A Hedge Fund as a Function

Hello

Exciting to be here. My name is Frank. I work at Coatue which is a technology investment firm across public and private markets

So, in our business, what you really need to do is be able to take high conviction bets

on big themes and watch those play out.

I think, honestly, a career is the same way.

And last year when I joined Coatue, the bet that I wanted to make was I think that agents

will have an even bigger impact in investing than they did at coding.

I know that's a big statement.

We're all here because of the transformative impact that AI has had in coding.

But I really believe it strongly.

And today I want to talk a little bit about the framework that we use to actually realize

that impact.

So, at a high level, you can think about a hedge fund as a function that takes in two

parameters, context external and context internal, and spits out one tuple.

Selection, size, timing.

stock, how much, when.

And I think this is a good framework to actually ground our work, which is we are trying to

solve this compression problem of how do you take all the information in the world and

spit out this one simple tuple and the product that we provide is essentially a time series

of this tuple that constructs a portfolio.

let's start from the top, which is the inputs.

simple philosophy.

We use our screens, we look at stuff, we do work.

Every single thing that a human can see in pixels on the screen, an agent in your building

should be able to see via API.

The analogy I use is imagine you brought the smartest people ever, the greatest investors

alive and you brought them into your company but you gave them a computer without logins

to 75% of your services.

It's almost immaterial how smart this system is if it doesn't have the tools to actually

action that.

So the two parts, external context, no surprises here, think the news, prices, filings, all

of that should be easily accessible and not via dragging and dropping, copy and pasting,

like directly via API.

Internal context is just as important, right?

So this is your own firm situation.

So that might be our current positions, potential liquidity and risk requirements we have around

certain names, and past case studies or history with a certain sector or stock or management

team.

That is all super important.

So this is the foundation, and I think, no credit to me, Coatue has been an amazing leader

on this for over a decade.

It is both technological and cultural.

We have an amazing data science team, amazing processes, amazing systems that bring all

this in, and just as importantly, we have a culture that is super, super rigorous and

built from the ground up to capture all this insight.

For decades, we filed every single note about every single trade, about every single decision

we made or didn't make about what went well and what didn't go well, and that has poised

us to expose us to AI.

If you think about it, I probably can't just take all of those things, jam them into a

context window and get my magic three numbers and go home.

It can't be that easy.

You probably have to break down this function a bit further.

So maybe the first step is I take in that external and internal context and I gather

it.

I want to gather it, I want to filter out what is relevant and not relevant.

Okay, well, I pulled some news articles about the MBA that probably isn't material to stocks,

but this is related to local permitting that might impact data centers.

There is a lot of nuance in this gather step.

you will see probably the next step is I need to analyze that information and form

a view.

I need to think about what that means for the markets, public and private, and then

I need to take that view and turn it into a decision.

A decision object has these three parameters, these three sub pieces.

You can see every single step has an input and an output, and the input for the subsequent

step is the output that the previous function generated.

I think as an engineer, this is a way for me to conceptualize the problem in a way that

makes a lot of sense.

But even this, it really can't be as simple as writing three functions.

So let's just, to really appreciate the scope and understand the full complexity of the

problem, let's look into the first step, a tiny sub piece of a tiny sub piece of just

gathering information and let's do a case study on interpreting the news.

So it's probably no secret to you guys that news from Asia and Korean media outlets has

been super important this year because semis, AI, have been a huge, huge theme in the market.

Huge theme.

And I think this is an area where AI is poised to have a lot of impact.

Reading Korean language news better than our completely non-Korean speaking staff.

I think I have a good thesis that this might be a good use case.

So you can imagine the first step is I have articles.

I need to collect the articles.

This

could be an MCP, this could be a CLI, license the data feeds, clean the data feeds. There are a lot of ways to do this and a lot of dimensions of freedom for how you can even just write this simple piece. How do I chunk it when I pass it to the LLM? Do I want to pull the images as images? Do I want to pull the images and then turn the images into text? There are actually a lot of knobs here.

I almost think about those knobs as hyperparameters in a traditional machine learning system.

I think about each of these knobs as something for me to tune and optimize against.

Obviously, filtration, we talked about it.

There are probably Korean NBA fans, right?

There is probably a bunch of stuff that is not necessarily material to the names and

themes and stocks in our portfolio that really, really matter.

So I want to make sure that I filter those out.

There is this translate slash extract slash should I summarize, should I extract this

into some sort of structured form.

Again, so, so many ways to do this, so many ways to experiment, how to expose information

to the model, and one of the reasons this is hard is it keeps changing.

And obviously checking.

Checking our own internal notes, our own internal views, potential conversations we have had,

meeting recordings against these things.

We actually need to cross-reference those things.

Actually the idea of pulling information from disparate sources and cross-referencing them,

that's super powerful.

