Maximum Lawyer

Tyson Mutrux 00:00:02 This is maximum lawyer with your host, Tyson Matrix.

Martin Kravchenko 00:00:11 Hi, Martin. I want to start with something, and I didn't I didn't give you any of these questions in advance, but I want to get your thoughts on vibe coding. And specifically, I don't know if you've seen this. There's it's string com. So string alpha it's it's through pipedream. And you can you can vibe code AI agents. And I just wonder if you have any opinions on vibe coding in general or about specifically about vibe coding agents.

Multiple Speakers 00:00:41 I think vibe Code and is definitely a useful tool for building something. Let's say quick and dirty, right? Especially if you're trying to experiment with things. AI agents, including. I do think that if we are talking really matter, like, how do we make sure that technology actually helps your firm? A lot of the solutions that at least we are working with, with firms, even very large firms, is quite more mundane than that. All right. It's simple things like, okay, how do we actually make sure that data flows in between systems correctly? How do we make sure that we can actually run proper reports on the data that we already have in our CRM, and maybe the CRM doesn't have the reporting capabilities we need? How do we set up, let's say, simple automations to actually like make stuff happen? So, so with coding, I would say I would say it's a it's a cool tool to develop something that's actually enterprise ready.

Multiple Speakers 00:01:31 At this point in time. I would be quite dubious about that.

Martin Kravchenko 00:01:35 You know, it's a really good point because I guess that's I mean, you hit the nail on the head, I think because string let's use let's just pick on string I think. And I do think you're right. I think it's what I think the value is. Maybe with something like string comm is that you can, you can test out some ideas and test out some concepts. And they'll then go build it out somewhere else if you need to. But it it's kind of hard to take something that you vibe coded and then fit it into this overall system of processes, and that's where a lot of the issues are. So how do you let's say that you've got someone, one of your customers and they're like, hey, I want to build this thing out, right? How do you make sure that that fits in with the overall system of processes that the firm has?

Multiple Speakers 00:02:21 Well, I think first of all, it's looking really where first of all, understanding actually all the steps in the process, right.

Multiple Speakers 00:02:28 A lot of times, let's say if we are actually talking to let's say the firm owner, right, they'll say like, oh yeah, this is done. Like step by step by step, see? And then we talk to the actual person who is doing the job, maybe like the paralegal or the clerk. Right. And they're like, oh, actually, they're just like step D, step by step F, you know, steps that. Right? So first of all, really like making sure that we map out the full the full process that we are working with ideally have some kind of diagram that I mean relative tools great tools on there like Figma etc. where you can diagram out the process. Make sure that everybody who is involved in the process kind of agrees to that. Right. Because that that can also be sometimes an issue if the firm doesn't have proper SOPs. Right. All those SOPs are not necessarily enforced process, but they look different from person to person. Right. So making sure that everybody is aligned with the stakeholders, then understanding how, let's say the data flows, right.

Multiple Speakers 00:03:18 Where do we get information from. Do we call up the client house get information. Do we have it in the case management system. Do we have it in the file. But let's say it's not uploaded to the case management system. And then design a workflow really around around that. Understand like what what what what data needs to be entered into the systems. Right. So we can then actually make some use of it with automation, with AI, whatever we're utilizing. And then after we have that in place, understanding where can we actually apply automation and what processes can be can be automated versus not. Right. And the decision there would ultimately come down to let's understand the full capabilities of the software that we are using already. Right. writes to say no. Case management system clear managed recently released automated workflows. You can now apply task list on stage changes right in the in the case lifecycle understanding we have that native functionality built in. Or do we need to build something extra using a platform like Zapier or Macomb or something more complex than that?

Martin Kravchenko 00:04:15 Yeah, I wonder if you have any advice for people that I'll give you.

Martin Kravchenko 00:04:18 I'll give you a little story, and then maybe you can give me some advice on this where I, when I, whenever I first started as an attorney, the firm I worked for, they had like their own kind of basic templates. They were somewhat uniform. But I know that each of us attorneys had our own set of of documents on our own computer that were kind of our own little templates. And like, the receptionist had her own and the paralegals had their own. And so they they weren't in like this joint database where everyone was using them. We had we had kind of like the, the, the general documents that kind of everyone sort of had modified to make their own. So when you go into a firm like that where like they don't have any like systems or processes. It's nothing's all integrated. Do you have any advice for people on how to when they're starting to build out these processes. Like how do you take all these individual templates and all that and try to blend them all into one unified system?

Multiple Speakers 00:05:13 I think ultimately here the problem is not necessarily a technical problem per se.

Multiple Speakers 00:05:17 It's more of just an operations problem, right? And a human problem, and making sure that, again, all of that knowledge is centralized. And and ultimately, I would say the solution here is, is quite simple. It's just like, make sure that whoever's doing a particular job where they sit together right in the room on the zoom call, right, and walks through exactly how to do a particular function right after we agree on that. Again, we can use maybe some diagramming tools. Whiteboard helps. Then take those documents. Right. Take that process that we've just outlined and put it in a simple SOP right inside of Google Drive or OneDrive or whatever you're using, right? Or your server. Ultimately, I think in terms of knowledge management as well, it's, it's kind of a big thing that a lot of programs out there that try to do, you know, say like, okay, where's the best knowledge management system? We also now working on that internally. We've tried a few of those and really just said, okay, we're going to use Google Drive.

Multiple Speakers 00:06:12 You are going to have Google Docs with those processes that has version control. We can share it with everybody. Nobody needs extra accounts. And actually Gemini connects directly to Google Drive. So you can just say ad drive. What is the process for setting up a new client account? And it will search all of your drive and pull up the dancer. And those answers were better than the custom platforms that we were paid, you know, $20 per user for. So I would say simplicity. And like first, first of all, making sure that everybody is on the same page in terms which is conceptually right on a, on an operational level and then not overcomplicating and not overengineered it and just put it out of paper and make sure that at least say the human processes is is well defined.

