# Harness Engineering: Scaling AI Agents in Enterprise Software

**Podcast:** Latent Space: The AI Engineer Podcast
**Published:** 2026-04-07

## Transcript

I do think that there is an interesting space to explore here with Codex, the harness as part of building AI products, right?
There's a ton of momentum around getting the models to be good at coding.
We've seen big leaps in like the task complexity with each incremental model release where if you can figure out how to collapse a product that you're trying to build, a user journey that you're trying to solve into code, it's pretty natural to use the Codex harness to solve that problem for you.
It's done all the wiring and lets you just communicate in prompts to let the model cook.
You have to step back, right?
Like you need to take a systems thinking mindset to things and constantly be asking, where is the agent making mistakes?
Where am I spending my time?
How can I not spend that time going forward and then build confidence in the automation that I'm putting in place so I have solved this part of the SDLC?
All right, we're in the studio with Ryan Lopopolo from OpenAI.
Welcome.
Hi.
Thanks for visiting San Francisco and thanks for spending some time with us.
Yeah, thank you.
I'm super excited to be here.
You wrote a blockbuster article on harness engineering.
It's probably going to be the defining piece of this emerging discipline.
Thank you.
It is fun to feel like we've defined the discourse in some sense.
Let's contextualize a little bit.
This first podcast you've ever done.
Yes.
And thank you for spending it with us.
Where is this coming from?
What team are you in?
All that jazz.
Sure, sure.
I work on Frontier product exploration, new product development in the space of OpenAI Frontier, which is our enterprise platform for deploying agents safely at scale with good governance in any business.
And the role of me and my team has been to figure out novel ways to deploy our models into package and products that we can sell as solutions to enterprises.
And you have a background, I'll just squeeze it in there.
Snowflake, Brex, Stripe, Citadel.
Yes.
The exact kind of customer.
My entire life.
Yes.
The exact kind of customer that you want to.
So I'll say I was actually, I didn't expect the background.
When I looked at your Twitter, I'm seeing the opposite, stuff like this.
So you've got the mindset of like full send AI coding, stuff about slop, like buckling in your laptop on your Waymos.
And then I look at your profile, I'm like, oh, you're just like, you're cracked in the other end too.
Perfect mix, perfect match.
It's quite fun to be AI maximalist.
If you're going to live that persona, OpenAI is the place to do it.
And it's certainly.
Token is what you say.
Yeah.
I have no rate limits internally and I can go, like you said, full send at this thing.
Yeah.
Yeah.
So the OpenAI Frontier and you're a special team within OpenAI Frontier.
We had been given some space to cook, which has been super, super exciting.
And this is why I started with kind of a out there constraint to not write any of the code myself.
I was figuring if we're trying to make agents that can be deployed into end enterprises, they should be able to do all the things that I do.
And having worked with these coding models, these coding harnesses over six, seven, eight months, I do feel like the models are there enough.
The harnesses are there enough where they're isomorphic to me and capability and the ability to do the job.
So starting with this constraint of I can't write the code meant that the only way I could do my job was to get the agent to do my job.
And like a, just a bit of background before that, this is basically the article.
So what you guys did is.
Five months of working on an internal tool, zero lines of code, zero, code over a mile, a million lines of code in the total code base.
You say it was Cenex more like it was Cenex faster than you would have if you had done it by hand.
So that was the mindset going into this, right?
Right.
That's right.
Started with some of the very first versions of Codex CLI with the Codex mini model, which was obviously much less capable than the ones we have today.
Which was also a very good constraint, right?
It's quite a visceral feeling to ask the model to build you a product feature.
Yeah.
It was not being able to assemble the pieces together, which kind of defined one of the mindsets we had for going into this, which is whenever the model just cannot, you always pop open the task, double click into it and build smaller building blocks that then you can reassemble into the broader objective.
And it was quite painful to do this.
Honestly, the first month and a half was 10 times slower than I would be.
But because we paid that cost.
Yeah.
We had to adapt the code base to something much more productive than any one engineer could be because we built the tools, the assembly station for the agent to do the whole thing.
But yeah, so onward to GPT-5, 5.1, 5.2, 5.3, 5.4 to go through all these model generations and see their kind of quirks and different working styles also meant we had to adapt the code base to change things up when the model was revved.
One interesting thing here is 5.2.
Yeah.
The code base that we had in the complex harness at the time did not have background shells in it, which means we were able to rely on blocking scripts to perform long horizon work.
But with 5.3 and background shells, it became less patient, less willing to block.
So we had to retool the entire build system to complete in under a minute.
And this is not a thing I would expect to be able to do in a code base where people have opinions, but because the only goal was to make the agent work.
So we had to make it more efficient.
It was, it was a very very quick we went from a bespoke make file build to Bazel to Turbo to NX and just left it there because builds were fast at that point.