So you will see on the right here I have code, LLM, LLM, code, person.

There's many, many ways to run these functions.

I think about, oh, yeah, and finally, update.

We update our views.

There are many ways to run these functions.

I think of each line as having a runner, and the most obvious one is code.

Code is very good.

It is fast, it is cheap, it is reliable, so for something like if the prices to earnings

ratio is less than 15, I should just use deterministic code for that.

Runner number two is statistics, classical machine learning, and you can imagine fitting

the line to a regression for a specific pattern, this is very powerful because you can model

much more complex relationships than just pure deterministic code.

And for even more complex relationships, the reason we are all here, LLMs, AI agents, that's

another type of runner.

So for something like summarization, that's the state of the art.

It's probably totally impossible to build a bunch of if statements that can summarize

better than a modern LLM.

Of course, people.

People are important runners in the system.

Imagine a function meeting the management team of a company.

I probably don't want to send an LLM or an AI agent in to do that.

I probably don't want to send an if statement into that meeting.

I think there are many cases where because of judgment and the ability to navigate the

real world and all of these things, a person is the best runner for a given piece of the

function.

I think this is a super, super important point.

There is no glory in automating things for the sake of automating things.

The goal is not to take as many things and make them LLM as possible for us.

The goal is for any given piece of this function, what can I do to maximize absolute quality?

And if you actually think about the function, it probably looks something like this.

It's probably not just a linear statement of a bunch of different things.

There's probably all kinds of branching logic and all kinds of ways to actually fork this.

So maybe I want to collect the information and then translate it, and my main goal is

to extract quotes and check those against sources to make sure that these are actually

the things that people said, and that's my approach.

But that might be totally wrong.

Maybe what I want to do is I want to de-dupe and then I want to filter and then I want

to pull external figures or maybe I want to do something totally different.

I actually want to, I'm passing in a note first and I want to find other confirmatory

data points or maybe I'm trying to red team.

There's a million different ways to configure this.

So yet again, more hyperparameters within the control flow, right?

So many ways to think about just this very simple problem of pulling, filtering, summarizing

aggregating the news for LLMs.

And each of these boxes probably has an optimal runner, right?

So the optimal runner might be deterministic code for collection, right?

I'm pulling last 24 hours for a given source.

That's deterministic code.

Filtration?

models maybe.

LLMs?

statistical methods, a combination, right?

So this probably understates the complexity.

The reality is most things are multi-runner.

Most things have deterministic code plus LLM plus statistical method or human with LLM

in conjunction.

reality is it's probably combinatorics between my four buckets and there's even more

buckets than that.

Because within the LLM category I can tune the model.

I can choose big model, small model, medium model.

I can tune thinking effort. X high, high, medium, I can tune harness. I can choose the harness. I can

choose which skills load with the harness. I can choose which hooks load with the skills.

So yet again, more hyperparameters within my search space. I have an absolutely enormous

amount of hyperparameters within my search space. And this is just for this one tiny problem, right,

of just filtering the news. So the way to think about breaking down these problems is what can I

actually compartmentalize in a way that we can understand and evaluate.

That's what I'm hill climbing against.

Otherwise I'm just tuning these things.

I'm okay, that should actually be a machine learning system instead of an LLM.

That should be a little model that we train.

Oh, no, that shouldn't be a model at all.

That should be an if statement.

Or, oh, man, LLMs are really, really bad at translating that to portfolio impact.

It should really be a human on that step, but they're using a deterministic system to

help them search and pull the information.

It could be all different things.

And if you don't have a north star to hill climb against, you're just kind of, you're

just fidgeting around.

And I think I cannot convey enough that this is just one tiny thing we do.

Imagine every single data source that we pull in, there's probably more than just three

transformations to get them to the intermediate output.

So the actual graph of Coatue and funds like Coatue, it actually probably looks, oh, not

like this.

is my screen saver.

The actual graph probably looks something like this.

It is probably massively complex.

In each of those nodes, we just talked about at least ten hyperparameters with at least

20 different values for them.

So the search space is basically infinite.

And figuring out how to actually lay this out in a way that you can comprehend both from

technical perspective, but also absorb culturally, organizationally.

That is the great challenge of applying AI in investing.

And beyond investing, what we're really talking about is creating a state machine that can

take information from the world and understand it well enough to make coherent decisions.

There's use cases for this far and above, wider than just investment firms, in policy,

in non-profits, in drug discovery, in corporate strategy.

I think one of the most exciting things for me

about being in forums like this

is talking to other people in different spaces

with different problems that kind of congeal

on the same problem space.

I'd love to keep talking about this.

I'll hang out in the hallway afterwards.

Here are my socials.

And thank you, everyone, for your time.

Thank you.