Datasite MCP for Blueflame AI

Good morning, good afternoon and good evening. Thanks for everyone joining us for our 4th and final in our series. Welcome to the data site MCP for Blue Flame Webinar. I'm joined here by Raj Bakru and Alice Azmarian. We're going to walk you through several different components of Blue Flame. Blue Flame AI Assistant with intelligence and we're super excited to have you here. My name is Doug Cullen. I'm Chief Strategy Officer here at Datasite, head of as well as head of corporate development as well as head of partnerships.

But I hear today we're going to talk with you a little bit about how Datasite and Blue Flame AI work together to bring governed AI workflows directly into deal execution. Our website, our web series has been really focused on the transformations that are available now with AI technology and really changing how deals get done. And as we focused a lot on previous webinars, we're going to dive right into the Blue Flame experience as well as showcase Blue Flame AI assistant in the diligence application itself. So before we get to those exciting things, I just have a few housekeeping items that I want to cover.

OK. The first of all is we want to hear from you. So you're going to see and ask questions on the panel. Please ask questions throughout the webinar, and we will do our best to get to those questions after the fact. If we don't get to them, we'll still follow up via some FAQs just to make sure that we address the most important topics. We also are going to put together a survey, so we want to make sure that you respond to that. You'll find additional resources in the console.

This has some of the FA QS from previous sessions as well as information about some of the things that you're going to be seeing here on the webinar today. And of course, we are recording this and it will be available on demand. And then you know what webinar would be would be here without a good legal disclaimer. So all The opinions expressed are our own and not those of data site or Blue Flame. So welcome here. Joining us here, just wanted to do some quick introductions. Again, we've got Alice's Marion, product strategist at Blue Flame. Why don't you tell us a little bit about how long you've been at Blue Flame, what you do previously?

Sure. So thanks for having us here today. I'm in the product strategy team at Blue Flame. I joined six months ago, so it's been definitely an exciting time with no rest. My background is in investment banking and private equity where I spent almost eight years. So very exciting to help being our bankers and private equity people are just benefiting from new AI products in their workflow. Awesome. And Raj Baku, Co founder of Blue Flame, can you give us a little bit of background about Blue Flame and maybe what some of the things you did before founding the company?

Yeah, sure. Thanks. Hi, everyone. Raj Baku, Co founder General manager here. My backgrounds actually on the tech side of things, started my career at Goldman, was later at Highbridge Capital and Capital Capital, started a security firm that we sold to a compliance firm, Eventually ended up running M&A and corporate strategy is the chief strategy officer of that company. That was AP back company under three different private equity owners. Saw a lot of the pains of the manual workflows that we had in acquiring, you know, dozens of firms.

We launched Blue Flame because of that. We saw, you know, there's a huge opportunity for where AI could step in and make make live lives a lot better for folks in the industry. We knew AI was going to be transformative, and here we are today. Awesome well, let's you know, we want to get definitely get into showcasing some of the capabilities. We have a lot to unpack on what's going on across deal making. You know a is becoming central to how deal teams think operate. Teams are increasingly wanting these AI flows, but some of these things are not super intuitive out-of-the-box.

So I think we want to showcase that. And then of course, you know, as we think about it from a deal making perspective and an overall strategy perspective, you know, governance, security and audibility are really critical to everything that we do to ensure that that sort of trusted environment of data site is extended into all these different work flows. So just I mean would love from your perspective, Raj, I mean what do you think is getting really excited about some of the things that are impacting deal execution in AI? There's so many, so many things that you can do with the tool in executing either a build of your data rooms, a launch of a process, all of the work flows that happened through the process, answering questions that are coming in.

And then on the flip side, if you're a buyer dealing, dealing with the data room and, and just working against it, asking the tough questions, running through your analysis and your work flows, whether that be customer retention data or HR analysis, all of that data obviously sits in the data room. It's unstructured data. And the AI has gotten really good at being able to parse through that data and, and address and find things for you that you might not be able to find on your own even, or it would have taken you hours and hours to find. And we're going to demo some of that today.

Alice is going to show us some of some of those work flows on both the buy side and the sell side. Yeah. And you know, we, we got to know each other about a year ago, met the team at Deal Max and struck up a great conversation. And ultimately we, we bought Blue Flame last year. I think we closed in July or something. So it's pretty amazing some of the things that we've brought to bear already from our perspective. You know, I really met the team, saw some of the things that you were doing and I was blown away.

