On today’s Legally Speaking Podcast, I’m delighted to be joined by Daniel Di Maria. Daniel is the Co-Founder and CRO at Spellbook. As a lawyer, he helped build the legal AI tool now used by 4,000 corporate lawyers and law firms. Daniel, having worked in the legal industry firsthand, is passionate about driving the goal of making lawyers’ working lives easier and more enjoyable through technology.

So why should you be listening in? 

You can hear Rob and Daniel discussing:

– Focusing on a Core Problem to Drive Success.

– How AI Must Be Grounded and Verifiable.

– LLMs Transforming Legal Workflows.

– Why AI Augments Lawyers Without Replacing Them.

– Data-Driven Insights Being the Next Frontier.

Connect with Daniel Di Maria here –https://www.linkedin.com/in/daniel-di-maria-340b80ab

Transcript

There is so much innovation that you can do in legal AI. Staying true to your DNA and just focusing on making sure you’re an absolute leader at that one thing that’s really important to your customers has definitely been a necessary component of our success. 

I think AI Slop Tolerance is at an all-time low right now, especially among lawyers. So grounding the reasons in citations, you might want to know why a certain entry was entered and where it came from, for example. So you will get those citations and on the legal research side, Spellbook will tell you specifically where this came from. It’s not going to be just, this is a law, right? It’s going to be, this came from the statute and here’s a link where you can find it and verify it. 

On today’s Legally Speaking podcast, I’m delighted to be joined by Daniel DiMaria. Daniel is a co-founder and CRO at Spellbook.

As a lawyer, he helped build the legal AI tool now used by over 4,000 corporate lawyers and law firms. Daniel, having worked in the legal industry firsthand, is passionate about driving the goal of making lawyers’ lives easier and more enjoyable through technology. So a very big warm welcome to the show, Daniel. Thank you for having me, Rob. Excited to be here. It’s an absolute pleasure to have you on the show. Before we dive into your amazing career and all the great stuff you and the team over at Spellbot are doing,

We have two very serious icebreaker questions. Firstly, what’s your favorite beverage? And secondly, what’s your preferred choice of footwear on a typical work day? Yeah, great question. preferred beverage. I’m going to do two. If I was going alcoholic, it’s going to be a fine Pilsner beer. That’d be my choice. when I lived out in California, there was this local ish brewery called Trumer and that was my favorite one. Trumer pills, not sponsored, just excellent Pilsner.

⁓ don’t know, not alcoholic, like ice water, you know, filter. We get a lot of chlorine here in Florida. So it’s gotta be filtered and, ⁓ footwear when working from home, just socks. like Steve job maxed my sock drawer. It’s only like black ankle socks for the last like 10 years. And if it’s going to be at the office, probably like basic Reebok sneakers or something. Good choices. And we agree with those. And with that, we can move swiftly on to talk all about you.

begin with, do you mind telling our listeners just a bit about your background and career journey? I got into legal tech and spell book pretty early in my career, I guess you’d say. I went to law school in Canada where I grew up. I practiced for just over a year before getting into tech. And that’s when we started the company that was Rally, which eventually became Spellbook. Now we’ve been at it for a long time. We started Rally back in 2018. It’s been a long…

journey, especially in the pre LLM side of the company. And yeah, so really I’ve been at the company for most of my career, you could say. Initially in sales, I’ve done every sales job you’d see in a SaaS company. was the first BDR, the first AE, the first sales manager. And yeah, I mean, that’s a short view of my path here. Did you always want to be in the law? What inspired you to move into that space? Yeah. You know what?

think I wanted to be a lawyer for all the wrong reasons. Suits was big when I was in high school, the show, and I’m like, yeah, that’s really cool. I studied philosophy in undergrad, which I really enjoyed. I did consider doing that professionally as an academic for some period of time, particularly, studied Continental Philosophy and Existentialism and stuff. was awesome. I still pick up some books around in that space now and then. But yeah, I thought being a lawyer would be cool.

walk around in a suit and do important things. And it was very, very naive. But I mean, as a high schooler, I guess you kind of are. ⁓ And I mean, very quickly in law school, ⁓ I summered at a small firm after 1L, and I saw what lawyers actually do. And I started to think that I, in fact, did not want to do that full time for the rest of my life. That kind of planted the seed early on in law school.

And then of course, when I graduated in an article and experienced what lawyers actually do firsthand, I kind of knew that I wanted to do something else. mean, getting into Rally, which eventually became Spellbook, was probably equal parts knowing that I didn’t want to be a lawyer full time and seeing what lawyers actually do and being 100 % sure that there was a better way with technology. So that was probably the two main pieces.

