[
  {
    "startMs": 12340,
    "text": "Good morning, everyone. Uh, I'm Sam Green, um, team lead for Applied AI at Bridgewater Associates, and this is my colleague Aaron Linsky. And today we're here to talk to you about the Vault, the data platform that we've built at Bridgewater to turn unstructured data into a first-class asset in our investment process. And as part of the talk this morning, we'd like to share three lessons that we've learned building the Vault. The first is that humans and agents have very different needs from a data"
  },
  {
    "startMs": 41920,
    "text": "platform, and so you have to build for those different needs separately. The second is that the greatest impact occurs when a single tool can meet both of these sets of needs at the same time. And the third is that the real prize is when you can build the foundations needed to make agents a proactive participant in your investment process or whatever you're doing with your, with your, your tools, uh, instead of a reactive, uh, reactive tool for your humans to use. Uh,"
  },
  {
    "startMs": 72040,
    "text": "before I, I dive deeper into talking about the Vault, I wanted to start with some, some background about Bridgewater. Over the last fifty years, Bridgewater has been in the constant pursuit of the world's best understanding of how markets and economies work and turning that into a systematic encoding that we can use to stress test our logic over time. And what originally began as a set of if-then rules on a yellow legal pad evolved into a continuous compounding process with humans at the center constantly"
  },
  {
    "startMs": 101840,
    "text": "looking for the next thing that's changing in markets. And more recently, we've been working on building AIA, the Artificial Investment Associate, which puts a machine at the center of this continuous process. Across all these phases of evolution, we've had a constant philosophy in mind, which is that we want to be constantly looking at how the world is changing and what's going on in the world, noticing what, what dynamics are not yet encoded in our understanding, and use that learning to improve and"
  },
  {
    "startMs": 131860,
    "text": "compound for the future."
  },
  {
    "startMs": 134920,
    "text": "For most of Bridgewater's history, that meant building and overseeing time series models on structured data, and that structured data needed to be carefully built so that it could be safe for use in our research process and aligned to our internal ontology and world model so that we could get great leverage out of using the, the data that we had built. With the emergence of language models, we had a huge new opportunity to engage with a, with a much wider world of data, um, you know, news and research,"
  },
  {
    "startMs": 164480,
    "text": "transcripts, policy documents, and all of the internal conversation that was previously just in the ether, so the internal memos and meeting transcripts and debate happening inside the firm. We quickly realized that all of that data needed the exact same treatment to be fit for purpose. It needed to be carefully cleaned, governed, and made ready for use in both point-in-time research questions today and also our systematic study over time. And when we looked out at"
  },
  {
    "startMs": 194540,
    "text": "the landscape of data vendors and data platform providers, there was nothing that provided us with all of the control that we needed to build and maintain our data advantage. And so we built the Vault, which is our repository of external and internal unstructured data, um, and the platform that indexes, organizes, and makes all of it ready for use by our human investors and agents. Today, the Vault has more than a hundred million documents in it, with"
  },
  {
    "startMs": 224420,
    "text": "thousands more added every day, uh, minute by minute, from a hundred and thirty-five external sources, and again, growing all the time, as well as all of the data from inside of Bridgewater. And crucially, all that data is not just dumped on our investors' desks. It is carefully aligned to our internal, internal ontology with, uh, enrichments like the countries, concepts, markets, and most importantly, time period discussed in the document. To bring"
  },
  {
    "startMs": 254420,
    "text": "this to life, I want to start with a, a quick motivating example. So what I did here is I asked a fairly basic representative investment question to an enterprise chat client. I asked, \"How is AI infrastructure investment impacting the Korean won, and do market participants expect this to continue?\" And as, as you're all I'm sure familiar with, um, the agent goes to the web and looks for resources it can draw on because I've explicitly asked it to go find, uh,"
  },
  {
    "startMs": 284460,
    "text": "other people's perspectives on the question. And you can see it, it zooms in and it finds fifteen relevant-looking resources to draw on, uh, before it gives me back its answer. And when I, when I zoomed in on the answer it gave back, a couple of things stood out to me. The first is that even though it found fifteen relevant-looking sources, it only picked one or two to answer, to answer my question. And the second is down at the end of this response, where the agent itself acknowledges that it hasn't answered my"
  },
  {
    "startMs": 314240,
    "text": "question. It, it didn't find enough documents on the open web to establish a market consensus and meet the, meet the parameters that I laid out. When I double-clicked even further, the problem got even worse. One of the notes that it primarily drew on to answer my question was published way back in July of twenty twenty-six, even though I asked this question and captured this answer just at the end of last week in early October. In the age of AI and in"
  },
  {
    "startMs": 344120,
    "text": "investing, for-- three months is a massive amount of time. It's not even close to good enough to draw, uh, draw on this resource to answer my question. When I ask this exact same query attached to the Vault, something totally different happens. The first is that the connection to the Vault helps to prompt the agent that it should look for a specific period of time when answering my question, so it zooms in on October first to October eighth. It finds a much wider array of resources, fifty-two candidate"
  },
  {
    "startMs": 374036,
    "text": "documents that are relevant to the query over this spec-specific period of time because of the Vault's much more significant corpus of content that's relevant to investing questions. And when it ultimately answers my question, it draws on seven instead of only one or two and gives me back a rich answer that the agent is co-- more confident is going to address my question. And so for us, this is the, the big lesson of-- from building the Vault, uh, to kind of motivate the talk today, which is that it takes great"
  },
  {
    "startMs": 403796,
    "text": "data and the right connectors to make agents impactful. And I'm gonna talk-- hand over to Aaron now to talk about some of the product engineering takeaways from building the Vault."
