Can Claude's AI Agents Build a Better M&A Model than Investment Bankers?

0:00Debs: What parts of this exercise do you outsource to Opus and Sonnet? And also, how do you or Fable decide what is a Sonnet task and what's an Opus task? It really is amazing, but it burns through the tokens. And I'm regularly hitting my token limits if I'm just using Fable. Until you realize you burned through all your tokens just switching and had no idea. I haven't hit my limits for this week. In fact, I even did a test run just using Fable for this same merge model. And the outputs weren't hugely different. When do you ever see a public merger announcement that's not accretive to EPS, right? It's just like insert synergy, goal seek synergies to make this greater than zero.

0:43Welcome to all our listeners. Welcome to this week's episode of What's the Big Deal? Graham, tell all our listeners, please, what is the big deal this week?

0:51Debs: We are looking at not a new deal, but a deal was announced last year that's currently under competition clearance review by the Surface Transport Board. I think that's what it's called. And it's the proposed merger of Union Pacific and Norfolk Southern. Is that the name of it, Devs? I actually always mess this up. I know, they're catchy names. I think just because I haven't really heard of them. Yeah. Well, yeah, and it's interesting. I think when the deal was announced, it did get a bit of press coverage because it's a really big deal, isn't it? I mean, I think Norfolk Southern,$85 billion enterprise value.

1:24And together they will form an enterprise that's worth$250 billion. So it is a mega deal. So it did hit some headlines, but maybe not the most exciting deal, you know, in terms of, you know, being able to talk about railroads, you know, and connecting ports with railroads and things. So I don't know. Graham, you tell us, what do you think is interesting about this deal?

1:48Debs: Oof. Well, I mean, okay. So I think U.S. rail is pretty boring in general. I think rail can be interesting, particularly if we're talking about new high-speed rail links that open up new routes and are interesting for a passenger. But I've been taking more American rail than I ever have, just spending time on the East Coast working around here. And I got to say, it sucks. Yes. It really sucks. Coming from the UK, I would agree with that. Yeah, yeah. Yeah. And arguably the UK is not great in the context of Europe either. So it's kind of like, you know, from best to okay to worst here. I was on this train to Baltimore, I don't know, like a month ago or something.

2:33Debs: And I swear as the train was moving around, doors were just flapping open and closed. It looked like it was built in 1950 or something. And I'm like, okay, what is going on here? But I have to admit, I actually don't have that much knowledge about U.S. railroads. I know there are a couple of big railroad companies. The one everyone thinks of here is Amtrak because that's the passenger. That's the passenger railway. I actually couldn't tell you what the ownership model of all these networks are. Do passenger trains and freight trains share the same actual tracks in some places? How do those arrangements work?

3:10Debs: I literally, I could not tell you. If anyone knows, let us know in the comments. Maybe you know, Debs. No, not at all. But what I was going to say is I think even my very rudimentary knowledge of European rail is that, yeah, the ownership models are generally complex because you get different parties owning the infrastructure, the rolling stock and the maintenance of that as well. So it is generally complex. So, yeah, it's a tricky thing to get your head around. But we're going to have a look at the deal today and see what we can learn from the numbers. We'll run the numbers. We've actually built a merger model for this deal.

3:48So we can take a look at some of the key metrics that we tend to look at when there's a deal announced and see if the numbers work. And also use AI to run those numbers for us because, of course, we don't need to do that anymore. Yeah, absolutely. So should we dive in?

4:03Debs: Let's do it. Let's do it. All right. So you used Fable, I want to say, to build this draft. Well, actually, no. It's kind of an interesting process here. There was Fable delegated to other agents, right? That's right. So I was really flexing my skills when it comes to AI this week. And part of that is because I'm experiencing what I think a lot of people are experiencing at the moment, which is challenges when using Fable, which is the frontier model for Claude, which is amazing. It's really good, you know, really high level, you know, taking on projects, taking on challenges. It really is amazing.

4:39But it burns through the tokens. and I'm regularly hitting my token limits if I'm just using Fable. And I had been reading about the possibility of delegating certain tasks within a project to other models which use fewer tokens, for example, Sonnet and Opus, still within Claude, and using that approach to kind of optimize your use of tokens and maximize efficiency. So I thought I'd have a go. and yeah we'll have a look and see the output shall we? Our financial and valuation modeling certification program is the self-paced version of what we teach inside investment banks. Seven courses, 46 hours, three statement modeling, DCF, trading and transaction comps, M &A and LBO all built in Excel from scratch using real case studies.

5:32Over 100 ,000 people have gone through this training. You get unlimited support from former investment bankers, a month of pitch book access, and the certification when you pass the exams. It's all at wallstreetprep.com.

