How TabAI stacks up as an Excel AI Agent for Financial Modeling Pros, with Ian and Giles

In this episode of The Mod Squad on Financial Modeler’s Corner, Paul Barnhurst, Ian Schnoor, and Giles Male take a close look at TabAI, a tool designed to simplify and speed up Excel tasks using automation and intelligent suggestions. With more tools dropping out of the market and Excel’s own Agent feature gaining ground, the question is simple: Does TabAI offer something worth switching to? From cleaning data and building dashboards to attempting a full five-year forecast, the team puts TabAI through a series of real-world modeling challenges to see what it gets right and where it still falls short.

Expect to Learn

• Where TabAI shines in helping analysts and where it needs improvement.

• How does it compare to Excel Agent in terms of speed, usability, and accuracy?
  Why finance pros still need to understand what’s going on under the hood.

• What to watch for when relying on tools that promise “done-for-you” modeling.

Here are a few quotes from the episode:

• “Agent was faster, but TabAI handled more advanced stuff better.” - Ian Schnoor

• “AI is great at building things fast, but one small mistake can make the whole model unusable.” - Giles Male
  

TabAI turned out to be one of the more impressive tools we’ve tested so far, especially when it comes to everyday Excel tasks and building dashboards. It’s not perfect, especially with full-scale models, but it’s definitely a step in the right direction. For now, it’s a great helper, but you’ll still need your own modeling skills to get the job done right.

Follow Ian Schnoor:
LinkedIn -  https://www.linkedin.com/in/ianschnoor/

Follow Giles Male:
LinkedIn -  https://www.linkedin.com/in/giles-male-30643b15/

In today’s episode:

[02:28] - TabAI Leaves Retail

[05:17] - Competing with Excel Agent

[06:50] - TabAI Feature Overview

[10:30] - The “Iron Man Suit” Claim

[14:28] - eSports Case Test

[23:12] - Dancing Fur Coat Model

[29:14] - Trial Balance Dashboard

[33:56] - Deferred Revenue Test

[38:36] - Full Forecast Model Build

[51:10] - Final Thoughts

Full Show Transcript

[00:01:17] Host: Paul Barnhurst: Welcome to another episode of The ModSquad on Financial Modeler’s Corner. Once again, I have with me my two distinguished co-hosts. We have the humble MVP. You want to take a minute to introduce yourself? Giles.

[00:01:31] Co-host 1: Giles Male : Hello, Giles. I'm co-founder of Full-stack Modeller and today I have come almost color coordinated with my other guest. That's all.

[00:01:40] Host: Paul Barnhurst: I'll rub it in that I didn't get the memo. Thanks, Giles. All right. Why don't we go ahead and introduce Ian.

[00:01:47] Co-host 2: Ian Schnoor: Yeah. Thanks, Paul. I am also rarely in red, but I was pleased that Giles did get the memo. I'm just back from the massive AFP Conference in Boston, which was great, and was able to deliver a talk there. And I'm coming back with my wicked smart Boston t-shirt that I've decided to sport for today's podcast. I am the executive director of the Financial Modeling Institute, the world's only financial modeling accreditation body. Lifetime and modeling. And excited to be with the two of you testing the AI financial modeling tools.

[00:02:19] Host: Paul Barnhurst: Thank you for those introductions. And for those who don't know me, I'm the FP&A guy lucky enough to host this show. Talk all about FP&A and we're super excited. Today we're going to be, uh, testing another tool. We're also going to talk a little bit about, you know, kind of the industry and what we're seeing briefly before we jump into, talking about TabAI. I think it is an interesting place to start. I'd love to get your guys' perspective. We all saw the note this week. The TabAI made the decision not to sell to retail. All existing customers continue to use it, but they're just going to go to enterprise. So maybe I'll start with what were your thoughts when you saw that announcement?

[00:02:57] Co-host 2: Ian Schnoor: You know, in the last episode, we've talked about the fact that a couple tools have already decided to shut down. We know the funding environment has changed a lot. Once Microsoft announced the addition of agent into Copilot, which is doing a very good job, certainly as good a job as any of the tools we've tested so far. To me, this is symptomatic of a fast changing, explosive new industry that's moving in real time. And they've obviously felt that it's going to be difficult to compete in the B2C space and, you know, choosing their battles and moving after enterprise. So I don't know, I think it's an interesting angle and we'll see how they do going forward. That's my take.

[00:03:39] Host: Paul Barnhurst: Giles, your thoughts?

[00:03:41] Co-host 1: Giles Male : Yeah. It feels potentially logical when you consider the kind of marketplace. I mean, you know, I run a training business. We've got B2C and B2B. If you bring on a team in a large company, it's a very impactful, you know, step. So I kind of get it. And you know as an MVP I know Paul you are as well. We get to see what's going on with Microsoft. Obviously it's all under NDA in terms of detail but Microsoft aren't slowing down. So what we talked about before with Agent Mode, where it is now, it's just going to keep getting better. Uh, so yeah, really interesting time.

[00:04:18] Host: Paul Barnhurst: I agree it's an interesting time. And I thought the TabAI announcement was interesting. I also see, you know, tray slides are still very much committed. I saw they were looking for a chief of staff this week. So you know, many of these tools, you know they have funding. They're continuing but they're trying to figure out what's the right path. Right. What's the product fit? How do I compete when we all know Excel is an 800 pound gorilla and nobody wants to go head to head directly against Excel? Yeah.

[00:04:43] Co-host 2: Ian Schnoor: And you know, Paul, you made an interesting comment before we started, which is that copilot is a paid subscription, right? So you're already. I mean, if you want to move into AI tools in the office, you're likely going to pay to subscribe to copilot. And now that includes agents. So if you did not have to pay for a copilot, you might feel inclined to try something else. But. But since you have to pay for copilot anyway to get it, are you going to pay for a second AI tool as well? And I don't know what you guys think, but that, you know, it's an interesting dynamic. I don't know what your thoughts are.

[00:05:17] Host: Paul Barnhurst: Well, I mean, unless it's superior, right? It has to have real benefits. I'm happy to pay for a second tool if it gives me enough savings. But the question is, if, you know, Microsoft is really focused on modeling, which they appear to be with agents, among other things, can another tool really reach that level, or am I going to pay an extra 50 bucks? I think that's the question. That or whatever, you know, 30 bucks, 100 bucks, whatever it might be. That's the question you have to ask. And I'm right now not convinced from what we've seen, that most people that answer is going to be yes.

[00:05:51] Co-host 1: Giles Male : We ask questions right at the beginning of the series, genuinely between us saying like, it would be really interesting to understand what these tools add on top of just a link to an LLM. But now an agent in Excel or Copilot is going to be linked to Claude, as well as ChatGPT and probably other Llms in the future. If the only thing these third party tools do is link to an LLM, I think they're in real trouble. But we don't know, do we? We still don't know.

