Why Datasite Stopped Building Its Own Parsing - Adit Abraham, Reducto & Raj Bakhru, Datasite

0:12 >> I'm personally really excited about this talk. just by way of quick intro, I'm Adee, I'm co-founder and CEO at Reducto, but most importantly, we have Raj here who is the global chief technology officer at Datasite. the reason why I'm excited, is I think Raj has probably one of the most interesting viewpoints for AI in that he founded company very early on in the vertical AI space. got acquired into Datasite and then got to see both like subsidiary within Datasite to think about Datasite as a whole. I got some of Raj's stats before this talk, where something like 60% of all transactions over $100 million happen through Datasite.

0:49 >> That's correct, yeah. >> Okay. if we're making a leaderboard, trillion plus tokens per year, I'm sure you have plenty of other cool numbers, but the goal for today is to make this conversation. We'll talk a bit about Raj's journey, some of the problems he's gone through, and then we'll try to open it up for Q&A as well for whatever you all are curious about. Sound good? Cool. maybe to start, do you want to just walk through that arc and what it looked like behind the scenes?

1:12 >> Yeah, for sure, appreciate that. good to meet everyone, Raj Bakhru. my background's as a technologist, so I spent my entire career in development, started my career at Goldman, Highbridge, Kepos Capital, was building research and trading systems for quant funds and all sorts of fun things. Started a security firm that I sold to a private equity back firm, ended up running M&A and corporate strategy for them. And then started this vertical AI solution called Blue Flame in the M&A space, because we sort of knew that the impact to unstructured data was going to be pretty pretty big. so we were building out for about a year, year and a half, and then Datasite approached us to acquire us. and we started working with Reducto actually while we were separate, so before Datasite had acquired us, we were small startup, we were scrappy, we built a lot of our own parsing and Doc Pipeline and ingestion pipeline.

2:03 had a great team, a great CTO, co-founders. We were trying to save every dollar we could. so we when we built all of that, we're like, "This is great. It's working." Until it did. I mean, I'll talk a little bit about that journey. and then as we got brought into Datasite, we were acquired obviously very early on. Our team was about 50 people at the time we got acquired. the first thing that Datasite wanted to do with us was bring us into all of the data rooms. And if you guys aren't familiar with the data room concept, data rooms are basically where all of the transaction documents get stored when you're selling a company. So, as I deep mention, something like 60% of all transactions above a reasonable size threshold, 100 million, happen on Datasite. It's a place where people, bankers primarily, are sharing all of that data with private equity firms.

2:50 so it means that there's a massive unstructured data on Datasite, right? Billions of pages of content. Every major bank is using it. Every private equity firm is using it. Every diligence provider is using it. Over 500,000 monthly active users on Datasite accessing that content. and that meant that adding AI solutions was obviously top of mind for the board and everyone else who was accessing the platform. Users were asking for it all day and day out. We had a great data science team from the days where my CTO co-founder and I sort of scrapily built the ingestion pipeline. We had obviously moved on to Reducto, recognizing that we weren't going to have the level of quality, speed, recall, cost that we could get with Reducto. And I can talk about some of the numbers that led us to that that decision. and why that panned out today with Datasite scale.

3:41 But we needed to build fast. We needed to get all of the data rooms that Datasite had, 55,000 data rooms a year, parsed, ingested into our vector database so that we could build out our graph rank platform and answer questions within the data room that users were submitting at scale. so that was a problem at hand. How How How do we build this into the VDR? They'd never done anything like this. They'd never taken their data their content out of their Azure platform.

4:08 Historically, it's you know the walls were high around the data rooms as you can imagine. It's the world's most sensitive data. All of the most material material non-public info out there sitting in data sites virtual data rooms. so we had to figure out a way to do this securely. We had to figure out a way to do it in a place that it complied with all the regulatory compliance regimes that our clients have and pass on to us. All of the certifications, the ISO certifications and so on that that we had. so we spent a lot of time with the Deeds team in figuring out how to get there, how to make sure that it all of the content remained protected and secured and get us all comfortable with leveraging Reducto's tooling.