Yeah. And you mentioned a couple of times, obviously Rally becoming Spellbook for folks who may be less familiar of that journey. Why did you decide to change the name? Just give it as a bit of context and a bit of journey around that. So in 2018, we launched Rally, Scott, Matt and myself are co-founders. And what we were trying to solve was the contracting problem. We saw how lawyers actually worked in contracts. There’s a lot of Microsoft Word, splicing, copying and pasting, searching old documents. And it just felt so odd.

given where technology was at the time. mean, we’re millennials, we grew up playing Starcraft and interacting with applications and stuff. And it was just odd to be in Microsoft Word late at night, like splicing documents, there surely should be a better way if there were apps that could do some of that. Now, these are pre-LLM apps. So we attacked the problem by building a template-based automation system, ultimately. Our initial customers were transactional private practice lawyers, pretty much in

in companies of all sizes, large law firms, mid-size, a lot of very small ones. And we did solve the problem to some extent. There were a lot of issues with that approach. Some other tools at the time were available, know, Contract Express or Hot Docs, some of the listeners might know. We were kind of in that space. We were a little more lightweight and web-based. The UI was more, I guess, in general, but I used in some ways. But the issue was, too, the time-to-value problem. You needed to configure your templates.

to be able to enter the questions to generate the output documents and the flexibility problem. mean, every legal matter, even if you have the most on Rails use case, there’s always additional context, there’s always nuance, and you need to edit the template after the fact a decent amount to get it to a point of usefulness. So we encountered a lot of the problems that you’d experience as a SaaS company with those two issues in the product. We had churn, adoption was a little bit slow. Now, we were growing, there was product market fit.

We had some very happy customers at the time, but we really came to understand the contracting problem and we knew that our current solution in Rally was not the best fit per se. you know, fun fact that listeners didn’t know this, GPT-3 was released in like 2020. Okay. It was available as an API well before chat GPT. I remember in like 2020, 2021, like developers were talking about this and it wasn’t

abundantly obvious that this early, good, large language model would fundamentally change the way that humans interact with text for the rest of history. It wasn’t obvious at that point in time. Now, we were experimenting with GPT-3 early, early. I remember we were building on it in 21. We launched internally Spellbook in, I want to say, like first half of 2022 and put it in front of our rally customers, at which point I probably had a few hundred at the time.

I think the company is going to be 20 people or so. So we were fairly really long. and you know, we just, we just saw the dopamine hit the dilated pupils. They’re like, wow, like the experience of just seeing text be generated in a word document, knowing the context was just totally foreign to anybody who not encountered large language models before. It was absolutely wild. And to tell you how simple spell book was, it was simply a cursor that you drop into a word document and click go. And it would generate a few sentences. And that was just like, so

revolutionary to the pre LLM mind to see. So, you know, that experience, we kind of knew at that point, we’re like, okay, you know, this might be the next level for our company. And the story goes, I’ll say it briefly, we launched Spellbook in earnest a few months before Chachi Buti got launched. The timing could not have been better. Chachi Buti got launched, lit the world on fire. Everybody was totally aware of it.

And we were already in position. We already had, you know, SEO and ads around AI for legal and eventually, know, chat, CPT for legal. And we had a lot of, a lot of interest in that basically caused us to rebrand in early 23 and yeah, we’ve been spelled with ever since. Yeah. And you’ve been flying.

Ever since, and even from the start, you you’ve had great traction. Like you say, you’ve had great product market fit. And I know you’ve put a lot of time and energy into that. in 2026 then for folks who are less familiar with Spellbook, maybe hearing about it the first time, how would you describe what your problem you’re solving within a couple of sentences? So really kind of hammers home for folks. So Spellbook is a, you know, end to end as much as end to end can be a legal assistant, legal AI assistant built for private practice, transactional lawyers and in-house lawyers for pretty much any contracting workflow.

The system lives, it wedges right into the workflow, it lives in Microsoft Word and is a dedicated web app for the multi-doc and knowledge base features and workflows. It can pretty much help with anything related to contracts. If you’re reviewing documents, either based on a rule-based playbook that you configure in the app or just constructing the AI to review a document, it can handle that, it can redline documents for you, it can respond to redlines. Any drafting workflow, whether it’s drafting a document from scratch, know, editing document,

from a precedent set, for example, can automatically do that just based on new instructions or a source file, like email or a term sheet or whatever. Draft clauses for you automatically like any good generative AI system can. And as an assistant built in that can, honestly, can throw any task at it in Microsoft Word and it will handle it. Fully aware of the document, the party you represent, your knowledge base, your past contracts, the clauses you like to use. It has legal research available right in the app itself.

I know there’s a benchmarking component where you can run a comparative market analysis of the document. could benchmark it against other document types. And then there’s multi-step workflows. So it’s a very full featured contracting app. Yeah. Built primarily for again, in-house and in-product practice for transactional lawyers. It’s phenomenal. As I said, I’ve had the benefit of seeing the product and the work that you do. know, we obviously had Scott on the show before and yeah, I think it’s phenomenal. The quality and how…

client centric you are and the feedback that you get from people from the market in terms of being really, really helpful. You know, not one of these sort of tools that is taking people away. It’s, pretty friction free and good to use. Okay. You talked before about the rally to spell book journey, and you said it rally your sort of hundreds of clients. Now, you know, spell book is thousands of legal teams using the product. Exactly. And that’s just a great case study and great success story. Could you talk us a bit about that spell book?

