Multiplayer Coding Agents in the Cloud - Charlie Holtz, Conductor

Charlie Holtz: Building anything great takes a bunch of people and I so I think in the future it's gonna take a bunch of humans and a bunch of agents to build great things.

Shane: Let's go ahead and bring on our first guest, or only guest today. No stranger to the show has been on before, and I'm sure a lot of you watching have probably used Conductor. So why don't we bring on Charlie? From Conductor. Charlie, how's it going?

Charlie Holtz: Good, good. Thanks for having me again. It's good to see you guys. Good to see you too.

Shane: Honestly, I don't remember how long it's been, but it's been at least three or four months, I think, since you've been on. And so I know you've been. Cooking a lot of things up over there.

Charlie Holtz: Definitely been a lifetime in AI time. It's funny, I was thinking about la last time we talked was it was also definitely pre-fable. And one of the main things that ch has changed for us is that we don't use our local computers anymore. We don't use local hosts, we don't use worktrees. Everything just happens on a remote computer that sits in the cloud somewhere. And it's kind of crazy to think that I used to live in a world where like worktrees matter so much. And so yeah. It's partly because the models have gone it's actually almost entirely just because the models have gone so much better that we've had to adjust to this new cloud world. So yeah, excited to talk about how we thought about cloud and how we got there. And but also just yeah, good to see you guys as always.

Shane: Yeah, I mean I think one of the things that You were definitely one of the first proponents of was don't look at the code. You know, you were you were definitely early to that and it was, you know, people were wondering, well, where's the IDE? Where's the editor? And I don't know if you ever even added that. And you I know you could like view the code in there, but I there's probably a lot of pressure early to add that. But you I know you were very resistant to it because you kind of saw in the future a little bit and you're like, there will be a time when Looking at the code will become less relevant. Not saying, you know, so folks listening, I still occasionally look at code, but it is much rarer. Than it used to be.

Charlie Holtz: Yep. It's funny, we anytime we're thinking about adding a feature that either w internally we want our user wants, we try and think of is it gonna be ahead of ahead of the puck or like Where the puck is or a little behind it. And one thing that we really debated was adding like the terminal in the bottom right. When we first released the app, which is now a year ago? I really didn't want to do a terminal because I just felt like that wasn't the future. But we still have the terminal. And so that's one thing that I actually think has like remained useful for a while. In terms of viewing the code and editing the code, we did finally acquiesce to user demand and we added a thing that we call caveman mode. Where you can edit the code. We're using Pierre's diffs library for that, which has been amazing. Shout out to the Pierre team. They're like They're awesome to work with. But yeah, we also don't look at the code that much anymore and it's like steadily trended downwards as the as the models have gotten better. I think like there are occasions where like the looking at the diffs, like the differ is important just to get like a sanity check. Honestly, actually the main reason I use the differ is like see which lines that AIs have commented on. But yeah, that even doing that is trending downwards for us.

Abhi: I mean the growth of how the product has changed so quickly is It's been so awesome to see. Also, congrats on your Series A, by the way. Thank you. That's amazing. So when did this shift for you? It's almost like Conductor became cloud agent native overnight. Like it just came out of nowhere. But it obviously was seated for a while. So like at what point did you know where you needed to shift and how did you both retain your current user base on the way there? So we've been talking about this since.

Charlie Holtz: December. That's I remember when we had our first conversations about cloud becoming the next important thing. I think we the reason we like hesitated and went back and forth for it so long was because we just weren't sure how long the models were going to run for. Like the thing that just kind of made it clear that we needed to do this was when Fable came out, it was like Oh crap, like these are gonna be these are quick quickly, we're gonna quickly gonna be in a world where these can run for like not just like minutes, but hours, days, like even weeks. And obviously, like if something is running for weeks, you can't just let it run on your You know, my I have a MacBook Air like sitting right here. I don't want to just leave it propped open for a while. But the other thing that's really important is like when we launched Conductor a year ago, it was crazy at the time to imagine running like even three to five Claude Codes at the same time. But now that the models are better and you can let them run for longer, it means that you can also have like more of them running at the same time because you don't need to like constantly be context switching, like oh what is What feature is this one working on? Does it need me to prod it? Oh, is this one finished plan mode? Do I need to like approve the plan? Like you can trust the agents to do a lot more work, especially with like fable class of models. And so because you can run so many more now, it's even crazier to like imagine them constrained to the computer. And then we started experimenting with multiplayer ideas. The gist of that is like I want to see what everyone on the team is working on at the same time. And so once we started like seeing the value there, which was now probably two months ago, it was like clear that cloud, we had to go all in on cloud. And then in terms of bringing our users along for the ride, that's a that's an open question. We're still like figuring out how to like there's a couple of issues. Like you're basically getting a brand new computer, and so setting up a new computer always sucks. No one likes doing it And so part of our job now is to figure out how to make setting up a new computer fun and easy. Actually, maybe first step is easy, then we can get to fun. But it's hard.