Martin Kravchenko 00:06:52 I think what you just said is I hope people don't overlook what you just said, because that is such a really simple, cheap hack. And I think it might be. Ultimately, it might be better than what we've been.

Martin Kravchenko 00:07:05 Everyone's been trying to find for years where like they want they want to have this, like unified system where, like, you can find all the documents, all the all the SOPs and everything. But I remember when I started, all of our subs were on a Google doc. It was like one Google doc. And if I had if we had continued to build out in Google Drive, I mean, like we could be doing what you're talking about now. We're like, you take you just go to Gemini, ask questions of it, and we'd be would probably be better off at this point. So I think that was a that's a really, really good hack.

Multiple Speakers 00:07:35 The look I over my career I've been this for over like 5 or 6 years now already in developing the solutions for law firms. We've built very complex systems on Zoho like the most like 50 different steps in in between 100 different flows. And what I realized that ultimately those systems are amazing. But you need to know when is the right time for those systems.

Multiple Speakers 00:07:59 Like controversial opinion until your firm is 2025 people. Honestly, technology is not your biggest bottleneck. Your biggest bottleneck is getting people on the seats, making sure they can actually deliver the work. And and you have, you know, good customer service. You have some standardized SOPs. But really technology is not the biggest bottleneck because if you have three, three people on the team, if you increase, let's say, process efficiency by 20, 30%, while that's still not even like one full time equivalent, essentially, right. If you have team of hundreds and you increase efficiency 20%, that's like adding 20 more people to your to your team, right? So those, those those let's say benefits really start increasing as a firm grows until you reach that point. Your problem are human problems not not technological problems.

Martin Kravchenko 00:08:51 Yeah. that's a good. That's a really good point. When it comes to we before the show, we were we had a little meeting and we were talking about prompting. And when you talk a little bit about prompting and how just prompting effectively can change the output substantially.

Multiple Speakers 00:09:09 Well, first of all, I think utilizing the I, I mean, considering what I said before, right? Utilizing AI is actually a very quick win that that firms can can adopt in terms of technology to actually quite significantly increase, increase their, their efficiency. Because let's say if you learn how to use tools like ChatGPT Gemini Cloud properly, you don't necessarily need to integrate all already all of them into your process and like build complex agents or complex workflows that do API calls, whatever. Right. You can just use the tool effectively. And even if you just do that in select tasks, you can increase your efficiency by 3,040%, but most importantly actually increase the quality of the output, right? Make sure you don't miss any details that could be overlooked. for example, by human. Let's say a personal injury case. Right? make sure that your your argument is as solid as possible. So, so by, by making sure that you actually communicate me well with those models. And ultimately it's it's not that hard.

Multiple Speakers 00:10:04 Like, once you get the hang of it, you will get a feeling for like what information the model needs versus what information is extra and not really beneficial. Right. And it's really striking that line. It's like, how do I manage the context that I'm given this, this AI model. Right. So it can do it. It's task effectively. But I'm also not overburdening it with too much information. For example, if I need to maybe draft a client email, I wouldn't want to put all of my medical records about that case right into the prompt, and then I'll ask it about it. Right? Versus obviously if I'm trying to, let's say, prepare a medical chronology, obviously I would need to provide all those medical records. Otherwise it wouldn't be able to do the job. So it's just really making sure that you provide enough information to the model to wait to complete the task, but not don't overdo it. I mean, ultimately, that's a fine line.

Martin Kravchenko 00:10:54 Yeah. Okay, so I'm gonna let's break down that example for a second.

Martin Kravchenko 00:10:58 So let's say you, you want a medical chronology created out of broke from your client's records. What is the best way of approaching that then? Because you said, you know, you don't want to dump them all into a into a prompt type of thing. So how how would you break it down.

Multiple Speakers 00:11:12 If it I mean, if it's a very simple case, let's say it's, I don't know, 100 pages of medical records. You can potentially only do it in one single prompt. And you have quite, quite, really high confidence that the model will do a good job. Right. If you're working with a more complex case, let's say, 3000 pages of medical records, then you need to understand the limitations of the models that you're working with, right? What we've seen, for example, with Gemini, is that after, I would say like 300, 400 pages, per per prompts, right? Per chat. It's it's it's hallucination rate starts increasing, right? Not only in terms of, let's say, making up information, which is actually somewhat less of an issue.

Multiple Speakers 00:11:53 It's more so errors of omission, which a lot of times people don't think about. It's, you know, I have supplied this, let's say 1000 page medical records. So Gemini, how do I actually make sure that he has included all the treatments? Right. And that is the biggest that's the biggest issues with big records, because ultimately the model is trying to do its best to summarize. Right. But it has a limited as well output window. So it kind of summarize necessarily everything if it's a very long record. So what I would do there is I would just simply break it, break or break this the the record up. Right. If it's multiple files it's obviously easier. If it's one single file, you could just really break it, for example by dates and then process those records individually in separate chats. Right. Making sure that you don't pollute the same chat with multiple records. So in separate chats get those individual summaries and almost you have like a display of a funnel. Right.

Multiple Speakers 00:12:47 You start with a lot of those like medical records, very big amount of information. You then condense it to summaries of individual records. Right. And then in a separate prompt you would then for example, drop the demand or drop the chronology from that where you just operate and let's say maybe with 20 pages of data, but it's already summarized data. So the model again can do a good job. Right. And that's where you distill it down to an actual piece of work that can be confident about and verifiable.

Martin Kravchenko 00:13:13 That is that's interesting. I don't think that's how we're doing it. I'm that is interesting. One of the ways that I've seen some of our case managers do some medical summaries was through notebook LM, and I wonder if you've got any thoughts on on that.

