Joel Hron

Like, take the tax example I just gave you, for instance.

Like, you know, I might decide, let's say, a year ago, if I was working on this problem, to go spend a bunch of time on data extraction.

Because, like, hey, if I don't extract good data from these documents, then, like, none of the downstream stuff works.

So I'm going to spend a bunch of time on that.

And in reality, if you look at where we are today, like,

LLNs are phenomenally good at this now.

And they've gotten phenomenally better in just in just nine months or so at this particular task.

And so, you know, that would have been a case where you like spend a bunch of time on something.

But at the end of the day, maybe that wasn't the most valuable use of your time.

Which is further to the point of why I think, like, build the whole system.

Like, put the agent system to the test and have it do all the steps, extracting data, looking at the tax law, inputting it into a tax engine, resolving errors.

Let it do everything and then figure out where it falls over.

I think I've heard some of the, you know, the large research labs and model providers say

Kind of say, hey, look, when we design our applications, we're designing for what we think the model might be able to do in six months rather than what it's capable of today.

And I think I think there's an element of that in how you approach like building as well, where you try to kind of forecast like where these models are going and what they might be good at.

And, you know, if you forecast that today, honestly, I don't think the models are going to get really good at math, for instance.

But what they're going to get much better at is writing code and planning and adapting and these kind of things.

And so, you know, you really need to think about, okay, well, how do I need to architect my system to make those components as flexible and profound as I want, but then go spend my time perhaps on the tools or the content under them so that as this boat rises, like these boats rise too.

I don't want to minimize the work to get something out the door, particularly in like professional use cases like this.

You asked how long sort of deep research took.