Interesting.
Talk to me about Turbo to NX.
That's interesting because that's the other direction that other people have been doing.
Ultimately I have not a lot of experience with actual front end repo architecture.
You're talking about JavaScript builds as if sky.
So like I know the NX team, I know Turbo Jared Palmer.
And I'm like, yeah, that's an interesting better comparison.
The head of the team and not the Microsoft team.
Yeah, yeah.
And that's Tána Sigh, they're both really very good at her.
And we were able to make The hill we were climbing, right, was make it fast.
Is there a micro front-end involved?
How complex?
React, Electron, single app sort of thing.
And it must be under a minute.
That's an interesting limitation.
I'm actually not super familiar with the background shell stuff.
Probably was talked about in the 5.3 release.
It basically means that Codex is able to spawn commands in the background and then go continue to work while it waits for them to finish.
So it can spawn an expensive build and then continue reviewing the code, for example.
And this helps it be more time efficient for the user invoking the harness.
I guess just to really nail this, like, what does one minute matter?
Like, why not five?
We want the inner loop to be as fast as possible.
One minute was just a nice round number and we were able to hit it.
And if it doesn't complete, it kills it or something?
No, we just take that as a signal that we need to stop what we're doing.
Double click, decompose the build graph a bit.
To get the time back under so that we can enable the agent to continue to operate.
It's almost like you're, it's like a ratchet.
It's like you're forcing build time discipline because if you don't, it'll just grow and grow.
That's right.
And you mentioned that like the software I work on currently is at 12 minutes.
It sucks.
This has been my experience with platform teams in the past where you have an envelope of acceptable build times and you let it go up to breach.
And then you spend two, three weeks to bring it back down to the lower end to be able to load and stop.
But because tokens are so cheap and so insanely parallel with the model, we can just constantly be gardening this thing to make sure that we maintain these invariants, which means there's way less dispersion in the code and the SDLC, which means we can simplify in a way and rely on a lot more invariants as we write the software.
You mentioned in your article, like humans became the bottleneck, right?
You kicked off as a team of three people.
You're putting out a million line of code, like 1500 PRs.
Basically.
What's the mindset?
Yeah.
What's the mindset there?
So as much as code is disposable, you're doing a lot of review.
A lot of the article talks about how you want to rephrase.
Everything is prompting.
Everything is what the agent can't see.
It's kind of garbage, right?
You shouldn't have it in there.
So what's like the high level of how you went about building it and then how you address, okay, humans are just PR review.
Like how is human in the loop for this?
We've moved beyond even the humans reviewing the code as well.
Most of the human review is post-merge at this point, but it's not even reviewed.
That's just, oh, let's just make ourselves happy by reading it.
Fundamentally, the model is trivially paralyzable, right?
As many GPUs and tokens as I am willing to spend, I can have capacity to work on a code base.
The only fundamentally scarce thing is the synchronous human attention of my team.
There's only so many hours in the day.
We have to eat lunch.
I would like to sleep, although it's quite difficult to stop poking the machine because it makes me want to feed it.
You have to step back, right?
Like you need to take a systems thinking mindset to things and constantly be asking, where is the agent making mistakes?
Where am I spending my time?
How can I not spend that time going forward and then build confidence in the automation that I'm putting in place?
So I have solved this part of the SDLC.
And usually what that has looked like is like we started needing to pay very close attention to the code because the agent did not have the right building blocks to produce modular software that decomposed appropriately, that was reliable and observable and actually accrued a working front end in these things, right?
So in order to not spend all of our time sitting in front of a terminal, at most doing one or two things at a time, invested in giving the model that observability, which is that graph that's in the post here.
Yeah.
Let's walk through it.
Traces.
Which existed first?
We started with just the app.
And the whole rest of it from Vector through to...
Yeah.
Yeah.
The whole rest of it through to all these login metrics APIs was, I don't know, half an afternoon of my time.
We have intentionally chosen very high level, fast developer tools.
There's a ton of great stuff out there now.
We use Mies a bunch, which makes it trivial to pull down all these Go written Victoria stack binaries in our local development.
Tiny little bit of Python glue to spin all these up and off you go.
One neat thing here is we have tried to invert things as much as possible.
Which is instead of setting up an environment to spawn the coding agent into, instead we spawn the coding agent, like that's the entry point, just codecs.
And then we give codecs via skills and scripts, the ability to boot the stack if it chooses to.
And then tell it how to set some end variables so the app and local dev points at the stack that it has chosen to spin up.
And this I think is like the fundamental difference between reasoning models and the four ones, and the three ones.
And the four O's of the past, where these models could not think so you had to put them in boxes with a predefined set of state transitions.
Whereas here we have the model, the harness be the whole box and give it a bunch of options for how to proceed with enough context for it to make intelligent choices.