We of course had our own organic set of capabilities that we've been bringing into the data site platform for like 6 or 7 years across the AI landscape. But I was really wowed by some of the buy side workflows that Blue Flame was bringing to bear and really kind of had this vision of, hey, imagine if we could take some of those capabilities and bring them into a native data site. Experience like this is really what we believe deal makers wanted natural language burying across large data sets. So from our standpoint, it just felt super comfortable and and very natural. You were Co founder, right?

You weren't expecting to necessarily get, you know, your door knocked on from Doug saying, hey man, I really want to buy your company. How did? How did you approach it from your perspective? You know, we knew obviously Datasight being the the biggest and best and most credible data room out there. We, we've used it in prior lives and we knew that we wanted to be embedded with that content. It's where all of the really interesting stuff in a deal lives. We knew our clients wanted that. They wanted to be able to access that data.

We knew the only way to do that really well was if we were really tightly coupled together, being able to replicate the permissions and the security that live within data site all the way down to the details, you know, what gets watermarked, what's allowed to be downloaded. There's a lot of intricacy in the in the security, in the permissions of a data room. And there was really no way to bridge that cap unless we're really tightly coupled together. We knew that the value would be tremendous, so we figured out a way to make it happen, and I'm glad we did. It's been a fun, funnier building together.

Yeah, it's, it's been absolutely awesome. So I guess the, you know, the fun question that we get to showcase today is, you know, what can AI actually do within this secure data room environment? And I think before we go into that, I think it's important to just set some context about what's going on within this because we've got a few different layers. You've got this sort of blue flame AI assistant, which we'll get into there. And then you've got this sort of MCP. Can you just give us a little bit of a one O 1, Raj, in terms of like what's what's working here?

How are these things interoperating? How are some of these capabilities technologically possible? Yeah. Big piece of what we've enabled with the data rooms is broad scale, deep and high, high fidelity search. And what that means is when content comes into the data room, we really want to understand what does this chart say? We need to understand what the legend, you know, how the legend corresponds to the bars that are in that chart. We need to understand logos that are on pages, charts, graphs, logos, All this stuff is really complex, but really important in understanding the context of the deal and in all of the highly visual materials that exist in a data room.

So a lot of what we brought into data site was the high fidelity parsing searching algorithms to work through that that massive data. What that means is now we can leverage that search either directly in the data room or directly in the Blue Flame platform against that that data room. We're going to show you both experiences today. So within the data site data room, there is now a sidebar, sometimes we call it Sidecar, where you have the ability to chat with the data room and that chat is leveraging Blue Flame behind the scenes to ask questions against the data room content. It's leveraging all of that, you know, high fidelity search that we built against the data room.

So this is not just a, you know, some of the agentic tools you see out there where it tries to search the file names and just read a few files to answer a question. This is actually looking through every bit of information that's in the data room to find Nuggets of information that might be buried in files that you wouldn't otherwise find. So you have the ability to do that directly in the data room with the sidebar chat. You also have the ability to go into the Blue Flame platform and do everything from create a data room to manage the data room, to ask questions against the data room.

And there's a number of different ways you can leverage that on both the buy side and the sell side that we'll we'll demo today. And then we just because we've been processing, you know, content for a long time at data site. And one of the things that I was really marvelled with was this sort of next level of processing and extraction capabilities that blue flame, you know, help bring into our environment. How is Blue Flame able to go into things like charts and graphs and pictures and org charts and and really make that information come to life? Yeah, We're leveraging actually vision models against a lot of that content to pull out, you know, all of the details that live live within that content.

Say over the past two years, AI models have gotten much better at being able to read that content. But there are still cases where if we have to optimize, you know, certain models do better against bar charts and certain ones do better against pie charts and so on. So it is it is very intricate data science work that happens behind the scenes to enable all of this. The result for, you know, someone who's interacting with the platform is when you ask your questions against the platform, it is showing you all of the places it's finding relevant search results, but then it's going ahead and answering it based off all of that question, all of those questions.