Multiple Speakers 00:13:28 Notebook Alam is is a great tool. But again you need to understand the limitations of that notebook. Alam has a higher hallucination rate than, for example, what you would get in Gemini app if you are using the 2.5 Pro model, right? So the 2.5 Pro is, let's say the more advanced model.

Multiple Speakers 00:13:43 It's things for longer, but it gives you better results. 2.5. Flash is the one that's more quicker, but but gives you potentially more hallucinations, less accurate. And so actually notebook A lamb on the on the background is run in 2.5 flash right. That means you're not necessarily getting the best intelligence per se. And it's great for discovery. Right. So if let's say you have let's say all of your medical records, police reports, etc. on the case, you can put all of them them in notebook alarm. Right. Maybe you could potentially share it with your team. Right. Have it operate in the hub for that particular case and ask it specific questions. Right. For essentially let's say supercharged control app. Right. That is an amazing use case of that when you try, for example, to generate the timeline, you know, in the sidebar it has like the reports, right? You try to generate the timeline of of that case with that. A lot of times based on my testing, it would emit stuff or it would hallucinate stuff.

Multiple Speakers 00:14:38 Right. And in that summary as well, it's not necessarily verifiable. You can just click on a particular fact and you'll see where exactly it got the information from. So for comprehensive chronologies that you can trust. I wouldn't use an old book. I would I would follow the process there. Just explain just because well, at this point in those individual summaries, what you can do is you can click on any response or any portion of the text, and it will provide a citation to the actual piece of text in the document where it sources that. And what I would do is almost divert, let's say, from the concept of, let's say single case manager per file. That's a bit more advanced by a single case manager per file. And as the records a comment in have a specialized person almost working in a conveyor belt style, which would be processed in those medical records, making sure that the medical summaries are correct. And when it comes time to drafting those medical summaries already would be in your case management system.

Multiple Speakers 00:15:34 And the legal design then could just take those notes that the information there is good and don't have to verify with the original records.

Martin Kravchenko 00:15:41 It's interesting you say that because that's that's exactly how we're setting up our medical summary agent that we're building out like we just started yesterday. But the mission team before that, we're having to do it one at one record at a time. So as the record comes in, it doesn't it. And so it starts to kind of build this overall template that that we've built out. So that's that's really interesting. Something that I really like notebook LM for is to like prepare for mediations or depots. What I'll do is I'll put information in it and I'll use the podcast function where it'll just it just has kind of like a refresher. And the question I have, though is, do you think that there's going to be a time where the podcast that people listen to are just going to be AI podcasts that are created from things like that?

Multiple Speakers 00:16:29 Well, if you go on the YouTube, there are channels with 100 K subscribers that are fully generated.

Multiple Speakers 00:16:36 You may not certainly know it, right? But but I guess if you've worked with AI voice models, you will be able to understand that that it is AI. So so I mean, there's this whole theory of like that, that internet theory, which pretty much says that let's say 90% of the internet is all bots, right? And just represent a small minority of it. I cannot say if it's if that's true or not, but but I think definitely not for sure. For sure, 100%, 100% right now. Like the concept of like you see it, you believe it is no longer relevant. I can create a deepfake video of of anybody doing anything at this point.

Martin Kravchenko 00:17:08 In time.

Multiple Speakers 00:17:09 With sound, with video or whatever.

Martin Kravchenko 00:17:12 So I think it's pretty obvious at this point for people listening and or watching that you like Gemini. Gemini is your preferred model. What's the reason you prefer something like Gemini over something like Claude or, or ChatGPT?

Multiple Speakers 00:17:26 So if you, if you, if your thinks here, first of all, let's start I guess with the most basic also not necessarily always relevant for plaintiff personal injury lawyers, we only really work with personal injury.

Multiple Speakers 00:17:38 Gemini is fully hyper compliant, right? In Google Workspace if you get it through Google Workspace, you could just accept a BA in three simple steps. And now the platform is fully capable of like GPT. No cloud offers that unless you're like super enterprise. Then the second, if you already use in Google Workspace, it is included. And so again, the whole, let's say part of change management of making sure your people actually use it becomes easier because you don't have to provision your accounts. They just literally go to their Gmail, click on the like nine dots, click Gemini Dada. You know, they're there. And then lastly, in terms of quality, I guess somewhat more subjective, but I do find that this it it hurts, needs less and it can process records better. So its document processing capabilities, especially for things like medical records, is superior compared to ChatGPT in cloud. It just seems to understand, let's say, especially if it's like a badly scanned PDF or or similar and just understand it's better compared to those models.

Multiple Speakers 00:18:38 But but really it's, it's you know, all of them are quite similar, but those are the advantages. I feel like Gemini is a bit on top. What we also need to understand is that, you know, cloud recently released new model ChatGPT recently well released a new model which is our outer, but okay, that's a separate story. Gemini 2.5 the base model also there has been revisions, has been released in March of this year and so it's already six months old. And so Gemini three is coming. I'm very bullish on that. And I hope that it will it will be better than the competition at all.

Martin Kravchenko 00:19:14 well, we're we're going to find out very quickly. I want to I'm going to change gears a little bit. I want to ask you about something. I'm going to show you this suggestion.

Multiple Speakers 00:19:22 Maybe just before as well. We consider like I have great actually report. I can also share screen share if you want.

Martin Kravchenko 00:19:27 Oh absolutely. Yeah.

Multiple Speakers 00:19:28 Yeah.

Martin Kravchenko 00:19:28 Let's do that. Yeah.

Martin Kravchenko 00:19:29 That's absolutely.

Multiple Speakers 00:19:30 So sorry.

