Claude AI to Automate Bookkeeping with Real Business Workflows

Welcome to another episode of Future Finance. I am one of your co-hosts, Mr. Ibitah. Oh wait, Paul Barhers, the FPNA guy. And I'm lucky enough to be joined again by my partner in crime. Glenn, how you doing, Glenn? I'm good, man. I was just going to say we've been missing each other this week. You've been emailing me and I haven't been responding. I'm like the ex-girlfriend that's making-- [laughs] But I've been head down on a bunch of work, but making my life better with AI every day. So I guess it beats the alternative to not having anything to do. Yeah, I've been realizing more and more how much I need to spend more time on AI as I keep digging into building some actual agents, doing more. But I've also spent a fair amount of time with Excel's agents. So it's fun. So you mentioned it's making your life better. I know when you and I chatted, you've mentioned you've been making a bunch of changes. So I think for this episode, we'd love to first hear the changes you made and some of these breakthroughs you had, maybe we could talk about how they relate to finance and we'll go from there. So first off, I wasn't trying to make a controversial post. I wrote in my substack, it's been several weeks now. Maybe I put it somewhere. I put it in my substack or LinkedIn. And I got a lot of flack for this. But I stand by it and even more so. I was an early chat GPT user and I thought I was committed to it because I loved its memory and it knew me and it was tuned in to my writing style and it was just a good assistant across all the projects that I'm in, it was able to pull in context. But it seems, and this isn't, oh, I miss 4-0 in the way at the Sikafant way it talked to me or whatever. This is even more recently from 5-1 to 5-2. And then I don't know what they're testing out now. Ahead of 5-5, it's going to come out. But-- - Oh, it's 5-5 next. Can I say something? Do they know how to number? - Yeah. Well, the thing is, in version control in software, that's normal to have the point whatever releases if it's not a significant release. But now, because their product naming is so bad, this isn't just open A.I. this is across the board. All their product naming is so bad that we're all now in tune with software version numbering which we shouldn't be. It should just be this is whatever. I've been pretty frustrated with chat GPT hallucinating for getting rules I've given it. And at the same time, my cloud use has gone up significantly, especially around modeling and anything where I have real finance and accounting work to do. And what we're using on the back end for some of these workflows that we're building for clients. The straw that broke the camel's back was some bad interactions with chat GPT where it just was not helpful. I was trying to hand off or bring a new resource onto a client where at all the client info in there. And it just was spitting out this like, I was trying to create a document where I was handing something over to a new very seasoned person. And it was talking like it was a kindergarten or coming in and I kept telling it, change your tone, write this as if this were an internal memo at McKinsey or whatever. And it just was terrible and all these weird like insulting parentheticals. And I was like, why would you put that? I didn't tell you to put it anyway. So frustration with that. Meanwhile, I should be embarrassed to say this, Paul, I've been in finance my entire career. But I'm sort of that what's the crying clown or the cobbler that needs new shoes. My personal LLC I've had for a decade, but it's always been, that's just what I run side hustle gigs through. And I've been really lags on tracking expenses around it and overpaying the government for years. But this year with all the, you know, all my speaking engagements, my training, my webinars and all that, I ran that through the LLC rather than through primary business. It was higher than my W2 income. And when I realized that on like December 4th, I thought, oh, I need to offset this with some expenses. So I had two credit cards, this is a really long story. I'll try to condense it down. But I had two credit cards that were co-mingled. I had personal and business expenses on both. One was primarily personal. One was primarily business. But neither were clean. And the one that was-- So you were a typical small business. You just weren't running contribution through revenue. Yeah, only contributions good. Yeah. So I thought, and I haven't talked to my bookkeeper. I love her, but I haven't talked to her in 18 months. And I thought she's going to kill me when I give all this data with no context. So trying to make this as short as possible. But I want to give enough detail to express just how valuable Claude was in this situation. So thousands of transactions on the personal card primarily. And then my business card, fewer transactions, mostly business. But we were going to have to go through, I say, we, me, and my wife, who, since I haven't talked