What we've seen happen over the course of the past, you know, 6 to 12 months is that the quality of those answers has become extremely rich, extremely high confidence and, and just frankly really good at finding the right answers by leveraging a combination of agentic search and this high quality semantic. Search. Awesome. Thanks so much for that. I think now let's just let's just get into it. You know, I love this sort of showcase in a diligence project. I think Alice is going to share a screen here.

Why don't we just dive right in and if you don't mind, kind of walk us through what you can expect now as a diligence user. And you have this availability of the date the blue flame AI assistant in the diligence project. Yeah. So we're going to cover a few workflows here. There are obviously many more that can be done. Feel free to drop in the question any workflow suggestions or workflow questions you have. But just to get started here on my screen, everyone will recognize the date site environment. In case you haven't enabled Blue Flame AI within your data room yet, you can simply do that by clicking this bottom at the top right here.

And when you do that, you'll be able to open more information and if needed, get in touch with your date site Rep so that they can help you add date Site AI to your VDR. If you created a new project, you'll automatically have the option to have that. So now I'm moving on to how it looks like once it's enabled, I want to start to showing you how you can leverage that to make sure that when you start your VDR, you have all your content organized and cleaned the right way. So here I simply ask the blue flame AI agent, can you help me just run through my in desk, the folder names, the document names.

I wanted to be very clean to that when I let buyers into my data room, everything seems very neat and they have an amazing first impression. So here the model has the ability to look at the existing names, but also the real content behind every document to inform how it should actually be labeled. And so that really helps me get really good feedback around. Well, here you're not necessarily using the right date because the date of the document is actually different, or you're not using standard naming convention for all your contracts or the date looks different. So it comes back with many different level of feedback for me that are very helpful into quickly pointing out the issues.

Whereas as a banker, it's typically a process that you would do manually scrubbing everything. And so that's time consuming. And now you really have this like level of feedback from a single prompt, which is pretty amazing. Another workflow that I really like. We've built this risk audit capability with the help of Blue Flame and they decide working jointly. And so here I'm just asking the model to look at the potential to create a risk report where I know that as a banker, you're typically going to be heads down into your deal and there are some oversight that may happen where buyers are actually going to be very focused on and you did not necessarily prepare the sufficient level of defense.

So here you really get this kind of third pair of eyes, extra person taking a look at the entire content of your documents, screening every single document that you might have shoved in there without actually reading every single line. And so it's going to give you a risk snapshot for both strategic and financial buyer if you want to. And it's going to look at very different aspect of your deal. It's going to almost like criticize everything it can regarding if you add back, for example, change of control clothes that have different type of risk around them, customer concentration for different vertical.

So it's really going to rerun a lot of the analysis and data available so that you can come prepared, get your defense where it needs, where it's needed, and then just open your VDR. And so here, although it might look like a lot of content, you can just then get that into simple table with risk buyer type defense. And then I'll put that into a copy and paste that into an e-mail. So I think that's a lot of work that has been done very quickly thanks to Blue Flame AI being able to just grab around all your content and and retrieve information from you.

And Raj, just from your like, how is this able to do such a high quality job looking at all of this content? I mean, we have a very large corpus of information potentially here as well as across data site. And I always feel that like Blue Flame has this innate ability to really understand things from a deal maker perspective. And I don't think that's accidental. It feels like it's been kind of by design. Yeah, that's, that's always been what we've been going after. The vision's always been how can we build for the prompt first deal maker.

So someone who wants to come into the platform naturally and that's where they go first to get their work done. What you saw Alice do here, you know, obviously could save you hours of time and you didn't need to custom up, custom create a prompt, a really difficult prompt to get to that. I chuckled briefly. Alice said thank you to the agent and then had her prompt there. Very natural language, it's able to just ascertain really well what the user's going for, what the, you know, the investment professional or the deal makers going for because we designed it to do the exactly that.

What we've seen happen over the course of the past 6 to 12 months is that the agent themselves, the agent harnesses have become tenacious is, is what we like to call it in the way that they go about searching for information. That last example Alice showed you, there was a lot of information that had dug through to generate that table of potential issues. That's exactly what you wanted to do It might have worked. I don't know how long that prompt took. It might have been a few minutes of work to go go do all of that, but that's exactly what you want You wanted to spend a lot of time working through all the information.

