Zach Lloyd
Okay. Hello, everyone. I'm excited to be here. My name is Zach Lloyd. Today I'm going to
be talking about self-improving software factories, the new open source model, and basically what
I think is happening to development.
A little bit about me just to begin.
So I am a former principal engineer from Google.
I used to lead engineering on the Google Docs suite.
I've been an engineer now for over 20 years, a long time.
I am still shipping frequently, but I
haven't written a line of code in the last six months.
And I'm the founder of a company called Warp.
Warp, if you're not familiar, is a open source agentic development
environment.
You may know us as a terminal.
That is how the company started.
We're basically a terminal that has agents built in.
We open sourced it a couple months ago.
And I'm going to talk a little bit about that experience
and the motivation for it.
It's a popular open source project, over 60,000 GitHub
stars.
We've had a couple hundred people contributing.
We have over 800,000 active developers who are using warp.
And increasingly, we are focused not just
on the terminal aspect and the interactive aspect
of development, but more so on how do you automate development.
I'm going to talk mostly about that.
So the thesis that I have is that the discipline
of software engineering is going to become something more
like factory engineering.
And I'll explain what I mean by this in a minute,
but just keep that in mind.
That's what I think is going to happen.
If you look at development over the past couple years,
it's crazy how it's changed.
We've gone from a world of chat and AI autocomplete,
a cursor, co-pilot, to the phase that we're in now,
which I consider to be mostly interactive agents.
So you're sort of sitting at your computer
and you are telling Cloud Code to do something,
you're telling Warp to do something.
And I believe what's gonna happen
over the next six months, a year,
hard to predict the pace, is that we're
going to move much more towards a world of automation.
But before I get into that, just a quick show of hands.
How many folks in here are building with agents?
100% makes sense.
How many folks are building typically
with multiple agents at one time?
So again, almost everyone.
How many people are running an agent right now?
I'm not offended.
OK, that's totally cool.
I would be doing it too.
How many folks are running agents in the cloud, out of curiosity?
So that looks like less than half, but still significant.
And how many folks have set up a system internally
to automate the whole software development lifecycle?
So everything from triaging, speccing, implementing,
reviewing.
So I see some hands.
So some people are doing this.
So this is what's going to happen.
Every project of significant size, I believe,
is going to have something like this.
And it's going to look kind of like this big loop.
And everyone is talking about loops.
There's nothing that complicated about loops.
This loop says the Cloud Software Factory.
This loop could literally just say, like, the software
development lifecycle.
It's the same thing.
But just to go through this loop, it's like ideas
are going to come in at the top.
Agents are going to do triage.
If something is complicated, they will write a spec.
These little blue boxes are where humans step in.
Humans will review the spec.
Agents will do the implementation.
A human and agent will review the code.
Agents will verify.
Human will review the product.
You ship and then you monitor and round and round you go.
And this is what software development for better or worse
I think is gonna end up looking like.
So I repeat the thesis which is that
if this is what software engineering is gonna look like,
software engineers are going to be the ones
who end up building and managing these factories.
Now, I promised at the beginning,
and I put in the title of the talk
that I was gonna talk about open source,
and so I wanna do that for a few minutes,
I'm gonna take a quick digression.
I bring up open source because one of the main reasons
that Warp open source was to build a public factory.
And so this is a picture of this website we've built
called build.warp.dev,
which shows all of the issues that are flowing through our system
and what state they're in, what agents are working on them,
what contributors are working on them.
And it's kind of like a proto-factory done at scale.
It's not working perfectly, but it is working.
And one of the reasons we open sourced
was to try to build this.
Just in general, I think it's interesting
to talk about open source in the time of agentic development.
This is a really stupid graph, but it's like, you get it?
It's becoming much cheaper to build software.
A corollary of that is that it's becoming trivial
to clone software.
And so if you are in the software business,
I don't know how many folks in this room
are in the software business per se,
but it's very hard to build a software business
if it's free to build software.
It's hard to capture the value,
especially if a competitor can clone.
And so my big takeaway or a big tip for everyone in here
is that the first thing you should do is patent your code.
I'm kidding, this is a complete joke.
Don't do this.
My first tip is obviously you need to have a great product.
This has always been the case.
But I would say a great product probably was never enough.
But even now, more than ever, if you
think that you're going to build a great software business just
by building and shipping a great product,
you're probably not going to succeed.
You need advantages beyond the product.
And so those advantages could look like distribution,
ecosystem, it could be that you have a great brand
or a data moat, you might have capital.
But if you're a startup,
again, I'm coming from the startup world here,
you just don't have these advantages.
And so you still want to break through.
And one of the ways that I suggest doing this
is by building in the open.
And so to be clear, it took Warp five years
of building closed to sort of make the leap
into building in the open, and I'll explain why.
But if you build in the open, it helps build your ecosystem.
