00:31:37 · Thariq Shihipar
[00:31:37] S0: Yeah. I I mean, I I do wanna say that I I don't think there's one pattern for org management, and it's not even clear to me that the Claude Code team should be the pattern because we are very, like, dog food oriented. Right? Like, we get... Like, we're literally building the product to build the product. Right? And so that has like a different feedback loop than maybe other organizations might. So, I'm hesitant to say that the Claude Code team is a model for, like, you know, how other organizations should work. But I think that like you can sort of think through some like first practices of like, how do you turn productivity into more, honestly, revenue, you know, is like ultimately the goal. Right? And I definitely talk to customers who I'm like, if you doubled your PRs, you probably wouldn't even change your revenue at all. You know, like you just are not able to turn that into increased revenue because there's so much of org design is, for example, like buy in, you know, and deciding what to do or like do people even want this as the market saturated or not or something. Right? And like, you know, most things fail. And so like, you don't actually make more money if you fail faster necessarily, you know, as long as... Unless you find the thing that that really works. So I I think that the prompt I... You use is like, okay, let's say that you're running a car dealership in, like, 1995 and email comes out. One thing you can do is like you can give your receptionist and your team email and they can communicate a little bit faster and they're gonna be more productive. But I don't know if you'll sell more cars, or you could like let people order cars via email, you know, and like... And via the web. Right? And hopefully that will like drive more revenue. And so I think trying to find that analogy for your specific problem, I think is one way to think about it.
00:33:19 · Aditya Agarwal, Thariq Shihipar
[00:33:19] S1: Are there specific things that are super extreme or heretical that maybe have become normalized to you? But if, like, somebody were to drop into the Claude Code team as, like, member technical staff, they'd be like, this is totally different. [00:33:33] S0: Probably some stuff I can't talk about. Yeah. Yeah. Yeah. I think I think one [00:33:37] S1: thing I've observed is because it's so cheap to create. I've been trying to wrap my head around what is... How do people prioritize now? And how do you prioritize work? Because you can kinda just spin up everything in parallel. And I think there's just weird tension with I'm not really sure... Kind of old ways in which you might like t shirt size something. Like, why even bother with that? And I just curious like how that's changed internally. [00:34:01] S0: Yeah. I mean, I I think that it still takes a lot of tenacity to make something, you know, and I I don't think that amount has decreased almost at all, you know. And I I think that when I see things that work at Anthropic, like Claude design, I was... As soon as I met Nate, I'm like, dude, this guy has it. You know what I mean? And I'm like, he will like, he really wants this to happen, and he will make it happen. You know? And I think that like, yeah, like it's cheaper to make things, but now you have to get buy in, you have to believe in it. Right? And so I think that like, it should increase your expiration phase, but you're the one who has to decide, hey, I think this is it. You know, like, is the direction. So... Yeah. One additional question on Oregon,
00:34:01 · Thariq Shihipar, Aditya Agarwal
[00:34:01] S0: Yeah. I mean, I I think that it still takes a lot of tenacity to make something, you know, and I I don't think that amount has decreased almost at all, you know. And I I think that when I see things that work at Anthropic, like Claude design, I was... As soon as I met Nate, I'm like, dude, this guy has it. You know what I mean? And I'm like, he will like, he really wants this to happen, and he will make it happen. You know? And I think that like, yeah, like it's cheaper to make things, but now you have to get buy in, you have to believe in it. Right? And so I think that like, it should increase your expiration phase, but you're the one who has to decide, hey, I think this is it. You know, like, is the direction. So... Yeah. One additional question on Oregon, [00:34:41] S1: and I don't know who's next with a mic. You can pipe in. Hiring is probably pretty different now in sort of what you look for. Are there specific questions or exercises that, like, are net new to Anthropic that probably other people should adopt when we're looking to hire really talented engineers?
00:34:41 · Aditya Agarwal, Thariq Shihipar, S6
[00:34:41] S1: and I don't know who's next with a mic. You can pipe in. Hiring is probably pretty different now in sort of what you look for. Are there specific questions or exercises that, like, are net new to Anthropic that probably other people should adopt when we're looking to hire really talented engineers? [00:35:00] S0: I think Anthropic is probably like a very different place for hiring right now just because of demand. I also don't do much, like, interviewing myself these days. I think it's a hard problem. Like, obviously, you want people who are technical and understand the concepts, but you also want to know that they are good at AI, and these are two separate things. Yeah. And sometimes you can find someone who's good at one and not the other, and you need both. You guys probably honestly have more insight there. [00:35:25] S1: Yeah. Yeah. There's sort of this sort of thought. There's tension with, like, somebody who's actually really experienced sometimes, probably doesn't have the neuroplasticity to actually build in this new way. And I'm... Yeah. I'm sure we're all learning on the fly what that looks like. Question here? [00:35:39] S6: So how are the people... Or how are... How's the Claude Code team using Claude Code? Or how are you using Claude Code? Are you still, like, babysitting agents? Like, what I'm doing as we're speaking? Are you like using ID? Are you using some kind of like special internal tool to manage the word trees? Are you using word trees at all? [00:35:56] S0: Everyone does some things differently, basically.
00:35:56 · Thariq Shihipar, Aditya Agarwal
[00:35:56] S0: Everyone does some things differently, basically. [00:35:59] S1: What's your what's your setup? [00:36:01] S0: I tend to I tend to be in terminal. I've been using Claude agents recently. I tend to have at most maybe two or three things that I'm doing. I tend to do a lot of exploration. And so I I I tend to multitask less, I think, than the rest of the team. Yeah. I I think that it's like everyone is so completely different from each other. Like, I know some people who like use GitHub as like a source of state. And so their agents will write to the issue and then like when they wake it up again, they'll read from the issue and leave comments there and things like that. They use it as a communication medium for example, you know, like there's so many different setups and... [00:36:45] S1: Yeah. I guess on that note, and we'll go right over here, is like, it's such Wild West with how people are doing things. Is is it just Wild West even within the Anthropic teams, or is there a lot of shared... There's like a process for sharing knowledge and best practices? [00:37:04] S0: I mean, there is, but you also... Yeah. Everyone's always, you know, experimenting and trying to find things as well. Yeah.
00:37:04 · Thariq Shihipar, Jason
[00:37:04] S0: I mean, there is, but you also... Yeah. Everyone's always, you know, experimenting and trying to find things as well. Yeah. [00:37:11] S2: We have maybe two questions packaged in one. To what extent do you think harness design is domain specific? And to what it... Like, what are crazy things you've seen people use Claude Code for that you did not expect it to work for? So, like, auto research when it came out was kinda like, maybe you guys were already doing it, but to me, was new. It was cool. But maybe completely different domains or, yeah, use cases.