Transcript: Datasite MCP for Claude

Good morning, good afternoon, good evening to those joining us from all around the world. Thank you all for coming and attending the first of an incredible set of series of webinars that we have. This is particularly focused on the Data Site MCP for Claude. It's the first in our series. So please join us for the remaining parts of the series over the course of the next couple weeks. My name is Doug Cullen, I'm Chief Strategy Officer here at Data Site, have been in the deal making ecosystem for a couple decades and I think right now is the most exciting time.

I actually oversee corporate development as well for us and actually joined acquired Blue Flame about a year ago where LS works for us. Before we get too far into the conversation, I just wanted to cover a few quick things, some housekeeping items. First of all, we want to hear from you. There is a ask a question button there. Please ask questions throughout that. We will leave some time at the end of the presentation to cover these questions and we really want to hear from the deal makers on what you want to know about MCP and talking about MCP specifically for Claude. Tell us what you think via our survey.

As I said, this is one of the new series. This is something of interest to deal makers around the world. Then we want to do a lot more of these types of series. There are additional resources located in the console. So couple different documents about MCP, about data site, some may be about blue flame as well. So please check those out. And of course, just so you know, the session will be recorded so it's available on demand. If your colleagues didn't didn't get a chance to join us live, then please forward it around and encourage people to take advantage of these new capabilities.

And then, you know, any webinar would not be the same without a quick legal disclaimer. A reminder, all opinions expressed are our own and in no way reflect those of or not necessarily those endorsed by data Site or Blue Flame. So with that, let's get to the program. Alice. Welcome Alice as Marion is a product strategist and is currently with Blue Flame AI. Would love to just get a little bit of background about you Alice. How long you been a Blue Flame? What were you doing before you joined Blue Flame?

So I've been with Blue Flame for six months now, so it's definitely been a very exciting time to be part of this AI ecosystem. Before that, I was in investment banking and private equity for eight years. So great having the opportunity to bring my past life experiences into this AI ecosystem. Yeah. So super important, we're trying to sort of bring our practitioners to the forefront, super important how we think about deal making. We do think about it as a both set of technologists as well as having been there, done that throughout our careers.

And so we'll, we're going to be really trying to bring some of that to life to really inspire you as deal makers on how to take advantage of these next set of technologies. But with that, like, let's just take a step back and we will get into the demonstrations. Let's think a little bit about, you know, how have you been reflecting on your journey at at Blue flame? How is some of the technologies really started to change the way you think about how deal making gets done today and then into the future? So it's been really exciting to picture our customers experimenting with AI, bringing in more and more technology within almost every workflow of the life cycle.

And so for us, really seeing people wanting to make AI very useful, practical, easy to use, but also maintaining total compliance and governance within their systems has been such an interesting question. So really the future of AI within the deal making is going to be how you can prompt drive a lot of what you do while maintaining absolute safety and governance within your systems. Yeah. And it's really a fascinating time for us. We actually launched our first MCP partners to data site. For those of those of you that are familiar with data site, we've been a bit of a closed ecosystem for a long time and we felt like we had a massive opportunity actually at deal Max to launch our first MCP server out connecting of the various different LLM.

So, you know, within that we did some videos with with Raj, the, you know, the founder of Blue Flame and he introduced this concept of a prompt first deal maker. I mean, how do you think about how deal making is involved and what does like a prompt first deal maker mean to you? Well, that's really interesting. And honestly this MCP availability for the site is really powering all our users to interact with their data rooms and bring together the content and the preparation of their deals from a single prompt. And so we'll be looking into it today within more practical workflow those, there's a lot of use cases that will apply to this MCP.

We'll cover a few of them. We've built a lot of skilling and putting really some gathered context for our users to use it from the easiest prompt possible. But yeah, it's really, it's changing and a lot of tasks that were very manual and time consuming are gonna be accelerated significantly to leave a lot more time for the real interesting part of the job. So very exciting overall. Yeah, I think one of the ways we we talk about it is MCP gives us this opportunity to to really introduce this sort of layer of of governance. And I know not everyone gets excited about talking about governance, but one of the things that's really paramount we think to effective deal making is this opportunity to leverage and build on the trust that a brand like data site has in the market.