The agent harnesses have have become really good. I mean, we've designed this agent harness to be really good at reading through the VDR and understanding all the content and, and finding, finding all those potential issues really well just off the natural language query and it's. And it's effectively, I'm asking almost a pretty basic question, but underneath that it's like it's firing off, you know, dozens of additional questions order to like Orient its way through the data room, find the answer and like pull it out it. I love that sort of resilience that it must have in the models themselves. Yeah, from a technical perspective, it's leveraging sub agents.

It can kick off dozens of sub agents in parallel to read through content, to ask multiple questions at a time, to aggregate the tables of information you know. Again, tenacious, resilient. It will always work really hard to find the right answer for you and. I think what's great on top of that is that this is all done within your date site instance. So you don't need to drop any document outside of date site. Everything remains safely stored within date site and so that additional level I think is very important. Yeah.

I mean, we really have taken a lot of time thinking about the guardrails. We we are the trusted place where deals are made right. And so we wanted the ability to be able to take advantage of these capabilities, but in a super, super kind of guard railed environment. You talk a little bit more about that, Raj, I mean, how difficult is that? You know what, what would be some other approaches if you want to take things out of the data room, obviously that would create a bunch of risk and exposure points.

I mean really doing this within the four walls of data site is a pretty, pretty important thing for I think for our deal makers out around the world. Yeah, and it has a a a lot of value, right? The download upload process itself is clunky. It's also error prone, right? Sometimes you just have old copies of information. You haven't brought in the latest copy. You start asking questions, you realize that you got bad data. You ask stupid questions because you're working off off wrong data.

This is all just directly built in its native. It's fast. You can just directly go ask questions against it. The permissions obviously are really important. So that was baked in from the gecko. No one is getting access to anything that they don't have otherwise have access to. The agent is only working through what you have have the ability to see and actually have the ability to download watermarks or preserve. We provide even, you know, I think about it as a guardrail citation, right? The ability to understand where is this, this specific figure, this data point coming from and being able to go back to that source document to verify as you need to, or to call it out and, and you know any of your, any of your follow-ups.

So we think the guardrails obviously were paramount. That's table stakes. We had to make sure that it was getting that perfect. And then obviously on top of that, we wanted to build a lot of the value add functionality. That makes a ton of sense and it's just so powerful to have these capabilities in the platform itself. This is kind of what I always felt, you know, search should be right in the technology just never was there to allow for this type of interrogation, natural language querying and ultimately like getting these incredible answers right within the data site, data room.

Yeah, and it's not easy. I will say even with a download and upload into, you know, any of the LOL tools that are out there, you're not going to get the same level of tenacity with the agent or the same level of high fidelity. Search through the charts and the graphs and the logos. So replicating a lot of what Alice just did through the core, you know, lol, tools that are out there is actually not, not necessarily doable. You'll hit token limit, you'll hit, you know, a number of other issues in in terms of fidelity of content that's coming in and and the ability to search through it.

Yeah, because most of the if it's just the LLM, they're limited to the context window that they have. And with the blue flame kind of agent experience, you're really not limited, you're not bound by those traditional constraints. You're really able to look at 5000 two hundred 500,000 pages worth of information in a data room. Exactly it, you know, if you were to leverage some of the projects tools that are out there, there are limits on the number of files you can have in there, the size of those files. It doesn't directly index all of those files. So we we can obviously work against much larger data rooms or complex data rooms much better.

Awesome. So I think we're going to shift gears a little bit and maybe showcase the Blue Flame platform itself because this is part of the, the connectivity here is you've seen the Blue Flame agent sitting within data site, right, the AI assistant. And now we have this other incredible experience in the Blue Flame platform itself, which is leveraging the MCP capability. But it's awesome to see what other customers, if you've invested in Blue Flame and you have it as an enterprise platform, which we recommend for everyone, of course, you even get in more enriched experience. Yeah, absolutely.

And so we've always had this connectivity into date Site where our clients were able to query Date Site content from their Blue Flame instance. Now the addition that we're releasing with this MTP connection into Blue Flame is the opportunity to push content into Date site. So here the example we're seeing on the screen, I'm starting fresh and just want to start a new project without ever leaving Blue Flame. So I'm going to ask Blue Flame, can you help me set up a new date site project? And it knows that it's going to need a bit of context to help me as best as it can.