to my bookkeeper, we're going to do this. We're going to have to go through every month of statements and pull out these or business and all that. So I did some context prepping. And I said, look, this is the travel I did last year, which I got, by the way, by having Claude go look at my Google calendar and pull on my trip cell. And then it identified, OK, this is when you did travel. And then I said, go through and look at webinars. And then it pulled out when I was hosting-- anyway, so I had all these various associated things that Claude pulled out for me. And I said, now, go look through these-- and I was actually able to get it down to just CSVs of every transaction. So go look through each of these. I did one card at a time. And I said, identify all possible business expenses, pull them out on another CSV. Here's the things that are happening in other cities around these dates will be most likely business. But it even pulled out things like I was paying on my personal card, my Google workspace account. I was like, I bet that's for business. So I was like, yeah, that is-- so anyway, I identified all those. Then I went through the other card and did the same thing, got a good number of files, or a good number of transactions. Did the human in the loop? I went through all of them, made sure it wasn't putting my YouTube premium subscription in business, or something like that. And then I did project accounting. I went through and I looked at, OK, these are my trips. This is-- and I had it tied, expenses to every trip. That's not for taxes. That was just for me. But then I uploaded my chart of accounts. Oh, and by the way, I did all this-- the first part of it, a big chunk of it, with the Excel plugin for Claude, which will talk more about plugins after I get done with my brand. But so I had it categorized them by business, and then I had some other expenses. And so then I had the two CSVs from the different cards, and I said, OK, now I haven't paid these out of the business, but I had owner distributions. I need to offset the owner distributions. Can you recommend journal entries for me? So I did quarterly journal entries. And my idea was, OK, well, now I'm just going to call my bookkeeper and say, just make these entries. I know it's four entries, but it's been a while since I've done bookkeeping. I didn't trust myself. So I was just going to give it to the bookkeeper and have her do those. But then I thought, well, I wonder if there's an MCP for QuickBooks, which there is, but it's in a sandbox environment. And it only came out in October, and you can't do anything with it. But then we've talked before. I've been using Claude co-work a lot. And I said, hey, can you do that through the browser control? Can you make journal entries to me? And it was like, heck yeah, I can. And so it basically, in one afternoon, I'd been worried about this really from the entire fourth quarter of '25 and then into getting ready to get everything over to my tax accountant. And it just in one afternoon did all this for me. And I stayed in the loop on it. And it really, I shouldn't be so surprised, because I do-- we build things for large companies. And I talked to individuals and companies about how they can use it. But when it's that impactful to you, I thought, this is amazing. And what I just saved in bookkeeping and everything I would add to do around that, that would pay for a good chunk of upgrading to the Claude Max for the year. So after my frustration with chat GPT, I went down from my max subscription that down to the Teams account that I have, or whatever they call the business plan. I like $20 a month one, the big-- Yeah. Yeah, that's what I have. And then I upgraded Claude. And oh, and it was interesting. And I probably should do a post on this. How do you extract all the meaningful data from 1LOM that it has in your memory and bring it over to the other? I didn't export like every conversation, because I don't need every conversation. But I did pull what was in memory. And I pulled my projects over and everything. And it's, you know, I'll be saying this. And then in three months, I may say, well, now I've switched to Gemini Ultra, you know, because these models are always beating each other. But I think the writings been on the wall for a while, going back to my original statement that I think chat GPT, my wife and kids love it. I think it's more of a consumer grade. I think Claude is making real inroads into businesses. And that's reflected in the market. I don't know if you saw-- I guess when this airs this will be last week, all the SaaS companies, Stocks, software companies, Stocks took a hit because Claude co-work is automating so much of what they do. And I know before I went on my long rant, we were talking about one thing we could talk about today is automating workflows and how, you know, a normal person would go through and do that. But I think after my rant, we can save that for another session, because what I really want-- and also, we've got a mailbag thing. But