Really make sure that we're maintaining permissions throughout that building on that sort of framework of confidentiality and really extended to the point of creating that audit trail and ultimate the confidence of deal makers because people certainly entrust us with some of the largest deals around the world. And so we wanted to make sure that people around the world knew that that as we extend, you know, our data site ecosystem to providers via MCP, we think that it's a super important thing to do so in a in a rather governed and kind of risk compliant way. Sorry. And that's exactly where Blue Flame AI really brings in this value.

We know that date site customers choose date site every single day for having their data in a very secured environment. And so having Blue Flame query this content and this context is the optimal way of maintaining all of these security layers, traceability, auditability, and we'll get into that in our demo, but that's the best way to bridge between an LLM provider and they decide content by bringing blue flame into the equation. Yeah. And that's where Blue Flame for us sort of acts as this layer, as Alex is saying, Alice is saying in between the data site, data room content and the LLMS.

And this is important because, you know, one of the things that we loved about Blue Flame is the kind of primary focus on, on deal making. And really we believe that that is a a secret ingredient to great prompt first deal making moving forward. But with that, you know, in the spirit of of of show, and I think we've been talking a little bit, why don't we get right into some of the demonstrations? Sure. And of course, we're doing this live, so hopefully everything will go well. But why don't we just pull up some of this?

You're going to open up Claude. It's got MCP access to the data site and to connected things. You know, one of the things I think is really critical is when you get this huge volume of content, no matter where you are, and you're really thinking about initiating and setting up a data room from the very beginning. Can you walk us through some of the powers that that Claude brings with that blue flame layer and ultimate ultimate connectivity to data site? Totally. So here, we're already connected and now we're just going to be showing you 4 workflows.

There are obviously a lot more examples of use cases you could be using by leveraging Blue Flame into your data room through your MCP connectors. Feel free to ask in the Q&A questions if there are any workflows that you would like us to discuss. We'll review all of that. That's very helpful for us. I connected here my data sites through MCP connectors, which you can see at the bottom from the plus button. And then I also enabled blue Flame, which is going to be able to enter the content of all my data site files and really absorb and reason around the content of this document, which is where the real value stands.

So the first workflow is really when you set up your data room, you're already being and during the smart environment where automatically the agent asks you a few questions to understand the context of your transaction. So it's going to ask you about what type of deal is that, what's the industry of the deal you're being covered, what's the size, where is the data hosted in terms of geography. And so that automatically prepares your deal into the data site environment and the model will come back with a suggested index. So this is something that we have been shipped within 8 skills that cover 8 different steps of the workflows and that we've really gathered to our audience because we understand the pain of some data site and data room interactions.

And so this is really accelerating that. Here, for example, I have a suggested index that covers 12 sections. Once I've reviewed that, I can just provide simple feedback. So in that particular case, I wanted to remove a section and a subsection. The model understands my feedback and we'll then once I've approved it, we'll push that into my data site environment. And so here it is, my project Angel is live and 155 subfolders have been created. It's crazy to think that this was just done in a few seconds. Prior to that, I would have had when I was a banker, I would have had to create all these folders manually, make sure there was no typos, that all the names were consistent across the 12 sections.

And so this is now completely accelerated. You just need to come back with your comments, come back with your reorganization, and this is all set for you. Yeah. So just to take a slight step back and we've sort of accelerated this a bit for the purposes of webinar, but you know, we are listed as a connector within the clawed ecosystem. So as you if you have a data site login and if you have the availability on your clawed desktop or clawed application, you can connect right into data site. One thing to note is we are always respecting the permissions that you have in terms of accessing your files.

And as you're seeing, we're opening up the ability to just create a data site directly from your cloud environment. And the other thing of note is we will be talking about things at a slightly different level, which this data room that we have or the data site has been really created with AI empowered content being highly processed and available via the Blue Flame AI assistance. So some of the things that you're seeing here may or may not be available on your project, but we're trying to give him paint this picture of availability. And I think this is so powerful because as Alice was saying, really if you had to do this previously, maybe you had the folders, maybe you had an Excel with the folders, but you're really being able to do this.

And we're able to do this specific to the type of deal, transaction type and or industry to really power some pretty amazing things. I think the next thing you're going to do, we got these sort of folders up there. We've created the index. You know, what are other some of the things that you may have been doing as a banking over long weekends or perhaps late at night in preparation for getting this data site or data room set up? So the next step in your workflow, typically you have your data room set up, You're going to start wanting to incorporate documents.