And so it's immediately going to ask me what's the industry of your deal? What type of deal is it, the size, where is it going to be hosted, which is obviously very important for our customers. And so just by providing this high level of context, it automatically returns Southside data room index that is scattered to my particular deal because as you can see here, it really came back up with some IT specific sections and and things that you'd expect to see in an IT services daily room. So that is great. And I can push it to data side, but I want to take advantage of the fact that all my data side data rooms are actually flowing into blue flame.

And so I push it a little and say, well, actually, can you look at this other deal where I really liked our index and inform from that what should be the final index for that new Pegasus deal, which the model does immediately. It looks at everything into that other VDR comes back with is a plan, and then once we kind of iterate together, finalize with a very detailed index that has all my main section. There's folders and everything prepare from a single push of a button to be accessible and then also provides the link so that I can open my Pegasus cell side data room within that side just to see that it actually did create all of that, which is pretty insane.

Like as a banker, it would take a lot of time to either move a clunky Excel spreadsheet into the the late side to have your index populated. You obviously need to think about how you want to orchestrate here. Here you can just leverage all your firm contacts from all your data rooms and build something very much tailored and all that from a single like natural language forms. Yeah, it's amazing how fast you can do things now. Yeah. I mean, and it's not just a matter of like in and of itself, I think getting access to a data room via blue fame or MCP and setting it up like, wow, super powerful.

And then you take it to a whole other level by doing a comparison against another deal. And you'll be able to dynamically operate in this blue flame environment, taking advantage of your previous work, your best practices, and then ultimately easing that setup for the project itself and doing it in like, I don't know, minutes as opposed to probably would have taken you days back. In the day, yeah, definitely. And another thing that is quite time consuming when it comes to setting up a date room is inviting parties. You're receiving names and e-mail addresses into different spreadsheets, emails, everything's unstructured and you need to manually push that into data site.

Now, the way it works with the MCP is that you can drop a spreadsheet, the models going to identify the role, the names and the e-mail addresses from the individuals. And here you can see on the screen, I pushed an e-mail list, it identified the right people, created the rules and then have the invitation ready to go to their inboxes. Obviously it's done for me to go into data site and make sure that they have all the accesses and that I can very much like keep control of that. We're not pushing that into the end of the other end quite yet because we feel that it's super important to make sure that the permissions are set up manually still at this point, but at least you can invite them and locate each individual role from a single prompt again.

So that's very helpful. I'm also conscious that having been in these shoes of the bankers, you don't always receive a nice spreadsheet with everything into an organized way. And you receive several emails in the same day saying, hey, can you add rush? Can you add duck and you? And So what I love with Blue Flame is that since it's connected to your e-mail system, you can actually pull the data from your emails having sit here and then push it into data side without ever leaving Blue Flame. So that's another way to really leverage the fact that all your systems are working jointly into Blue Flame AI.

Your CRM, right. I mean one of the big value points for Blue Flame is connectivity to all the kind of primary systems of record. So you know, you could be a banker that has ACRM connected, you're connected by Office 365. Like how is that working Raj, to enable, you know Blue Flame itself to have access to all these critical business? Systems, because we're connected to all those systems and we have proprietary integrations and all the major CRMS in Office 365 and obviously Data site and Grata, you have the ability to have the agent correlate data across them.

So again can pull information from 1, push it to another. You can do some pretty cool things there of, you know, who do I have in my CRM as potential buyers for this project who have not been, you know, set up in data site yet. And you can reconcile a list across across the two as well. Obviously Office 365 comes with e-mail and calendar access and you can automate quite a quite a number of things by leveraging the data room. With the Office 365 integration. You can create your process letters, auto send out your process letters.

You can have point people to, you know, specific files in the data room with links. So many things that you can just do by pairing these systems together with the agent. It's kind of how I think people have always wanted it to work. You just had to go to these different places to do the different things, and now you're able to almost sit in this beautiful environment and allowing the orchestration to kind of be at your fingertips. Yeah. There was another webcast we had done where Alice created a whole SIM through prompting, right, A 55 page SIM created through prompting and now you can upload that into your data room directly through the MCP connection.