5:45Debs: What things, what parts of this exercise do you outsource to Opus and Sonnet? And also, how do you decide, how do you or Fable decide what is a Sonnet task and what's an Opus task? A really good question. So I actually asked Claude that question myself because I had never done it before yeah so i gave claude a very basic prompt to build a short form merger model for the deal okay the short form it just means it's just for basic calculations it's not a full uh integrated income statement balance sheet and cash flow statement and i give it a bit of guidance on the data sources to use and but then um the second half of my prompt is basically that i want to optimize efficiency and minimize token usage by delegating lower level tasks to sub agents opus and sonnets.

6:32And then basically I asked Claude which tasks can be delegated and provide the prompt and subagent so I can run these separately. So I'm basically leaving Claude to make the decisions on this. Now the one thing I should...

6:44Debs: Okay, and are you having to prompt separately and pull the data together or do you give an instruction to Claude Fable to instruct the subagents automatically? So I tried that and I failed because basically I was using Excel add-in. Yeah, so if you're using the web interface, you can actually get Fable to do the delegation for you. It does allow that process. But unfortunately, in the Excel add-in, I'm not sure why, but it doesn't. Basically, once you put the prompt in and you select your model, the whole process has to run with that model. So what it then does, if you want to split the tasks up and have Fable as the orchestrator, and then the sub-agents doing some of the lower level work, you actually then have to create a new prompt within that same window where you then switch between the models.

7:34So you're effectively jumping between models for different parts of the task and then you come back to Fable at the end, you know, for the kind of the more important tasks that you really need that sophistication for. The process was a bit clunky. It required lots of starting and stopping the prompt or the process running, But to be honest, it worked. So I'm happy with that. And I'm sure the process will improve with time as more people start to use this kind of orchestration approach. Yeah.

8:03Debs: And you know what I do? I also think that the web interface, the desktop application, whichever one you want to use is actually getting a lot better at Excel work as well. So if you're one of the students in my class this week, and you're doing the case study today, lo and behold, a lot of that was done and put together by Fable as kind of a actually is really, really interesting, right? It's a case study based on an existing Aries deal that needs needs plenty of money. of information to put a model together and then a whole PowerPoint presentation for the actual case study. And there was a lot of back and forth to get it where I needed to get it.

8:45Debs: But you know what, for the amount of, I'm not going to say amount of effort, but compared to when I was doing some of this work with other models before, the results I was getting just straight out of the Fable application in terms of download and kind of review were actually pretty good. Much, much better than even a couple months ago. So I think maybe starting the process off in the desktop app and just saying, okay, instruct the subagents accordingly, get me the first drafts, and then continuing to work in the Excel add-in interface. Maybe that's the current best workflow. Oh, Graham, I think we have another episode awaiting us then.

9:26Debs: Yeah, exactly. But yeah, this was definitely a little bit clunky. and in terms of the tasks just so basically fable is amazing for planning and high level structure and you know and even the fact that it was the one that was orchestrating sort of working out which tasks should be done by which sub-agent and if we go down through the tasks basically the data mining fable has recommended that sonnet do that piece of work and it gave me the actual prompts that i needed to use within sonnet so i just toggled the actual model within the within the window and then finding the consensus estimates again that's just data mining and then for opus that comes right at the end for more complex reasoning basically it says to use opus for just basically a check after the model's been built stress test the logic make sure it's kind of all cohesive and that you know yeah okay it's kind of sense checks it at the end so i think it's not a Bad solution.

10:25I mean, the one thing I have read is that if you're juggling between the different models within the Excel add-in, it actually does use quite a few tokens, just handing over tasks between different models. So you can offset the efficiencies, I think, if you've got too much juggling between models. But I did ask Fable to optimize the efficiency. So I'm assuming that this is kind of the best use of those sub-agents and minimizing handovers.

10:54Debs: Until you realize you burned through all your tokens just switching and had no idea. Well, honestly, I haven't hit my limits for this week. And I have definitely been using Fable quite prolifically. And in fact, I even did a test run just using Fable for this same merge model. And the outputs weren't hugely different. So that gives me a little bit of confidence. okay let's dive into the actual model itself yeah let's see what we got okay so we have our merger model our short form model uh starting off with the market and deal assumptions so we have the offer details here so uh we've got uh cash consideration of 88.82 dollars per share and also an exchange ratio of one for one so effectively it's a cash and share mix in the consideration okay and that gives a total value of 398 spot for one dollars so I think it's what does make it interesting I think in this deal is that you have that got that nice mix of consideration which is quite common when you've got very large deals and it is a mega deal you do need a stock bit of stock in there so yeah so that's the kind of the initial setup up.