Martin Kravchenko 00:19:30 Sorry to got it. No you're good. But I want to ask you about this article I talked about this on our live show yesterday. But I want to I want to talk to you about it. And this is the anti which the title is stupid to ignore that Thomson Reuters Multi-agent system slashes 20 hour tasks of ten minutes, and they talk about this new thing, where it's going to do research and all that kind of stuff. And this is, you know, rag was the start but doesn't go deep enough. And the reason I want to ask you about it, when we were chatting beforehand, either you or Max, your partner, your co-founder, he had one of you had mentioned the fact that, you know, people, they got this kind of like FOMO. So they'll go and they'll go, you know, pay for a product kind of like that. You all didn't specifically mention that, but I would I what I thought was kind of interesting is, is that it appeared to be like they just built out an agent, an AI agent, or a workflow that goes and does legal research.

Martin Kravchenko 00:20:25 This is basically what it does. And what I wanted to ask you about was a couple things was the the what are your thoughts on people that go and are about them going and not not them, Not necessarily the people themselves, but just the idea of going out and paying for something like this that I think can just be built out by by someone like you that can build out like workflows. So I just want, because it seemed like this is probably like an overpriced workflow, that you could probably just build yourself for a fraction of the cost.

Multiple Speakers 00:20:56 I would go with even step further and say, you don't build it, you actually just use the app and use it well, right? And the reason for that is, is I looked over the last like three months I've been on AI research spree. I have been looking at all the legal AI vendors, specifically in personal injury space, have also built workflows myself with Macomb connecting directly, let's say, to the APIs of these platforms. And what I realized is that also the output in some of them was sometimes marginally, marginally better, sometimes actually worse than the years in the app.

Multiple Speakers 00:21:31 It didn't justify the cost, right? It didn't justify paying $300 for a case unless it's like a very high stakes litigation case. I understand right. But let's say like 80% of routine personal injury cases, it didn't justify the cost of paying $300 per case with an annual subscription where you can do the same thing, maybe spend five ten minutes more, but then you're just paying $20 per month per user for your, you know, Google Workspace subscription already. Right. what ultimately happens is that with a lot of these tools, human verification is still needed. Whatever legal AI vendor tells that their, you know, product is close to nation free is that's complete BS, right? It's based on AI. So ultimately, just like AI itself, generative AI, its architecture is ultimately somewhat creative, right? It's replicated patterns and it's not deterministic, meaning that you cannot get 100% accuracy. And so would you rather, let's say, pay $20 per user tool and, and do manual review or pay $300 per case and still do manual review? the What I would also say is an issue, I would say with some of these tools that are like some very specific or let's say, integrated directly into the workflow that still need manual verification is that instead of giving your team and investing in your team and giving them a better skill that they can use not only for that particular narrow task, let's say for medical record summarization, but they can go and ask it to explain a concept to a client.

Multiple Speakers 00:23:03 They can go and ask it to, I don't know, create an image for a marketing campaign. They can go and learn a new concept by themselves, right? With that tool, instead of investing in in your team. Right? And given the meta skill which will serve for their career, you are paying this provider and providing maybe like, you know, three, 4 or 5 seats to the lucky ones in your organization who get to work with it. So I would say there is use in those tools, but again, enterprise level. Right. Or if you let's say you said, okay, I run a 20% firm, I don't want to grow anymore. I just want to make it more efficient. Okay, maybe make sense as well. Right. But if you're trying to grow. Keep it simple. Make sure you actually adopt technologies that drive real value, tangible value as soon as possible and require minimal maintenance. Right. Because what we also need to understand is even if you hire an engineer to build a more complex system like this, it also needs maintenance.

Multiple Speakers 00:23:58 Right. So I think practicality is probably the, the, the most desirable skills I want to have. Let's say law firm orders to have when it comes to to all of this.

Martin Kravchenko 00:24:07 So you built you and Max have built out swans. So for those of anyone interested swans co and we offer sustainable and scalable solutions. And so there's you know you build out these systems and everything for people. But we offer sustainable and scalable solutions. We're marketing consultants fall short. That's that's from the website and everything. But you definitely do more than that by 2030. Our goal is to empower 10,000 law firms across North America to double the revenue. That is. That's amazing. I think that's a wonderful vision and everything. I do wonder what what got you into doing this specifically with law firms. That's because, I mean, usually there's some sort of something that triggers someone going into a specific injury industry. So I wonder what what what about law firms and specifically P.I. firms?

Multiple Speakers 00:24:57 My. Well, originally I would say my response would be somewhat anti-climatic.

Multiple Speakers 00:25:01 It was a bit by an accident I wanted to do back like six years ago. I wanted to do automation. Right, I wanted to I really got excited by tools like Macomb and Zapier, where I could build workflows with little to no coding and provide actual business value without waiting for, let's say, a month of a Python engineer, you know, building that on your back end. And I got very excited by that. I wanted to specialize in a particular industry, and I felt like legal is quite an antiquated industry in service with processes. And there was a lot of potential in there. And so that's why I started automation for lawyers. Originally for my solo consultant agency, I worked with multiple clients throughout the time. I actually then joined a law firm in the UK Settlement Agreement Solicitors. Then they actually became a partner there later. And and for them essentially built out their full CRM and case management system, bringing the company from five people to now more than 40, and the company having more than 6005 star reviews and tries.

Multiple Speakers 00:25:58 Pilot. It was a very specific, let's say niche of of of employment law in the UK. But what I think that showed me is that there is and a huge opportunity for more entrepreneurial spirit within within legal right. The the law firm owner and I that founded the firm was actually an entrepreneur, right? The entrepreneur had previously ran actually a few consumer brands they partnered with legal director, opened up the firm because they saw that it's just an opportunity again in the market where not not not good enough customer service was delivered in that particular niche. And so And so he decided to to form the company and reimagine the process. Like, okay, forget about how law firms are doing this. I want to actually understand, like what drives customer value, what's actually valuable, and let's design the process around that. So we design the full system, the company group now later then partnered up with Max to to to reform out of which followers into Swans. And the reason that we we chose to to go for personal injury is I feel like that's the most as well somewhat entrepreneurial parts within the legal ecosystem.