Yeah. And I feel that another way to really benefit from this integration is around the process that comes when you prepare your data room. As a banker, you work with your client to make sure that they're populating the right information and that you're going to have everything covered. And so here in the in the screen we're looking at, I attached a data request list or IRL where you're going to have all the requests you submitted to your clients. You never know if it's really like the process of tracking what's been uploaded, what information is there, not there.

It changes for every single process, so it's quite manual. And here I just uploaded it. The agent's going to read through all the 241 items that I requested my client. It's going to crunch the entire data room to see what's in there or not and come back with a very detailed feedback. It's going to produce the material I requested to for me to run through these conclusions, which is the detail DRL with annotations, sources, page numbers for each of the different information requests as well as summary in a PowerPoint that can share to my client and tell them, well, here is what I need from you.

So those sets of documents are produced by Blue Flame. You can see here the IRL tracker as well as the, Sorry, it's just loading for a little second, but the IRL tracker in XLS well as the PowerPoint. And then on top of that, what I'm asking a blue flame is that it should put it into an e-mail that I can send to my clients so that I don't even need to move back, download the files, put them into Outlook or whatever apps you, you use, draft the e-mail and turn that out. It's already sitting into my draft folder and I can just push it to my client and they can easily navigate where they need to prepare and, and submit more.

So that's really a great way for me to leverage AI and save time while keeping all the traceability, auditability of everything you're doing within Blue Flame. Yeah, an incredible value for for the advisors and the clients, right. I mean, ultimately, you know, having the bank or other trusted advisor run a process for you, part of the the difficulty, you know, you ran strategy as well as you're trying to navigate who needs to get access to it, what files need to be provided. Of course, they're always going to be gaps, but being able to really focus on the missing pieces as opposed to all of the pieces is just crucial for customers and really allows you to have that optimal conversation, Kind of trusted advisor to underlying corporation.

Yeah, definitely. And we've covered a lot of Southside workflows today, but this is obviously something that is going to benefit our buy side clients. We just released within Blue Flame what we're calling spaces, which is a way to, on top of getting access to your, to your data room within Blue Flame, create a space around it where you can put your SharePoint data, your, any content really that is flowing around a particular deal or around a particular industry that you're focusing on where you can work in this close vault. Invite team members where you want to collaborate with them and leverage both the content of the day room as well as all the analysis that your team is working on.

So here you can see it's my homepage of my project. I love the fact that I have an activity thread and I can track who's been doing what on that project. You can here. I've been working quite solo, but team members will see everything everyone is doing if they decide to share it. You can add people here and you can see that. Then I have everything concentrated with my chats around that particular project, notes that I take. So that can be notes from a call one team member is having with a CEO, but then another team member is talking to an expert and another one to the CDD provider.

So you can just share all of that and then query your date room contact with this additional layer of context to really optimize your your work around the ideal. Yeah. And just and just to take a step back because I think this is so profound and we've gotten a ton of questions around this, which is really, you know, what we are covering on the data site side of things. And with Blue Flame, AI assistant was really highly oriented towards that sell side and many of the things that Alice was showing there again that sell side advisors. We're jumping to the other side of the coin here because you know, now you're really thinking about most of the interaction that happens around the deal is not necessarily on the sell side.

It's really around the buy side and all the interesting parties. So as a Blue Flame customer, yes, I get access to the data site, which is a super crucial part of it. But now I have my own space to operate. We've got this project and I can add so many different contextual components. I can invite my team members, I can invite my advisors, I can invite, you know, experts from third parties, etcetera into this space. And I'm tracking it really kind of working through the diligence from from my point of view, which I think is just going to transform how how buy side deals are done.

Yeah, absolutely. And I think that by side people love the data room space, but they also love having their things working in their own instance. They're creating a lot of analysis on top of the data room. They might want to leverage previous deal material as well to inform the decision they're making and the risk they're identifying. And so here it's really the opportunity to work side by side. You open a note on one side, you open a chat on another one or a document.

And everyone works with this close context that is empowered by by being. And I think what's really nice for the buy side is that it's a place to collaborate, right? The data room has historically been a place to share information. This is a place where I can go to my colleagues, work with my colleagues. As as Alice has up here, you could take your call notes. Everyone on your team can see that same set of call notes and that all feeds into the same context that's being used in the chats of this of the space.