So sales.
So like a lot of that is around scaffolding, right?
Yes.
Previous agents, you would define a scaffold, it would operate in that loop, try again, that's pivoted off from.
That's a key factor.
reasoning models they're seeming to perform better when you don't have a scaffold right and you go into like niches here too like your spec.md and like having a very short agent.md agent.md yes yeah so you even lay out what it is here but i like the table contents like stuff like this it really helps guide people because everyone's trying to do this this structure also makes it super cheap to put new content into the repository to steer both the humans and the agents you reinvented skills right one big agent skills from first principles skills did not exist when we started doing this you have a short 100 line overall table of contents and then you have little skills right core beliefs md that tracker yeah yeah the skill is over the tech jet tracker and the quality score are pretty interesting because this is basically a tiny little scaffold like a markdown table which is a hook for codex to review all the business logic that we have defined in the app assess how it matches you to all these documented guardrails and propose follow-up work for itself before deeds and all these ticketing systems we were just tracking follow-up work as notes in a markdown file which we could spawn an agent on a cron to burn down there's this really neat thing that like the models fundamentally crave text so a lot of what we have done here is figure out ways to inject text into the system right when we get a page because we're missing a timeout for example i can just add codex in slack on that page and say i'm going to fix this by adding a timeout please update our reliability documentation to require that all network calls have timeouts so i have not only made a point in time fix but also like durably encoded this process knowledge around what good looks like yeah and we give that to the root coding agent as it goes and does the thing but you can also use that to distill tests out of or a code review agent which is pointed at the same things to narrow the acceptable universe of the code that's produced i think one of the concerns i have with that kind of stuff is you think you're making the right call by making it persisted for all time across everything yes but then you didn't think about the exceptions that you need to make right and then you have to roll it back part of it is also sometimes you can follow your instructions too it's somewhat a skill right so it determines when it uses the tools right like it's not like it'll run at every call it'll determine when it wants to check quality score right yeah and we do in the prompts we give these agents allow them to do that so when we first started adding code review agents to the pr it would be codec cli locally writes the change it pushes up a pr on those pr synchronizations a review agent fires it posts a comment we instruct codecs that it has to at least acknowledge and respond to that feedback and initially the codecs driving the code author was willing to be bullied by the pr reviewer which meant you could end up in a situation where things were not converging so yeah we had you should thrash add more optionality to the prompts on both of these things right the reviewer agents were instructed to bias toward merging the thing to not surface anything greater than a p2 in priority we didn't really define p2 but we gave it good fine p2 we gave it a framework within which to score its output and then greater than p0 is worse right yes p0 is you will need a code place if you merge this thing right but also on the code authoring agent side we also gave it the flexibility to either defer or push back against review feedback right it happens all the time right like i happen to notice something and leave a code review which could blow up the scope by a factor of two i usually don't mean for that to be addressed exactly in the moment it's more of an fyi file it to the backlog pick it up in the next fix it week sort of thing and without the context that this is permissible the coding agents are going to bias toward what they do which is following instructions yeah i do want it to check in on a couple things right like sure all the coding review agent it can merge autonomously i think that's something that a lot of people are comfortable with and you have a list here of how much agents do they do product code and tests ci configuration and release tooling internal dev tools documentation eva harness review comments scripts that manage the repository itself production dashboard definition files like everything yes and so they're just all churning at the same time is there like a record that that any human on the team pulls to stop everything because we are building a native application here we're not doing continuous deploy so there's still a human in the loop for cutting the release branch we require a bless human approved smoke test of the app before we promote it to distribution these sort of things so you're working on the app you're not building like infrastructure where you have like nines of reliability that kind of stuff that's correct that's correct okay and also like full recognition here that all of this activity took in a completely greenfield repository there should be no sure that this applies generally this is a production thing you're going to ship to customers of course yeah so this is real and like one of the things there as you mentioned you started this as a repo from scratch the onboarding first month or so was pretty it was like working backwards right and then you had to work with the system and now you're at that point where you know you're very autonomous i'm curious like okay so what how human in the loop is it so what are the bottlenecks that you wish you could still automate and part of that is also like where do you see the model trajectory improving and offloading more human in the loop we just got 5.4 and it's a fantastic model by the way yeah yeah it's the first one that's merged top tier coding so it's codex level coding and reasoning so general reasoning both in one model so and computer use and vision now whatever now with 5.4 i can just have codex write the blog post whereas for this one i had to balance between chat and oh i need to um i might be out of a job oh my god you just gave me an idea for a completely ai newsletter that 5.4 could do this sort of thing is just one example of closing the loop right like the dashboard thing you mentioned we have codex authoring the json for the grafana dashboards and publishing them and also responding to the pages which means when it gets the page it knows exactly which dashboards are defined and what alerts what alert was triggered by which exact log in the code base because all this stuff is collated together it has to own everything yes yeah and it means that if we have results in a page it has the existing set of dashboards available to it it has the existing set of metrics and logs and can figure out where the gaps in the dashboard are or in the underlying metrics and fix them in one go in the same way you would have a full stack engineer be able to drive a feature from the back end all the way to the front end so it seems like a lot of the work you guys had to do was you as a small team are fully working for a way that the model wants the software to be written it's like less human legible for better code legibility than the agent legibility how do you think that affects broader teams so one at openai do you liaison like this is how software should be written like i can imagine say you join a new team with this methodology this mindset there's ways that teams do code review teams write code like teams are structured and a lot of it is for human legibility so should we all swap like how does this play back one broader into openai and then like broader into the software engineering right is it like teams that pick this up well it's pretty drastic right you have to make a pretty big switch Should they just full send?