growth specifically and any tips for maybe aspiring legal tech entrepreneurs or people looking to build out their own platforms and how you’ve been able to achieve that growth? Yeah, that’s a great question. It can go a lot of ways. I’ll speak to what I think like the necessary component of Spellbook was to its success. And that would be finding a problem that you have a hundred percent conviction of and really focusing on that and letting that be the core thing you’re trying to solve. Like Spellbook does a lot right

But the central DNA has always been making contract workflows significantly easier and more enjoyable for lawyers. ⁓ You know, we were pretty early with with LLMs, which was good. But I think for us, like we saw that LLMs were just so flexible and good at dealing with the friction points that we encountered with with rally, you know, which was the flexibility problem and the time to value problem. mean, LLMs deal in the

currency of text as lawyers do. And we always thought of the contract problem and really just focus on that and iterating on that. There’s going to be other competitors or other tools out there that might come up with a new feature set that transactional lawyers and house lawyers want to use for a given workflow. But we always want to be leading on the contracting side, the editing and reviewing of contracts. So I think there’s a lot that goes into the growth of a SaaS company like ours.

But staying true to your DNA and just focusing on that making sure you’re an absolute leader at that one thing that’s really important to your customers has definitely been a necessary component of our success, I’d say. And I love that you said that because I talk a lot about that when people ask me about podcasting growth and I always talk a lot about TOI, which is topic of influence. What is the topic of influence your show wants to be lasered in and focused on when people are going to…

chat GVT now, or Google historically put in, what are those one or two words that they want that pain point relief around that you’re delivering on? And for us, obviously we’ve been all around legal careers and large part of that is technology in recent years and where that’s shaping and changing careers, et cetera, et cetera. But we focus on that and know, mental set specific is terrific, right? The more you can be specific in times of your audience and double down and deliver.

better. So I love it. And clearly it’s working for you guys and it’s been a huge, huge success. So congratulations. Just talk a little bit. You touched on some of the features because I know you do not more. You’ve got review, draft, ask, benchmarks, associates, you know, it has grown. So again, folks new to this today and getting excited about hearing about spell, but just talk us through, you know, maybe one of those features, few of those features, how they work and, maybe some of the most used of those features and the benefits lawyers are seeing.

Yeah, totally. I’ll talk about a newer one. Just it’s more interesting and top of mind and then I can touch on some of the others. So we’re in the process right now of releasing a new feature called compare to market, which we’re really excited about. It’s going to be, I think, particularly used by in-house lawyers. Definitely some of our private practice ones might might have an interest in it, but it’s more in-house focus. So, you know, right now, AI, right now there’s a problem when negotiating contracts around the we call the this is market problem. It’s like, OK,

We’re negotiating with the counterparty. look at a specific term and you say, Hey, we, we’re going to use this term because it’s market. And the counterparty goes, no, actually it’s not market. think this is market. And it’s kind of like a, an impasse because there is no objective framework of what market is. And this is normal because, uh, to understand market, you’d need to, uh, analyze contracts in private repositories and CLM systems and DMSs of private companies all over the world. And it’s really, hard to do that. So market data is quite opaque. Now.

these pre-trained models that we use, they’re trained on a ton of data. You can throw a question at it like, hey, like is this term market? And it’ll give you an answer, but it’s going to be maybe an AI slop answer. don’t, it’s not grounded in anything. It’s just generating a tech, giving you an answer to serve you. Right? So the way that we’re dealing with this, this is market problem with LLMs. I mean, Spellbook does millions and millions of contracts per year and it’s growing quite fast. So we’re taking our contracts that are run through Spellbook, our customers contracts. We’re anonymizing.

the contracts, stripping the deal terms, ⁓ and then ⁓ categorizing the deal terms based on the contracts type, the industry, the jurisdiction, other metadata factors like that. And we’re pooling that in a RAG database. So basically these deal terms and the metadata are beddings that go into a database. And what our customers can do, or starting to be able to do, is when they encounter a contract, they can run a comparative market analysis that’s based on the millions and millions of contracts that have gone through Spellbook.

Spellbook will find the appropriate ⁓ pool of contracts that kind of fit the one they’re comparing it to and give it a term by term breakdown of how each term fits within the the market framework that was found by Spellbook. It’ll tell them which terms are outside of market that benefit or disbenefit their party. And then they could ⁓ automatically with the app, redline a term and provide an ⁓ explanation as to why it’s now within market, for example.

and actually provide the grounded data on this. So it’s a very grounded data-driven approach to understanding what market is for a given contract and letting that be a pretty strong reason as to why a certain term should be revised within a contract when you’re in negotiation. So that’s certainly one that really excited about. Of course, we’re leveraging RAG or Retribulog Metageneration for this, and it’s working really, really well. Some of the features that we’re really

seeing a lot of use from right now that customers are loving at Spellbook, one is associate and the multi-doc drafting. So, as you know, worst kept secret, lawyers don’t draft from scratch, even if the bills look like they do. You’re always starting with a template or a precedent or a previous matter that you did. And Spellbook makes the drafting from precedent experience significantly easier. With associate, could pull a set of documents that you did for say a similar deal or matter.