  },
  {
    "startMs": 414196,
    "text": "Thanks, Sam. So hi, I'm Aaron. I run product engineering at Bridgewater. I'm gonna take us through a few of our learnings from building the Vault over the past few years. I'm gonna start with one that might seem obvious, but I still think it's worth saying, which is search is hard."
  },
  {
    "startMs": 431676,
    "text": "But it gets even harder if we're designing for two different consumers. In, in this case, we're designing for humans and agents. I'm gonna go over the difference here, starting with us. So humans need precision and a high signal-to-noise ratio because we can only read so much. Even a fast reader manages about three hundred words a minute, and personally, I'm much slower. Agents are a different kind of reader. They're far less sensitive to precision. If the data is there, they'll find it, and"
  },
  {
    "startMs": 461336,
    "text": "basically anything you hand to them will get attended to. They scale super quickly, and they come-- and they consume about, uh, a hundred times faster, thirty thousand words per minute. And so we need to build Vault for both of these. And when we're thinking about the dimensions that matter, there are these five on, on the board: recall, precision, filtering, entitlements, and scale. Some of them matter to people, some matter more to agents, many to both."
  },
  {
    "startMs": 492096,
    "text": "I'm gonna go deep on three of these: precision for people, scale for agents, and then filtering for both. So precision. Once we've filled the Vault, our-- which was a heroic effort by our data and legal teams, recall was no longer a pres-- a pressing issue. However, the number one complaint was Vault search is bad. As the product owner, it's painful to hear that, but my response was, \"Let's benchmark it.\" And that's what we did."
  },
  {
    "startMs": 522176,
    "text": "We collected questions and found the best documents by hand, including ones that looked helpful but weren't. In all-- in total, it was about two hundred examples, and it took us less than a week. It was not fun or very glamorous, but it was very helpful. And after we ran it, it was very clear search was bad. The key metric we were looking at is precision at ten, which is of the top ten results, how many are the right documents? And we were hitting about sixty"
  },
  {
    "startMs": 551856,
    "text": "percent. So the people were right, it was bad. But now we had a way to measure all of the improvements, and here on the board are five of them. And by the time we got done with agentic search, we were up in the ninety, ninety-five percent, uh, recall at ten or precision at ten."
  },
  {
    "startMs": 571156,
    "text": "All right, so that was precision. Now on to filtering. Like anyone, we want the most relevant documents. But when we looked at the production traces, what we were seeing is that almost always there was some condition, either as of a certain date or from a certain source or about a specific asset. And all of that requires advanced filtering, and that's where we ran into our first major performance issue. So I'm gonna quickly go through this of, uh, a"
  },
  {
    "startMs": 601176,
    "text": "little bit technical here of there's classically two ways to fil-filter a, a vector database. Post-filtering will use that vector index first and then filter the top results by metadata. It's fast, but recall could be pretty low because the globally relevant results might not match your filters. On the other side, we have pre-filtering, where we'll filter first and then calculate distances for every one of those matches. The advantage there is that the recall is very good, but it can be very slow, and"
  },
  {
    "startMs": 631216,
    "text": "we needed something in between. So that's what led us to try and then ultimately switch to Turbopuffer. Their approach, which they call na-native filtering, looks only in the nearest clusters that contain matches and then scores just those. What you end up getting is something that's fast like post-filtering, but with close to the same recall as pre-filtering."