Shane: You're exactly right. I think we're gonna look back at the time of last year when people had their laptops cracked open. Right? All the time like walking around like this. And then there were apps. A lot of people had like apps that would just keep it running so you could close your screen and that was a big thing for a while. And we're gonna look back and kind of laugh at that because y you're exactly right where, you know, whether I was running Claude Code, Mastra Code, Conductor, if you have too many sessions opened, it's gonna bring your computer to a halt, right? And that's I think everyone's probably experienced it. At some time where they just are trying to run too much and their computer slows down, why should you be constrained to just your local machine? Especially when you pretty much want to kick off this task, let it run for a while, and then you'll check in on it later.

Charlie Holtz: Yeah. And maybe actually I could share my screen and show you.

Shane: Yeah, we love seeing demos. So if you can show a demo.

Charlie Holtz: I wanted to give a quick demo of something that I think is everyone is overlooking in cloud right now, and that is multiplayer. The first like instant thing that you get from moving to a cloud world is that like Like this is a this is a cloud workspace in Conductor. As far as the user is concerned, it looks and feels just like a local Git worktree. But you can see this little subtle green cloud icon in the top left and click it and see that it actually is running on the cloud, and you can see the little information about the computer you're using. But everything on the right also just feels exactly like normal Conductor. Like I can click a file and view the file changes or even like make edits and it just streams that information from the cloud workspace to my local Conductor app. So like that's like the stuff that everyone like already knows is cool. Like I can quit the app and the agents are gonna keep running. I can have a bunch of them all running and it's not using up a bunch a ton of RAM. But the thing that people aren't talking enough about is when you are cloud first, you can see what everyone is working on in real time, and then you can actually like prompt together, which is pretty cool. So if I go to this home page. I can see these are all the workspaces like across all my projects and then I can see these little avatars and those are people on the team. So I can click on this workspace. And it's going to it takes a second to load and I can see that up here on the top right that like I'm online, Caden's online. I can see his prompts. And if I scroll to the bottom here, I can actually see in real time that like his agent is working. And I can see what he prompted. And if I want, I could be like. Hi Caden. I don't actually think I should mess up his workspace because he's probably he looks like he's doing real work. There's a small like a few kind of cool UX things that we can do here so we can tag people and I can be like at Jackson, like what do you think of this? I can click up here and follow the workspace. So like even though like I it I didn't create it, I can like have it in this little following section in the top left. But also we've given all our agents access to a Conductor API. So you can see here that the agent actually decided to create a workspace itself. And so I can click that. And it will take me to a workspace that an agent decided to create. And here in the bottom I can see the workspace it was sent from. And so all of this stuff theoretically could work in a local world if you like always had your m computer open and caffeinated it or something. And then we you uploaded your teammates transcripts to the cloud somehow. But anyway, it would be it would be really confusing. And so by just going cloud first, it makes like multiplayer super seamless. It makes the ability for the agents to create workspaces super seamless. And then obviously we now have an iPhone app, which is going to be too hard for you to see, but I'll go to this workspace and I'll just say like, hi from iPhone. And send it and then you could see the messages popped up.

Shane: So it yeah I mean I think the whole concept of multiplayer wouldn't work without cloud. At least not intuitively. You want to be able to stream the results from, you know, so you can. I can see the same stream you're seeing. We can steer the agent together. Exactly. Yeah. The one thing that this does, which is an unlock that has always been something difficult to do. Is like handoff work to someone else.

Abhi: Yeah.

Shane: I mean, you can know of course you just push up a PR. It's not that challenging, but it's even better if you can actually see. Everything that went into creating that work. What was the person thinking? How were they prompting it? You know, what were they explaining? Maybe you can look back at their at what they were saying and find flaws in their logic. Instead of just flaws in the code. Like actually flaws in that I wouldn't have done it this way. I think it's gonna end up in the wrong spot because we didn't provide the right details on whatever the feature is, right?

Abhi: Yeah, and the session context. Right? The agent has the context from that session, even if I'm jumping in and taking it over, as opposed to well, you have to deep research the PR when you take it over. And then start from scratch.

Charlie Holtz: The way I think about it is like Code is almost like the sawdust of the conversation. It's sort of the byproduct that you could throw away in two months when a new model comes out, and then you can just like replay the conversation again and get new code that's better magically because the models are better. But the other analogy we often talk about is like Figma made it so that like in one click you can see in real time what your teammates are working on and see an artifact of their work. And so our goal is to make it so instead of creating a PR and then sending that and then going to Slack and copying and pasting it and then opening that in your Claude Code, like opening the PR or like copying and pasting parts of the messages, says. Like in one click, I can press Command Shift C. I don't even have to click, and I have a link to my workspace that anyone on the team can access. And that has felt really magical.

Abhi: So another good like implication of this is like I mean there's a loneliness problem in SF, but there's also a loneliness problem in engineering teams because no one pair programs anymore, right? There's no sense of camaraderie when you're doing your craft. How have you seen that in your own team? Are you pair planning? Are you pair Are people collaborating again? People are collaborating again.