a few months ago, just like, you you’d be like, oh, you know, I think I did something kind of like this three months ago with this client. So you pull those documents and put them in a associate, which is basically like a sandbox multi-doc environment. You dump them in and you can then upload any additional context that you think associate needs to be able to edit these documents. It’s almost like you’re throwing it into a blank slate junior associates brain. here, I want you to load all this context. I’m going to give you a task. So you load the precedent documents from the previous deal.

you upload, maybe a term sheet, whatever tent, maybe just like an email correspondence that in despite all the noise in the email correspondence, you can distill all the facts needed for the new matter you’re working on. Just dump it all in there and say, hey, listen, this past precedent set that I did before, there’s some good stuff in there. It’s not perfect. I want you to use this to generate draft documents. This new matter, you’ll find all the information you need and much more in this email correspondence go. And then it will start cooking and ⁓

natively edit all the precedent documents in DocX in the app and you can then download them and accept all the changes or accept them right in the app itself. So, ⁓ you know, that experience which lawyers have done and doing is very monotonous, administrative. mean, there’s nothing like legal judgment involved, but it’s very much like a text synthesization experience. And that’s one that Spellbook does particularly well.

And we think, yeah, we think the future of drafting is going to be largely done like this, you kind of, you tee it up and then you let the AI go and do its thing. So you’re not spending your time doing those mechanical tasks, I think. That leads nicely onto my next point around teaching AI actually, because you’ve shared that Spellbook aims to teach AI to sound like lawyers, not replace them. Why is this important to Spellbook? I don’t think AI is going to replace lawyers.

Firstly, I don’t think it’s smart enough to do that, right? ⁓ I talked before about the end to end with like, know, air quotes end to end for those who watching this. AI is not end to end. It’s middle to middle. Like you need to start the matter with it. You need to like tee the task up and then direct it to go and do the task. And it’s gonna be really good at document synthesization.

at taking into account all the data in the document set that you gave it, for example, so can go ahead and do a task, whether it’s generating a summary, a table, ⁓ editing documents, whatever, doing research, whatever it might be. But you need to guide it through this experience. And it needs human intervention at points. And we try and train Spellbook to prod the user with, hey, I’m about to do this. I’m kind of in creative mode right now. Can you do?

point me in the right direction. Like associate will often prompt you and say, Hey, I actually need you to let me know like which party you’re representing in this document. There’s a bunch listed. It’s kind of different than the others, for example, and it would go ahead and do that. And then it will tell you kind of how long it needs for the next task, for example. So you’re kind of like, you know, guiding it around this, this, this path toward completion. And once it gets to completion for the AI, you kind of need to do the remaining, you know, 5%, I could be like, you know,

assembling the documents in a in a folder so you can deliver to the client like it’s not going to be able to do that just yet, for example. So the lawyer is always in the driver’s seat and it’s always kind of it has the full human level knowledge of the matter that it’s trying to complete. But the AI is doing the like the lifting that would be well suited to the AI. again, the document drafting, synthesization, pulling out facts, compiling them that

Yeah. Yeah, absolutely. I see this sort of, you know, you’re, running the race. You are the person you need to be running the race, but you’ve got a rocket on your back, you know, as having like an electric bicycle, which I think is good. You’re still driving it, but you don’t need to pedal. Yeah, exactly. And I think that’s a good, good analogy flipping back to when you graduated. Now I think I’ve got a quote here. You talking with issues from practice. When I graduated from law school, I didn’t realize a large portion of the work I’d actually be doing as a lawyer would consist of splicing.

pasting, editing multiple word documents, it wasn’t what I envisaged. So when did you particularly realize that the traditional legal workflow was not sustainable for practice? think it was probably the first real task I was given as a lawyer or article student in Canada. ⁓ I had like 13 word documents open and needed to generate one from all these past precedents that were kind of relevant and ⁓

you know, all these documents that I need to pull stuff from to make sense. And I’m kind of like, wait, like all the data is here. And like the actual task is just like, just polishing this final word doc that I need to deliver. ⁓ And I just thought that that can’t possibly be it. I, I, this is like not even a lie. This is true. Like I remember like calling my friends who were lawyers and I’m like, Hey, like, is this what you do? Is there a better way?

And the answer was largely no, like there’s a large part of what you do, like, you know, getting to the final documents that is a big part of what lawyers do. ⁓ and I just found that to be odd. And, again, like I, I didn’t, I wasn’t like a tenured lawyer with 10 years of practice. Okay. And I wasn’t a computer scientist that really understood like the, the, the nuts and bolts of techs for doc X, but I had a very strong conviction that this was not the way that lawyers will practice based on the pace of technology that I was seeing just as a millennial who grew up with.

of seeing the analog digital transition in the world. I just knew it wouldn’t be that way. So I’d say the strongest thing that I had going for me at that point was just conviction that this would change and that there would be companies that would deliver this change in some way. And I wanted to go and explore it. So yeah, I would say that was probably the point. Today’s Legally Speaking podcast episode is proudly sponsored by Clio. If your legal management software feels more frustrating than helpful, you’re not alone.

Many solicitors across the UK delay switching because moving client and case data sounds like a headache. Clio makes it simple. As the intelligent legal work platform, Clio combines context aware AI with trusted legal research to power your practice. And when you switch, their dedicated migrations team supports you every step of the way, ensuring a smooth transfer of your data.