It can take you from being hated on Hacker News
to tolerated.
It can burnish your brand, it creates community,
and so there's all these advantages to it.
And some of the things that I think have traditionally
been a pain can now be managed.
And so the traditional pain of open source
might be something like you get a lot of noisy issues.
You get sloppy PRs, you can end up in code review hell,
you can end up having to spend a lot of time verifying changes.
And so the solution,
it's a kind of a long-winded way of getting to this for open source,
or at least for warp in the case of open source,
the thing that made us finally decide to do this was that we built a whole set of
automations, really a software factory,
around managing the open source project.
And so, like I said, this is what I think the future is going to look like.
I'm going to drill into it a bit just to get a little bit more technical for folks who want to try to build something like this for their own projects.
So what are the components of an effective software factory?
It's really not that complicated to start or at a high level.
You need a set of automations.
You need a way of providing context and skills.
you need a way of bringing humans in at the correct time,
sort of like when things get stuck on the factory.
And then a really important thing is you need some set
of self-improvement capabilities.
So think of this as loops.
And if you do this right in the open source world,
you can get a world where agents are helping
contributors contribute,
they're helping maintainers maintain.
And I wanna emphasize, there's nothing special
about open source here.
I think every sizable project can benefit from this approach,
and I predict that every company, every open source project,
will have at its core a software factory,
kind of like the way that CI CD became just like,
oh, of course you have that.
Maybe, I don't know when that happened, 10 years ago.
Let's tour the factory floor for a second here.
So you're not going to look at this.
This is too much.
The point of this slide is not to have you read the workflow.
it's that the factory floor is basically a graph
of steps where you are defining like,
okay, how does software get built for my product?
And it looks pretty similar for every product.
Things come in, they flow through,
they get stuck at certain points.
And, you know, broadly speaking,
just to back out a second, so there's the inputs.
The inputs are really ideas.
The inputs could be coming from your team,
They could be coming from your users.
The inputs themselves tend to come in
through certain channels that you should think about
as like your task tracker is an obvious one,
or Slack, your Teams, like your communication channels.
It could come directly from like your terminal or IDE.
They could come from your monitoring systems,
but there's some set of inputs
that bring work into the factory.
There's triage.
This is a really important step.
So again, I boil it down to something very simple,
but like you want an agent that is looking at issues
as they come in and just saying, you know,
if this is easy and this is unambiguous,
just implement it, and this is how you can actually
get going with a factory.
If an issue is hard, I recommend having an agent that produces specs.
Folks in here using spec-driven development, show of hands.
You can do this many different ways, but I think it's very effective.
The way that we do it at Warp that I recommend is having an agent write what we call a product
spec and a tech spec.
Product spec describes the product invariance that you're building towards.
spec describes the architecture and the shape of the code.
Then you have an implementation agent.
This is basically a coding agent that runs somewhere in the Cloud.
It makes a diff. You can use all sorts of coding agents for this.
You have review. This is in many ways the most painful part.
Like I expect that people are a little bit tired of reviewing
agentic slop. I would have an agent to code review first,
And then it becomes over time like a risk management exercise
of like when do you bring in humans to do code review,
but you want to have a step in here where humans can do it.
This is a very important step for certain types of apps,
the verification step.
So this would be things like computer use.
If you're building a sort of UI,
having the computer actually use the code that the agent produced
and producing videos and screenshots.
CI, CD still use it, obviously.
And then monitoring, so agents don't stop in your factory when code is shipped.
They should observe what's been shipped.
Is it crashing?
Is it being used?
And round and round you go because you take the output of this monitoring step
and you feed it back into the top of the factory.
Now, you could try and build this.
And I went to a talk earlier that my friend Adam gave where Uber has built
an internal version of this, and it's pretty cool.
I would say for most organizations,
it really depends where you are,
you'll be able to build a simple version of this easily,
but to build a thing that actually scales,
it's probably, like you should probably be focusing
on your own product, not building this infrastructure,
because there's a lot of stuff that you end up wanting.
You're not supposed to read this.
It's just a lot of stuff.
If you do build it, or if you buy it,
you'll end up with something that looks kind of like this,
which is you're going to have a bunch of ways
of getting work into your factory.
That's what's at the top here.
You're going to have a sort of control plane
for figuring out how work gets distributed
across your factory floor.
You're going to have the actual place
where the work happens.
And so that's going to be cloud sandboxes.
It's going to be figuring out what agent to run.
So what's the harness?
What's the model?
And then finally, I think this is a really important thing.
you're going to want to set up some kind of data plane that sits below your factory.
And so that's something that lets agents remember what they've done, learn, improve over time.
The factory is not just like a product, it's also a mindset.
And this brings me back to the thesis I had at the beginning.
You need to measure and improve.
So factory, this is where the, I don't know, you can stretch this metaphor as far as you
want, but like you should be thinking of efficiency.
