00:04:24 · Ruby Justice Thelot, Dexter Horthy
[00:04:24] S1: Yeah. What's the hardest part about this? You mentioned a lot of things when it comes to security, when it comes to governance, cost tracking. What do you think is the hardest piece from an engineering standpoint? [00:04:34] S0: Oh, I mean, just the the the the core, you're you're essentially... HumanLayer essentially was a... And and Factory as well is is a giant distributed system with all these different moving that do all do different things and have different different responsibilities. And so building the actual technology layer where something can happen on my workstation and someone else can interact with it, but only in certain capacities. So we we explored a lot of, like, modern technology, like sync engines and durable streams and kind of, like, almost things shaped like a... This idea of, like, conflict conflict free replicated data types where, like, you can have multiple disparate systems making changes to a single item or object, and how do you merge those all together? This is how systems like Google Docs, and Notion and Figma work where you have lots of actions happening in real time, and the system has to take all of this, assume maybe some of it is coming late or coming, twice and being retried, how do you actually maintain one single, you know, source of truth distributed across all these stateful components?
00:04:34 · Dexter Horthy, Ruby Justice Thelot
[00:04:34] S0: Oh, I mean, just the the the the core, you're you're essentially... HumanLayer essentially was a... And and Factory as well is is a giant distributed system with all these different moving that do all do different things and have different different responsibilities. And so building the actual technology layer where something can happen on my workstation and someone else can interact with it, but only in certain capacities. So we we explored a lot of, like, modern technology, like sync engines and durable streams and kind of, like, almost things shaped like a... This idea of, like, conflict conflict free replicated data types where, like, you can have multiple disparate systems making changes to a single item or object, and how do you merge those all together? This is how systems like Google Docs, and Notion and Figma work where you have lots of actions happening in real time, and the system has to take all of this, assume maybe some of it is coming late or coming, twice and being retried, how do you actually maintain one single, you know, source of truth distributed across all these stateful components? [00:05:32] S1: I wanna ask because typically when you're talking about a Notion or you're talking about a Google Doc, yes, you have multiplayers, but it's no more than a dozen at a time. Now when you bring in agent swarms, so this is not just multiplayer agents, these are swarms of agents. How does that change the underlying software and how you have to think about these tools?
00:05:53 · Dexter Horthy
[00:05:53] S0: I mean, we we are always talking about leverage is how do you give humans better leverage on their time. The the slowest way to work with an agent is to ask it to do a thing and it does one thing and then you go review the work all in one without without any upfront planning between the human and the agent. And then as as as you get a little bit more sophisticated in your workflows, you do some upfront planning, maybe these plans get reviewed by multiple people, And the fact that swarms of agents are now able to do, you know, months worth of work in a couple days makes it all the more important that humans can get together and align either one one human with the agent or a team of humans working with that agent. And and the human's job is in software, in teams where there's, you know, regulated industries, we can't just go lights off and ship, you know, a 100,000 lines of slop and hope for the best. Right? If something is wrong, someone's getting fined millions of dollars. There's a need for humans to maintain control and understanding of the system and be the end all decision makers. And now that the scope of work of what agents can accomplish in a given amount of time, the need for alignment and the ability to pull both context and decisions out of the human and also push context from the agent about what was done and why and what needs the most attention during the review phase, is just even more important and even more high leverage.
00:07:09 · Ruby Justice Thelot
[00:07:09] S1: Man, that is so exciting. So today, you officially announced your team is joining Factory and you're open sourcing the platform. What does that mean? What can customers expect to see?
00:07:20 · Dexter Horthy
[00:07:20] S0: Yeah. So, we're we're really excited to, jump into Factory and get all the coolest stuff from HumanLayer landed in what is, to be completely honest, a a very mature and stable platform. And so the main reason we were, like, in love with this deal when we started chatting with this about Matan and Eno is it's a way to get all of the crazy frontier, like, I know, I like to think that some the stuff in HumanLayer is things that people won't even realize they need for six to twelve months from when we built it. Landed in a in a in a place where people can also get all of the stuff that they've been asking for for six, nine months, but we just didn't have time to build it. But Factory is this is this landing place. So in the end in the end state, you know, give us a couple weeks. The the goal is to invite HumanLayer customers into Factory and give them all of the stuff they loved about HumanLayer in the Factory product. Now in the meantime, we will keep the kind of cloud infrastructure running for a set period of time so that people have time to transition either into their own thing. And then we're supporting the community. We have several of our larger larger customers have engaged us to just kind of like help them move to self hosted. The code is open source. You can go run HumanLayer yourself if you want, and we're kind of invested in making sure that people wanna go that path can. And at Factory, one of our core operating principles, I've said this, is is earn the right. Rather than say, oh, HumanLayer's gone, you better buy Factory, we wanna go and take and and and create a really like... The the parts of HumanLayer that people love, put that in Factory before we go back to all of our users and say, hey, we have we have something really special to to share with you. So we wanna give people continuity and then also be able to and also be able to give them eventually the best of both worlds.
00:08:57 · Ruby Justice Thelot
Ad[00:08:57] S1: I wanna shout out our sponsor, Lovable. You know, the app you've been meaning to build, the internal tool, side project, or product you'd otherwise lose a weekend to? With Lovable, you get software you can ship today. That includes an editable codebase you can inspect and change, plus two way GitHub sync. Lovable also handles the backend and infrastructure, including managed Postgres, auth, hosting, payments, and more so you don't have to wire it all up yourself. And through Lovable's MCP server, you can create and deploy your project directly from the agents you already use. Turn ideas into software people love with Lovable. Lovable. Dev. Now onto the episode. You brought up a really important point that you're building a tool that maybe as an engineering team, don't totally realize you need until six to twelve months later. And so wanted to get your thoughts in general. How should an engineer right now think about ensuring they're using the most frontier tools and technology as they go about coding and building agents?