You’ll also get award-winning support 24 5 via live chat, phone and email. So help is always there when you need it. Ready to leave frustration behind? Visit clio.com forward slash UK to learn more and discover why so many UK solicitors choose Clio. Now back to the show. Corn is it sounds the only constant of businesses change, right? Things are going to continually evolve. Things are going to going to happen, particularly exponentially in the world that we live now with with tech and AI and sticking with

AI, we must of course talk about governance and security because you’ve emphasized that governance and security are non-negotiables when embedding AI into contract workflows. So what should legal teams listening to this be doing to adopt AI responsibly? Yeah, really good question. think responsibility with AI has like, I would say like two different categories, I would say. The first one is responsibility from a data privacy standpoint. Like you need to make sure that you are maintaining, you know, lawyer client privilege, that there isn’t any sensitive data going where you don’t want it to go.

So, our customers, whether it’s in-house or private practice, they typically have an IT component or questionnaire that they’ll want us to fill out or they’ll interact with our trust portal that will describe all of our security protocols. ⁓ And they’re always satisfied with what we do. mean, firstly, Spelbic has zero data retention at the LLM level. So there is no LLM training happening. None of your data is leaking to an LLM where it’s going to train any Claude models or OpenAI models or anything like that.

The next is around like the configuration side. So you can configure Spellbook quite a bit and that data is going to be going to be stored of course, within Spellbook servers. We’re SOC 2 compliant, we’re HIPAA compliant. We really do cover that data privacy component of it. I think like knowing that is really important. When you go and use an AI system, you have to make sure that it is secure and that these trees are the level that you’re comfortable with for your firm and your practice. And the way that the law societies manage it is they basically say like, okay, like, you know, the law firms and the lawyers are responsible for security.

they’re not going to go and audit every tool out there. That’d be impossible. it is your responsibility and make sure that that kind of checks the box. Now, the next component, the next category of AI responsibility, I would say is on quality AI outputs that you can actually deliver. I mean, we’ve all heard about the case in New York where I think some lawyers submitted fictional cases to it. Right? Like, come on, that’s a problem. We need to avoid that kind of thing. Right.

So AI responsibility, coming into the actual outputs and managing those. How do we manage that? Well, I mean, first and foremost, we tell our users that AI is not perfect. Like this is not like any other software system you use because AI is non-deterministic, right? There’s trillions of parameters in these LLM models. They’re not going to be deterministic like using any other app you’ve used up until LLMs. When you put something into it, you don’t know exactly what’s going come out. And if you give it the exact same input, you know, one hour later, they’re getting a different output anyway, as we all know, using generative AI.

So a big part of reliability comes down to how do we like frame using the system? And our approach has always been, you this is probably commonly used in legal AI at this point. It’s going to be trust, but verify. Like it is good. It is smart. You can trust it to an extent, but you always want to verify the outputs. Now, Spellbook being primarily on the transactional side and like commercial side, it’s mostly doing, you know, doc review and document synthesization with, you know, ⁓ rule-based playbook or a bunch of documents to generate an output that you’re giving it on Rails.

There isn’t really a lot of room for hallucination in these use cases. It really is like the LLMs doing the doc, like, like synthesization stuff, right? And we do communicate that to our customers. We always do want them to verify. When you give it, you know, legal research tasks or more creative tasks to go find stuff in the web or the ether, you know, that, that can introduce a greater chance of hallucination. So I would, would say, you know, the trust and verify approach is how you should, should think about this kind of thing. It’s incredible that you’ve got so much there.

that in terms of people actually knowing you need to do your DD, don’t you, in terms of the organization? And like you said, you’ve got all these components already. So as the people using it, these are the sort of questions you should be asking. So I appreciate that, but you’re going to say a little bit more. carry on. Yeah. mean, another way that we deal with that is citations. People are getting sick of AI slump, like just generating an output with, no grounding is, is annoying. And I think AI slump tolerance is at an all time low right now, especially among lawyers.

So grounding the reasons in citations whether you’re drafting a net new doc from a document set that you upload to associate for example You might want to know why a certain you know entry was entered and spellbook will tell you where it came from for example So you will get those citations also going like a table review of a document set as well And on the legal research side when you when you do a legal research task when spellbook it will tell you specifically where this came from it’s not going to be just you know, is a law right it’s going to be this came from

this Florida statute, and here’s a link where you can find it and verify it. mean, you typically be correct, but you can always go verify it. So that’s certainly another way in which we communicate trust there. And the next one is just like being good. Like the AI needs to be good. needs to generate useful outputs. ⁓ That’s super important as well. And we do a ton of stuff on the, I guess you could say the orchestration layer. So we’re an application ⁓ layer system. We leverage the LLMs and there’s a lot of magic that happens, whether it’s model routing, long context orchestration.

um, did multiple documents, we do a lot of stuff at that layer and that allows it to be, you know, accurate and useful, uh, when it generates the outputs, um, whether using, you know, rag or other technologies. So, you know, that’s certainly a way in which you, uh, allow the system to be reliably used, which makes, you know, which makes a responsible lawyer more likely to use it. I there we have it folks. TVG trust, verify and be good. I’m happy with that. love that. Okay.