Multiple Speakers 00:27:03 It's one that's a bit more competitive and one that's a bit more open to trying out new things. Right? And so we feel like that's just the natural first step into making an impact in this industry, and almost making sure that we help a few firms a lot, right, to actually drive impact and doing that almost like brute force this industry into into providing better customer service, being more customer centric and as well being more entrepreneurial. By using technology and AI and everything to do.

Martin Kravchenko 00:27:36 I think historically, I think you're absolutely right about the pie space. It has been more entrepreneurial. I do think that that's changed substantially over the last decade or so, where it's shifted quite a bit. I still think it's pie is probably still predominantly the most entrepreneurial of of the entire legal space. But it is it definitely has changed quite a bit, which I think is good. I think it's good for the legal space in general, but I think you're really interesting because you're different from a lot of automation people and AI people.

Martin Kravchenko 00:28:09 It's funny because they are different, but you're now sort of both. You have to sort of be both. You can't just be automation or AI, you have to be both. But what makes you different, though, is that you have been inside the inner workings of a law firm and helped build the systems and processes, which makes you substantially different, I will say, because it you have to understand how the legal space works, you really do have to have an understand the inner workings. And with that, what are some of those basic, maybe agent AI agent workflows or workflows in general, or automations in general that you think that law firms should have, like every law firm should have them?

Multiple Speakers 00:28:50 Every law firm is a tough question. Just because I feel like, again, at different stages of your growth, you will need different.

Martin Kravchenko 00:28:56 I knew, I knew the moment I said every law firm, you were going to be able to pull it back, but but okay.

Multiple Speakers 00:29:01 It's it's like it's like if you are a solo team, like what do you need? You don't need Clio.

Multiple Speakers 00:29:07 Like, you need to hire your next paralegal. Your first paralegal. All right. You need that. And you could work on an Excel. That's fine. All right. what are your three? Okay, get a case management system. Right. So so I can I can talk about, like, let's say a few major things we are working on, if that's helpful.

Martin Kravchenko 00:29:26 Yeah, I think so. Let's let's hear that okay.

Multiple Speakers 00:29:28 So I mean obviously one that we've been talking about now. Especially relevant now. So I would say this AI adoption, making sure that your team, not building some crazy guy workflows, which there is a place for that again, once you've covered the basics, but actually making sure that each one of your team members adopts this technology, is comfortable with it, and and use this on a daily basis. Right. That is really where the power comes. And that's why I feel like where a lot of this legal AI vendors ultimately fall short is because they provide this great tool.

Multiple Speakers 00:29:57 They do a few onboarding sessions and then that's it. Right. What we found is even if we do group sessions, we still need to jump one on one or at least department level with our clients and actually walk people through. Make them feel comfortable with the technology. Try out a few things with them to get the ball rolling and then to check in on a periodic basis. So AI adoption would be one thing. Another big one for growing firms is actually analytics, right? I think a lot of case management and CRM systems in the legal space don't do an amazing job at providing great analytics. Things like for example, in your case management systems. On average, how fast our case is progressing from stage to stage, right? If you're growing your firm, I would love to know the information to understand where the bottlenecks and other bottlenecks due to, let's say, the client provide information to the defense. Being too slow, or is it actually an internal holdup that I can solve for? Right.

Multiple Speakers 00:30:50 That's critical information. I need to be able to make the decision. Things like, for example, especially if you're working in Pi. One thing that struck me is that a lot of firms, even somewhat substantial, substantially large firms, don't have proper financial forecasting and analytics. Right. So understanding when it's cash flow coming in, making sure that data is synced to your case management system where you have, let's say, projected settlement values, right. Understanding how much is coming in every month to in the future to be able to make it harder decision, for example. Right. Not only that, but also actually understanding how much value is your team generating every month. Because obviously in Pi, like you start working on the case, you invest essentially for nine months into your team doing the work, but then you only see the result if you look at your books and you're growing fast like you want to like, you will think that you are you. You are unprofitable. But it's not really the case, right? Because you are now building value for those future cases.

Multiple Speakers 00:31:43 And so having some kind of infrastructure to be able to again, take the information from the case management system process and aggregate right and display the nice analytics dashboard is very important. And obviously all the stuff on the CRM side of things like intake speed to leads, obviously a lot of big things there. And then we would say, let's say optimizing your CRM and case management capabilities, right? A lot of firms are already using great tools, but they're not fully maximizing. Right. Maybe you're not using conditional logic within your document templates. And you have 200 templates sitting in your case management system where you could only just have 30, which obviously complicates maintenance and errors whatever. Or maybe, for example, your case management system actually has the ability to apply task lists automatically when the case goes from one stage to another. Again, that's very useful. You can run analytics on those types, does completions later. You can make sure your SOP you don't need that many SOPs because pretty much everything is in your case management system CRM side of things.

Multiple Speakers 00:32:37 Again, automation on that front, making sure that they get data is properly organized and displayed within that. And then we would go into, let's say, more advanced stuff, such as creating custom automations with Zapier, those modified platform reagents, etc., etc. but as you can see, there are a lot of basic steps that you know you there is more benefit to get in them, right? Rather than immediately say, jump in into the most advanced flashy workflow. Because if you don't have good data, if you don't have good processes, like that will not work.

Martin Kravchenko 00:33:05 So I had a I was quickly trying to pull up the data from one of our dashboards because you mentioned the Logjams. And there was I, we actually, went through this yesterday during our quarterly meeting, and I, I was very, very surprised. We I don't know what the type of chart is called, but it's, it's the, it's those charts where it kind of flows. You take the name of our charts are it's source versus phase.

