00:35:02 · Khe Hy
[00:35:02] S1: That's super cool because we were saying before, I've been working with a few folks like, an FDE or, you know, of sorts between an investment firm and a software and an AI engineering firm, software development firm, where it's a headless CRM. So here, it's for the LP and biz dev function of the house, so but same similar concept, right? It's all, I mean, it's not in text and stuff, but it's all in email. And I guess you send the new deck to 50 LPs, someone's got to go into Dynamo and like click two flags and then type in the firm name, right? And then people, busy people aren't gonna do that, right? And so I think this is super cool. And I think you're already... This is where Codex and all these, like the more hacker types, they're already doing versions of this where they have a skill that's like every day go through my email and look for X on names and put them into a markdown file just with a date, you know, and then go through my Slack, do it with, you know, same thing. Put it... And and then at a minimum, you just have, a daily markdown file of everything you ever communicated on the name or the idea, And then you can throw a clot at that markdown series of markdown files. It's so much better than MCP, like a generalized MCP or some off the shelf RMS vendor that no one has time to figure out. I'm with you. I mean, headless and it maybe bears repeating because I know some people on my side that are there like, What do you mean by headless? And so headless meaning that there's no user interface, right? It just, it is acting on your raw materials, your granola transcripts, and just creating artifacts, creating infrastructure. But the point is that you can't, you don't have to click anything. It's just happening in like background session. So yeah, I'm super excited about that.
00:37:12 · Brett Caughran
[00:37:12] S0: Yeah, imagine this Kay, imagine I'm looking at, you know, DraftKings, right? And all I have to do is put the ticker in my sort of dashboard and it populates all of my research and notes and news and podcasts right into one dashboard. And it shows here's a series of calls you've had with management. A sort of, here's the granola recording of the internal bull bear debate you had on the name. Here's the, you know, sort of the six sell side notes that you starred as sort of particularly, you know, you sort of grade sell side notes as sort of relevancy. You know, here's a sort of data dashboard of, you know, historical correlations of KPIs. And it has a dashboard where you're seeing all of the work like that to me is the unlock. It's not this open claw that's like if I ask an open claw or a grok pot to go, you know, build an investment thesis on DraftKings, it's going to do the wrong things. And it's going to pull from the wrong data. And it's going to give me slop and burn a lot of tokens. If I can create this headless system around me with the right context, it's surfacing the right signal, right? When I need to see that signal. To me, that's like the future that is here now.
00:38:31 · Khe Hy
[00:38:31] S1: Yeah, yeah. Let me ask you this. A deadly problem. What if you did, like, what if you had a skill? Let's just use DraftKings for an, as an example. And you have email, you have something on MCP, you have, like, your internal notes, and you have your granola calls. What if you had a skill, like DIY Codex or Claude CoWork, and you have four skills? You have, like, draft, you know, granola scraper, you know, granola extractor, email extractor, and notes extractor. And you just say every at the end of every day, look at the emails from the last twenty four hours that mentioned DraftKings. And then this is where your skill comes in. You're like, I really think, like, Goldman really understands this name well. You might see, like, public betting, you know, betting data from, like, the state data, right, in, like, the body of an email and just save it on markdown, put some little metadata, who it's from, what's the date, DraftKings, save it as a markdown file in the folder called DraftKings. And you do that for three skills across three different kind of channels of data. At the end of a month, you've got 90 plus pieces of data that's pretty like again, it's curated because you created the skill. You told it what to look for. And these models are pretty smart, too. They can figure things out. And then whenever you have a DraftKings question, you just point your folder, you know, your coworker codex at that markdown folder. And you're like, hey, what's give me the bull bear thesis just off of my extracted knowledge, right? And you're going to have systems that do this, but people are like, we're helping clients do this. And I think who said it? It was Doug, who's like, you know, you get a few power users that like, this is my use case, and I'm going to kind of chop wood to make it work for me. And then the knowledge graph vendor comes in and like, Hey, we know that Brett in the corner has got these skills that every night he makes sure that it's this and that, and here's this markdown folder. And then the markdown, the knowledge graph vendor comes in and is like, yeah, we could do that, and we could do this across 100 names, across your cloud, across your Excel models, across... And so that's where you're kind of seeing this, like, nice interplay between kind of the tinkerer and the app player.
00:41:11 · Khe Hy
Like, I don't think they're in isolation from one another.
00:41:17 · Brett Caughran
[00:41:17] S0: Totally. And that's my sense. And you're closer to the technical backbone of how that's done. This sort of concept of knowledge graph is ascendant And right it's sort of Chuck supposes against the sort of first order use case of if I want to do a DraftKings earnings preview, I just ask Claude and it's web searching for all the right information. That's not a, that's not a one that's token inefficient. Two, you're going to get your reasoning on low quality context. You know, it's not an output you can trust. The skill layer is important too for the sort of like the breakdown. But if you can start to create this knowledge graph of internal external research and data, then actually like assembling that into an earnings preview with your structured skill, that's pretty token efficient. You can almost have that always on running earnings preview, ingesting your model architecture in to say, hey, based on what's happening, it looks like DraftKings is tracking ahead of revenue guidance by X amount. And you can see that like that's in a passive dashboard. That's not a chat. You know, that's not a chat interface where I have to think about, oh, maybe I should ask questions about this. No, I have that dashboard amongst all of my portfolio into a portfolio thing where it has sort of alerts of what's happening, hey, which companies are tracking ahead or behind, which key drivers are sort of improving, deteriorating, etc. That to me is like the real, not holy grail, but that's the, I don't know what you call it, the codex moment for public equity AI. Like that to me is within reach and more of an assembly problem rather than a technology Absolutely.
00:42:57 · Khe Hy
[00:42:57] S1: And I think that's the phase we're in now, right? Because even in the example you described, still a big problem there, which is the Microsoft three sixty five connector or you know, BIP sync or tamales, lack thereof, right? It's like, you know, in that example with a three sixty five connector, it's still running a search across your entire firms for like DraftKings, right? DraftKings earnings, DraftKings 2026, right? And trying to guess, you know, if there's, you know, 50 word documents on DraftKings, it's trying to guess which one do I wanna open, which one, you know, there's V7final, right? Like, is that the one with it? You know? And so that knowledge graph and the skills that build the knowledge graph is like, yeah, there's seven memos of, you know, Q2 twenty twenty six, but like, this is the one, but not only this is the one, these are the parts of the one that really matter to the analyses.