Let’s talk about more of the success with Spellbook because you’ve raised a lot of cash as well. You recently closed a 50 million, think series B round. So what is the investment meant for Spellbook? What that’s been able to achieve and go on to do. We’re a product company. Uh, first and foremost, like we’re not, we’re not building for, you know, large enterprise companies to say they check the box by adopting the AI system that has all these, you know, box checks, other thing. We like to build good products that are useful, that are fun to use.

that are reliable, where the design is really intentional. We’re a product company and our product roadmap is extremely aggressive. There is so much innovation that you can do in legal AI and we raise money so we can, well, firstly, continue to grow the company at the pace we want it to grow. think that’s a massive opportunity to grow, especially right now. I think we’re kind of past the early adopter phase of adoption in the market. know, every responsible lawyer I think knows they need to leverage AI in some way.

And that’s been true probably for a little while, but it’s definitely true right now. So taking advantage of this window of growth is a big reason why we raised. Of course, hiring on the sales marketing side, but more so on the product to product support side. I mean, we think there’s a ton of room for innovation here. So our product roadmap, again, is really, really aggressive. Customer support is massively important. ⁓ Onboarding adoption is really important for us, making sure our customers are actually using the system and using it to the fullest is extremely important for us. So investing in that too.

We recently have developed a legal solutions architect team. So these are going to be lawyers that, ⁓ whether they practice in in-house or private practice or both, are joining Spellbook as product experts to help our customers adopt Spellbook, the most use out of it, and make sure it’s on track for the use cases they had in mind when they adopted Spellbook. Because these systems are very flexible, and sometimes users might have a use case a little bit.

nuanced and making sure that the company can handle that and handle it well is something that we want to have a lawyer help them do because they’ll really understand it. So that is mostly where the cash is going. Yes, making the product good and growing the company. Love it. Yeah. And you articulated that beautifully. And I love that you’re really focusing on adoption as well, because that shows you care. It’s not about just selling the product and away you go and hope it all works out. It’s you generally partner with your clients. You accept to be customer centric. You want them to have that good experience, delighted experience. They’re more likely to refer you. They’re more likely to get extra benefits and

Want more of your products as you roll out the maps. think that’s not only just good for business, it’s just super smart and good for kind of that customer satisfaction piece. on that, know, Spellbook is on track, I believe, to triple its revenue this year. So how do you see AI evolving the practice of law in 2026? We touched about a bit around AI, but how do you see this sort of going forwards? Yeah, great question. Hard to project, think, firstly, but 2026 is this year. So definitely a couple of thoughts on this.

I think one specifically on the in-house side of things, think routine drafting and review baseline time is going to be much faster by the end of 2026 for teams that are leveraging AI. I don’t think we’re going to see, if done well, the legal bottlenecks at the in-house level as much as we’ve been seeing them. That is something that I think we’re going to see by the end of 2026 when these systems are well adopted.

Another big component and a big part of what we’re building at Spellbook for this year is I don’t think AI is just going to be a system that does work when you give it a task. I think it’s going to find work. If it’s well integrated into your system, your email system, your knowledge base, contract system, whatever that might be, identify risks that might be coming within a certain obligation or contractual relationship you have with the counterparty. And also preemptively get ahead of work that’s not

quite at the legal level. So for example, if a procurement ⁓ rep or sales rep is interacting with a counterparty by email and in their CRM and they’re getting close to when there’s gonna be a deal, when there’s gonna be a draft contract either by your company or the counterparty, ideally AI systems will be able to preemptively expect there to be legal work and almost like pre-work some of the risks and get that teed up to the…

in-house team so they can know when they’re going to work on this. The AI will already have provided a summary of what the work is going to be. So I really kind of see this like AI being less of like a passive partner to be more of an active partner in the workflows in 2026 and a lot of our product roadmap, know, in addition to the feature set that we have out there and improving that and expanding that is going to be on this, you know, how do we ingest systems so we can find

proactively find work to get done. the NS team is more of an eagle eye on what’s happening around the org from legal standpoint. And this is where I know sort of well-documented CEOs in legal tech space talk a lot about moving from systems of record to systems of action. Actually, being proactive and moving things along far quicker for you and giving you that chance to almost multiply.

amplify your effect as a lawyer. So sticking with that then we’ve talked about 2026. What does the future lawyer look like? know, AI now embedded into drafting, reviewing, planning legal work. What do you think the lawyers of 2030 are going to be doing? Yeah, it’s a great question. We do think about this. It’s extremely hard to even come close to predicting just the rate of how AI is changing. mean, it’s really hard to know, but we do think about this. think lawyers in 2030 are going to have a better life than they have right

Okay, that’s what I think firstly. I think when we were entering the legal tech space, there was always this issue or question that we had around the friction between how lawyers bill and a tool that makes them more efficient, right? Like private practice lawyers bill hourly, right? And our tool would make them more efficient. Like would this not be a friction point, right? It turns out, Spellbook either for private practice lawyers or of course in-house don’t bill hourly, but in either case, it’s never been a friction point.