And so that means like how much software did you ship, how much did it cost in terms of
human time and token time, and you're going to want to measure this and try to improve
it over time.
A key part of this is creating loops.
So loops are, again, they sound complicated.
They're not that complicated.
are basically ways of having agents improve
by like observing what they're doing,
where they're failing.
And so a common kind of loop that you're gonna wanna
put in your factory is like a skill loop.
That means you're gonna have your factory agents
that are running skills,
and then you'll have observer agents
that are seeing how those skills are being applied,
looking for issues and trying to improve the skills.
So for instance, if you had a code review agent
and it was leaving comments
and a senior engineer on your team
going and correcting those comments,
you'd want an observer agent that would look at that
and basically improve the code review agent for the next run.
This is one thought just to leave folks with.
Like, where does this leave engineers?
I think you're going to have to get into this mindset.
And I'm trying very hard to get our team into this mindset.
not always easy, that you're not just building the product, but you're building the thing
that builds the product, and that's like, it's just different. It's more like process
engineering or manufacturing or something like that. And you could think like, okay,
maybe that's a bummer. Like, is that a bummer? Is that, you know, and it depends. Like, it
it depends what joy you get out of software engineering.
If your joy is in writing the code,
I think everyone in here who is a software engineer
is going to be writing less code.
But if your joy is in shipping product,
like it's never been a better time,
and this is actually where I find my joy.
It's like I like building and shipping the thing.
So everyone in here is gonna code less,
but they're gonna ship more,
and that's gonna be a trade-off.
But if you approach it like you're a factory engineer,
I think you can see that there's still a really cool set
of engineering challenges.
You can almost think of it as meta engineering,
like how do you engineer your system of agents
to be the best possible of engineering?
That I think is a very compelling
and interesting set of challenges to solve.
So that's it.
For folks who are interested,
if you follow the link on this QR code,
I've set up a open source GitHub repo
where anyone who wants to try building their own factory
agents can do it.
This uses Warp's agent platform as part of it.
But you honestly, you don't have to use it.
I'm not trying to push into our product.
But this should give you a good sense of, OK,
if you want to set up an agent that does triage
or an agent that does spec writing,
how do you actually do that?
How do you get from the theory of working with a factory
to actually putting it into practice.
I don't know if we have the capability
to do questions in here.
I saved a few minutes for questions,
if anyone has questions, otherwise I will wrap up.
Yes?
Yeah, I have a question.
There's a bit of a tension in what you said,
where it's like you don't want to build it,
it's a lot of work.
Yes.
But you are also a factory builder,
like where do you get down to it?
It's a great question.
So I said something that's almost contradictory.
I think you should, the way you should think of it
is everyone's going to deploy some sort of factory,
but then the tuning of the factory,
the like, are these the right skills for my domain?
Is this factory building my product in the right way?
I still think there's a bunch
of interesting engineering challenges.
And for some places, you can build this.
But again, I think that you should probably be focusing
on building the core product for your company
for the most part, but there's a bunch of tuning
and figuring out how to make the factory work for your product that matters.
That's a great question.
Yes.
Hey, Tom.
Thank you so much.
I have a question.
So if you were an college student right now, and graduated and entered the workforce, where
would you expect that?
Yeah.
So the question in case people couldn't hear was if I was a college student graduating
and entering the workforce right now.
So I think that the most important skills in this new world are adaptability.
I think that's critical thinking, it's like the speed at which you can learn.
I do think, I don't know if you're a computer science student, but I still think there's
a ton of value in understanding the underlying systems and architecture and being able to
reason and understand the code, understand the specs that agents are writing.
So I would focus on those skills.
And like, I don't know, we're hiring more people than we've ever hired.
There's a lot of kind of like misdirection around like, you know, people not being hired
because of AI.
That's not the experience we've had so far.
And what I'm looking for are like really adaptable product focused thinkers who can like basically
be great problem solvers even as the underlying technology changes.
Yeah, I think I have time for one more question.
Yes?
What about the, like, so the question was what about the product taste in like the,
how do you actually build something useful I think is probably the right, like maybe
the framing and like where do the ideas come from?
And so I think that the problem with the factory metaphor, even though I'm like leaning into
it because I think that's like, there's something to it, is that it can kind of sound like mechanizing
or dehumanizing. And I still think underlying all of this, the only thing that matters is
are you building something useful? And if you have a factory that is churning out shit
that no one cares about, it's like what's the point? And I think that human taste, human
input, human product sense, humans guiding at those touch points where you can't automate
absolutely like essential and like that's like what I do I'm like I'm trying to
figure out what do customers want what do people want what's gonna be valuable to
them so I think that's an absolutely key point to it I think I'm at time so I have
to go I hope folks enjoyed this chat I'm really grateful for being invited to
speak so thank you all very much