Joel Hron

Thank you guys for having me.

Nice to see you, Corey and Granton.

Yeah, excited to talk about it.

It's been a lot of great work from the teams over the last nine months or so to get here.

So it's an exciting topic to talk about.

Yeah, that's a good question.

So there's a number of implementations of deep research today, as you mentioned, like ChachiBT, Perplexity, Claw, Gemini have a variant of this, and most of them really orient around research via the web, right?

So they're tremendous at kind of navigating all the deep links of search and sort of reading and learning and taking notes along the trajectory of learning and doing more searches and

Uh, as you think about, you know, let's say like a B2C use case of like planning a vacation, it's a very iterative thing.

Like, uh, you know, I'm going over the summer and like, what are the options?

I could go here.

Like what's cheaper?

Like what's more family friendly.

And like, there's a ton of just like trajectories of like search that you would do for that problem, which is why deep research is, is really phenomenal.

Um,

The same is true in the legal context, though, and in legal research context as well, in terms of the various different trajectories of research that could be taken.

And it's actually even more complex in many ways because many aspects of the law, like, you know,

say the same thing but in a different way or they might like overrule each other or the jurisdictional nuance you know might be particular to the context and where you are and sort of where the case is being tried and all this stuff and what judge is in front of you and all these things that kind of i think formulated from a human's perspective like how they would go do that research

And so the sort of aspect of how the agent reasons through that process needs to be tuned for the domain of law.

And, you know, when I'm not a lawyer myself, but.