[00:06:18] Host: Paul Barnhurst: Yeah, we know they do some things, but it's how much and what we're seeing doesn't tell us it's enough yet. I think what we've tested so far also, you know, Claude just released Claude for Excel. So, you know, you can do a lot of these things just straight in Claude with your $20 subscription. So it'll be really interesting to see. It's why I say you're going to have to have a key differentiator to survive. So let's go ahead and take a look at their website. I think we're going to skip their document with the recent announcement. It just changed some of the pricing and things. So I think we'll just kind of go through the website. Next we have a brief video from the founders of TabAI. They're kind enough to share with us a minute video talking about the tool and thanking us for doing the testing. It's a great little video to give you an idea of TabAI. They've done a lot of great work and then we'll be on to the testing, which I think you'll be pleasantly surprised with.

[00:07:11] TabAI: Hi, I'm Iris. When I see an Excel workbook, I don't just see rows and columns. I see endless nights and canceled plans. That's why we built type AI to make your Excel work easy and fast. Here's how people are using it today.

[00:07:24] TabAI: Hey Andrew here from TabAI. Here's how we're helpful for our friends. Firstly, we're adding to Excel. So you can download this there. It's not a spreadsheet app. You can use Excel Desktop for this. Three examples of how we're helpful. Creating a tab on sensitivity analysis. Collecting stacked bar charts. Right. We natively read your sheet right on your sheet. We can search your web. We can make plots, make charts. Everything can be done in our sidebar here. Secondly, data massaging. I would like to do this. Just bring your own data. Ask AI to add a column to standardize the names, right? Get it done in one shot. Lastly, variance analysis. Just type it in the sidebar and type II can do all of it on its own. And you might say, hey, I don't like the format here, right? I don't like how it's structured. Kevin has a memory feature, can come in and type out whatever feature you want. Turn it on and off depending on the workflow you're in. So we'd love for you to try this out. Bring on your sheets. If not, we have a starter kit as well for you to try it out with real world sample financial data. We're very thankful for our friends Zhao Yun and Paul here for being independent arbiters and testers. We hope you appreciate our love and sweat into Terry. Thank you.

[00:08:25] Host: Paul Barnhurst: So here we can see. Transform your team's Excel workflows. See your spreadsheet in a new light. Excel at any task you know, kind of similar to the others, although I think it's interesting. They focused on workflow, you know, not modeling, not being superhuman in Excel. I thought that was an interesting choice of words. I don't know if you guys have any thoughts, but a little different angle than what we've seen from the others.

[00:08:47] Co-host 1: Giles Male : Yeah, there's nothing that feels overly hypey, which obviously, you know, I'm very sensitive to. Uh, but yeah, it looks reasonable.

[00:08:56] Co-host 2: Ian Schnoor: Admittedly, as a finance person and a corporate finance person, I'm not 100% sure that I know what they mean by that. I mean, I know, when someone says build better models, I understand it. I mean, I think I can infer what they mean by transforming your team's Excel workflows. But I, you know, I think all teams work. Is it obvious to the two of you exactly what that means?

[00:09:18] Co-host 1: Giles Male : Or it makes me feel like they're thinking more about data and and what you might use in a well, in nowadays in Microsoft World workflows, I would be thinking of things like fabric and where is data going through, you know, a fabric environment, data lakes, power BI, Excel, Python? I don't know that. But that's something like workflows.

[00:09:41] Host: Paul Barnhurst: The other thing I think of when I think of workflows is, you know, what are the monthly tasks I'm doing in Excel? The variance commentaries, the pms, the whatever, the reports. And so how is it changing and simplifying those workflows?

[00:09:56] Co-host 2: Ian Schnoor: Yes, I suspect those are the things they're talking about. And I guess, you know, we'll learn more.

[00:10:01] Host: Paul Barnhurst: All right. So let's just go through a little. I think it's interesting. You know this speaks to the fact that it says try TabAI for free. You have to contact them. Right. It's the enterprise. Hey if you're an individual customer it's kind of like yeah you're not our. So they're definitely taking that approach of gating it. Now here's what I thought was interesting. You can read the whole story. You know, uh, Lance Rubin is a well respected modeler in the industry, you know, has done a lot of great work. And you know, his take, you know, he's clearly a big fan of what they're doing. TabAI is like giving every finance professional an Iron Man suit. It supercharged our services and transformed how we deliver value to clients. Any thoughts on that?

[00:10:42] Co-host 1: Giles Male : Just that I want to see like let's see. Because if it does that, you know, a statement like that makes me feel like we would expect something maybe better than we've seen so far.

[00:10:53] Host: Paul Barnhurst: Agreed. The other thing I like here, this gets to the workflows showing inputs. Hey, we connect with Xero QuickBooks. We want to add these other data cleaning automation. This really speaks to the whole you can see right here your client serving workflows supercharged. I think that's where they're advertising a little differently than the other tools.

[00:11:11] Co-host 2: Ian Schnoor: Yeah, no, I like and I like it. Listen, it feels like it is in that image. That's much more visually helpful at explaining what they mean by workflows. I always think of project management when I hear about workflows in my world, but this is clearly helpful to, um, to visualize what? And it makes sense. It helps explain why they're focusing on the enterprise market that is needing to, you know, connect, uh, with, uh. So anyway, curious to continue.

[00:11:36] Co-host 1: Giles Male : It's interesting because that makes me feel like they're actually quite vertical in the accounting space. If the highlighted inputs are just.

[00:11:43] Host: Paul Barnhurst: Yes.

[00:11:44] Co-host 1: Giles Male : Zero and.

[00:11:45] Host: Paul Barnhurst: Customers are focused there. And what I like is what they've highlighted. I think this is where they want to play in some of these other places. It almost feels like, hey, here's our strengths, here's where we're at today, but here's a map. And I could be wrong, but here's a map of where we want to be because. Right. They say PDF images, web search. They mention all these but you don't see them connected. So I don't know if it's yeah, that's what we want to be able to do. It's a little confusing, but I think what they're trying to say is here's where we're at and here's kind of where we're going, um, we'll run through the rest of it. Data dump to structured Excel. Yeah. Formula recreation PDF to Excel with citation okay. Formula builds and web searches. Workbook revision and template fills. Review and board ready presentation. I think it's interesting they're mentioning board ready presentations but they're just an Excel tool. I don't see PowerPoint here, so that's a little interesting, but nothing else really. I mean, I think this is an interesting one. We'll see what you guys think about this, but calculate your ROI. So what they're claiming is okay. Financial reporting. So let's take financial modeling. Do they have model reviews? Hourly cost takes you 30 hours. They're saying you're going to save $2,250 an hour and deliver faster, more accurate work to clients saying it's going to cost you 250 with Tab 4500 without buying it. I'm not.

[00:13:09] Co-host 2: Ian Schnoor: Know.

