Transcript: Datasite MCP for Copilot

Good morning, good afternoon and good evening to those people joining us all around the world today. And welcome to the data site MCP 4 Copilot webinar. This is actually the third in our series. All the other ones are available on demand. So please go ahead and check those out if you happen to be interested in either Clawed as a surface of interrogation or ChatGPT of as a surface of interrogation. But today we're here to talk about Copilot, Microsoft Copilot to be specific. My name is Doug Cullen. I'm Chief Strategy Officer here at Datasite. I actually also oversee corporate development, and I've had my hands in most of the acquisitions that we've done for my last over a decade here with Datasite.

And I'm here to introduce today's topic, which is really trying to frame how deal teams can work with AI tools like Copilot while keeping sensitive deal content protected inside governed environments. Before I kick things off and introduce my Copilot in today's webinar, I just wanted to remind a few people around the world about some few housekeeping items. So first of all, we want to hear from you. So please, there's a ability to ask a question on the panel. Please ask your questions and make sure we will have about 5 minutes, we hope, towards the end of the discussion.

And we want to get to your questions, whatever you have all around the world. The other thing is we're going to get a survey. So we'd love to know what you think about this program. Past programs asks areas for improvement. We are always in a continuous improvement environment here at data sites. We want to make sure that we are giving you what is valuable. There are Speaking of what we hope is valuable. There are a bunch of additional resources at the console, some FAQ S, some guides along the way to help you on your AI journey specific to MCP for Copilot.

And just like the previous sessions, this will be on demand, so please forward this on to your colleagues, ask for additional access. We'd love the world to understand what we're doing here at Data Site and specifically how we're powering up Microsoft Copilot via our MCP connection. And the quick legal disclaimer, all The opinions expressed are our own and not those of Data Site. So with those behind us, I would like to introduce my friend and colleague, Caitlin Murdie. Caitlin, your VP of Sales Engineering here at Data Site. Like how long you been with us? What do you tend to focus on?

Help our customers understand. Yeah. So hello everyone. Like Doug said, I'm Caitlin Murdy. I run our sales engineering team. I have been with Datasite for six years now. So seeing Datasite over the transition of the past six years, bringing new products to market, working closely with our product team and our sales team to bring those products to market, receive client feedback, bring it back in and continue evolving what we offer. Yeah. So Caitlin and her team, we've got global team that does this as well sort of sit as a linchpin between our customers, our go to market teams, our service teams and our product teams.

You've been a great partner helping us build what we think are pretty amazing products of the year. So thank you for that. And you know, we want to now I think transition a little bit and it should be stated just to give people in context that we are currently in process with Microsoft in order to get this capability approved. So we have the capability, we're going to be able to showcase that capability. I'd love to be able to tell you, you can go and find this capability immediately. And sadly that's not totally the case. So we're going to get a little bit of a foreshadowing of what will come.

We're kind of really more in a production environment that's available for internal folks here at data site to at least be able to get a sense of directionally where we're heading from this capability. But don't drive yourself crazy if you're continuing to look for this as we're going through the final stages of approval by our dear friends at Microsoft. So with that as kind of a backdrop, I just wanted to talk a little bit about the overall dynamics that are happening across deal making as we covered in the other sessions. You know, AI is, is kind of omnipresent and it's really changing some of the ways that that we tend to think about, you know, how deal making is getting done today, how it's going to get done tomorrow, what tools people have at their disposal.

So I guess from your perspective, you know, Caitlin, before we dive into the the nitty gritty's of, of some of the demonstrations, I mean, what are some of the, you know, industry trends that you're seeing? You're out on sales calls, you're showcasing some of these capabilities to customers all over the place, across corporate development, across private equity and across investment banking. Like what are some of the kind of backdrops that you're hearing or or points that you're hearing over and over again about sort of industry dynamics? Yeah, I think over the course of the past year, there's been this big transition of people being very scared of AI to people feeling that they need to adopt it.

They have to figure out what tools to use, but are still getting more and more comfortable. And every month that goes by, I think we see more and more teams adopting tools. But there's definitely been an underlying tone of which tool do we go as you have the people who really want to use Clod and then all of a sudden ChatGPT gets ahead with something else. So there's this ever changing dynamic going on that it's tough for teams to decide which tools and where to commit. Yeah. And so just as a refresh, a lot of these capabilities that we're showcasing today are, are are very new to market.