4:51 The reason that we went with Reducto's tooling as I sort of alluded to is we basically had to one move fast, but two we did a whole bunch of benchmarking actually with our data science team around sort of our scrappily built tooling for extraction and parsing and ingestion. And what I'll say about sort of that landscape is that it's all edge cases. Like literally is everything is an edge case. I remember getting, you know, after we had built this we were working with some of the world's largest private equity firms and they would send to us examples where our reg platform got a question wrong. And actually Carlos here will will remember some of these.

5:26 >> >> you'll dive into it and be like, well I got it wrong because the shade of blue on the legend of this pie chart didn't correlate perfect perfectly and the LLM just read it wrong even though we used the best vision model in the world. And actually if you were to pass that same thing as a pie chart or that pie chart as a bar chart to that same model it would have gotten it right. It just the devil's in the details on all of this stuff. on Excel sheets, we had to deal with merged cells. And as you guys know, finance spreadsheets are the most complicated documents in the world.

5:55 Like it is hard for a human to understand these things. so getting the models to actually understand the way to parse this this content out and understand the content was very very difficult. so we found that we were just spending an enormous amount of support time dealing with all these edge cases. And if I sort of think about the buy versus build trade-off, what do I want my limited set of high-quality engineers working on? It is not the support cases of making sure that we're extracting extracting content properly when that's already been solved. Like you know, rebuilding the wheel doesn't make sense. so we we got a tremendous amount of benefit and leverage out of saying let's let's pass that on to Reducto. Let's let our engineers work on value-add revenue-generating business problems. Focus on building agents that our clients care about executing on the interface and the rag platform.

6:48 building out graph rag was actually a big thing for us and we leveraged the outputs of Reducto in that process. So we wanted our data science team focused on that, not on how do I get the right data out of a spreadsheet and dealing with all of the pains that we experienced on that. Then you you run into the pains of like if it's an XLSB file macro-enabled, if it's a template file, it just it's endless.

7:11 Literally the end edge cases are endless. So we're very thankful to Reducto for solving a lot of those problems for us. >> I appreciate that. at this point we've had like a year of context, but I think one of the most interesting things about your journey is that you were very early to the vertical AI app space. and the problems that you work on are hard for many of the reasons that you mentioned, but also like things beyond that. and especially earlier with the model landscape as it existed, I'm sure it felt even more insurmountable.

7:42 so I'd love to start maybe just by hearing a bit more of the pre-data site journey of like how you got started with Blue Flame, what you were hoping to achieve, and how joining Data Site has kind of changed that. >> Yeah. so when when we launched our our startup startup, we had started we had sold the startup very early on before. The last startup, cybersecurity startup, we sold a year in. And we started this one saying we are not going to sell quickly. We are going to see this out.

8:07 And it's going to be a long time and we're going to be a unicorn and do all those fun things that we wanted to do. So, that was that was the the initial state. I brought in a lot of folks that we'd worked in worked with before and that's one of the nice things of being a second time founder is you kind of know the network, you know the people you want to bring in. So, we were very fortunate to bring in a lot of those people and start with a lot of the people that we knew and trusted and we could yell at each other and still be really good friends at the end of the day. and we knew each other's families and all that. So, that really nice experience to start as a second time.

8:38 >> >> We also had the ability thankfully to fund ourselves to a large extent this this second time. So, we bootstrapped for a while and started building. Now, that again made us do some things that might have been a little excessively cost-sensitive and not the most optimal decisions, but that's what you do as a startup and when it's your own money especially. So, we had a really great experience building that out. we were actually going to do our first VC round. We had our LOI signed, term sheet signed.

9:04 We had done sort of the dating process with all the VCs out there, the Sand Hill Road walk and all the New York ones and we were you know, a week away from sort of final final signatures and there was additional capacity on our round and they said you should go you know, see if these folks are interested and so we we approached Data Science and we're like, do you guys want to put in 5 million in this round? And we demoed and showed them a bit of what we were doing and they said to us actually, we just want to buy the whole company.