[00:13:10] Co-host 1: Giles Male : I struggle with very specific numerical measures like this. Is that okay? How well did you come up with these numbers? so yeah, that I'm not going to knock it.

[00:13:21] Host: Paul Barnhurst: So it says with Tab it's 15 hours. So it's 2002 50 okay. So you're saying it's going to be a 50% savings. I'm just okay, maybe maybe not. Interesting.

[00:13:32] Co-host 1: Giles Male : Well so so okay. Take that example. Review time. If it's saying it's going to halve the cost of review time, what you're saying is literally that using this tool you would halve the time taken to review financial models professionally.

[00:13:45] Host: Paul Barnhurst: Yep. That's what it's saying because it's going from 4500. It's saving 2250, which is half the cost. So let's just run through a few of these. I think this is really interesting. It's bold they're saying 50% here. They're saying almost 80% on data ingestion, 70, 80, about 65, 70% here you go from 50 to 15 hours. So 70% savings on data cleaning, workbook updates, 50% format and reporting 50%. I'd love to see the math of how they came to that conclusion that I struggle with telling me, you're going to save me that much with AI. I just haven't seen it yet.

[00:14:25] Co-host 1: Giles Male : But hey, you know, that's why we're here. We're going to test.

[00:14:28] Host: Paul Barnhurst: So are we ready? Should we jump into testing? You ready to go, Giles? I'm ready. All right, well, let's put it to the test. I'm excited to see the cab. I mean, I've definitely heard some good things, and I think we'll be good to jump in here.

[00:14:39] Co-host 1: Giles Male : We're gonna get moving. So the background is, uh. I've got, like, 100 pounds worth of credits for this, for. I'm assuming that is the equivalent of sort of token credits. I think I have logged in appropriately or successfully. This is the easier case for esports. Looks like I've got a. Oh, okay. There you go. Uh. It has. Let me sign in. There we go. So as a reminder, we have an esports case, five bonus questions, and seven levels. I'm not really looking at the bonuses.

[00:15:09] Host: Paul Barnhurst: Before we jump into the case. I'm curious, what are the things across the top like? What's the auto? The new the agent? Yeah.

[00:15:16] Co-host 1: Giles Male : Fantastic question. Don't know. I'm assuming that is a new prompt.

[00:15:20] Host: Paul Barnhurst: It's a new prompt. So auto it looks like auto select the model versus select it yourself which I appreciate then let having default be auto versus asking me to decide.

[00:15:33] Co-host 2: Ian Schnoor: Look at how many models there are. My goodness. But yeah gosh. So it's great we talk. I like the auto, but do you think there's a part of you that would still be curious and say it's the chosen one? I wonder if it chose the best one. Maybe I should just try.

[00:15:49] Host: Paul Barnhurst: Yeah, there will be some people for sure. I would be a little interested, right?

[00:15:54] Co-host 2: Ian Schnoor: I mean, there's like ten tools, isn't there?

[00:15:57] Host: Paul Barnhurst: Well, there's. I think there's five tools because you have OpenAI, you have Gemini.

[00:16:02] Co-host 1: Giles Male : There's about ten plus options there. I would say.

[00:16:06] Host: Paul Barnhurst: Oh, and whatever GLM is I don't recognize the bottom two are either. Are you familiar with them? The rest I recognize. But those bottom two. Are you familiar with those? No I'm not. No. Interesting. And then click on the agent. What's an agent versus ask like what it say when you hover over it. Okay. So it will directly and then ask is like if you click on ask, you get to approve each change before it does it.

[00:16:31] Co-host 1: Giles Male : Oh okay. Well should I go with oh let's just do oh let me just stick with the agent I think that's fine.

[00:16:36] Host: Paul Barnhurst: Try it. It's clear they've given a little more thought here than we've seen with other tools of hey, you can automate or you can kind of do it yourself. The agent asks others to have different things like the audit mode and trace light and things. But I do think they've done a pretty good job there with that setup.

[00:16:50] Co-host 1: Giles Male : So that was literally what 30s. And it's answered at level one. It's done correctly.

[00:16:55] Co-host 2: Ian Schnoor: We've got to know which tool. Do you know which tool it used.

[00:16:58] Host: Paul Barnhurst: Yeah that's what it's asking. Does it tell us what model it used? If you scroll up, do we know the question.

[00:17:03] Co-host 1: Giles Male : Good question. I'm not sure. Oh, uh.

[00:17:07] Host: Paul Barnhurst: It doesn't appear.

[00:17:09] Co-host 1: Giles Male : Anywhere.

[00:17:09] Host: Paul Barnhurst: What if you click on that symbol.

[00:17:11] Host: Paul Barnhurst: Does that tell you I'm not now.

[00:17:13] Co-host 2: Ian Schnoor: Because when you click on when you click on agent again and you it says auto but it doesn't somehow in that download it says auto. But it's not telling you which one it's actually used at.

[00:17:24] Host: Paul Barnhurst: I would like it to tell me which one it used. You can save it as a workflow. I mean, I wonder if you ask it, can you tell me what model you used?

[00:17:33] Co-host 2: Ian Schnoor: Oh. Good question. Wow. That's smart Paul, a good idea.

[00:17:37] Host: Paul Barnhurst: Um, so it looks like it was chosen. I'm assuming it chose clod for that one, or that's its default to answer questions. Don't know for sure, but yeah, now that level one is confirmed, so it look like it used clod three five sonnets okay.

[00:17:50] Co-host 1: Giles Male : Cool. Okay, so I'm going to get it. To solve the remaining levels, we might want to pause again. In theory this should take a bit longer and then we'll come back.

[00:17:56] Host: Paul Barnhurst: So we'll pause and see how long it takes. All right we're back. That took, what, about eight, nine minutes there? I think you had it re prompted in the middle. So you talked about how it's done. Let's walk through some of this. Yeah.

[00:18:08] Co-host 1: Giles Male : So I think it kind of stalled somewhere after level five. And I had to stop the thinking and say, hey, can you restart? And it's fine. So it's got all of the answers, right? And actually, for the most part, I would say it's done a very good job. So we've seen in prior episodes, it's using things like indirect and column to get the column number, uh, Len and substitute it's used. These are the solutions that we would expect from, you know, esports players for the latter levels with the map indirect is correct. It's done a really simple ish approach to level seven, which is an offset with an indirect. That's probably one of the cleaner approaches I've seen. Or you're using two volatile functions, but it's fine. But there's a couple of weird ones. Okay. So level two, which was to take the text string that includes a bunch of numbers, find the two largest and add them together. Genuinely, we were all just saying I don't think any of us have seen this function, but it's using filter XML. It's getting to the right answer. I've just genuinely never seen that before in my life.

[00:19:14] Co-host 2: Ian Schnoor: I mean, I think the three of us can put our heads together. We need a bit of time to, you know, dissect that just to understand what it's doing.