We actually launched the MCP connections at deal Max earlier this month and brought out the first ever kind of blue flame enabled AI assistance with in diligent diligence and acquire. Those are some foundational elements, but I think one of the things that I I find fascinating have been some conversations that we've had along the way and really a notion of, of prompt first deal making. And as you're saying, I think, you know, AI is certainly omnipresent. I think people are in various stages of their journey embracing AI like many people around the world. Microsoft is omnipresent for a lot of us deal makers as part of the critical software suite that we have at our disposal.

So I think Copilots a certain interesting addition to, to our set, but one of the things that we've been thinking about a lot is really ensuring this sort of level of of governance and compliance. So can just give us some perspectives from your side in terms of like how we, we've been thinking about AI, how clients tend to think about AI and, and kind of how we approached it from a strategic standpoint in terms of activating within our, when our, within our various surfaces. Yeah, definitely. I think first and foremost like we are a security first company.

We want to make sure we're doing right by our clients and protecting their data. So everything that we're rolling out is with that mindset. And so as we think about like our MCP connectors into the data room, it's really to allow you to protect that content, but leverage AI against it. And I think that's something through my conversations with clients, it's one, a gap and what they have available today because they don't have tools to leverage to use AI throughout the diligence process. And then two, it's always one of the first questions we get around protecting their data. So I think that's super important.

And then I'll also say because you mentioned Copilot and that's kind of the theme of today, but so many people, Microsoft is president. So we get a lot of excitement around Copilot and what we're doing here because I think for a lot of clients we work with, Copilot is kind of their first foray into the AI world. Yeah, totally makes sense. And I think what we're really trying to get to here is showcase what can AI actually do securely within the data room. And so today that we're going to showcase the sort of MCP integration with Copilot.

And then we'll talk a little bit about, you know, our blue flame assistant. And so this is active again, we've, we've caught in ChatGPT, so you can find those as connectors. And we're in the process of getting approval for Microsoft Copilot. But with that, I just thought it would make sense. And we're going to try to level set across a couple different areas that we're going to be framing today. So 1 of this is you're going to hear me talk a little bit about the Blue Flame AI assistant. So this is something that is available today for both our diligence application and our acquire application.

So as a person that is running that process as an advisor or potentially the underlying corporate or potentially even a private equity company, if you're dealing with a potential divestiture or portfolio sale, you can elect to have Blue Flame AI assistant enabled in your project. So that's actually a side panel that's available today and that will allow you to have a full gentic experience within the diligence project. And we'll be covering some of this on some of our future programming upcoming, particularly around Blue Flame and the abilities that we have via that MCP connection as well. But then you also then sort of layering in this additional layer.

And so this is sort of MCP, right? Think of MCP as a different surface, like that's something that you can use. So in this instance, we'll be talking about Copilot. We've got this surface that is actually connecting based upon your credentials. So what you are authorized to do within the platform, what projects you have access to, what you are able to do within that project, you will then have this connector that gives this beautiful surface of Copilot, which gives you another way to act on the data room content. And we'll showcase what those things are able to do. So we've got sort of the blue flame AI assistant within the project experience.

So you can go there, you can activate and then we have some customers that are seeking to do things outside of the traditional data site experience and they want to be able to interact with content via MCP, which again we're going to showcase. So you can do it within Data site, you can do it within MCP or Copilot. So just wanted to sort of try to level set those two things. If you have any questions, please reach out to anyone at data Site and we can be able to talk with you about that. So with that, let's get to the demonstration portion of it and we want to like talk a little bit about some practical.

Again, these are going to be more like sell side admin workflows and you know, Caitlin's going to pull up her screen here and we're just going to talk about. So OK, let's scenario plan here a little bit. So I now want to set up a project. Can I actually do that from a surface like? Copilot, you can, it's pretty incredible. A lot of the things that you used to have to log into the data room do through our UI we're now offering via the connector. So without further ado, I'll pull it up so you all can see it and I'll call out as we go through.

Doug mentioned using the Blue Flame AI assistant for to enable AI powered search and understanding and interaction with the content. So I'll call that out in this first example where you're just creating a new project that can be done just via the MCP connector. So I said create a project title. It's Snow Flower, sunflower, don't know what a snow flower is. And what you can do through this is you'll see copilot actually comes back and there's a level of detail that we need in order to create the project. Copilot knows that it asks, it confirms, I give a quick response free text in what is needed, and then my projects created as easy as that.

If I want to go in, it provides me with the link so I can quickly access it. And it actually prompts me to say, do you want to create a folder structure? Like how do you want to build it out? And based on the data I've already provided, it then goes ahead and builds out my folder structure. I can obviously edit this later, I can alter it to be more specific to my process, but it doesn't first pass at that and builds out the in depth folder structure that I'll need to leverage. And then I'm thinking about it. Doug's actually supporting me on this deal, so I want to make sure he's added to the project as well.

