# A factory stack starts with declarative code and shared traces

Markdown copy of https://realalpha.app/s/a-factory-stack-starts-with-declarative-code-and-shared/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Zach Lloyd](https://realalpha.app/builders/zach-lloyd/) · Zach Lloyd is founder and CEO of Warp.dev. · Founded Warp and led its April 2026 open-sourcing of its agentic development environment, built around cloud agents.
- Host: [Shawn Wang (swyx)](https://realalpha.app/people/swyx/) · Co-founder, AI Engineer · Wrote “The Rise of the AI Engineer” and founded Smol AI, maker of AI News.
- Show: Latent Space
- Episode: [⚡️ The 2026 Software Factory Infra Stack — Zach Lloyd, Warp.dev](https://realalpha.app/v/LL0YmIyBKSU/), Nov 3, 2026
- Moment: 19:18 to 24:02 of the episode (5 min), playing on https://realalpha.app/s/a-factory-stack-starts-with-declarative-code-and-shared/; the episode from there: https://realalpha.app/v/LL0YmIyBKSU/?t=1158

## Quote

> “the foundation of a **self-improving software factory** setup is define your factory declaratively”
> — [Zach Lloyd](https://realalpha.app/builders/zach-lloyd/) at [20:25](https://realalpha.app/v/LL0YmIyBKSU/?t=1225) · Latent Space

## Takeaways

1. Define the factory declaratively so changes can be versioned and tested.
2. Collect agent conversations and artifacts to diagnose failures.
3. Keep compute, inference and harness choices pluggable.

## About this segment

Zach Lloyd lays out a factory stack: declarative, versioned workflows; shared agent data; controlled tool access; and pluggable compute and inference. This gives teams a way to replay tasks and change components without locking into one setup.

From “⚡️ The 2026 Software Factory Infra Stack — Zach Lloyd, Warp.dev”, Nov 3, 2026. [Watch the full episode](https://realalpha.app/v/LL0YmIyBKSU/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[19:25](https://realalpha.app/v/LL0YmIyBKSU/?t=1165) whether it's warp or not if it's i would obviously you know warp warp is this is what we're fully focused on we have an awesome platform for it but just in general what i would think about if you are trying to build something in this space is a i would view it as like a stack so as infrastructure at the bottom of the stack, I think it's really foundational and important that you define your factory declaratively as code.

[19:51](https://realalpha.app/v/LL0YmIyBKSU/?t=1191) So again, the analogy is like Terraform here, you get the same benefits, but actually more. So the benefits you get from defining it as code is like you get a versioned view of like, what was your SDLC, AI, DLC, PDLC, whatever DLC you want. You get a versioned view of that. and then you get the ability to create branches off it which you can test you get the ability if you change it to revert it so all the obvious things about source control that are great and then you get the added benefit that's extremely cool where because it's in code coding agents can suggest improvements to it so to me this is like the foundation of a self-improving software factory setup is define your factory declaratively the next step up in this stack as you think about architecting it is someplace to gather all of the information

[20:47](https://realalpha.app/v/LL0YmIyBKSU/?t=1247) that agents are producing. Because what you want to be able to do is examine that information, look for failure modes, or replay those same past tasks with different variables to sort of, I don't know, scientifically is the right word, but from a measurement standpoint, really optimize your system. So that's the mindset. So you need the data to do that. You need the agent conversations and you need the agent artifacts. You need a record of all of the interactions from all of the tools to get to a result. And so what I mean by that is like, you might have a factory conversation that starts in Slack and then continues into linear and then continues into GitHub. And there's a code review comment. And that whole interaction is going to result in some piece of merged code.

[21:37](https://realalpha.app/v/LL0YmIyBKSU/?t=1297) In fact, it might even result in something gets shipped and then has a server crash. And you want the ability to retroactively go back with an agent, most likely, but you could do it as a person and diagnose how could that have been better? What was the failure in it? You also need, this part will seem fairly obvious, but you need a way of getting data into this system. So you need some way of plugging in MCPs.

[22:00](https://realalpha.app/v/LL0YmIyBKSU/?t=1320) And then we find that as companies get bigger, they want different access for different parts of their organization. So they want things like what MCPs can the marketing team access versus the sales team versus the engineering team. And so, like, again, you'll find there's a bunch of complexity depending on how big your organization is if you're trying to roll something like this out. You really want a compute layer.

[22:24](https://realalpha.app/v/LL0YmIyBKSU/?t=1344) You should think of that as a separate thing. And so there's obviously a lot of agent sandbox providers at this point. So if you're going to use a third party one, I would just make that pluggable. We use namespace as our primary one. the large data europe namespace is awesome but this should be pluggable i think that's really important so if you wanted to use daytona or modal or e2b or whatever like i would architect it so this is a pluggable component of it i would make sure depending on your requirements that you can do different platforms so again by default you know i think you'll probably want to use like a linux type sandbox but for computer use like the way that we test like ios apps is you're going to want to have the ability to run a mac vm and actually like have it run the simulator and

[23:10](https://realalpha.app/v/LL0YmIyBKSU/?t=1390) click around we have a very open approach to inference and this is like this is very much with our ethos of trying to be super duper flexible so we find that a lot of companies right now will have pre-existing commits with anthropic or open ai or google that they want to burn down. And so we're, we provide like a very big variety of like, you can plug in your own inference provider, or you can buy inference through us. You can even plug in your own harness, which I think is a pretty big deal. So, you know, you can orchestrate things like Pi, like I mentioned earlier, basically any ACP compatible harness. And then you want this improvement layer. And so this is some of the stuff that I showed in the demo where it's like,