[00:19:20] Co-host 1: Giles Male : Yeah, but it's right. So? So a weird one. I'm not going to knock it too much, but it is unusual. And then on level five, I think it was where you've got to find the number of times, you know, any of these numbers appears and essentially add them up. It did a really odd thing where it's rather than just substituting out the number of times the number occurs, it substituted the number and the semicolon next to it. So every find is actually two characters that it's taking out. So then it has to divide the answer of this by two to get back to the number of characters that it found, and then multiply it by the number. So it got the right answer in a bit of a weird, convoluted way, but 100% score wise.

[00:20:03] Host: Paul Barnhurst: Yeah, we'll see about the bonus. I'm curious if they get the color.

[00:20:06] Co-host 1: Giles Male : Yeah.

[00:20:06] Host: Paul Barnhurst: Because nobody's got that one yet.

[00:20:09] Co-host 1: Giles Male : So, uh.

[00:20:10] Host: Paul Barnhurst: I think they did.

[00:20:11] Co-host 1: Giles Male : Where's my answer sheet?

[00:20:12] Host: Paul Barnhurst: I'm pretty sure that's right. They just changed it to 430 or 4, so they're close.

[00:20:17] Co-host 1: Giles Male : This is my right answer. And these were. So he's got a couple of them wrong. Uh, but. Yeah. Close.

[00:20:23] Host: Paul Barnhurst: What did they put in there? What are they just putting the number in or did they.

[00:20:26] Co-host 1: Giles Male : Okay. Did it. I don't know.

[00:20:28] Host: Paul Barnhurst: Oh, interesting. But the closest I've seen yet. At least they were in the ballpark.

[00:20:32] Co-host 1: Giles Male : That is the closest I've seen to. So. Okay. But I, you know, case one, and I'm trying to move this at pace, you know. So we.

[00:20:40] Host: Paul Barnhurst: Of.

[00:20:40] Co-host 1: Giles Male : Course the answer's 100%. A couple of weird options 100%.

[00:20:45] Host: Paul Barnhurst: Couple missed a couple bonus. I think the others all missed that one bonus. So similar to others, they did miss one other bonus. So I think slightly lower than Rosie, but very similar.

[00:20:56] Co-host 1: Giles Male : And just out of interest because I think this is interesting. I'll bring up the dashboard I've got on my website interface with them. So we've got 100 pounds credit for this. That cost us 2.40 pounds. So four so far and we've made 36 API calls.

[00:21:15] Co-host 2: Ian Schnoor: How do you feel about that? How do you feel about the fact that you've got this? Because we haven't seen this on another tool. Have we? How do you feel that you've got this credit? Is this going to encourage you to use it, or are you going to be the type of person that is going to use it carefully, because you're watching your credits go down? It's an interesting psychological relative to just having a monthly subscription, right? I don't know.

[00:21:37] Host: Paul Barnhurst: Do you think they do have some monthly subscriptions? I know they gave us a usage, so I think they allow both.

[00:21:43] Co-host 2: Ian Schnoor: Got it.

[00:21:43] Host: Paul Barnhurst: And there definitely is a psychological to if I have credit. Right. If you see how much you're using every time you're gonna be like, well, how much is it for another model? Because I saw an article recently, the guys who do all this, which is one of the tools we've talked about testing, showed credit usage and optimization. And hey, if I use ChatGPT every single time versus this tool, you're so much at cost. Here's the accuracy and tested like 10 or 12. And I think if you didn't optimize your credit usage it was like 50 times higher. The cost was really interesting.

[00:22:14] Co-host 2: Ian Schnoor: Which way.

[00:22:14] Host: Paul Barnhurst: Your.

[00:22:15] Co-host 2: Ian Schnoor: Credits were way more expensive.

[00:22:17] Host: Paul Barnhurst: Yeah, it was way more expensive. You're not optimizing which model you're using for which, because if you use a lightweight model for a simple task, it could be ten, 15, 20 times less expensive than using a complex model, because it's going to do a lot more calls and think a lot longer. So it's really interesting. You know, they're now starting to show those types of things, you know, as a business, I know that's not what we're focused on, but how do you optimize that? How do you incentivize behavior? Because if you're not using usage, you're using a monthly and someone's always using the most complex model. Hence why I think that you want to select the model to start with. So you can try to optimize your cost as well as accuracy because right. You got to consider both.

[00:22:57] Co-host 2: Ian Schnoor: Yeah.

[00:22:58] Co-host 1: Giles Male : Interesting. By the way I just hit go on model two. I've started my stopwatch but I'm just letting it run. Obviously we can pause at any point on this one. I just get it to get stuck into all seven levels.

[00:23:12] Host: Paul Barnhurst: Yeah. And this is for anyone who hasn't joined us before. This is a case about dancing fur coats about Giles or humble MVP. It's a much more difficult case than the first one, of course. We'll see how.

[00:23:25] Co-host 2: Ian Schnoor: We.

[00:23:25] Host: Paul Barnhurst: Do it naturally, because it's about a guy who's an awesome modeler and, Excel competitor.

[00:23:31] Co-host 1: Giles Male : Great pictures in here, though. Look at this. Who's this wonderful Jesus-like character?

[00:23:36] Co-host 2: Ian Schnoor: It's stunning. That's gonna not even.

[00:23:38] Host: Paul Barnhurst: Touching that.

[00:23:39] Co-host 2: Ian Schnoor: You know? You know, the tool is gonna suck up all your credits for that. Like, it's so beautiful. It's just gonna charge you a fortune.

[00:23:46] Host: Paul Barnhurst: Yeah, we'll see how much this one cost. All right, we'll go ahead. And that might be a good spot to pause. We'll let this run for a few minutes and we'll be back. We're back. It runs for about 15 minutes. How did it do, Giles?

[00:23:58] Co-host 1: Giles Male : I think it's done better than any other tool so far. So it's interesting. It's struggling on level six. Remember this is seven levels. Uh, but every tool has struggled pretty significantly. And actually it has so far got levels 1 to 5 completely correct. Uh, and there are some tricky bearing in mind there's a lot of information in this model. I didn't direct it. Remember, we've got all of this closet information on one slide. Uh, tab. We've got dancers and formations. I didn't say, like, here's where this stuff is.

[00:24:30] Host: Paul Barnhurst: How to interpret everything.

[00:24:31] Co-host 1: Giles Male : It had to interpret all of that. So to even get levels 1 to 5 is massively impressive, I would say. And again, this is where it gets interesting. If you look at some of these formulas, they're not pretty. It's definitely choosing a kind of single cell solution. And again maybe I could have helped by prompting that to say, you know you can.

[00:24:53] Host: Paul Barnhurst: See here for a second. I think it's interesting. Why is it doing zero time zero times. So is it turning on and off somewhere two times?

