Latent Space: The AI Engineer Podcast
01:06:59 · Shawn Wang, Mihail Eric
[01:06:59] S0: Yeah. One thing that I observed you talking about from Monaco, but it's not here, is the SRE side. When you close the loop, you actually want to have the agent read your logs for builds, and then ideally read your analytics for live production. [01:07:15] S1: That's right, that's right, yeah. Not explicitly, but it's a really good shout out. So I think that I'm gonna weave that in in like two places. One is in the background agents, week, and then also in the software factory week. So you're absolutely right. I do... It's a really good call out. This idea of, like, trigger slash event based closing of the loop, which, you know, now is one of the one of the two or three entry points when people talk about agents kicking off tasks in the software factory, that's absolutely right. That'll come in there. [01:07:40] S0: Yeah. It's interesting that people call it trigger or event based, which I guess that is the actual technical implementation of it. Yeah. It just seems too low level almost. Mhmm. But I... So so the trigger is usually a cron job. Right? Like, let's let's be real. [01:07:55] S1: Sure. Sure. [01:07:55] S0: Sure. Event based is usually a cron job that, like, surfaces an event, and then it's event based. But it's all crons.
01:07:55 · Shawn Wang, Mihail Eric
[01:07:55] S0: Sure. Event based is usually a cron job that, like, surfaces an event, and then it's event based. But it's all crons. [01:08:02] S1: Yeah. Yeah. That's right. That's right. Yeah. Yeah. Or, yeah, like, webhooks or something like that. Yeah, that's absolutely right. Yes. And, you know, the technical term, of course, because at the end of the day, yeah, being sort of like a a person by by by trade and and, yeah, we we we call those things, and so I guess that's... I fall back on that terminology. [01:08:19] S0: Yeah. And have any AI SRE companies made an impression on you?
01:08:19 · Shawn Wang, Mihail Eric
[01:08:19] S0: Yeah. And have any AI SRE companies made an impression on you? [01:08:25] S1: So, okay. I mean, I think the Resolve folks are doing well there. Resolve is doing well. I would say Nightshift is also doing quite a good job there, in terms of broadly background agents. I'm a big fan of kind of... They're Greylock backed. I think they're doing doing real well in this area as well. Yeah. I I would say that where... I think SRE is an interesting use case, and this might... Back to the build versus buy question. I think what's interesting about it is, like, where do... When does it become... Like, where does an SRE, an AI SRE, like, really see the most value? It's typically when you have, like, a tremendous number of, like, service dependencies, and these, like, massive sort of, systems, and tons of Kubernetes and Helm files, like, you know, like, tremendously large Kubernetes infrastructure Helm that's, like, files kind of strewn everywhere around. I think that's why Resolve has done really well in, like, the enterprise, right, where you go and you sell to a Fort, you go and sell to, like, a Walmart, and you kind of say, hey, you have... Your service level dependencies are crazy. And you see these these, like, you know, these diagrams of how things are set up. Then And they kinda go in and they're like, we'll we'll we'll try and make sense of all of this. I think that, like, at at smaller scales, it's usually still manageable that you can kinda roll your own. But, you know, I will say that for the enterprise, think they've they've done a good job.
01:09:33 · Shawn Wang, Mihail Eric
[01:09:33] S0: Yeah. For for people who I have never worked at this scale, because it it took me a while to to to see this, it is on the order of, let's let's call it tens of thousands of repos, more repos than developers. These are the situations where, like, you don't know what code is running That's absolutely anywhere in the company because probably the guy I wrote is no longer here. Right? That's absurd. By the way, it's still load bearing. [01:09:55] S1: That's absurd. Yeah, that's the scariest thing. That's absolutely right. And then you're the person who's on call, and you're interacting with a system that goes down where that person still isn't there, and there's like old out of date runbooks, you're like, what the hell is going on here? It's a scary, scary thing. And yes, at the enterprise level, it's a whole different beast. [01:10:16] S0: Yeah. So kind of college hacker, one person per repo, they've never... Totally. No appreciation. But I think if you just give that idea, you drop them in a simulation of, okay, day one on your job, this happens, what now?
01:10:16 · Shawn Wang, Mihail Eric, S2
[01:10:16] S0: Yeah. So kind of college hacker, one person per repo, they've never... Totally. No appreciation. But I think if you just give that idea, you drop them in a simulation of, okay, day one on your job, this happens, what now? [01:10:32] S1: Yeah. Yeah. So another shout out I'll give here. So the Resolve folks, actually last year, they made an assignment for the class where they effectively created a sandbox for students to go and then the sandbox was like strewn... I mean, within the sandbox, there was, like, many many services that were doing their various things, and there was even, like, bugs in the services within that sandbox. And then as part of the assignment, the students had to, like, go and actually, like, use the Resolve agent and kind of, like, probe and play the the human on call person probing the system, discovering what's happening. [01:11:07] S2: They've gotten interesting. [01:11:08] S0: Yeah. Yeah. It's an interesting website. [01:11:09] S1: I do not. It's been a while Yeah. Since I've seen [01:11:12] S0: This is very interactive. Okay. They're being a PagerDuty now. [01:11:17] S1: Yeah. Checks But also this, like, this video, I was... [01:11:21] S2: You know, you were shouting out. Interesting. Interesting. But okay.
01:11:21 · S2, Shawn Wang, Mihail Eric
[01:11:21] S2: You know, you were shouting out. Interesting. Interesting. But okay. [01:11:25] S0: Yeah. Is it... So... Okay. We, you know, we never get a chance to talk about this side of the world except for conversations like this. Any other segments? Because I I think AI SRE is maybe too broad or even too narrow, depending how you look at it. Right? Like, too broad meaning, well, there's there's several subdivisions of AI. Sorry. That's interesting. Mhmm. Or too narrow being like, well, actually, that's not even the biggest problem that we have. Mhmm. So I take it however you like. [01:11:48] S1: Yeah. You mean, like, specifically for for, like, Monaco or just, like, broadly for, like, organizations thinking about this? [01:11:53] S0: Broadly, because that is our audience.