Most of them you receive from your client. And the client let's just say are not going to spend a ton amount of time into making sure that the naming conventions are respected, that any scan document doesn't read as scan 002 and so on and so forth. And so having a very clean a pass at renaming all your files is something that is cumbersome yet extremely necessary, obviously, but kind of requires you to open every file, make sure that the name ties to the right here, the right quarter. So that's complicated. And now by enabling this AI into your data room, the system is going to be able to 1st get a first pass at making sure that all the years and dates are being applied consistently.

When you're referring to the company name, it's always referring to it. Within the same spelling and and wording. You're going to have the ability to flag any duplicated names extra. And so here you can see how the model went and just by reading the file names, suggested changes to each of them. However, as you pointed out, this is not leveraging any of the content within the files. This is just cleaning up existing file names. What you really want to me to really replicate what you would have done as an analyst or as someone working on the deal is to really look into the content of this file so that it can intelligently provide guidance regarding the renaming I've put here.

I use cases that I think is quite speaking to the capabilities here. I want. I wanted all my contracts to have the same structure to be the name of the party that signed his contract and the year at which the contract was signed, which is not readable. So just a simple document name. So Blue Flame AI is enabled. It will safely go into your data site, read all the information with no document or any information ever leaving your data site ecosystem. And then with this data reason as to where are your contracts?

What are they? Are they employee contracts, Msas, vendor agreements? And how do I rename these so that they're consistently labeled and just in a few seconds and just with a few prompt, you can see here the model batched down between type of contracts and rename everything and I just need to kind of agree with that and it's just done. I mean, and this is not to be overstated in terms of the power that something like a blue flame and and and Claude come together in this great marriage because I've been in many a data room through my life.

And I'm sure we've all encountered data rooms that have poorly named folders. And then once you get in within the folders, you get even more poorly named folders. And then maybe you get subsets of documents that aren't properly named either. You know, many I book 08 dot XLS have I had to click into and look in order to try to figure out what year is this from a financial operating perspective. And so here you're demonstrate such a valuable sort of light touch in terms of, hey, let's make sure there's consistency in terms of how this document has, but we're going one layer deeper of value and presentation, sort of looking into the content itself, extracting key components like the type of legal document and then ultimately the year.

I mean, I think that both accelerates the set, the setting up of the data room, but I can also imagine you've been on the buy side a lot. I mean, what have been some of your experiences in trying to sift through massive amounts of content in order to find the information that you need to get going? Yeah, absolutely. And so really having this ability to enter space as a buyer and a reviewer and automatically seeing the level of care that has been put in place, the work that has been done by the banker and their team to have the best buying experience, he's already setting you up for a successful process.

And so I feel that this is value add from the person who's gonna have more time to think about their deal preps, think about the content of the day room rather than being stuck in the nitty gritty. But also on the other end, as appointed from buyer standpoint, entering a space that feels organized, clean, where you can easily identify the data you want, the year you want, the name of a particular customer or vendor that is clearly labeled in a contract that's already setting you up for success. So that's. Great value and I always think that the the quality of the organization, the quality of the data room is a reflection on the quality of the process and ultimately the underlying asset.

So I think from the preparation side, on the sell side, it's super important to understand the documents. Ellen's are very good at helping us do that blue flame even better organizing the content in a very digestible way, allowing you to really get to what you're looking to accomplish. An ideal which is typically you know, looking to try to understand what is the underlying asset. Is this something that is consistent with your investment thesis? Is this something that is additive to your corporate portfolio? Really trying to get through that initial phase of diligence in order to figure out is this something that you want to move forward with?

But on that side, I think the next thing we're going to talk a little bit about is let's talk about Q&A, one of the most probably painstaking process parts of the process. What are some of the things that you've been able to leverage via MCP and via blue flame to make maybe Q&A a little bit more seamless and effective and efficient? I wouldn't say a little bit more, I would say immensely more. But yeah, so with Blue Flame enabled, having the access to all this content being aggregated, reasoned upon, and queryable in an unlimited way is super helpful.