[00:25:02] Co-host 1: Giles Male : Yeah. So this was a hard level depending on my mood. There are certain characteristic scores for the.

[00:25:10] Host: Paul Barnhurst: Oh that's right I remember. Okay. So those are the.

[00:25:13] Co-host 1: Giles Male : So that's okay. Uh, look at this. This is the wow dancer ecstasy scores based on their proximity to me on the stage.

[00:25:25] Co-host 2: Ian Schnoor: You're a let user. Why is it using a let there?

[00:25:28] Co-host 1: Giles Male : Well, because it's chosen as a single cell solution. There are lots of elements to what you would have to work out in this. So I haven't taken the time to look at everything it's doing. But essentially this looks like it's working out positions of me versus dancers. And then off the back of the kind of steps spaces between us, it's doing that calculation for the ecstasy value. It's clever. I mean, it's clever. We've left it running just to see if it did get any further. But I think the answer is really impressive. Nothing's got this perfectly right yet. I have a feeling if we left this for half an hour, it might get there. But we, you know, we've only got so much time, So yeah, 100% of what it tried and it hasn't solved 6 or 7 yet.

[00:26:13] Host: Paul Barnhurst: Yeah, I had six wrong. And it's trying to figure out why. It just hasn't been able to get there.

[00:26:16] Co-host 1: Giles Male : I'm impressed. I don't know, we were saying just before we restarted the user interface, the information you're getting back. I mean, compare this to an agent. I think you know, Excel excels. The agent has got a long way to go in this instance. But the information you're getting back about what it's doing at all times is fantastic. And you've got this checklist as well that one of the other tools had, you know, it comes up with a task list and then it's just picking them off one by one, which is great.

[00:26:42] Host: Paul Barnhurst: No, I think it does have a clean interface. Fairly useful. I mean, I think it even allowed I can't remember, but earlier it may allow you to drill down in some cases, but it feels like it has the right level of balance for the most part. Yeah, I agree, I'm impressed.

[00:26:56] Co-host 2: Ian Schnoor: I mean, it's continues to make me believe that again, you're I think there's going to be a long time where for a long time, people are still going to want to check and make sure that these tools are actually generating the right answer, because we've seen a lot of instances where they do not. So you're going to save time for sure. It's doing an awesome job, but I sure hope you spend the time checking it and double checking it. And you might have to learn a few new Excel skills in the process, right? That is less common, more obscure to ensure that you know what it's doing and why it's working right. That it will always work.

[00:27:29] Co-host 1: Giles Male : How are you going to test this?

[00:27:30] Host: Paul Barnhurst: Watching a YouTube video on how to build a filter XML. What are you guys doing?

[00:27:34] Co-host 2: Ian Schnoor: I don't know. What were you saying, Giles?

[00:27:37] Co-host 1: Giles Male : Well, just to that exact point. I mean, if it comes out with this answer, obviously we've got the benefit of green ticks here, which you don't have in the real world if you don't know modern Excel, if you don't know what a let is and what variables are, how are you going to debug this formula?

[00:27:51] Co-host 2: Ian Schnoor: Well, my point, yeah, my point is exactly. So you're going to have to figure that out. You're going to have to learn let functions and watch a bunch of videos and understand what variables mean. So it solved this problem. You know if we talk about real world issues. It has solved or, you know, sort of a problem. Call it five minutes, but you might spend a couple hours learning and understanding what it did, which will elevate your own skill set, right, to make sure that you can confirm to your boss that it's right as opposed to building it. A simpler multicell solution, which would take longer for you to build. But you'll know what you're doing and you know, right? So there. So there is a trade off. Undoubtedly.

[00:28:29] Co-host 1: Giles Male : All right. Am I handing it over to you, Paul?

[00:28:31] Host: Paul Barnhurst: You had one more, didn't you? The, uh, data to analyze the trial balance?

[00:28:36] Co-host 1: Giles Male : Yeah. Do we want to do that as well?

[00:28:37] Host: Paul Barnhurst: Or we could do that one real quick.

[00:28:39] Co-host 1: Giles Male : I do. Okay, I'll try and be quick on this one. Uh, so let's bring up round three. I'm not going to go into too much detail about what I'm asking it to do. Again, if you've been watching this series, you'll know. But essentially there is raw trial balance data on a tab, and I'm just asking it to produce an output, you know, something with KPIs and potentially some visuals. There's some interesting stories, I think, to tell in this data where the net income I think goes negative halfway through the year and then pops back up at the end. That's it. Should we pause and come back?

[00:29:14] Host: Paul Barnhurst: Yeah. Let's go ahead and pause it. Give it a few minutes to run. All right, we're back. Giles, take it away.

[00:29:20] Co-host 1: Giles Male : Yeah. So I think again, it's doing a good job. And, I mean, I have literally just re prompted it to say, can you just format these numbers? It may have been getting there anyway, but obviously, you know.

[00:29:32] Host: Paul Barnhurst: In the interest of time because it had been running for quite a while. We did cut it a little short, but let's see what we got.

[00:29:37] Co-host 1: Giles Male : But it's done. So this is the first one I think out of any tool. Again, that's built good charts like these are actually charts that as an analyst you would. Yeah, you would probably turn to, you know, what's the revenue trend, the EBITDA trend over time. There's a graph there that has got those lines or bar charts together. So revenue, gross profit, EBITDA. Uh it's continuing to go. So we've got key ratios and metrics being created at the bottom here. I'm really impressed again with this tool so far.

[00:30:09] Host: Paul Barnhurst: I think it's the most complete analysis we've seen. I mean, doing all the ratios and everything, it's still obviously we need to check, make sure everything's right. But on the surface it all appears kind of right. Numbers. Right?

[00:30:21] Co-host 1: Giles Male : I think so. I mean, certainly the high level number that I look for.

[00:30:24] Host: Paul Barnhurst: Is showing formulas. Like if you look at some of them, can we quickly trace.

[00:30:28] Co-host 1: Giles Male : Yeah, yeah.

[00:30:29] Host: Paul Barnhurst: We can trace it.

[00:30:29] Co-host 1: Giles Male : All formulas. But that, that line, that EBITDA line that goes negative. Here we go. So it's yeah this is the thing we haven't let it finish. But it's now formatting these.

[00:30:40] Co-host 2: Ian Schnoor: Mhm. Oh it's doing that now. It's still finishing. Wow okay. Really nice.

[00:30:44] Co-host 1: Giles Male : Okay. Let me just zoom out a bit I'll just expand this out. It's doing some.

[00:30:49] Host: Paul Barnhurst: Got the currency right. Did pounds for you.

[00:30:52] Co-host 1: Giles Male : I wonder if it's going to take off these decimal places for me. But it's. Yeah. I think what it's getting towards, you know, if I expand that out a bit, maybe it would have done this for me. Uh, but this is getting to the stage where you would actually have a pretty comprehensive dashboard.

