it's very, very impressive what it did. Let's see here the balance sheet is still balanced. We can see here the balance sheet is still balanced but now we actually have a bank revolver, a revolving credit facility in the model. And now it's a formula. It's taking the prior year plus the change. It's doing that and you can see cash is now zero. It's not negative anymore, it's borrowing but it's taking the prior year's revolver and it's adding in the change from the financing activities. Now this is a bit of a long formula and if you follow through it, it's calculating the change in cash flow, the change in cash, the change in cash flow each year and it's saying if that change in cash flow is less than zero, then borrow otherwise pay off. Not the most elegant and you know as a modeler we could give it guidance to improve it, to fix it. But it's still getting the right answer. So I don't know Giles, I would say I'm quite impressed with this. I still wouldn't want to have it run in 15 minutes handed in that someone but impressive it can get this far.

I'm really impressed and actually you know, it's, I think, I mean we would have to test it further. Mechanically it's doing a lot of things that the other tools were nowhere near doing, which is fantastic. I actually posted about this today. This is the exact point I was warning about on LinkedIn today though, which is we're going to go through a phase now where it's going to look exciting and you go oh my God, the balance sheet Balances, it works. And I feel like this is the most dangerous period where you go, hang on a minute because I think you were saying, Ian, when you tested this a couple of days ago, actually, it didn't get the right answer and there were one or two mistakes.

That's right.

So the thought of going from this, which is immensely impressive to oh my God, I can just click a button and I know it's going to be right. Balance sheet, balances handed in. That's so dangerous. However, massive step in the right direction.

Yeah. No, and again, as a good partner, as a partner to help you with your work and to get started and give you a boost for sure. But I need to be able to challenge this new partner of mine and double check. And again, I still have on the balance sheet my deferred income taxes, which is just a dead. It's just a straight link. It's a straight up link to a sell. It just said assume the deferred income tax was constant at $8 million per year. I have no idea why it said to assume it was constant. I guess it made a very simplifying assumption for income tax. Again, we could ask it to run a couple more tests on income tax. But suffice it to say, this far. Maybe we'll do some more at a later time, Giles, but this far it has, it's impressed us and I think tread carefully and tread cautiously and understand what it's doing. But you know, in a half an hour here, generated with a couple revisions, pretty robust, helpful tool so far.

Yeah, I think this is, I mean bear in mind, this is beta mode. This is. There have been some wild claims from third party tools and obviously we will get round to all of them. But weirdly, it kind of struggled with some of the easier audit kind of review things that you asked, which I would, I would have thought it would have found easier. And then this, which is by far. This requires far more kind of accounting and modeling knowledge it seems to have done a much better job on. So I don't really understand that.

Well, why don't we try one last one. You're right, it was struggling on the easier. And why is the balance sheet not balanced? Because in this model I deliberately unbalanced the balance sheet and, and you can see here that it's out of balance. I'm going to say why is the balance sheet not balanced? Let's see if, let's see if it is clever enough to pick that up.

Because while it's doing that in just, just off the top of my head. What I'd. We're probably of the same mindset. I'd love to spend more time on this and give it more detail as a prompt. Because, you know, what if you did say, like, okay, well, you know, there's debt sculpting that you have to deal with, or like, reducing balance depreciation, I get the sense that there may have been a chance that if we'd given it the specific prompts to do that, like you did with the revolver, maybe it would have done them. I don't know. But you have to know. You have to know what you're looking for and know what to ask.

Oh, absolutely. You need to know what to ask. You need to know what you're looking for, and you need to know how to construct it, at least in your mind, so you can test, challenge, and make sure it's quite reasonable that it will come back with lots of very long formulas. And you'll need to know what they're doing and how they are all working to deliver them to your team. So. Absolutely. And we'll see here if it gives us an answer to my question. Why is the balance sheet not balanced in this model? And it's saying analyzing financial. And why is the balance. It's changed. Why is the balance sheet not balanced? It's investing range issues. It's searching for the balance sheet. It's trying. I mean, again, impressive. It can see it and be aware of it. We're asking it to do a lot here, but did you want to just keep watching or pause and then come back?

I think there's pause. We'll see how it gets on. We'll give it a few minutes and then we'll come back. All right, Ian, we're back. How did it do?

Yeah, I mean, it was really interesting on this one. It worked for about 3 minutes, 162 seconds. And again, reminder, I asked it, why is this balance sheet not balanced? I think we're not thrilled that it's tendency, as we know with these tools, to make things up. It says the root cause in A1. I'm not sure why it's sending us to A1. It's off by one column. References in the balance sheet totals. So totals don't point to the same column's components. So you said K167. This one here, K167. It's currently L161 to plus L165. And it should be K. Well, actually, it is K. Like, this isn't true. It's making that up. The total assets is currently L161 plus L165. That's not true. K167 is the correct answer of K161 plus K165 and it says K186. K186. This one here, total liabilities plus equity, it's saying is currently L184. So it's, it's making that up. It's not. This cell is not linking to L, it's linking to. It's looking to K. So I'm not sure. It doesn't seem to know and I'm looking at here, it did not realize or figure out that we have a working capital, a change in working capital sign issue which is what's causing it off. So yeah, definitely not solving it perfectly by, by any stretch. Charles.

So bizarre they to Again, I don't understand the underlying logic because if it can pretty successfully build, you know, a simple mechanical model, you would have thought it would also be able to review and find errors where what you've got in front of you doesn't match that logic. So I don't know. But I mean if we were to kind of wrap this up for me, I'll go first, then I'll hand over to you, Ian, quickly. So agent mode has not done so well in some tasks, but then actually in the financial modeling task, it's done really well mechanically. It's done some things that we would not want to be done in a certain way as professional modelers. But that is still very impressive and for me, still now entering a phase where that's very dangerous to people that don't know what they have to do as the next step.

Yeah, I mean, listen. Agreed. Really exciting to see that. Yeah. I don't understand why it did better building. It did better when I asked it to build a model from scratch than it did checking an existing model. But that means you got to be careful. It was doing seemed like it was doing some hallucinations in its answers when it was looking at an existing model. Again, extremely impressive that it could take a historical set of statements and build up a forecast. But you're right, there will be some line items that it seems like you are not correct, that you don't like it. You'll need to be able to provide guidance and ask it why there's a mistake and how to fix a mistake, et cetera. So but overall this is just beta and you know, version one. It's exciting to see and think what's going to happen in the future. However, you know, as we've been saying, it does not mitigate the requirement to fully understand every every element of it if you truly want to have credibility and impress your colleagues and your team and be reviewed as someone who has a great level of understanding. So it doesn't replace that, I don't think. But it's pretty wild that it can do this very quickly. So that's kind of what I've got. Maybe we'll do some more testing on this tool next time, because I think there's some other things we could do.

All right. Well, there you go. That wraps up this episode. Thanks, Ian. Thanks, Paul. Who's ducked off early. And we will see you all in the next one.

See you in the next one. Take care.