As a banker or someone who's preparing a data room, you're going to be able to track the information request whether the information has been provided or not. And you're going to also be able to populate questions, whether they're from your vendor diligence providers before launching your process or just further down the road as you start receiving unstructured questions from different buyers and all their advisors. It's all flowing through e-mail. It's hard to really track. And for each of these, you have someone from the South side team pre populating draft responses, then going to management team for a sign off. And so that's a long process that here you can submit your question to the LLM.

And because blue flame is layered in with all these skills that we're bringing together that know how to respect a banker tone, know where to locate information, know how to really provide the right source and level of confidence to the reviewer. Because obviously here, everything we're showing is not that's replacing any human work. It's more at enabling and empowering our users to have this layer of human review, human overarching view here that is just accelerated and and simplified. And so here the example we're looking at is uploading AQ and a tracker, but that could also be a data request please and RL.

Everyone has their different references, but you feeling an unstructured set of request and the model understands what they. They are and what it's supposed to do. So it's organized here. It set them up by workflows, legal, tax, technology, etcetera. Found the right information within all the content of your VDR and then pre populated responses and sources. One thing I'm very adamant on is the 0. Hallucination. And so the skills really prompt the model to be highly transparent about its ability to respond to a certain question. And so you can see here that of my 7 22 question, the model clearly tells me I, I'm confident about 51 of these.

For 20 of these, it's partial and one of them I couldn't. You then have the option to review that, whether it's in an Excel tracker of or a dashboard. And here when I open my dashboard, I have all my questions with their level of confidence from the LLM. So as a banker, I can just jump into this where the lowest level of confidence is. And then when I open it, I have the draft response leveraging here. It's an AR bridge. It leverages the customer revenue cube and the financial data and all my sources with the VDR index, immense time save.

You can just cross check the information, check that the document reference is right and you have all your Q&A already have the first pass of responses. So that's a massive safe time. And this is, I don't have to tell you, but probably one of the most crucial parts of the process because we've got these questions, whether you're on the buy side seeking answers from the sell side banker or a different advisor sitting within the middle, you're doing your best to involve all the subject matter experts around the organization in order to answer this. And with with really this capability, you're able to query the content itself, the content gets cited and you're sort of putting together a confidence score based upon that.

So really taking potentially 5600 perspective questions, narrowing in on probably the most ones that need a little bit extra attention. And I've also heard bankers really doing this preliminarily. So to get familiar with the content, really running this almost as a simulation, what customer questions do we anticipate to come? Getting familiar with that content and almost preemptively looking at what queries may be coming up to get yourself even more prepared. Yeah, which is a great transition to our last workflow that we'll be showing you today. We did the pre launch readiness.

So this is something that we felt as old practitioners would have been really helpful when you're about to to push live on your date room. You also always have this moment of stress and it's an anxiety to think, oh, is there anything that actually doesn't die? Is there a document that is corrupted? Is there any information that shouldn't be there? And so we packed this skill that we call pre launch readiness that will cover three main elements. The first one being a gap analysis. So for each section, it's going to have a sort of reference and know if you might be a bit light on some topic.

And so you will kind of prompt buyers to immediately react with information and additional request. So that's being looked at. Then the second one is a document quality. So it's going to look at any document corrupted, any blank scanned, any unsigned contract, more importantly any PII information that has been not reducted and available in your data room. And then the last section is a risk review. So we put together a list of potential risk for each of tax, finance, tech, IP etcetera. And so the model and blue flame are going to look at your content and cross check any of these risks and assets.

Is there anything that is going to kind of prompt the buyer to think about potential for the assets you're presenting? And so all of that is treated and then available into a Word document here where you can see kind of the overall context of your project, the recommendation of the model, and then for each of these section where it sees the most need for attention. I think that as an old practitioner, this has, this would have given me an extra layer of comfort. It's like having an extra person in the room, an extra pair of eyes that really gives you the confidence and the last mile before pushing press.

So I think like this is another great way of leveraging the flame within your data room. Yeah, very powerful. We've always talked about sort of data site broadly as an extension of your of your deal team and I don't think that's ever been more true than it is right now. Real quickly and then we'll go into the Q&A. We've got some great, we've got some great questions here. So I'll be able to get to hopefully a few of them. Can you just quickly cover Alice, the difference between maybe a connector and a skill?