  },
  {
    "startMs": 653376,
    "text": "And lastly, I'm gonna talk about scale. Human scale for us is pretty pedestrian. A hundred queries an hour. We have three hundred users. They're gonna search, you know, every so often. It takes our users minutes to read the docs that they're, that they're receiving. Agents, on the other hand, are a few orders of magnitude beyond that. Easily a hundred plus queries a second, and agent swarms can hit thousands easily. And they obviously will read, as I said earlier, will read docs in seconds. So we needed something that could"
  },
  {
    "startMs": 683256,
    "text": "scale as well, and again, Turbopuffer handled that easily too. So we were covering all five dimensions. I didn't talk about entitlements, but I'll be talking about that later today. Um, but we covered it all. It unlocked new workflows, but it didn't change how our researchers worked. They still weren't coming to Vault every morning. And that's my second lesson that I wanna share here, is that no matter how amazing the tools are, we can't just drop them on our investors' desks and expect them to be used. We need"
  },
  {
    "startMs": 713316,
    "text": "to migrate their old habits into a, a, a new form. And so we looked at what they were already doing. Many of them were living in email. The research came straight from the brokers. They had subscribe li-re-- lists. They had rules that filtered everything into folders. It worked, it was familiar, and they knew that they weren't missing anything. So we had to build all of these features into the Vault. So that's exactly what we did. Everything's searchable, the subscribed lists"
  },
  {
    "startMs": 743188,
    "text": "became saved searches, and folders became saved collections. It's the same habits, just a new home. And once we had them there, we can open up new habits. So we can ask-- they can ask questions across all the data, as Sam showed. They can follow dynamic feeds by topic, and they can hand those collections over to their agents to take further action. And that's when we clearly had product-market fit. And once we had that fit, the users wanted it everywhere, so we put it in chat, we made a phone app,"
  },
  {
    "startMs": 773308,
    "text": "it's in Slack in their IDE, and of course, we availed all of that to the agents as well, um, including a, a CLI because agents love CLIs. And so the main question here is, okay, so what does this enable? Sam's gonna talk about what we're building right now, but first and foremost, it's helping us to move around that research circle faster. With our Pocket Analyst, which is our first AI analyst, it can do hund-- it can do hours-- it can do hours of research in just a few minutes for a"
  },
  {
    "startMs": 803208,
    "text": "few dollars, and that's relying on the Vault. And then we're expanding that now with the researcher, which is the next generation. It's the same idea stretched across days or weeks. We're also able to train custom models to more intelligently reason over the Vault's data and use those together with other foundation models to feed systematic decision-making processes. The forecaster is our first one, which produces AI-generated macro relevant predictions. And then we"
  },
  {
    "startMs": 832788,
    "text": "als-also have, uh, built investment signals from the Vault, turning unstructured data into structured tradable strategies. Now I'll hand it to Sam to take us through Vault's latest capability."
  },
  {
    "startMs": 845508,
    "text": "Thanks. So like I alluded to at the beginning of the talk, the real prize is when you can take agents from a reactive resource that can be ready to answer a, an, a human's question and instead make them proactive participants helping to steer your high-value professionals towards the most important areas for their attention. And the way that we're solving that problem is in an experience we're calling the Investor Workbench, where the agent is always"
  },
  {
    "startMs": 874968,
    "text": "on tracking what's important to that investor and presenting them with the areas that are most in need of their attention. It looks like an experience like this that relies on the Vault, where a topic is proposed and several pieces of information are presented to the investor to decide whether they should dig deeper or ignore that topic entirely. You can see here the card that an investor sees in order to decide whether to dig in deeper into the same AI impact on currencies question that we looked at earlier in the talk."
  },
  {
    "startMs": 905548,
    "text": "And the investor receives everything they need, an agentic summary if they want a quick scan across the agent's findings. They also get the exact evidence that the agent was drawing on so that they can assess for themselves what was leading to this recommendation. And if they choose to dig deeper, they have a direct connection to the research output from the analytical tools that Aaron was just describing. And when they dig deeper alongside the agent to look at the dynamics driving this question,"
  },
  {
    "startMs": 935288,
    "text": "the learnings are automatically captured. The results of their collaboration are automatically captured back in the Vault. And so this for us is the key lesson. The Vault enables compounding because it provides the right evidence, the right ext-- internal and external information at the fingertips of our investors and agents, and it automatically captures the synthesis that they generate and puts it back in the corpus for the next turn. And that makes us go around the circle faster and better."
  },
  {
    "startMs": 966588,
    "text": "And so when we think back to our-- the, the question we began with, what it takes to make an agent work is the right context and the right understanding of what's going on in your world. And so our question for you is: Does your AI know what's going on in the world, and does it remember what your firm has learned about it? Because we are teaching ours to, and if these sounds like an-- sound like an exciting challenge, we'd love to talk. Thank you."
  }
]