9:32 We're like, okay and literally happened over a dinner. Like whatever meeting in the office, subsequent dinner that night and then they told us that. So, we we very quickly sort of figured it out. And the reason that we thought it was really compelling was if you know, this was about a year and a half ago now. At that point sort Cloud and Office Suite hadn't taken off. You sort of have to go back to remember where we were a year and a half ago. It feels like forever ago and the world was entirely different. Agentic coding hadn't taken off to the level it has now.

10:04 So, we knew that we had to raise a massive amount of money. Our competitors in the vertical AI space, of whom worked with Reducto, had raised hundreds of millions of dollars, literally. so we kind of knew that if we're going to remain competitive, we were going to be raising hundreds of millions of dollars, we would be taking masses mass dilution in doing that. we also knew that staying competitive against the frontier models was going to be increasingly difficult, particularly as they were starting to launch vertical strategies. And at that point, sort of OpenAI for FS and Cloud for FS hadn't been fully announced, but there were some rumors around it. They'd made some some ins- insinuations about it. and we knew that just to remain competitive and differentiated, that we would have to bring in new types of data. And to us, the VDRs were this incredible valuable resource of prop data that had never been opened up to anyone in the world, and we would be the only ones with access to it at that time. So, that was super compelling.

10:58 Datasite also owns a private company database firm called Grata. Has about 20 million private companies in its database, has transaction data, contacts, etc. Used very heavily in private equity and banking worlds for, sourcing and business development and origination. So, how do I find add-ons for my platform portfolio company? very classic Grata type query. That data would be brought into a BlueFlame as well. So, now we had these two really nice proprietary data sets feeding us in a vertical AI space where no one else would have that. Really nice and differentiated. And that's played out really nicely. So, over the over the course of the last year and a half, we've been bringing those really tightly together and that's that's been a really nice story for us to combine engineering teams, combine data, combine solutions.

11:45 and then we actually benchmark that. Like, the the ability or the the fact that we brought the data closer to the models saves on token costs, it saves on run run times, and increases quality of what we're doing. So, that's been a that's been, quite a nice thesis to see pan out. all of that data, obviously, requires scale. So, that's that's again where Reducto comes in and helps us with a lot of that. Ingestion processing and and so on. Datasite over the course of the last year and a half since we've joined them has grown, I want to say about 40% top line.

12:18 so just the amount of content that's coming into the platform is is growing pretty quickly and pretty massively. the demand on our AI solutions have gone up. So now people aren't just saying I want to ask questions against documents, the agents are obviously iterating against those documents, doing much more fanciful diligence analysis, or generating PowerPoint decks, IC memos, and so on. so it's pretty fullsome suite of what they can what they can accomplish with the solution together.

12:44 >> Yeah. it's an interesting position to be in in that I I I think you have one of the most compelling data sets in the industry. you're in a position now where obviously it's a global workforce. We were talking about all the different offices and all of that. and model capabilities have gotten a lot better. so more broadly like how do you think about what you invest in internally versus what you build and buy externally as well?

13:09 and also just like what sorts of things are top of mind as you think about the coming year? Yeah. great question. So we think a lot about the build versus buy, right? We we work with a lot of vendors. We spend a lot with a lot of vendors. and that's an intentional decision. if I think about what I want my my most talented people working on, it's not things that vendors can easily handle and are dedicated to handling and solving every day.

13:36 it's really hard to find really high quality good engineers, right? The fact of the matter is where everyone in market is trying to hire the top tier talent of engineering talent right now because what we're seeing, what you guys are all probably seeing it is with AI coding, the folks who get the most leverage and value out of AI coding are the folks who have really strong mental models of code bases, really understand engineering principles, have done it for a long time.

14:00 so they've all been 10xed, you know, over their normal 10x with AI with agentic coding. The middle layer, so-so. the bottom layer is actually getting a getting a lot of leverage and now they don't they don't sort of have the burden of trying to figure out documentation that doesn't exist in all of that. The LLMs can build that dynamically for them. so we're seeing sort of a barbell effect where we want to hire really really strong talent and really junior talent and build that up.