And it’s because it turns out lawyers build the same, whether you’re spending an hour working through a complex legal issue with a client or spending an hour three in the morning in Microsoft Word, relining a document because there’s a deadline, the next day, for example. You build the same for those. And one of them is a lot more enjoyable than the others. In fact, you go to law school to do the first one and you don’t really know you’re going be doing the second one a lot more until perhaps your last year of law school when you actually start practicing. I think by 2030, a lot of that

that grindy document work is going to be handled by AI. I think the lawyers are going to be more zoomed out. They’re going to be more engaged with the legal judgment side of their practice and the actual document side. Like I don’t think there’s in 2030, know, partners going to drop a 200 page contract on an associate’s desk at 6pm and say, hey, you know, I need you to summarize this by, you know, by tomorrow morning, for example, right? There’s going to be an AI system that can do that effectively. And it’s going to deliver

like a choose your adventure output where it’s like, hey, like, where do go from here? Like, here’s what I, what I, what I recommend. You know, I did some legal research here on this and lawyers can almost like be a pilot, uh, with really powerful, you know, we did the bike example earlier, really, really powerful plane, uh, under them, you know, guiding them toward the end of the, uh, of the legal matter. And it’s, it’s going to be collaborative too. mean, I expect a lawyer is going to negotiate with counterparties, both of which are going to be largely powered by AI doing a lot of the.

you know, grindy work and it’s almost going to serve up like some of the more contentious issues in negotiation with a bunch of contracts on each side and the lawyer is going to work through that live. So yeah, I foresee that. Now this is a very amorphous description, right? I’m not kind of going into the, into the low level stuff. It’s really hard to predict, but I do expect AI to really pick up a lot of that kind of grindy document work and make a lawyer be the, you know, use their actual expertise and judgment. Would we be closer to end to end by then? Probably yes. But I do think lawyers are still going to need to kick off.

matters in some way and rap matters in some way. We’re not going to trust AI to do that even by 2030, think. Fascinating insights and it kind of lends itself nicely, particularly when you’re talking around the judgment piece too. We’ve had a Piers Linney, former Dragon’s Den, Shark Tank investor come on the show before and my listeners probably be sick of me telling them this, but it’s so true. He talks a lot about the value pyramid and he said, it doesn’t matter if you’re a doctor and a lawyer, an accountant, technology is coming in to this pyramid and

exponentially getting better. at the moment, we’ve obviously seen it with regards to basic level paralegaling work. So certain contract associate works, it’s, it’s, it’s going up the value pyramid and you as a service provider need to find a way of being ahead of technology through maybe creative thinking, judgment, strategic thinking. And I think those people that are able to do that are going to be able to have you highly, highly successful. So it just lends nicely to what you’re saying there about where you see potentially the future lawyer going. Let’s talk now about AI watermark.

because you envisage lawyers trading contracts with AI watermarks, citing market data to justify different positions. You were touching on that before. For folks who may be less familiar, can tell us about what actually AI watermarks are and the potential consequences of utilizing them? So, specifically in the context of our comparative market feature that I mentioned before, we foresee a very near future where if a lawyer runs a comparative market analysis on a document,

they’d want an indication in the actual document in the form of watermark or some other indication that they ran comparative market analysis and it came back with a certain score. For example, it could be like this contract, the contract terms are 94 % within market, given the contract type, industry, geography, et cetera, and could potentially provide a record of the terms and where they all land relative to market, for example. So why do we foresee watermarks in this context, particularly being useful for lawyers? Well, if market data is less opaque and more clearly available to both parties,

we expect for more trivial contracts where the negotiation power of each party in the grand context of the matter doesn’t matter as much, doing what’s market is probably best. So this could reduce unnecessary friction and extra negotiation on these relatively simple contracts. So we just see people being like, okay, you know what? This is market, fine, done. And a lot of the experience of maybe servicing up, like,

passing up an NDA, for example, like sales to in-house when it’s like, hey, like, as long as it’s fine, it’s fine. It’s an NDA, right? Simple contracts like that, just like getting the market score done. Or if you’re sending a contract to a counterparty when you’re starting a matter with them and you’re sending it with an AI watermark, like, hey, this is our NDA. This is what we use. We don’t use, know, like a standard one that you might know. We use ours, but it is within market, except for these three terms. And here’s an explanation on the market report as to why.

And it’s really agreeable. we expect a future like that to happen in the very future. For more complex contracts, where the context is really important and negotiation is like the negotiation is going to be more complex just by the nature of the contract, for example. I think having a market watermark can just help make the negotiation move smoother. can look at the 80 % of terms and be like, right, know, these are market. We’re not going to be to really fight on these. And they’re pretty reasonable. Let’s just get right to the non-market.