Martin Kravchenko 00:33:32 And so where are all of our clients coming from, and then what phase of the case is it in. And one of our phases we have case on hold. And it could be for a variety of reasons. And it could be you know the clients I get on got this information. Can't get Ahold of client. There's things like that where we okay. Case is all hold until, you know, we figure out whatever's going on. And the biggest source for case on hold is client referrals. So current clients or clients that have referred US cases, that is the biggest source for case on the whole. And it's interesting without this chart, I guess we could do with the chart in another way. But it is that one was kind of you've got like the it kind of connects each other and it's like kind of waving itself. I don't know the name of that.

Multiple Speakers 00:34:14 What a waterfall.

Martin Kravchenko 00:34:15 Is that what it's called is a waterfall chart.

Multiple Speakers 00:34:18 So it's, it's sourced against, let's say in your case management system.

Martin Kravchenko 00:34:21 Yeah, exactly.

Multiple Speakers 00:34:22 Source again. Stage.

Martin Kravchenko 00:34:23 Yep.

Multiple Speakers 00:34:23 Yep. Probably. Probably just the matrix chart, I guess.

Martin Kravchenko 00:34:26 Yeah, it's kind of interesting. But the so it's interesting though is like, wow. So it really has me thinking maybe we need to reassess where like whether or not we want to devote as much time to try and get client current client referrals. I don't think I don't think that necessarily we're going to stop trying to do that, but or we're going to whenever a client refers a case, maybe we just look at it a little bit harder as to whether or not we want to take that case. But it's interesting when it comes to that data, though. So I'm glad you mentioned that because it triggered that that member from yesterday. Because that data is so important.

Multiple Speakers 00:35:01 Look, if you're running a law firm, a law firm is a business. You need to think like a business owner, right? It's a law firm owner. You're not an attorney. You're a business owner.

Multiple Speakers 00:35:09 Right. And so and so you need good data to make good business decisions, right? Finance sites, things like this. You know, I'll probably go in further. I would say, okay, let's analyze, for example, average settlement values for the different sources. And maybe like those client referrals are the lowest one on the list. You're like, okay, you know, maybe we should have taken referrals, right? If you don't have the data, you kind of make the decision and then you just fly in and rock pretty much in your business, you know?

Martin Kravchenko 00:35:32 Yeah, people definitely need to know that one. That's one that you definitely need to know. Where are your highest value cases? That's. Yeah. No no doubt. for sure. is there going to be a point where when we talk about AI that AI and agents are just it's just synonymous. It's just like when you're AI is just AI agents, like, is there going to be a point where that that happens?

Multiple Speakers 00:35:56 Maybe.

Multiple Speakers 00:35:56 I would say I would think that there is I think an agent, right, is like we need we need to understand what is an agent. Right. And an agent I would say is, is, let's say, the capability of a system to make decisions by itself without without supervision. Right. And so even if you look at, for example, two point, let's say Gemini 2.5 Pro ChatGPT five external thinking, it is a somewhat a generic system already, right? It is when you ask it a question, it reasons about it, right? It makes certain conclusions, you know, goes one path versus the other. Right. It has, let's say, chain of thought, which can actually see in the, in the software as well. Right. So, so it is already somewhat in a genetic system. Right. Extrapolating that further would be okay. You just say okay, send an email to this client about X, and then it goes to your case system and pulls up the email, draft the email and actually send it out.

Multiple Speakers 00:36:46 You give some more tools to to.

Multiple Speakers 00:36:48 To to to to the system.

Multiple Speakers 00:36:51 so so I think those are very related. I think it will ultimately depend on, I guess, just the social perception of the media. But but I think it also will be quite synonymous in the, in the end, especially the, the abilities of the systems become higher and their capabilities become more extensive, primarily through ways of integration. I mean, actually be able to do, let's say, actual work, right? Send an email, look up certain information, not just look up a website. Right. Make a certain action within your CRM case management system that will become more synonymous.

Martin Kravchenko 00:37:25 What misconceptions do you think lawyers have about agents in general?

Multiple Speakers 00:37:29 I think most people don't know what the agents are. Right. okay. Let's let's start with the fact that it's like most, most people don't truly understand the full capabilities of just like, ChatGPT and Gemini and Claude. All right. So, so I think, again, like, it's almost let's cover the bases first.

Multiple Speakers 00:37:52 Right. Make sure that we are comfortable using the tools. We know the capabilities of those tools. In some of our trainings, we even have, let's see some younger people on the team of our clients that have used ChatGPT for their, like, school schoolwork, for example, you know, university or whatever. and then we hear back from them, it's like, oh, I actually didn't know that this tool could do X, right. Like, they're just like, okay, I could use deep research or like, oh, I could create this. And like this prompt would generate this result. And so and so I think like really there's a lot of legwork that we need to cover in there Once we go into that, we can speak about agents. I guess in the future. Right. But but it's somewhat more experimental. Unless, again, your team is fully adopting AI already. You have your systems on point, you have your data point, you have an analytics on point. I feel like agents are a distraction.

Martin Kravchenko 00:38:38 Yeah. For but I'm going to stay on agents though for a second though, because I do think that it is it can be a distraction for the the people that are just kind of they don't have some sort of integrated system with it and all that. But early on, when agents were starting to develop and become a thing, it was a lot of what I was seeing was you're kind of building teams of agents where like they supervise each other and everything like that. And I wonder if that's if that's something you would agree to, to a ways of setting it up, or do you think that that is a flawed way of thinking now?

Multiple Speakers 00:39:15 Well, that I would probably even call more so like agents swarm Agent one. All right. Swami. Okay, I think that's that's the term that is being used. If you look at, like, anytime YouTube videos, agents swarming in like, it's it's it's essentially an, a group or team of agents working together. Right. I would say, how would I define, let's say, an agent in a more, I guess simple sense is just like a system that can make decisions and then can use tools.

Multiple Speakers 00:39:44 Right to, to.

Multiple Speakers 00:39:44 Execute its goal. And so for that, I wouldn't necessarily say that the team of agents is necessary or a team of those systems is necessary. it could be one of them.