Because we've also taken liberty to publish specific deal making skills into the clod environment. So can you just cover quickly the difference between connecting and skills, and where can people find the skills if they're looking for them? Absolutely. So the way this works is that whichever LLM you're connecting your MCP into, you will rely on it to have access to this indexing and names and then do the reasoning. When you enable blue flame within your video, blue flame is going to do the work of reading the content and analyzing all of this content.

Now when you add the skills on top of that, you're really providing guidance as to how each workflow should be processed. And so you're removing any risk for your LLM to not read the information the way it should and provide guidelines and guidance for the model to do it the way your firm or yourself would expect expect it to be. So how we build these skills is really thinking about buyers and how like the pitfalls you want to avoid, the information you want to make sure are surfaces and triangulated together. That's really add additional value to your work to your work flows.

Yeah, awesome. So kind of the superpower is the connectivity between the data, the data room into the MCP environment via blue flame as well as these skills. So you can find these skills and our GitHub repository searching for those. You can add those to your clawed and that will give you the benefit of of our deal makers having sort of pre built a several of these based upon some of our experience. So OK, we got a lot of questions. We've got not as much time. The best question I had was is there going to be availability of a recorded from Jesse?

Yes, this is being recorded. It will be available. Please access it, pass it along. Please. Let's propagate and help build more prompt first deal makers around the world blasting through things. Okay question, do you anticipate data site MCP for Claude being used outside of IBS? Such as consulting companies, being able to query data, site project for specific people's pieces of information. Totally. So we are fully cognizant that we don't want that to be just for our banker clients here.

This is going to be available to the reviewer side. So buy side and all of their advisors and as a banker and as you on board more advisors or even your client, you'll also have the ability to give anyone who has access to a date side account and LLM to get access to that. Yeah. So hyper focus here on more of a sell side workflow, but we will do probably some future programming around the buy side. There are a lot of questions on what is available. So there's a whole set of capabilities if you go within your clawed connections environment that are available to you if you were on the buy side or the sell side, in other words, an administrator or a reviewer.

So you can seek that again. One important thing to understand is the the project itself must have the Blue Flame AI assistant enabled, which is something that the sell side would set up in order to extend a lot of the powerful search capabilities to be able to look into the document there. So we don't have a ton of time talking that. I encourage you to reach out to Data Site via any of our channels and we can walk you through in great levels of detail or maybe I'll do some follow on content around that. But this is sell side focused. Just to avoid the doubt here, you know 88% of the viewers of Data Site are reviewers.

So we have a lot of familiarity with these workflows across the entire deal making community. This one happens to be there, but let me see if I can blast through one more question. Let's see. Let's just go back. So does batch uploading question lists by function or other segmentation yield better responses by managing context? I haven't tested that, but I don't expect it would. In any case, whether you batch submit your questions, just the tech ones, the LLM and Blue Flame will always make sure that there isn't any other document or information available in a section that is not specifically labeled technology.

So even that he's going to do the work of almost like scrubbing every single information for any question. I don't anticipate it might obviously accelerate in terms of timing, but it wouldn't necessarily get you better outcome. Yeah. And I would just offer as well that one of the powerful, this is probably the worst these models will ever be in terms of our interaction ability to connect to data sites. So I anticipate a lot of additional functionality developing capabilities to be able to develop. We think context is super relevant. And then there's kind of we feel also at the center of really understanding these workflows as well as anyone out there.

So with that, we're at time. Thank you for joining us. This is our first in a series of webinars. So I think we've got a couple other programs coming. So check out the recording. Make sure that you want to become a prompt first deal maker. We certainly aspire to be prompt first deal makers. We've been utilizing the capabilities ourselves and I'm marveled every day about how much better things get. Make sure you understand that this is a true leapfrog. We think the models are very accessible, the conduit within data site make sure it's quite secure, compliant and and remains audible.

So hopefully we've we've earned your trust through the years and we certainly want to maintain that moving forward. Well, Alice, I want to thank you for joining us and bringing to light some of the capabilities. Of course, thank you for those around the world that joined us for this webinar. And then we've got a little bit of a announcement at the bottom around upcoming webinars. So I think the next one will focus on a different frontier model, but a lot of the the content will be somewhat similar. But we'll try to learn and hopefully make sure we're giving you what you want out there.

So thank you for joining us in the next level of deal making. Thank you Alice, and we look forward to seeing you on the next webinar. Thanks everyone.