Charlie Holtz: I think our the most common use case has still been review that's mostly when we've been using it. It's just like I have a workspace, I have all the changes, and I just want like a quick sanity check on something. But it's a good point. I think I think even we even though like I we're at the frontier pretty close to it, we're still kind of figuring out the new like cultural norms. Like do we at each other in the workspace and then collaborate like that? Or do we like prepare a bunch of plans and then share that? These new norms are being invented. We haven't quite figured it out yet.

Shane: I mean a weird byproduct which I'm not predicting, but if I was bold enough I might predict is you know, a Conductor for your team basically becomes like a second slack. I could squint and see that being a possibility where, you know, here's the feature we're working on. Let's just collaborate here with the agent watching and interacting alongside of us. I d I don't know if all your chats are going into Conductor, but I could certainly see a subset of communication ending up there for sure.

Charlie Holtz: Yeah, especially engineering discussions. And I think if anyone is watching this, works at one of the labs or is working on models, interesting problem we've run into is that all of the Language models are trained for these like one-on-one turn conversations where like I say something, then Opus says something, then I say something, and Opus says something. And like Opus might say a lot of stuff, like it might have multiple turns within its response. But it's not trained for a world where, you know, I say something and then Abhi says something, then Shane says something, and then the model responds. I think this is partly like a harness problem, but also partly just like the way the models are trained. And I think that building anything great takes a bunch of people. And I so I think in the future it's gonna take a bunch of humans and a bunch of agents to build great things. And so I think there's opportunity to train the models to understand what a multi-person turn multi-turn conversation looks like.

Abhi: We struggle with this too with our agents. Like we built some s like we built some primitives in Mastra. So you can have these multiplayer conversations, but that doesn't mean the model is good at responding to them. We can cue messages, we can insert context. But it still like has to acknowledge that there's other questions that are like not addressed, but it's still like so singular focused on the thing it was working on. As humans we can do multitasking, multi-context in a single conversation. I could respond to both of you at the same time with threads or whatever, you know, but it's agents aren't that way.

Charlie Holtz: And very importantly, you know when to not say anything.

Abhi: Exactly.

Charlie Holtz: Like sometimes I'll say like at Abhi, just FYI, like you should be aware of this, and you'll know that you don't need to respond. Whereas the models love to they love tokens. They're gonna Charlie. Thank you so much. Yeah, exactly. It's like thumbs up, like looks great. And then five hundred words on like its thoughts, yeah.

Abhi: I'm curious, Charlie, why you just why did you decide to do the iOS app versus like A common surface people have is Slack, right? Would you have been able to achieve the same thing just using a Slack app or did you want a rich mobile experience?

Charlie Holtz: Great question. So we do have a Slack internal app that will release as like a first party thing. But something I didn't mention that I also think is super cool is that we have a API now. So anyone can build anything they want on top of Conductor workspaces. And so we've seen people build their own Slack bots and their own like mobile apps and even one person made like this like chicken farm game where like the chickens are workspaces and they're like eating when they're working and then they like look up when they're done. But Long story short, Slack is too noisy. I think there's like a lot of exciting interface ideas that we have, and so we just wanted to like control the interface for mobile. Like live activities while the workspace is working, or push notifications, or like seeing the avatars when someone's in the same workspace and things like that

Abhi: Suppose you get to d control the design experience as well.

Shane: One of the things we've said on this show, if you if you're have been watching for a while, for those of you tuning in Now Abhi and I always talk about, you know, either the bar test or, you know, sometimes we call it the beach test, right? Is what can you, you know, kick off and then go and finish the work. From the bar or from the beach, right? And I think we're getting closer to that being possible, right? With you know, with the mobile app, with, you know, there's there are tools you can use within Slack or whatever, but we can basically take it with you and actually be very productive just from a mobile device. And you don't have to bring your computer everywhere.

Charlie Holtz: Yep. I think there's a world where the mobile Conductor mobile app is the primary way, people are using Conductor. And then I think there's like a world ahead of that where it's agents are the primary users of Conductor. They're the ones spinning up workspaces, deciding when something is finished, deciding when to merge and stuff like that.

Shane: All right. Well, anything else you wanted show off today, Charlie? Otherwise, we appreciate you coming on the show. I think a lot of people probably know what Conductor is, but If someone is living under a rock and they don't know a Conductor, they haven't heard of it, where do they go to get started?

Charlie Holtz: They should go to conductor.build. Thanks for having me as always. And it's crazy how much has changed in like three, four months. I'm next time I'm on, I'm curious what kind of world we'll be living in.

Abhi: I'll be in those Ohio Waymo cars and you know, just coding from our phones. Charlie, are you guys hiring?

Charlie Holtz: Yes, we are hiring. If you live in SF or want to move to SF and are excited about building the future of orchestrating agents, reach out to me at charlie@conductor.build.

Shane: Build. Every week in AI, something insane happens.

Abhi: And there's so much drama. Every Monday we break it down live.

Shane: We do the news, we bring on guests building in the space. And we go deep into the stuff that actually matters. Agents Hour. Every Monday, noon Pacific.

Abhi: Follow, don't miss it.

Shane: Peace.