[00:31:11] Co-host 2: Ian Schnoor: Yeah, I agree.

[00:31:13] Co-host 1: Giles Male : That. I think that's great.

[00:31:14] Host: Paul Barnhurst: You'd validate, maybe make a few changes, but this is the closest I've seen to a presentation. Ready?

[00:31:19] Co-host 1: Giles Male : Yep. Yeah I agree. I think the column widths would be fine. So yeah.

[00:31:24] Host: Paul Barnhurst: Yeah I think it will get there. But we can just mean that's all you're doing is adjusting column widths. I call that a win.

[00:31:30] Co-host 1: Giles Male : Oh totally. And it's put two decimal places on for every number, which is not ideal. But I would say that is a pretty good job.

[00:31:39] Co-host 2: Ian Schnoor: Absolutely.

[00:31:40] Host: Paul Barnhurst: All right. Well, why don't we, uh, go ahead and switch. I'll share my screen now, and we'll run through just a few so we can leave some time in here as well.

[00:31:51] Co-host 1: Giles Male : I'll let this carry on running, by the way. So if we have two minutes right at the end and it's finished, we can always see what it looks like at the end.

[00:31:57] Host: Paul Barnhurst: Yep. All right. So the example I have that we started with each time is the price variance mix. So I said before we have a budget and actuals. We're looking at you know gross margin volume and mix for three different products. Having it explain it. So what we're going to kick off here is we're going to start with asking it to do just the price and see if it gets that right. Again I've done agent mode similar to what you did versus asking, and we'll see what it comes out with. So we're back and we did the PVM so we could see the first formula. It took the actual minus the budget times. The actual units give you the price variance. Then it did the volume. Then it did the total mix variance. And so what you're going to see is you can see up here I have the total variances. It's 220. This is 220. So that works out. If we look at you know, kind of the individual ones it looks like, because this one's all three together, it all looks right. Let me just pull up the actual answer here for a second and validate it all. But what was interesting is it didn't put anything in. And then it asked me if I wanted something and it answered all three, even though the prompt I gave it was just the first one. The other ones haven't done that, so I thought it was kind of interesting. And here's the let me look at the actual answers here for a minute. All right. So yeah. So it looks like it got everything right.

[00:33:26] Co-host 1: Giles Male : Interesting okay. Good stuff.

[00:33:29] Host: Paul Barnhurst: All right. So let me now open the deferred revenue one. I'm going to close these and let's open that file. Actually let me just open it over here since I have it up okay. So we've done this one before. We'll go ahead and do the deferred revenue schedule here. We'll give it just one minute to pull up. Let me get my prompt. Go ahead and get started and let's see what it does.

[00:33:53] Co-host 2: Ian Schnoor: Do you want to read the prompt again or as it's working?

[00:33:56] Host: Paul Barnhurst: Yeah, I'll go through the prompt. So basically let me just kind of explain the data. And what we're doing here is we're doing a deferred revenue schedule. So if we take customer one, you see the first invoice customer name, there's a contract start and end date. How many months is the contract amount? So there's 24,000 roughly I think it's 9.99 a month. The spread over the 24 months as the product name and address. So what I've asked it to do is on a separate sheet, take this and create a deferred revenue schedule. That schedule should include the invoice, the customer name, how much revenue I should, you know, recognize each month, and a check to make sure I recognized all the revenue. It should be over a four year period from January 1st, 2026, all the way through the end of 2029. So we can see now it's labeled a sheet called deferred Revenue schedule. And it's thinking. So we can see it's put in the dates and we're going to go ahead and pause it, and we'll come back in a minute. It'll take it a few minutes and see how it does. But it looks like so far the work it's doing is similar to others so far. Alrighty, so we're back. It finished its analysis. You know, it's formatted. You can kind of give me all the instructions. It went through its seven tasks. The schedule is ready for use for monthly revenue recognition. So if we look here, you know, one thing it didn't do is column width. Come in and fix that. But the dates look right. Number formatting I'm not a huge fan of showing the zeros, but I'm sure I could ask it to correct that. But the biggest thing to me is again, and you know, we could probably ask it to prompt, but notice it's hard coding the dates.

[00:35:36] Co-host 2: Ian Schnoor: Don't love that because it can do it instantly, but that becomes unusable. And here's the thing I actually believe as we see these things go more and more what I believe is going to happen is these are going to be our partners. I believe that it's going to build tools that people will take over. I think it'll do a great job. You know, they'll do a great job building a foundation, a tool, but someone is going to want to play with it on their own and extend it. And I think by doing it we saw some of the tools that do that. Admittedly, this tool did not. Giles, for your oh, it didn't stick in hard dead numbers like some of the other tools did, which is great on TabAI, but I think that we're going to have situations where people will take a formula built, know what's working, and then copy it down on without realizing that it's done something that makes it not modular, not dynamic. Anyway, that's my thought.

[00:36:25] Host: Paul Barnhurst: So I'm going to ask it to make it dynamic and just see how it does real quick. And then we'll move on to the end. Examples I know, Giles, you're going to bring those up. You know, the other thing that's interesting is the other ones all did an absolute value and said, hey, as long as it's within a penny, because sometimes you get rounding errors. They didn't do that here. I like that a little better to have that, you know, kind of Hey, within a penny. Tell me it's okay. Because here many of them gave conditional formatting. This just said, hey, here's all your zeros. And so now I got a filter. Is it really all zero? I love when there's just a quick check, but that's a minor thing. Um, I don't see totals at the bottom. They checked it, but some of the others did that. So I mean, it's good, but on this task I think it's on par with some of the others. Some actually did the date formula properly. See. Now I asked it right. That's what I would expect is, you know, J one less than or equal to D4 or E4. So if it's in that date range then recognize the revenue. So it fixed it once I asked it to use a dynamic formula. But you would expect it to do that. I would know I'd want it to do that. So easy fix. Took a minute, did a good job on the whole. But this hard coding is a concern to me. All right, so why don't I turn it over to you, Giles? To give you back the screen here and.

[00:37:48] Co-host 1: Giles Male : Yeah, give me back the screen. And just for 30s, I'll just give you a quick update on that, um, trial balance analysis, uh, tasks. That's it. I was going to call it out for getting something completely wrong because I, it's so it's created this budget versus actuals analysis. Now, I didn't even spot that. I did have some high level budget variance numbers against each trial balance line. So I was going to accuse it of hallucinating and making up numbers, which to a degree I think it may have done, but also it's kind of picked up that I did have some budget variance percentages in there.

[00:38:26] Host: Paul Barnhurst: Um, I wonder if it used those percentages like the average of them or. It's hard to tell.