So everyone is working off the same set of information. You no longer have these little silos of knowing what's going on or digging around, you know, SharePoint files or whatever it may be to find, find the internal context on a deal. Right, because you may be taking this to IC, right? I mean, and I think that's one of the great use cases within within blue flame is, you know, taking that all of this context, all of this information to that next level to to present to investment committee. Exactly. And getting getting to that, you know, ready draft of information Blue flame already has all of the context of this is how our firm likes to build PowerPoint decks.

This is the branding guidance around, you know, what we do for Excel models and in PowerPoint decks. So it just makes building that material so much faster and easier when it's already coming into the format and the style that you like. So we're going to go to the next portion of this or we're going immediately into some Q&A. All right, so I am going to read from the questions here. We probably don't have a time for everything here, but I think the most important question is Alice. How do I get the Blue Flame AI assistant on my day to site project?

So any date site project, you'll always have this button that I showed at the beginning of the of the webinar. It's a date site AI on the top right of your screen. Once you click on it, you can get more information around exactly how it works, what it's able to do, but also activate it or get in touch with anyone at date site that will be very quickly able to help you and enable it. That's for existing project. And then when it comes to new project, it's something that you should immediately discuss with the person at site helping you setting up a new VDR.

And I think what's worth noting is that you don't need to be a Blue Flame subscriber to leverage the Blue Flame AI assistant within data site. That can be something that you do on a per VDR basis if you so want. So desire lots of reasons to become a Blue Flame subscriber as we showed, but you don't need to be to leverage that. Yeah, awesome. And then I guess, you know, maybe the paranoid in me here, Raj, but how do we ensure that redacting redacted and or permission to content data isn't accessed improperly? So that's, that's part of the trust of data site, right?

You're using data site because data site puts, you know, top premium. Make sure that that's always right. And that's part of why, you know, we paired together, we wanted to do a build tightly together to make sure that we're never showing information to folks who are not permission to that information. We're never allowing people to download things that can't be download. We're always redacting information the same way. Translation still applies the same way watermarking still applies the same way that it always does. So we, we took all of it into account to make sure that we were putting out something that was safe and, and you know, adhered to all of the, the expectations that everyone has of data site.

And and this wasn't necessarily entirely new to Blue flame, right, because you basically we have to do the same thing from a blue Flame standpoint by respecting share porting permissions and content availability and visibility. Like this is almost kind of core DNA for blue Flame. And a lot of our team come from cybersecurity backgrounds, privacy and compliance backgrounds. And there's a big piece of why we knew Blue Flame, a big piece of what we knew we need to deliver as part of Blue Flame into this space, right? Just the sensitivity of the content is, is extreme, right?

Just as high as it gets. And we wanted to make sure that we were, we were protecting that. And then question here, which I think is super important is around audit trail. Like how do I know what has been asked? How do I know what's been presented? Like we want to make sure that we maintain this sort of crucial set of information around the deal so that there's kind of no, no dark spots in the room, if you will. Yep. And again, no different.

We wanted to make sure that we were doing things consistently with how the data room was handled in things historically, all of the queries are archived. We have the ability to surface that all of the file accesses still go through the same auditing and the audit trails still applies. Yeah. So Needless to say, kind of table stakes, right, We couldn't do this in any other way. We wanted to make sure that we extended all of that monumentally important kind of government's compliance auditability, just like everything that happens on data site that is just paramount for deal.

Success. Exactly. OK. Also talk to me a little bit about some of the advantages for sell side work streams who may or may not be a deal admin. Well, it's true that today we've covered a lot of workflows that are focused on the person really setting up the data room. So the team that is going to be in place to do that. But there are a lot of sell side individuals who are going to be added to data room and do easier focused work for VDD reports or maybe other folks at the bank who are less involved into day-to-day process, but still want to enter the day room and be able to understand what's happening.

And so I feel that this ability to question the content with Q&A, understand where documents are, is there any information that you might have missed? Let's say you're a commercial diligence provider, you're going to look at the commercial contracts, but there might as well be other bits of information in an IP folder that you might want to actually be aware of. So that's a very good way of orienting yourself and getting very quickly into a deep level of information for someone who's less into the the building with of the data room. Great context and I we covered this, but I think it's super important.