All I need to do. Doug Cullen, and he's now added as a project admin. I specified his role. If I hadn't, it would prompt me with the different roles that are available and then ask me which one I want to provide to him. So pretty cool and powerful what it can do when you think about having to log into the site, having to do those things through the tool. Now, if you're already working in Copilot, you can just continue working there and do exactly what you need. Yeah, an amazing thing for us. Like, you know, we have literally hundreds of thousands of users that access data site every single month, you know, across 28,000 companies.

A bunch of people are super sophisticated and experienced. They've done this a bunch of different times. Others may be doing it for the first time. And so one of the things that you're able to benefit and draw some, you know, some power from, if you will, is our collective experience having supported literally hundreds of thousands of transactions across the world. So here you're basically able to create this folder structure. You can get these as templates within our core platform, but it's really going to create this dynamic folder structure. So you're already a step ahead. Maybe you had to ask a former colleague, hey, if you do have a previous index, maybe you call our project Protein.

They can do this. But right now you're able to do so much just out of this surface of Copilot that it's already, I think, game changing. Definitely. And I think what's really cool too is the flexibility. So if you know exactly the deal you're working on, you can describe that asset that you're selling and it'll get even more in depth in particular to your deal. Or if you want to keep it vague, you can do that, but it gives you the flexibility to run it how you need. Yeah.

And so then you know what typically ends up happening before this. I get my folder structure, I start to organize, add the the appropriate documents. If I'm the corporate, I'm doing that directly. Maybe I'm working with this as an investment banker, a lawyer, depending on where you are, maybe an advisor of some sort else. And then I think sort of a really powerful thing. Usually you want to get a sense of like, hey, how's this looking like? Is the content logical? Is it connected to the right things?

Are there potential gaps? I mean, is something like AI there for us to be able to get that type of insight? It is. It's pretty incredible. I think what you're describing, that kind of launch ready list, check readiness checklist can be one of the most tedious, time consuming, nerve wracking parts of the process. Have to make sure everything is ready to go. So the right buyers are getting access to the right thing. And now you can leverage AI kind of as that first pass.

So in this case it's leveraging the blue flame AI to analyze the content, understand what's in there and determine where you have gaps. But then also leveraging just the regular MCP connector to look at like are things published who has access to what. So in this case, I've asked it to run my pre launch readiness scan. I love the visual traffic light status it provides. So I can really easily see my 1 folder looks ready to go. My other is not fully published and I might want to look into that or maybe it's intentional.

But then we dive deeper into the Round 2 and I can see a lot of these folders based on the AI scan, they have the right content in there. There's not a lot of gaps, but where it is then or where things are missing, that's flagged for me to dig deeper into. And then it even goes ahead and it gives the top five issues or fixes that I should make immediately. So what I love about it, and with a lot of these prompts you'll see it really drives me to take action and points me towards what a viable next action is. So I need to figure out my gaps in what's published and unpublished, or I need to rename specific files as it went through certain things in here.

We're not named with the greater naming structure. Or maybe there's some draft documents or things that look unfinished that I need to look into. And then the final thing I asked it to do as part of the readiness scan is start to anticipate what buyers might ask me. I want to get in front of what their questions are going to be. I want to understand if there's going to be any gotcha moments before I go live. And it drafts all of that within here linking obviously back to the data room, which I think is crucial to and then a quick launch checklist.

So like I said, it's going to drive you to take action, which I think is super important in this situation. Yeah. So let's maybe take those little bit one at a time and unpack them. So first of all, we've got the blue flame enabled content. So we're able to have the we're able to have the folder structure that we've established. We're then able to look into the content of the documents themselves. So do a little bit of a compare and contrast against, hey, the content of the document.

Is that being represented by the name? I supported quite a few deals in my life, but I can tell you that, you know, adding me, I think it said like scan 4.000 is not very helpful or book 009 dot XLS like if I'm on the buy side doing a review, very difficult to kind of understand it. So I think this is a crucial element for those on on that preparation fate as a sell side, you want to make sure your house is tidy, it's in order, you've got a logical index, you've got the right documents in the right locations. Those documents are named properly in order to facilitate smooth diligence, right?

And I think this ultimately is reflective of a high quality asset. I mean, and I most people, when you're looking at a platform like data site, you're really dealing with the best of the best and we're trying to layer in the best technology to to aid you on the way. You know, and that you mentioned it is probably one of the most stressful times that a deal maker has that sort of before launch. You know, it is a proverbial measure twice and cut once moment. I've heard massive stories around literally managing directors individually reviewing every file in every folder prior to get that because it was her that was ultimately representing this on behalf of the customer.