[00:38:32] Co-host 1: Giles Male : Yeah. So I think that may have been what he's done, in which case he's done a fantastic job. Here's an example where you've got to be really careful, albeit it hasn't quite finished. It's built out of a really nice little balance sheet summary. But if you look at these formulas here, and I see this in so many of these tools, the total liabilities and equity formula is just linking to the wrong sell. It sells short each time. So it's got zero there. It's just like a human accidentally has linked to the wrong sell. So it's not perfect. However, an incredible job. Um, Ian, I don't want to take up any more of your time. So, uh, we're.

[00:39:06] Co-host 2: Ian Schnoor: Doing it, so I, I don't have. As you know, I wasn't able to install the tool because they made a switch, as we know, to there. Uh, so Giles is going to be my partner, right, in this instance, and we're going to, uh, we're going to do this one together. Now, typically, I would be, uh, getting it to test an existing model and then asking it to build its own. Do you want to start this way? Do you want to start by asking it to build a um, I think.

[00:39:32] Co-host 1: Giles Male : I don't know about you. I think that's like the most interesting first check in your areas, like, can it even get close to building a model like agent did the job.

[00:39:41] Co-host 2: Ian Schnoor: Why don't you take, uh, this prompt that I've shared with you and, uh, toss it away? You know, I've been asking them to build, um, a five year forecast model. Uh, I've been asking it to make reasonable assumptions. And so for revenues, cost, depreciation, really just see if it to see if it understands the architecture, the design, the structural requirements, um, and how it goes. So you've uh, pasted that in and we'll see now if you know, the other tools did take a few minutes to do this particular step. I'll help you build a comprehensive. It's doing it perfectly. It says it can see the historical data. Now, I'll go ahead and build a comprehensive schedule with separate schedules. Let me create a oh, it's building a to do list I like that, I like that it's got a to do list. Right. Uh, to do list good modelers have.

[00:40:28] Host: Paul Barnhurst: Starting with the assumptions section. That's reasonable.

[00:40:32] Co-host 2: Ian Schnoor: Absolutely I like that.

[00:40:33] Co-host 1: Giles Male : So we want to come back. Is it worth pausing because I'm guessing yeah.

[00:40:36] Co-host 2: Ian Schnoor: Let's pause and let us know how long this takes. And, uh, but as we've asked it to build a pretty blue sky thinking of a five year forecast model, let's see what it does.

[00:40:44] Host: Paul Barnhurst: All right, we're back. It's been running what, about 18 minutes now, Giles?

[00:40:48] Co-host 1: Giles Male : Well, I think it's like 21, 22 minutes, actually.

[00:40:51] Host: Paul Barnhurst: So how's it doing so far? Let's talk for a minute and then we'll let it finish.

[00:40:55] Co-host 1: Giles Male : Yeah. So I think we've all decided even though it's been quite a while, we feel like we need to try and give this a bit more time because it seems to be doing quite a good job in the sense that underneath the three statements of actuals that we had, it is building out the underlying kind of assumptions and drivers for the forecast. I think we also don't particularly like the fact it's got the forecast years kind of along the same lines within the same columns as the actuals. Really pedantic, but also not pedantic because it's just important. Um, and then it is creating each of these schedules. Now again, there always seems to be one line or one row or column issues a bit. So it was mis-referencing something here on the growth rate. And because it was doing that, now the formatting is a bit off. The growth rate is here. Um, and the, the actual kind of value is here in percentage formats, which is a bit weird, but it's going through each of these schedules, you'll see lots of zeros and it's finding its own errors. And what we're getting towards is on the right hand side of the actuals. We do have five years of forecasts being set up. There are some gaps here, but in principle the revenue line looks reasonable. The kind of freight warehousing uh, net cost line looks reasonable. It's not doing something right for the cost of sales and operating expenses. Essentially this should be on this line because that's actually EBITDA. So not perfect. But I think we all agreed it's close if it can fix its own errors. So we want to see what happens.

[00:42:31] Host: Paul Barnhurst: Yeah. And that's the question I think Excel agent. You know, unless this fixes its errors, it was a little cleaner.

[00:42:39] Co-host 1: Giles Male : Yes.

[00:42:40] Host: Paul Barnhurst: And what we're seeing so far. But we're going to give it another five, ten minutes here. We really want to finish this. Then we'll be back and kind of wrap up the episode and share how it did so well.

[00:42:51] Co-host 1: Giles Male : I guess the point is, none of the other tools other than agent even seem to be getting close, did they? So they didn't warrant the extra time, but this feels close.

[00:42:59] Co-host 2: Ian Schnoor: A couple of them stopped early, didn't get there. We're really not getting this one is, um. Well, I'm curious, of course, to see, uh, you know, some of them, the other ones were also iterating, iterating and improving upon themselves and then kind of stop. This one's still working. Uh, so I want to know what it feels comfortable with as a deliverable to us because, uh, I've, you know, I've learned that it might look, you know, it might look messy or sloppy, but it might keep working at it. And I want to know what it delivers. So we'll, uh, we'll come back.

[00:43:30] Host: Paul Barnhurst: All right, so we're back. We've been going good 30 minutes now on this one, Giles.

[00:43:35] Co-host 1: Giles Male : Good. 30 minutes. And you know what? It's really interesting because I think if we had not experienced what we did with the last episode, we'd probably be sat here going like, wow, this is miles ahead of anything we've seen. Agent did far better in less time. Uh, it's getting there, but there are some massive holes all the way through this at the moment. Like to the point where there's just. This is not a finished or complete model. I mean, look, look at this. My caveat is it's still fixing things, but yeah.

[00:44:06] Host: Paul Barnhurst: It's still thinking, but it's but.

[00:44:07] Co-host 1: Giles Male : You've got you've got a term, you know, kind of mini corkscrew of sorts for term debt, beginning debt, amortization, closing balance. But it's just the wrong links. And you've got like the signage switches for the amortization from the actuals to the forecast. It's -25 there. Then it's positive. So that I mean that's just wrong.

[00:44:28] Co-host 2: Ian Schnoor: If you look at 2023 I've never purported to be the most, uh, you know, the fastest on my arithmetic. But how is it that you could start the year with $250 million of debt, pay off 25 and end with 25?

[00:44:41] Co-host 1: Giles Male : I mean, it's going for the wrong column, and this is just a little.

[00:44:44] Host: Paul Barnhurst: And then the next month, you're 275, then 50, then 250, even though you're paying off 25 every month.

[00:44:49] Co-host 1: Giles Male : Yes, it's a column out for his references. But again, this is I think Tabbi has done brilliantly across the board today. And when you get into this financial modeling territory, one mistake like that, the model is useless.