So I'll read this question aloud and maybe Raj, you and I can probably tag team this a bit, but what data site? MCP only versus when do you need blue flame AI assistant and then is the assistant included in the data site license? Yeah. So the assistant is that first experience that Alice showed today within the data room. There is a chat on the right side. That's a data site AI assistant, the Blue Flame AI assistant within data site. That is its own separate commercial terms on the BDR.

There's an extra, you know, piece to the SOWSOW or you can upgrade as Alice showed to get access to that. Blue Flame clients have access to that by default. It's enabled for them to to ask questions there. That said, they also have the ability to ask questions directly in Blue Flame and it's the exact same tooling behind the scenes. It's all going to the same place and running the same queries. At often times you want to be within Blue Flame itself because we have wider integration access. You have the ability to go out to your Office 365 and CRM.

In fact, set or cap bike here or what have you. So you can do a lot more across the ecosystem directly in Blue Flame, but you have the ability to leverage it in either. If you're a subscriber, you don't have to be a subscriber to to get access to that data site sidebar chat that we are. We are. That is the Blue Flame AI assisted within data site. Awesome. Yeah. So if you have A, and I think Alice covered this as well, but just to reiterate on net new projects that you may be engaging data site with, it will be an option to be able to add this as a set of capabilities.

And then if you actually have active projects, which we have 10s of thousands active projects before this capability really was available, we can actually add it to those projects as well. So any active yield that you have, you can do so either directly within the app itself or of course you can always contact either a service professional or a person in the sales organization and we can turn it on for you. OK, we got one more question and this I think is great as well. And maybe Raj can talk like what? What LL Ms.

are being used to create this magic? Yeah, great. Question. So that changes potentially all the time. As everyone knows, models are constantly leapfrogging each other. We leverage all of the best, best to breed models, open source models. We'll leverage, you know, whatever we need to leverage that can be secured the right way. And, and our data science team is constantly benchmarking models to understand who is doing the best at what in that at what actually matters. Some will do better at, you know, certain types of questions or certain types of content and we will get specific about what we point what to for, you know, particular circumstances as we go out to, you know, certain integrations like CRM or Office 365 in particular, we might be using different models for that.

Then we leverage for asking a question against data room content or for running the agent harness itself. Sorry, I can't tell you the exact single LLM because there is no exact single LLM. It is multi model by nature and that is intentional and the models that we're using for different things change all of the time. And part of the, I think the benefit to the user is you don't really ever have to think about it, right? It shouldn't be your job question. It shouldn't be your side. We got plenty of people that benchmark the models, test the questions, figure out what's best at what types of questions.

I'm asking one question. And really, the blue flame agent is kind of routing that, if you will, to a variety of different places to get the absolute best response possible. Exactly, and that is more than a full time job for a lot of people to figure out. Yeah, we're testing the models, we're doing performance, we're doing benchmark all the time. It's a crucial thing and we certainly take it super seriously here. OK, well, I think for that we'll have to wrap up. Thank you both for such an amazing thing.

This shift is amazing. Things are happening so quickly. I love your notion of a prompt first deal maker. I think this is just changing the way that deals are going to get done. We showed a lot of sell side use cases. We showed the blue flame AI assistant within the diligence project. Then we kind of jumped out to the enterprise blue flame experience. Again, you really got that same type of admin flow and we got a little peek into the future, I think on what we believe buy side diligence is going to look like.

We've got this sort of MCP availability, the enabled content and really all of this is coming together I think because our partnership, right, you can't do this type of groundbreaking innovation without being super connected across our strategic teams, across our technical teams. And I really believe like the best is yet to come. Yeah, it's. Getting better every day. It's been exciting to watch and it's been fun to build. So thank you for all the people around the world that were able to join us today.

Thank you, Raj. Thank you, Alice. As a reminder, this is recorded, so take a look for that on demand replay and please forward this on to your friends and colleagues. We'll probably back with future series, but this is kind of a wrap for our MCP or data site MCP series. Once again, I want to thank everyone for tuning in. Thank you my esteemed guests and really enjoy and take advantage of this next level of deal making. We think the best is yet to come. Thanks everyone.

Thank you.