12:07And then Claude has grabbed the standalone company data. So we've got the debt and cash and some of the earnings numbers, both EBITDA and an LTN basis, and then EPS forecasts. I think they've done a good job in terms of grabbing the adjusted numbers. Those are the ones that the analysts tend to focus on, the cleaned, adjusted EPS figures. And that's the live deal so it hasn't closed yet so and probably the focus be on the 2027 numbers um okay and then we've got some of the key assumptions uh that are going to be used in the numbers so we've got the cash used from the balance sheet tax rate interest rates and then that important number that's the one we all like to focus on is the synergies 2.75 billion of synergies there so um a good decent bit of strategic overlap hopefully for this transaction gone and what is the what's the

13:04Debs: okay, net income, we got, what, eight billion for Union Pacific, 3.2 for Norfolk Southern. So the synergy number is material for sure, but it's not crazy. I would use that word in the sense that was it Paramount's, not Paramount Skydance, but Paramount Warner Brothers where, you know, combined net income was$100 and synergies were $400, something like that. Yeah, no, you're absolutely right, Graham. I mean, actually, to be fair, the numbers, it's quite punchy when you compare that to the LTM EBITDA of Norfolk Southern. It's the$5.5 billion of EBITDA versus pre-tax synergies of$2.75. So it's still quite a punchy number.

13:54Debs: Yeah, and I'll admit, they have a whole website to basically sell the benefits of the merger and they say there's going to be no layoffs and more union jobs created and all this stuff. I don't know. What are the costs you really cut out of combining just these two separate rail networks? I mean, I don't know. What is it? Or is it literally just we own all the rail networks and we're going to put prices up and there are revenue synergies? So I'm sure there's some overheads in there. But as you point out, a really important point, which for me, unionization of a workforce is a big challenge when it comes to cost savings because it does create huge obstacles to headcount reduction um but yeah so uh yeah maybe it's a lot of overheads but yeah i'm not an expert on railroads unfortunately so right so let me move down we've got a few more adjustments a little bit more advanced actually graham this is something that you spotted when you first when i first shared the results uh which is some slightly more advanced items in the calculations.

14:58They've got some adjustments for step-ups where you revalue the assets of the target in the calculations of earnings per share. And that's a little bit, that's not always one that we would do in our first cut on the numbers, is it?

15:14Debs: That one in particular is really used to figure out what your increase in depreciation amortization is going to be and if you make the argument well that's a non-cash expense so who really cares i mean you care in the sense you get tax shield on it so that's you know that's something um but a lot of times and we were we were talking a lot of times when you look at this on a cash basis you just don't even think about that kind of adjustment absolutely cash eps all the way so um it's been a little bit more sophisticated than we probably need when it comes to that um we then have our sources and uses of funds.

15:49So that's really standard, clear layout. So I've done a good job there. Most importantly, the sources equal the uses, which is always what you need for a deal to be able to go ahead. Indeed, indeed. Yeah. Is there anything particular that you want to highlight from that? Or should we just keep going?

16:05Debs: Actually, I was just, you know, I was thinking I'm going to correct myself on the whole cash tax savings from the depreciation step up, because I'm assuming this is a, we'll know, this is a stock deal, not an asset deal. So the step up doesn't actually get you a cash tax savings. So. Ah, yeah. Okay, great. And then this is where it starts to get interesting, I guess, is where we've got the accretion dilution analysis. So effectively, we're combining the net income of the two companies. We're putting through some adjustments for things like, you know, all the extra interest on any debt used to finance the deal, interest lost on cash used to finance the deal and then once you've got your pro forma net income we then calculate the pro forma diluted shares that takes into account all the new shares issued as part of the equity components and the consideration and that allows you to calculate pro forma eps and you can compare that to the standalone eps of union pacific and that gives you a nice bit of eps accretion uh in the second year uh so that's uh 2027 uh on a pro forma basis so we've got double digit eps accretion and that presumably is just the synergy ramp from 50 to 100 right yeah so that's what i think it's quite nice about this uh particular model is that you can flex this so you can you know so we'll actually by 2027 maybe it's only gonna be 75 percent uh synergy run rates achieved.

17:33And it just allows you to flex the outputs based on your sensitizing that number.