Martin Kravchenko 00:39:53 Yeah. Because as we built out more of our agents and everything, it's it doesn't it does seem like it's more linear than having this, like, stacked pyramid of, of a team of agents, because the way early on, it was, okay, so you got this, this team leader, and then there's teams underneath it and teams underneath it. And I'm not saying that it's wrong or right, but I can tell you the way we've built ours out, it's more of a linear thing based on other triggers, not necessarily based on supervisors and team leaders and the worker bees and all that. It's it's the setup is way different.

Multiple Speakers 00:40:31 It's a workflow. It's a workflow, right? It's a AI augmented workflow. It's not necessarily, let's say an agent, an AI assistant. You can ask anything.

Multiple Speakers 00:40:39 It is designed to execute a specific mission, and it is operating within the boundaries of that, which I think is the right way to approach as well. Ultimately, automation at this point in time, because again, you know, you can, for example, interact with ChatGPT agent, right? It has the build function there now, but the results you're going to get will be very variable, because there's still a lot of because AI hallucinates because AI is still deterministic, there's still a lot of opportunities for error. And so I don't think it's just like it's it's there yet to consistently be delivering value in those very highly genetic systems compared to more narrowly scoped automations that use AI. Right? AI augmented workflows.

Martin Kravchenko 00:41:16 I'm very hesitant to ask you this question, because I don't want you to say something other than what I'm using. But when it comes to build out agent workflows, what is your your preferred system to use?

Multiple Speakers 00:41:29 There are a few. There are a few on the market. I would say any of ten is, is quite popular.

Martin Kravchenko 00:41:33 Thank you for saying that, because I was afraid you were going to say something else, and I I'm, I love it, and I think it's great, but I, I know there is others out there, but I think it is to me it's, it's the most intuitive, but it also has the, to me the most features.

Multiple Speakers 00:41:50 Yeah. It's somewhat, I'll say, more technically focused. And again, that's why we really only like deployed for like more advanced customers per se. Right. Or like where we're progressing more. One thing there that I kind of dislike is just the fact it doesn't have a proper, like, cloud hosting option. Like if you use a cloud version by night and it's hosted German servers in Europe, if you use a self-hosted version, obviously you can use it whenever, but there's more technicalities than setting it up and maintaining that than than Then just sign up for Zapier. Make the company.

Martin Kravchenko 00:42:19 Interesting. I mean, I, I didn't even notice one of those things over here.

Martin Kravchenko 00:42:23 I just didn't notice at all. That's that's really interesting.

Multiple Speakers 00:42:27 Well, check check, check out that.

Martin Kravchenko 00:42:28 No. Now I want to go and look and see for sure. is there anything that you are. Because it seems like technology is is it's changing so rapidly, rapidly. And it seems like there's something new that comes out every single week, and you kind of the shiny object syndrome. But is there anything that you've seen out that you are super, super excited about and you're like, oh my gosh, like this tool is just amazing.

Multiple Speakers 00:42:54 I get those moments through marketing copy and then I try it out and then I have the solution. But. You know, it's it's it's especially if we talk about like specific, you know, vendors coming into the market and promising the world what I think ultimately is the last, you know, doing this for the last year has taught me is that simple systems, boring systems are the ones that actually deliver value. All right. And and and as a tech minded person, I'm very drawn to finding the latest and greatest.

Multiple Speakers 00:43:29 But then when you actually put into practice, when you think about security considerations, you know, I know HIPAA compliance, where's your data store, etc., it you're like, oh, okay. Like this tool is not ready, right? If I need to recommend a tool to, you know, 100% organization, I cannot necessarily come up with like a startup that has three employees on LinkedIn and tell them, oh yeah, I use this, right. It's like I would be failing my duty as a consultant, right, to tell them that, like this, this, this tool is quite new on the market. It may fail. Your data may not be fully secure with them. Right. So that's why I think the, the scope of solutions that you use for enterprise or for bigger firms, just like really narrows.

Martin Kravchenko 00:44:10 Yeah. I'm so glad you showed that. I think that's really smart. Boring is I mean, boring is better. It's one of the things I just think boring is better.

Martin Kravchenko 00:44:16 A lot of times consistency is boring, but that consistency is way better than anything else. Would it comes to adoption? because let's say you're going you're starting with a clean slate that you've got you've got kind of nothing. And so people have like the right mindset about this. If you were to and I guess you're never really going to be fully integrated with everything, because you're always going to probably be adding on and building things to, to improving and changing things. But to get a fully workable system with all your workflows, and I'm not even talking about with AI, I'm just talking about just generally from a tech standpoint, what is generally for like a, let's say, a midsize firm, let's say you got, you know, ten people. What like what is the the whole timeline when it comes to, from the point you start to the point you end. Is it is it a year or is it a month? How long is generally does it take?

Multiple Speakers 00:45:09 I think again, it's somewhat a hard question to ask because like there isn't had been like a clean slate for a 15 person firm.

Multiple Speakers 00:45:16 Like they're already using something. Yeah, right. So so I and ultimately, like, even when I worked in house right in my, in my firm worked there for about three years. And even after those three years of full time work, there still was stuff to automate. And I still stuff those features to develop, right? So I feel like almost like it's somewhat infinite, right? Especially if you expand potentially into different case types. As more people join, like your problems start becoming different. I don't know if you go past 50 people. Okay, maybe I need an HR system, right? Maybe I need a more, I don't know, expensive, powerful payroll solution, right? It's like the types of problems change. What I would say is you really need to just, like, start simple and take baby steps. This is the most important thing if you're going from a clean slate. Unless unless you're working with somebody who has like already built a thousand times to just advise you on that.