You can kind negotiate at that point. That could be reason as to why you might be negotiating terms that are outside of market, for example. So we expect that to be a very near reality as well. Yeah, I love it. I think it makes perfect sense and see all the positives with it. This year and previous years, Spellbox has done some huge collaborations and partnerships. But one I wanted to talk about, just because I use them myself, is Dropbox. Because earlier this year, your colleague Scott, think, put on LinkedIn, Dropbox has chosen Spellbook as its AI contracting platform. So what

has been the effect of Dropbox, legal and commercial teams using Spellbook to review and negotiate contracts. Yeah, mean, it’s a drawbacks, of course, the household name in tech. So it’s been great for us. I I think it really just shows the market that Spellbook is a trusted provider in AI tooling to in-house legal teams specifically, given the fact that Dropbox is just so widely known and so prolific and successful.

Yeah, I mean, it’s just a really good signal that we are in fact, a leader in the space that we’re building for the best and most technologically advanced companies. mean, Dropbox is of course using the latest and greatest tech because it is that in their own category. So it’s been excellent for us. We’ve had a lot of customers see that I think and be more confident in Spellbook. A lot of prospective customers look at that and know that they are in fact with a tier one company in Spellbook by that announcement. We have a lot more of those coming by the way, so.

Oh, I can’t wait. can’t wait. know. I’ve been watching them. When I saw Dropbox as well, like, I literally live on it all the time. I think it’s incredible. And I was just like, that just makes so much sense. I have no doubt there’s going to be some more huge brands coming along the way, which I’m excited about. We have a lot of aspiring lawyers that listen to the show as well. Before I let you go, a couple of final questions. Spellbook has also launched programs for law students. So how should AI tools be integrated into learning at law school generally? Curious to get your thoughts.

It should be integrated into learning it in law school for sure. That’s probably number one. You know, we’ll say this. I was talking to a, so I did an event a couple of days ago down in University of Miami and I was talking with a law student there. I think he was 3L and he actually wasn’t sure what he was going to do next. He didn’t have an internship teed up or anything. was just thinking about his next path and wanted to see what’s going on in the legal tech space. And he told me about his curriculum and I was amazed. Like they had some really good,

tech forward courses. Like I graduated law school in 2016. My curriculum looked the same if it was 1965. Like was virtually the exact same courses you were taking, right? So I do think law schools are really starting to get ahead of this already, at least from what I’ve seen, which is great. But I do agree law schools do need to get AI specific courses into their curriculum ASAP. Now, for the law schools that aren’t, or maybe just starting to, the good news is,

Just about every law student that I’ve spoken with is using AI in some way, whether it’s a pre-trained model like ChatGBT or the Spellbook partnership where law students could get access to Spellbook or using domain specific ones like Spellbook. All of them are using that and they are kind of going into the practice of law acutely aware of the fact that they are going to be, need to be AI proficient to keep up given this new era of law practice. So law students are probably leading law schools right now.

on the AI front. So there certainly is room for law schools to be, to get ahead of this, I think, and build some really solid AI programs. And I expect they will. I also suspect they will as well. And before I let you go then, finally, it’s been a wonderful conversation. Really enjoyed learning about your career and from Rally to Spellbook and the huge success you’re experiencing now and going to continue to do. What would be your advice to lawyers who would like to pursue a career in legal tech? Great question. Okay. So I’ll speak of it from the perspective of a sales leader. I think selling legal tech,

to lawyers these days is probably like the least traditional salesy role ever. ⁓ The sales, like the performative salesperson is not gonna be successful here. The people that are successful in legal tech, I think are so deeply curious about legal and AI and where they intersect. Like that is like the number one thing.

As we know as lawyers, if you’re looking into legal tech, know that lawyers are lifelong learners. You need to constantly educate yourself on changes in the law, you new regulations, new cases, whatever. The most successful people in legal tech, whether it’s sales, CS, even developers, they’re so deeply curious that they approach every conversation with this like passion of preparedness. They’re like, they’re excited about solving this problem because they know deep down that LLMs

deal in the currency of text as lawyers do. And it’s such an amazing opportunity. I would say curiosity, like let your curiosity self go in this space. Like read why like a new model with a bigger context window is relevant for legal AI. Like learn about all the new tools that are being developed in the space. Like read, you know, articles of people that are thinking about like the future of legal AI and where it’s going. Like I would say let your curiosity just guide you and let that like, let that obsession just go.

That will make you so valuable to a legal tech company, I think, more than anything else. So that’s my maybe not obvious, but that’s my perspective.

I think it’s wonderful advice. know, curiosity is so important in so many aspects of our life, not just professionally, but personally as well. And I love that. So thank you for sharing it and thank you for joining us. And if our listeners, which I’m sure they will want to know more about Spellbook or indeed get in touch, what’s the best place or social media platforms for folks to get in touch yourself or Spellbook to learn more, feel free to share any websites, social media handles will also share them this episode for you too. Yep. spellbook.com

I always start there and you can always reach out to me on LinkedIn. Happy to answer any DMs that come my way. Awesome. Well, thank you so much once again, Daniel, for joining me on the League of Speaking podcast sponsored by Cleo. It’s been an absolute blast having you, wishing you lots of continued success with your own entrepreneurial career and indeed all the team at Spellbook. But now from all of us, over and out. Thank you for listening to this week’s episode. If you like the content here, why not check out our world leading content and collaboration of the Legally Speaking Club.

over on Discord, go to our website www.legallyspeakingpodcast.com, there’s a link to join our community there. Over and out.