before we get into our mailbag, because a couple of these questions were around this, I'm fired up about Claude in Excel. because it's so much better than what I used before. However, you've been in co-pilot a lot, and I know I've dogged co-pilot over time, but you're seeing improvements. I'd like to talk about that for a few minutes, and then maybe we dive into our mailbag, and we can, the stuff moves so fast, and then really testing it for real use cases versus just, hey, build me a model, and you're like, okay, so what I will say a couple of things, really interesting this week, I'll start with this. So I'm working on my data visualization course right now and I have an AI section, and I decided to take some fake data, I'd take an a P&L, then I'd normalize it into a table, generally a little easier to read, although they're getting so good at reading the regular P&L, that I'm not sure it makes a huge difference as long as it's a clean P&L, whether you normalize it or not. And so I'd done that, and I decided to run it through an agent and asked it to create some graphs. I ran it through co-pilot, I first told it, you know, analyze this data and give the recommended graphs, it went ahead and built them, co-pilot, even though I didn't directly ask, but they were decent. It went great, there were some color issues, and it didn't follow all the best practice, I probably could have prompted it and got there, but they came up with some graphs I'd call pretty good. So I gave the same exercise to Claude, and I looked at it and I got all done, and it had this chart, the word chart, in three different places, and it brought over data, and the data was just a table. And so I said, where's the chart, and there are thirds right there. McWire, I want a graph, these are supposed to be visuals, and it just spun and never gave me an actual graph. Even though when I ran that same exercise through the LLM, it produced three graphs, you know, using JavaScript or Python, or I can't remember what it used to write it, you know, using one of those codes. So my first experience with Claude in Excel, even though I hear everybody raving about it, was like, I got better results using co-pilot over here, at least attempted to build the visual. So that surprised me. No, take that as one limited use case. So I fully recognize, that's not real big, but what's interesting with these agents, and I posted about this on LinkedIn, is a couple things, then I'll share something. What we're seeing right now is a blurring. I expect small to medium businesses to turn more to Excel in the future than traditional planning tools. Not to say traditional planning tools are going away. Not to say they're still not a big market for them in a need, but that smaller and medium are going to go to these hybrids, where the tool is just built as an agent in Excel. Yes, there may be a database, and there's some out there, but they're going to streamline and be lower cost. What you're seeing with several of these tools is they're becoming workflow tools already. EBITDA AI, pulls in campfire. It connects to zero, tab's AI connects to zero, and quick books. And you're seeing some of these new analyst tools building agents with them. So yes, some of the planning tools will build their own Excel agents, for sure. But if you're a small company, do you need the heavy? Most of them use Excel today anyway. So does that extend, let's say a company hits 50 million, they start looking at a plan until you've been there, 100 million, whatever. You really start to grow, you deal with all the headache, with agents, and having an agent layer in Excel, can you get to 200? Can you get to 250 before you need a tool? I think it's going to increase when people decide to switch. There's going to be higher numbers as these agents get better. And then something that's really interesting that I want to share. So I'm going to bring something up on the screen, and then we'll get to the mailbag. So I've been following this for a couple months now. The first version I saw, like three, four months ago, I think had co-pilot, wasn't co-pilot in the cell, it was like Chatchy PT agent at like 45% and then shortcut, I think when it first came out, it was like 56%. This is a benchmark score by spreadsheet benchmark. Look at how much the agents have improved. Now the sudden we're up around 70%. Accuracy, one I saw had humans at like 72%. What's interesting is two of the top three are now coming from China, King's Office, which is the Microsoft knockoff in China, basically. And so I thought that was really interesting. Univir has already been tested. They're still in beta. They haven't even come out. They're not testing everybody. So it's rapidly improving. I mean, to go from 50% basically a few months ago to 70, now, I mean, that's a 40% improvement, right? 20 points, 50 to 70. So it's amazing how quick this is moving. I feel like anytime I say something, am I the cramogen? 