Multiple Speakers 00:46:07 If you are a 10% firm, you're starting to actually like Use the most approved tools on the market. For example, the systems we like to recommend based on everything that we see generally would be, let's say, Clio manager for case management and law matters for the CRM side of things, just because those are easy enough to be able to configure it and and and maintained by the firm staff themselves at the same time, it's providing the necessary functionality for some more advanced automation, right? Like email or SMS, task list and clear manage, etc. and so take baby steps. Don't try to do too many things at once. Start with your, you know, biggest issues like, hey, you know, document management is the biggest issue. Okay, let's solve that. Right? Okay. Now I see that, for example, my people are doing like not necessarily following the process. Okay. Let's implement task lists and go step by step. But I don't think there's like a very simple answer to this to build a functioning system.

Multiple Speakers 00:47:02 If you dedicate, I don't know, maybe like ten hours per, per week to it, I think you can have something like an MVP already within, within the first months. You know, you'll just need to add on top of it and potentially then utilize more and more features of the software that you already have, and always check the features of the software you already paid for before trying to, I don't know, like go into make Zapier and then because you may you may be surprised. You may be surprised.

Martin Kravchenko 00:47:26 Amen to that, that's for sure. I think that's a great answer, I think. I think you answered that perfectly. the last few questions I have for you, it's more of a prediction. Questions. So yeah, yesterday we were having a little bit of a discussion about Neuralink and all that. And, you know, whether or not you can put a get a chip, put your head where you're having a kind of fun conversation in the firm. And what I said was, here's the here's the problem, right.

Martin Kravchenko 00:47:48 You've got you're going to have some attorneys that when it's available, they will get the neural, they'll get Neuralink, and they will have access to just gobs and gobs of data and information, that let's say you're arguing in court. I think this is a real scenario. What I want, what the prediction. I'm gonna ask for you if you think that this is actually a real world scenario Where you've got one. It turns out Neuralink and they can. They're gonna be able to argue all this information that's in their head, because they've got the chip against someone that doesn't have it. It was going to have a substantial disadvantage. And do you see? Do you see a situation like that coming in the future where you're going to have attorneys with Neuralink versus attorneys with that? Neuralink are arguing each other against each other in court.

Multiple Speakers 00:48:30 I think that would be the, I guess, a natural progression of how things are going, right. If you look at the past few years, it's almost right now it's like, okay, lawyers using AI versus lawyers not using AI and banning its use in their practice, which I think is insane.

Multiple Speakers 00:48:46 you know, it will be similar, I guess, divide just in that particular scenario, I would say with, you know, using it in court. Question is, how fast would they be able to process, let's say, the data that is coming through Neuralink. You know, it's like and actually make better decisions. If if you actually prepared your case well, it's like, how much more can you boost your performance by having a And you're like, I don't know. I don't know. But but it's it is it is a scary and exciting times. I feel like it will be coming with this. I don't think I'm putting that thing in my head, but I still want to. It's not like they have like, puts it, puts it essentially, you know, kill switches and cars and whatnot. Right. It's I don't want to put a kill switch in my head. Thank you very much.

Martin Kravchenko 00:49:35 I mean, it was a scary thought. It really it was a scary thought.

Martin Kravchenko 00:49:38 And so I'm. I'm. I'm with you on that, though. A couple more questions. What skills do you think next generation lawyers should prioritize over the next few years?

Multiple Speakers 00:49:50 Empathy and customer centricity. More so than just like say. Yeah I mean yeah of course. Right. But with introduction of AI, I feel like being that guide for the person, for your client in distress will be the differentiating factor. Add in more customer centricity to this profession will be the differentiating factor. Ultimately, just as I have seen again and in the firm in the UK, which dominated the industry because it focused on the customer. I feel like that that is common for other areas and regions of law as well.

Martin Kravchenko 00:50:25 Last question. So if we zoom out 20 years from now, do you think that law is going to be similar to like aviation, where you've got pilots that are monitoring the autopilot system and all the systems going on in the gauges where you've got agents, where the firm, you know, paralegals might be monitoring different agents doing different things, attorneys monitoring different agents doing things.

Martin Kravchenko 00:50:49 Do you think it's going to be do you think it's going to shift more towards that? Is that is that what the legal profession is going to look like in 20 years? And again, this prediction we don't know. We don't know how much things are going to change. But I, I'm curious what you think.

Multiple Speakers 00:51:01 Okay. So on the strategic level, unless the judicial system changes right. Until and so long as we have human judges, having human lawyers and being able to transmit emotions and and stories will stay relevant. Right? So I don't think that strategic part unless, you know, we just the whole judicial system gets replaced by superintelligent AI, which you don't think is happening. I think that it will stay stay the case for more. I'll say mundane work, man. You know, analyze and medical records. You know, draft and draft and responses, etc.. That part, I feel like will get closer to what you are saying, just as we are seeing now in coding, right? I look at people using cloud code for it's like an AI coding solution pretty much.

Multiple Speakers 00:51:48 And copilot pretty much for, for coders. And, and they have their computer with like three different charts. Like one is writing a new feature, another is running a unit test. And the third one is, you know, debugging an issue. Right. And they just switch in between them quite quickly. Right. And it's well, well, well wait in the the work on the other one. So so I feel like that is a possibility. but but I don't think that will be for the more actual strategic work or again, the primary function of the law which will be like that guide.

Martin Kravchenko 00:52:22 All right. In 20 years you're going to play this back and see if you were right. Very good. Martin, thank you so much. If anyone is interested, go to Swanscombe if they want to reach out to you personally. Is there is there a some sort of social media team?

Multiple Speakers 00:52:34 Hello. Hello at Swanscombe or you can reach out to me on LinkedIn Martin Kravchenko. Yep.

Martin Kravchenko 00:52:40 Love it.

Martin Kravchenko 00:52:40 Thank you Martin, for doing this. I look forward to working with you at the workshop in Nashville, at the conference at Maxwell. And if you want tickets, go to Maxwell. Martin. Thank you so much for doing this. Really appreciate it, I enjoyed it.

Multiple Speakers 00:52:52 Thank you so much, Tyson.