I've heard of general counsel's that corporates literally going through every file. I've looked at controllers going through every single financial disclosure in order to tick and tie this. And not saying that you don't want to look at that, but this is where like AI can be super powerful in terms of helping us connect those dots. Exactly. And that's what it is. It's almost an extra layer of eyes on what you're doing so you can feel more confident in what you're doing and what you're executing. And to your point on file renaming, as we went through that checklist, we saw like some of the files were not to the consistent naming standard.

As you said on deals, when you're looking through and you're trying to find content and it's named incorrectly, that's going to slow down your deal. What? So on one hand the AI is helping the admin to craft and do all of this quicker, but then on the other hand it's helping the buy side because you're finding a better formatted data room so you can go through, find the content you need quicker and keep the deal progressing. Which I. Yeah, no. And I was going to say that.

Then the next thing that we just covered, because I think this is a super important part, and maybe just bring up the screen again, if you don't mind, is this notion of preparing for potential Q&A. OK. One of the most critical things within a deal is, you know, really trying to think about, you know, if I'm selling an asset, I'm always thinking about what are the likely questions that I'm going to get right. If I'm an advisor, I'm trying to anticipate that. If I'm an underlying corporate, I'm trying to deal with that. I'm working with advisors around doing a deal in order to try to understand that, not only to make sure that we're prepared for any perspective questions.

Do I have the right documents? Do I have the right command on the overall content? Some of this has massive amounts of content that we're dealing with in some of these projects. So if you showcase that again, can you just walk a little bit about through that anticipating potential questions and then how you're leveraging Copilot in this instance to maybe give you a little bit of some preliminary responses to that? Yeah. And So what we're seeing here, it's going through my data room. It's again, reading through the content to understand what's there and then start to think about like what buyers might ask or what gaps might we have or gotcha moments.

If there's something that maybe you didn't realize you were sharing or how you were sharing it, it even flags where it thinks you're going to get a lot of questions. I was talking to a group yesterday of bankers that mentioned a lot of times what they're doing now is they want to make sure their data room is set up and ready to go in alignment with the story they're trying to tell from the SIM. So to be able to use a tool like Copilot to say this is a story we're selling by uploading the SIM and what they've crafted there, does the data room align to that?

And that's exactly what this is doing here. It's helping you get a sense of the story you're telling with your data room by the questions people might ask. Yeah. I mean, it is a crucial component of how deals get done. And really, you know, on the advisory side, you're doing a lot of this hard work upfront, right, to try to anticipate, be prepared and really optimize the time of the people that are involved in the deal. And across the deal team, of course, you've got the deal team extension, which we like to think of as your day to site team, project pros and of course our platform, our experience.

But this is really kind of showcasing some new capabilities that that platforms like Copilot really leveraging the the capabilities that a blue flame AI brings to the table are just taking it up a notch. 100% And I think to that point, another use case that we want to show is really the file renaming. So we flagged it as we went through our readiness checklist, you might identify you have an inconsistent naming standards as well as you might be working where you're receiving all this content, like you said, scan documents where the title is scan #4 XYZ. And it's really tough for teens to understand what that is.

So in working with admins of data rooms, I often get asked like, how can we use AI to rename files? And so this is one of my favorite use cases to show. And again, this is an example of where it's leveraging both Blue Flame AI Assistant as well the MCP. Sure, with just the MCP, you could push out new file names, But by having that blue flame to AI enable the content to provide the LLM with the understanding of what's in the document, the titles that it's going to provide are going to be a lot more accurate and realistic to what the content is.

So if you're ever a buyer in the data room, you know what you're looking at when you open a file. And so in this case, I'm saying review the standard file naming convention and then in this folder update the file names to make sure they incorporate that. What I love about it, obviously naming the files in a data room is a pretty risky task. You don't want it to go wrong. So Copilot is going to double confirm with me it's going to 1st layout what the naming convention it sees across the data room is where it sees the gaps, and then put together what its plan is to proceed.

Once I go in and confirm that, then it executes and now my file names are all consistent throughout. I mean, it's kind of magic. I mean, if you think about how this was needed to be done even in our world class platform and diligence, there are a couple different ways that we had this. And before last, you could do it in a Excel spreadsheet, you could kind of load that, you could tap into our project pros. They spend plenty of time renaming files on behalf of customers. I mean, literally hundreds of hours of work we're happy to do on your behalf.