17:37Debs: Yeah. I mean, we're looking at a reasonably well put together. I mean, it's a short form model. I mean, to call it a model even is a little bit of an overstatement, perhaps, but it's pretty, you know, it's well constructed. Yeah, absolutely. And then if we keep going down, we have the other critical metric that I would always have alongside EPS accretion and dilution and that's pro forma leverage because as you know hopefully our listeners are aware that eps accretion is very easy to achieve if you leverage up because debt's cheap as a source of financing yeah so um there's a risk that you just achieve eps accretion by using too much leverage so having an idea of what any debt financing does to your leverage numbers is really helpful so here they've calculated the pro forma debt pro forma net debt combined LTM EBITDA including synergies and that allows you to calculate pro forma net debt to EBITDA including synergies and I'll just highlight the number at the bottom there 2.9 times so it just gives us a bit of reassurance that the debt used to finance the deal doesn't result in them being you know a huge credit a risk of credit rating downgrade or anything like that yeah yeah Yeah, yeah, yeah.

18:50Debs: And I don't have, the one thing that'd be interesting to see is just what the standalone leverage positions were before this deal. Because I know a bunch of new debt is getting issued to make this deal happen. Yeah, that's a really good point. Because I don't think there is anything, no, it hasn't given us anything on a standalone basis. So no, you're right. It's a bit of a shame that you can't compare that step up in the leverage. Yeah, and do we just combine EBITDA? I don't know if I can't remember if up above in the model we had stand-alone EBITDA and you can just calculate it quickly yourself.

19:28Debs: But it would be helpful if Claude had thrown that in. Yeah, it would be. In fact, what we could do is actually update the prompt. Should we do that? Oh, yeah. Yeah, yeah, yeah. Okay.

19:44I'm so polite. I say please do that stand alone.

19:51There we go.

19:54Debs: And then one thing I noticed while it's tinkering on that, one thing I noticed is the sensitivity analysis down at the bottom is still following those same kind of not data tables, but all one giant formula. It's really hard to audit. And obviously we finally got the answer why that is the case because I think it's something like the Excel Cloud API does not allow data table creation. So we got to run with these kind of crazy tables for the time being. Or I think last time when I asked it to do a data table, it just literally gave me the setup and even said what prompt, not what prompt, what cell to link to what input, that kind of thing.

20:35Debs: So that's not bad either. Yeah, absolutely. Because it's running the query at the moment, it's kind of jumping around a bit. But yeah, so what you were referring to there, Graham, the crazy formulas, yeah, we definitely still have those. But we do have a decent data table, at least, which allows us to see how the EPS accretion varies in terms of the financing mix and the level of synergies which can be achieved. So yeah, we have the outputs, but we just try and ignore the actual formulas which are being used to derive those. Yeah. How is our query getting on? It's still... running uh in the background oh here we go here we go let's see plus okay so it's another it's another full turn of leverage it's not that's not nothing in in the context of a of a corporate credit like this i mean because in the world the world that i used to work in looking at something that's 3.4 times leverage say oh that's like you know senior bank debt that's nothing um but for a for a corporate credit like this it's a little bit more material it is i mean there's obviously a little bit of industry flex and the one thing i do know about railroads is they're very asset intensive and you can generally stretch the leverage metrics where you've got you know all that you know all that track rolling stock whatever um so yeah we probably would expect the numbers to be higher than for lots of other kind of industries like consumer businesses that's totally fair yeah yeah um but yeah as you say another turn 1.2 times excluding synergies or 0.8 times extra when you include the synergies.

22:16So it is a big jump up in the leverage for them. So yeah, but it's useful to have that information side by side.

22:22Debs: So what do we think about the deal? Is it weird if I say I don't care?

22:30I think I was quite excited by the clawed elements and the running, you know using the orchestration of using fable the deal itself oh i don't know i don't think i

22:41Debs: can get it it's just a bit it's just a bit meh yes it's been there the numbers don't look bad you've got eps accretion you've got leverage which doesn't look too yeah i mean when do you ever see a public merge announcement that's not accretive to eps right it's just like insert synergy, goal seek synergies to make this greater than zero. True. I think I have actually come across a deal. It was a defensive move by a company where the analysts are running the number that it was like, this isn't EPS accretive. But actually, funny enough, the actual press release didn't comment on EPS accretion. It talks about all the strategic benefits and things like that.

23:20Debs: Gotcha. So, but yeah, it ticks the boxes on this deal. But yeah, there's not a lot of exciting stuff happening from my perspective. to us. No, we'll still take trains. They're still going to suck here. That's it. Yeah, that's it. But we've learned a new way to work with Claude, which I'm really excited about. A hundred percent. A hundred percent. Great. Well, I hope everyone enjoyed listening to this week's episode of What's the Big Deal? I hope you all learned a little bit about how to optimize your use of Claude. And yeah, definitely we'll keep revisiting this topic as we get more and more skilled with our use of AI.

23:59Tune in for next week's episode.