00:00:55 · Dexter Horthy, Ruby Justice Thelot
[00:00:55] S0: Yeah. So we announced that we are we are joining forces with the Factory team, and we're gonna bring all of the really cool multiplayer stuff that we've built in HumanLayer and proved out with hundreds, and in some cases, thousands of engineers, into the Factory product. [00:01:10] S1: Lots of cool human stuff that you're bringing from HumanLayer to Factory. So for people who aren't super familiar with HumanLayer, tell us a little bit more about it. What are the features? What are the tools that you're bringing to Factory? [00:01:23] S0: Yeah. So when we were building and we were working and we spent a lot of time sitting with larger teams at larger enterprises and trying to solve problems that were probably not quite as well served by off the shelf coding agents, off the shelf coding harnesses. And one of the things we realized that was a lot of the work needed to shift left in the SDLC and the software life cycle, and move collaboration on not only the code at the end of the work, but the planning and the documents and the incremental commits that were being put into features. And so we built a ton of tech to sync all of that information real time. The code changes, the actual, like, agent session back and forth, and any documents and plans were built, fully collaborative so that whether an agent is running locally on your workstation or in a background worker or anywhere else, anybody in the team can jump in and collaborate on the work being done.
00:01:23 · Dexter Horthy, Ruby Justice Thelot
[00:01:23] S0: Yeah. So when we were building and we were working and we spent a lot of time sitting with larger teams at larger enterprises and trying to solve problems that were probably not quite as well served by off the shelf coding agents, off the shelf coding harnesses. And one of the things we realized that was a lot of the work needed to shift left in the SDLC and the software life cycle, and move collaboration on not only the code at the end of the work, but the planning and the documents and the incremental commits that were being put into features. And so we built a ton of tech to sync all of that information real time. The code changes, the actual, like, agent session back and forth, and any documents and plans were built, fully collaborative so that whether an agent is running locally on your workstation or in a background worker or anywhere else, anybody in the team can jump in and collaborate on the work being done. [00:02:14] S1: Yeah. Tell us a little bit about the big shift that's happening right now in 2026. Of course, people are using agents when they're coding. That's not super new to this year, but the multiplayer aspect is a bit new. People don't totally know how they should be interacting with multiplayer coding agents. So tell us a little bit how the landscape's changed.
00:02:14 · Ruby Justice Thelot, Dexter Horthy
[00:02:14] S1: Yeah. Tell us a little bit about the big shift that's happening right now in 2026. Of course, people are using agents when they're coding. That's not super new to this year, but the multiplayer aspect is a bit new. People don't totally know how they should be interacting with multiplayer coding agents. So tell us a little bit how the landscape's changed. [00:02:33] S0: Well, I think the the the biggest benefit to multiplayer, right, you can say it and it and it does a cool demo, but the real question is, like, does it help you ship faster? And then working with customers, what we saw was when people were able to align on an outline of the work, a high level, you know, 200 line plan document before they get to the coding that caused... It it reduced the need for rework later on what was built. And that has what has led to a much greater velocity for people who are adopting and trialing these workflows in in in HumanLayer. So this collaboration drives speed and outcomes more than anything else. [00:03:09] S1: Yeah. And I know you spent the last time actually talking to a lot of these enterprise customers and like you alluded to, things work great in a demo, but then when you get to production, there are all these issues that enterprise customers are facing that maybe weren't as obvious. Can you tell us a little bit about that?
00:03:09 · Ruby Justice Thelot, Dexter Horthy
[00:03:09] S1: Yeah. And I know you spent the last time actually talking to a lot of these enterprise customers and like you alluded to, things work great in a demo, but then when you get to production, there are all these issues that enterprise customers are facing that maybe weren't as obvious. Can you tell us a little bit about that? [00:03:26] S0: Well, so multiplayer brings with it a lot of interesting challenges in the enterprise, especially around audit and authentication and access to systems. If I'm talking to my agent, the agent can just act on my behalf and perhaps look at my Slack, edit Notion documents as me, interact with GitHub. But as soon as you have multiple people in a single conversation, you need to kind of compute what is the what is the minimum surface that all those people have access to, or or or assign a specific authentication profile to that session. And then when things are done on behalf of the agent, there's all these audit needs as well. And so it's like how do you how do you actually track and attribute specific actions to a human upstream from what was said and how do you sort of bring that all together. So I I think the the enterprise, and what Factory has done really, really well is build a system with all of these governance and controls and even things like cost tracking, which are not really like a compliance thing but are incredibly useful when you have a large team with hundreds of engineers. So we're excited to kinda bring these ideas together.
00:03:26 · Dexter Horthy, Ruby Justice Thelot
[00:03:26] S0: Well, so multiplayer brings with it a lot of interesting challenges in the enterprise, especially around audit and authentication and access to systems. If I'm talking to my agent, the agent can just act on my behalf and perhaps look at my Slack, edit Notion documents as me, interact with GitHub. But as soon as you have multiple people in a single conversation, you need to kind of compute what is the what is the minimum surface that all those people have access to, or or or assign a specific authentication profile to that session. And then when things are done on behalf of the agent, there's all these audit needs as well. And so it's like how do you how do you actually track and attribute specific actions to a human upstream from what was said and how do you sort of bring that all together. So I I think the the enterprise, and what Factory has done really, really well is build a system with all of these governance and controls and even things like cost tracking, which are not really like a compliance thing but are incredibly useful when you have a large team with hundreds of engineers. So we're excited to kinda bring these ideas together. [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?
00:04:24 · 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?