But again, these are human centered processes. Now we can have that consistency at the content layer, you know, at the folder level, at the file name level. And you know, again, that sort of tidiness I think goes a long way around the quality of the asset and ultimately the quality of the diligence. And what we're looking for is effective and efficient diligence, you know, when you're when you're selling an asset. And efficient is such a keyword there. It's efficient in how the admins are doing it because now they can rename the files or whatever. The task is way quicker than before.

But it also adds efficiency to the buy side because they can find what they need quicker. Yeah. And just to clarify as well, because these have come up a couple different ways. So these are capabilities right now that are enabled on the project via the Blue Flame AI assistant and what we're showcasing right now are tools and capabilities that are available to admins only. So these are people that have full rights to be able to rename, move content, etcetera. So our plan is to extend some of these capabilities to the reviewers or you know classical kind of sell side capabilities, administrators, reviewers would be by side, but that's something that we are currently working on.

And so you can sort of stay tuned for some of those capabilities. So we have a few minutes, so maybe we'll kind of go in here to some of the Q&A. OK. So this question is, does this mean that sellers preparations can largely take place in the data room rather than beforehand in their own file storage system? Yeah. So they can definitely do things in the data room or if the content is moving over to the data room, they can manage it there. They can upload directly be a copilot.

It'll bring them a link to their data room to upload there so they have some flexibility in how they work with these things. Yeah. And like just to add some color to this, it is not uncommon for people working with that preliminary set of content to have it on a local shared drive, a local hard drive set of material that they're working with in order to stage it prior to loading it on onto data site. Our recommendation would be get it up there immediately, take advantage of these tools, take advantage of the blue flame enabled content.

I know if I have an environment just on my laptop, my capabilities on data site are vastly superior than what I'm able to do just in a standard operating system. Definitely. And that's what we've seen as we first went to market with the Blue Flame AI Assistant. It helps understand, especially for admins, the content that's going into the data room. So if you're a sell side advisor and you're not as familiar with the company but you need to start to move all of the content around, you can easily understand that based on the Blue Flame AI Assistant.

Yeah, and just a quick question here as well. If files are renamed, will links shared previously 2 docs still work? And the answer I believe is yes. So the document itself doesn't really change your authorization or permission to that document, it's just going to be refreshed. From a naming perspective in the UI itself, does the file naming system limit the characters to avoid downloading errors? I think there is a character limit on this system. I'm not sure what it is these days. So we have built in when you download the ability to concatenate the file names if needed to avoid errors. So we do account for that.

OK. We've got one more question. Thank you so much for the participation. And I think we talked a little bit about it, but it's probably worth reinforcing here. Which advantages do you feel Copilot can bring to data site for work streams in corporations during DD who are not involved in data structure? Data structure Setting up As investment bankers, you want to take a shot. Yes, because I think it's actually the perfect question. We were running out of time, so didn't show our last prompt.

But one great example of this is responding to buyer questions. So if you are on a corporate work stream, you're managing as part of the sell side and you're getting a lot of questions from buyers that you need to respond to based on the content in the data room. You can easily upload that tracker into Copilot or your preferred tool and it's going to to read through the content within the data room and be able to pull out responses. What I love about it is I've prompted it as well to give a confidence score, so it's and to link back to the data room.

So it's really directing me to take a first pass to get a draft of my answer, but then to validate within the data room. Yeah. And I think I think it's going to really transform the ways that get deals get done. I've been doing this for a couple decades at this point. But I think having the ability for people with all sets of experiences to log into the data room and ask some basic questions, prepare via natural language for this opens up for corporate users, people that may or may not be as familiar with it, as well as a bunch of senior people that typically may not log into it.

And we heard a story from a senior banker that kind of laughed and said, I may log into a data room for the first time in like a decade because that's been effectively almost put down to some of the junior levels. While it is really paramount for advisors to be in tune with all the different shifting dynamics of the content within the deal, what questions people may ask and and how you ask a bunch of questions here. But we're going to have to leave that here. Want to thank you, Caitlin, for such an amazing job here today. Always a pleasure working with you.

You too. Yeah. It's a good time here and we're going to have to wrap things up here. Look, this is happening. We're at the forefront of capabilities with MCP and showcasing what Copilot will be able to do for our users around the world. Thinking about this through the lens of governance compliance and ensuring that that confidential information that you have does not leave and is not disclosed unintentionally outside of the secure barrier of data site that you've come to trust and love so much.

But with that, please refer this to other people. We do have our next in the series where we're going through a little bit more in detail with Blueflame. I want to thank people from around the world for tuning in. I want to thank you, Caitlin, for doing such a magnificent job of showcasing these capabilities. The webinars are recorded. Please forward them around. And just an extended thank you to everyone that spent time with us here today, and I hope to see you on the next webinar next week.