'Cause I'm questioning how good it is with how quick it's moving. - Yeah, that's interesting. And it's across the board, seeing Chinese companies at two of the top three there is that's reflective of the broader what's happening in AI and in general. And I think the difficulty right now is not to be an alarmist. However, it's sort of like quantum tech. Like whoever gets there first, it's significant in that you win and that it's a zero-sum game here where, there are consequences down the line if you don't win this. And I think, I don't know, there was, there's a lot of bluster and talk about, the Manhattan Project for AI. And I don't know what at a state level is, but if you look at infrastructure and what's come before, states have been involved. And I just, you can't assume on any level that the US is just immediately gonna win the AI race. And I don't know what that means long-term, but that's a whole other road to go down. But it's like, the legislation went, or didn't go out around social media in understanding of the internet and what it is and how it works. These are career politicians who don't understand technology and I don't think they're being advised well enough on tech policy. And I know current administration is tech forward and crypto and somewhat on AI and all that, but I just don't think we're putting the right resources there, but that's a whole other tangent that, maybe isn't even suitable for future finance, but it's worth noting that we are not the runaway and clear winners in the AI race globally. It is interesting to know, right? It's important to remember, we don't know who the winners will be here. There's a lot of countries developing and how that impacts what we can use. Do we have access to the best technology at plays or role? We won't get into it a lot, because like you said, it's probably not the conversation we want for finance, but I think you'd mentioned the Mel bag. Maybe you wanna ask me a couple questions from there. This is people that submit questions for a session I'm doing here. And I thought it'd be really interesting. And then I'm gonna ask you a few questions about what I'll call "agentic workflows." I know you're very particular about agents versus the "agentic workflow." - Well, and maybe your pedantic is I like to say. - Yeah. And maybe the questions are just two sides of the same coin, because first off, Microsoft, and this has been a peave of mine when you're calling things agents that aren't truly agents. And I don't understand, I had talked into a client today, about a billion dollars in revenue, public company that they said they do most of their work in FPNA and Excel, which, you know, so your reference to small businesses, I mean, huge enterprise customers. - Even if you have a planning tool, some level of your forecasting, some level of work is happening in Excel, right? Excel's not going anywhere. What I think my point was more around, can you get away with not having to have a special built planning tool longer? - Yeah, okay. - Especially if more and more of the ERPs manage consolidation, is Power BI and BI tools get better at the reporting or having an agent layer? Does that allow you to go longer and longer? 'Cause could you just take from what is Excel as and push it to your warehouse for reporting purposes of your forecast with AI, with that layer? So that's kind of more of what I mean. There's things beyond just the planning, but that's kind of where I'm coming from. - Got you. And I saw someone in internal from Microsoft and in their finance department talking about the agents that they were building and the automations that they're building internally at Microsoft. And I've just been so frustrated with what co-pilot can do in PowerPoint versus like, how is co-pilot not just integrated with design? Anyway, a whole other tangent. But I've just been like a lot of people who are frustrated with co-pilot. - We mean it's designed suggestions when you click on it. Why doesn't it just use co-pilot? - Or why didn't co-pilot then, even though the design suggestion sometimes can be terrible, like co-pilot when you talk to it and PowerPoint, it's like, or even if you have it create a slide deck, it is there's no design, there's no anything to it. And it's like, you want me to drop this in your company template? It's like, no, I want you to drop it out of a window. It's terrible. - Last thing we'd like to say is if you've listened this long, email us. We'd love to hear from you. You can reach out to us. I'm P. Barnhurst at the fpnaguy.com. And we'd love to hear your questions so we can have another mailbag episode. So there's my thoughts, let you give last word, Glenn. If you're listening to this podcast, chances are that you're already pretty deep in the AI world, but don't stop experimenting and it's moving faster than any technology I've ever seen. So thank you for listening and hopefully we've given you some good ideas and tips for going forward. And like Paul said, we'd love to hear from you and hear what's working with AI with you and what's not. - Right, well thanks again for joining us and have a great day.