[00:45:04] Co-host 2: Ian Schnoor: A couple of my thoughts as well, and this seems consistent with some of the other tools. They seem to be better when they have very specific guidance and instruction on populating and answering questions and filling in cells. When you give it a set of historical statements and say, just go for it, build something. Um, you know, unsurprisingly, they've struggled more. But for me, the frustration is we've now been here for 30 minutes. Um, we don't know how much longer it's going to take. It might take another five minutes. Another four hours. Um, I mean, and if you look at a formula like that one there, the operating I mean, what's in. Can you click on the previous column cell I this again I, this I know. So that clearly was there. We gave it that that's a sum that it knew that in 2024 we were doing a sum to arrive at operating cash flow. And yet when you go to J, when you go to the exact same cell in J, it's done that. And um, you know, the net income is like no man's land there up in row 37. Why is it like a little island all by itself. Um, hey, it I would highly caution that nobody should be submitting a model, uh, yet like this to their boss. Obviously. Now it might fix it and make it perfect. It's still thinking we just don't have a sense for, you know, uh, where it's at and how much longer. But, yes, we clearly have seen some errors. Do you want to point out one more thing that we noticed? Uh, you know, if you go down to the debt schedule Zell, one quick thing that I noticed, uh, you know, on the revolver piece of the debt, right? I mean, right click on cell three. So this is a row with no label, so I'm not really sure what it's doing, but it's. So what is it doing? It's taking a total long term assets minus. And then it's adding. It's taking.

[00:46:46] Host: Paul Barnhurst: Why is the bank debt.

[00:46:47] Host: Paul Barnhurst: Revolver equal to long term.

[00:46:49] Co-host 2: Ian Schnoor: Well I mean.

[00:46:51] Host: Paul Barnhurst: It's it's quite.

[00:46:52] Host: Paul Barnhurst: It's.

[00:46:52] Host: Paul Barnhurst: It's taking.

[00:46:53] Co-host 2: Ian Schnoor: A negative of negative. It's adding up and minusing. But listen it's obviously in a bit of a spin here because it's numbers don't make sense but it's unclear. It's unclear how much longer we're going to need to wait to get something that might be useful. Listen, I don't want to sound too negative. It's extremely impressive that it's doing this and building something, but I think people you know should know you can't exactly take a historical set of financial statements and say, build me a rough, a quick and dirty five year forecast with some reasonable growth rate assumptions, reasonable schedules, and in 5 or 10 minutes, we're not getting, you know, a beautiful model that we can then play with. Like we're going to have to troubleshoot this quite a bit before we can use it. And we don't know how much longer it's going to take.

[00:47:32] Host: Paul Barnhurst: Prime example. There's a guy Michael on LinkedIn I think it's Khan or something like I can't remember the last name, but you know, he mentioned when I use Claude, I have 30 pages of prompts to build the model and I'm still doing 40 hours of rework. Right. He's trying to prove it can be done. You can get there, but it is not a go get your coffee. It's not a just trust it. You got to know what you're doing, and you got to be willing to do a lot of prompt and put time into it. I mean, the whole tabs, I think the summary is tabs has done a very good job today.

[00:48:06] Co-host 1: Giles Male : Very good.

[00:48:08] Co-host 1: Giles Male: Yeah.

[00:48:08] Host: Paul Barnhurst: Ben, Ben has been really impressed. On the whole, there's a few things that you know, but despite it being impressive in general, you gotta know what you're doing and you gotta realize the more complex it is, the more time it's going to take you and you have to decide, is that worth it?

[00:48:25] Co-host 1: Giles Male : I think he made a really good point, which he may have made on a previous episode, which was in those battle workbooks. Even though the prompt is quite high level, there's a huge amount of text information saying, right, this is what I want you to do. This is an example. Here's an example answer with this information. So those sorts of workbooks give so much guidance versus this where the prompt is kind of like saying you need to understand financial modeling. Here's a rough starting point. Go. And agents, the only one so far that we've seen that mechanically has done a pretty good job, actually agree.

[00:49:01] Host: Paul Barnhurst: They've all really struggled when there's limited structure and you're just asking them to go like the PVM is quite structured. Did good. You know, the deferred revenue schedule is a fairly simple task compared to building a full model, right? The Excel use cases are very structured. The um, analysis you have to do is less structured. And, you know, in general, they haven't done quite as well. I'd say Cab did the best job on that by far. Still had its issues, but it was very impressive. I mean, I'd give it a nine out of ten on that one for sure. Not higher. It was really good.

[00:49:35] Co-host 1: Giles Male : I think Tobi's done the best of the third party tools. Ignoring agent X from Microsoft. I think we're doing a shortcut next, which is the one that, you know, has got a very high price entry point for one of the packages. So I feel like the third party bar has been raised by TabAI, but Adrian has already kind of taken our.

[00:49:59] Host: Paul Barnhurst: I think it depends on where you look. I think cab I did a better job on that, um, ledger that you gave it the analysis there than Excel agent. I think it was on par with the structured cases. I think about building the model. Excel has done the best so far. So I think it depends on what you're doing. I think it's on par, just different.

[00:50:21] Co-host 1: Giles Male : Isn't that really interesting already though, that the agent has done better on the task that requires more specialist knowledge? In one respect.

[00:50:31] Host: Paul Barnhurst: It is really interesting. I think from an instruction standpoint and the fact that you can ask or add an agent, I think the most clean interface so far has been tabAI tray slide is probably next on instructions and thing agent has work to do there. But it's interesting.

[00:50:49] Co-host 2: Ian Schnoor: Yeah. Listen, I'm excited about the future. They're all going to get better. They're still learning. You know lots of reasons to be excited and lots of reasons to be very cautious. And uh, and hopefully this is helpful at, you know, letting people see where they're at, what they're doing and what the experience that we're having running these tools. All right.

[00:51:05] Host: Paul Barnhurst: So I think, uh, we'll call that a wrap. Another great episode. Thank you. In Giles.

[00:51:10] Co-host 1: Giles Male : You say you wanted me to wrap. Sorry. I wasn't sure what you said.

[00:51:12] Host: Paul Barnhurst: Oh, yeah. Go ahead. If you want to wrap real quick to close this out.

[00:51:14] Co-host 2: Ian Schnoor: Yeah. Let's go.

[00:51:15] Host: Paul Barnhurst: Giles, give us a rap.

[00:51:16] Co-host 1: Giles Male : If you think I can actually just rap freestyle. Uh, you've bought into those videos too much. Next time.

[00:51:24] Host: Paul Barnhurst: Well, I'm very disappointed then. Giles, you're kind of like AI all hype and. No. I'm saying that.

[00:51:31] Co-host 1: Giles Male : I'm all hype.

[00:51:33] Host: Paul Barnhurst: So on that note, what we've determined is it's all just hype. No, in reality, it's impressive. Just like your videos are. Giles. But they take work. They do? Really? The message here is it takes work, right? Your videos don't just happen on demand. Nothing really does. Ai is getting better and better, but you need to know what you're doing. Nothing's changed in that tab. Ai's been great. One of the best tools we've tested has been very impressive. And we'll keep going. So we'll see you next week. Until then, thank you.

[00:52:01] Co-host 2: Ian Schnoor: See you gents. Good job. Thanks, everyone.