14:27 where I want those people working is obviously not on support cases. It's not on things that are already solved. it's on the hardest and most pressing problems for the business. At our scale, so Data sites not a billion-dollar top line, but general range of a billion-dollar top line. at our scale to grow 20% a year, which is our ambition or board's ambition, we need to be generating $200 million of revenue incremental revenue every year. And if you ask yourself how you're going to go do that, it's going to be by putting new AI products out in market, leveraging, getting on top of token flow, expanding solution set that you're delivering to your clients.

15:08 reinventing the wheel is certainly going to get in the way of that. having internal teams trying to iterate on some of the existing solutions that are that are already out there and deal with the support burden of those is not the best use of my talent. I have about 250 engineers in the org. So if I allocate out where I want those 250 focus, we have five major initiatives across the firm. those are five revenue-generating projects that we're putting out, new new builds or consolidations of tools, new commercial or monetization models.

15:39 I want those 250 people split across those five and I want as few working on the layers underneath that as possible. And if I can outsource everything on the under the layers underneath that, that's an ideal ideal split of time for my my team. >> Yeah. before I turn over for questions, I realize we have 2 minutes. I guess maybe one last thing is like where do you find friction today? what are problems that you would hope people in the audience would solve for you?

16:06 we still struggle with getting the models to do exactly what we want all the time. we do a lot of working of all of the models and actually, you know, if you you back to pre-Reducto world, we wasted a lot of time on trying to figure out the right model for the right type of chart for the right type of document that we're passing in. So, we've we've gotten rid of a lot of that, but we still deal with it on the agent front, trying to benchmark out, you know, why is 61 Soul tool spam doing tool call spamming when Opus 55 is not, but then 61 Soul is so much cheaper that we want to move in that direction, and we're trying to get it to go to go there.

16:41 so, we do a lot of sort of the optimization of the three factors we care about, which is cost, speed, and quality. Quality is top top of mind for everyone in our space, right? Like, any finance user will pay any amount of money to have the best answer. so, we need to make sure we're always optimizing on quality while trying to solve the other two. >> Yeah. Makes sense. Any questions from the room? Yeah. >> Can you zoom a little bit about the integration between Data Science and Reducto?

17:09 >> Yeah, so we have an environment where Reducto's operating in our environment against all of our content. We have bill- billions of pages of content. We have very big spurts of content when bakers are dropping in large data sets, potentially up to a terabyte of data can get dropped in on a moment's notice. so, we have an ingestion pipeline that takes all of that, passes it through Reducto. We get that back. We We leverage Turbo Buffer as our vector database, so we're passing it off to Turbo Buffer.

17:35 and then we build our graph rag on top of that. We're executing all of our graph rag queries using Prop Python code against all of that. Yeah. >> I'm on the sell side of things. we're we are actually customers of Data Science. >> sell side is. >> >> curious about Reducto. So, we're sitting on a transaction like, we have a file system with a ton of transactions, and we want to make that available to agents, but there's a way of obviously it's MNPI. We want to anonymize that before it makes its way into something like Reducto.

18:13 >> Hm. >> We're going to either build this or buy this, so very helpful conversation. That being said, giving it to the agents You You mentioned before that you built a custom eval. And so I I'm curious about how Y'all went about this eval. >> Yep. >> Potentially open sourced. but like curious about how you guys >> Yeah. So our custom eval that's related to We have a few custom evals, but the one that's most relevant to Reducto is what we call VDR bench. We haven't open sourced it. We're actually thinking about doing that, thinking about partnering with OpenAI on a paper around it. what we're doing with VDR bench is we basically take a common virtual data room of hundreds of documents, and we ask a few hundred questions against that data room with the known set of answers against those.

19:02 we run that every time we make changes to to pretty much anything. the scores on that we expect to be higher than any of the frontier labs directly. So if you were to, for example, drop that same set of files into cloud projects or OpenAI projects, we need to make sure that we're beating that. and a lot of the reason that we beat that our data science team benchmarks of our recall rate at, you know, improving 22% because of our Reducto parsing.

19:27 you know, a lot of that's because of the the way we pull out the content. It's actually not the other side of it. A lot of people think that sort of all the work needs to be done on the other side, the answering side, and most of the work actually is on the extraction side. You get that right, and everything else can follow.