Yeah.
The mindset is very much that I'm removed from the process, right?
I can't really have deep code level opinions about things.
It's as if I'm group tech leading a 500 person organization.
Yeah.
Like it's not appropriate for me to be in the weeds on every PR.
This is why that post merge code review thing is like a good analog here, right?
Like I have some representative sample of the code as it is written.
I have to use that to infer what the teams are struggling with, where they could use help, where they're already moving quickly, and I can pivot my focus elsewhere.
So I don't really have too many opinions around the code as it is written.
I do, however, have a command base class, which is used to have repeatable chunks of business logic that comes with tracing and metrics and observability for free.
And the thing to focus on is not how that business logic is structured.
But.
That it uses this primitive, because I know that's going to give leverage by default.
Yeah.
Yeah.
Back to that sort of systems thinking.
Yeah.
And you have part of that in your blog posts, enforcing architecture and taste, how you set boundaries for what's used.
There's also a section on redefining engineering and stuff, but yeah, it's just, it's interesting to hear.
And as the models have gotten better, they have gotten better at proposing these abstractions to unblock themselves, which again, lets me move higher and higher up the stack to look deeper into the future on what.
Ultimately.
Is a block the team from shipping.
Yeah.
You mentioned, so you, this is primarily a, it's like a 1 million line of code base, Electron app, but it manages its own services as well.
So it's like a backend for front end type thing.
We do have a backend in there, but that's hosted in the cloud.
This sort of structure is actually within the separate main and renderer processes within the Electron.
That's just how Electron works.
Yeah.
Yeah.
Of course.
So I have also treated like MVC style decomposition with the.
Yeah.
Same level of rigor, which has been very fun.
I have a fun pun.
This is like.
Okay.
Okay.
tangent.
MVC is model view controller.
Any sort of full stack web dev knows that.
But my AI native version of this is model view claw.
The claw is the harness.
That's right.
That's right.
I do think that there is an interesting space to explore here with Codex, the harness as part of building AI products, right?
There's a ton of momentum around getting the models to be good at coding.
We've seen big leaps in the task complexity with each incremental model release where if you can figure out how to collapse a product that you're trying to build, a user journey that you're trying to solve into code, it's pretty natural to use the Codex harness to solve that problem for you.
It's done all the wiring and lets you just communicate in prompts to let the model cook.
Yeah, it's been very fun.
And it's also a very engineering legible way of increasing.
It's fantastic, right?
Yeah.
You just give the model scripts, the same scripts you would already build for yourself.
Yeah.
Yeah.
So for listeners, this is Ryan saying that software engineering or coding agents will eat knowledge work, like the non-coding parts that you would normally think, oh, you have to build a separate agent for it.
No, start with a coding agent and go out from there, which OpenClaw has.
Yes.
Pie under the hood.
Yes.
Basically define your task in code.
Everything is a coding agent.
By the way, since I brought it up, it's probably the only place we bring it up.
Is any OpenClaw usage from you?
Any?
No, no, not for me.
I don't have any spare Mac minis rattling around my house.
You can afford it.
No, I just, I'm curious if it's changed anything in OpenAI yet, but it's probably early days.
And then the other thing I want to pull on here is like you mentioned ticketing systems and you mentioned PRs, and I'm wondering if both those things have to go away or be reinvented for this kind of coding.
So the Git itself and is like very hostile to multi-agents.
Yeah.
We make very heavy use of work trees.
But like, even then, like I just did a drop the podcast yesterday with cursor saying, and they said, and they're getting rid of work trees because it still has too many merge conflicts.
It's still too unintuitive, but go ahead.
The models are really great at resolving merge conflicts and to get to a state where I'm not synchronously in the loop in my terminal.
I almost don't care that there are merge with disposable.
Yeah.
We invoke a dollar land skill and that coaches codecs to push the PR wait for human and agent reviewers.
For CI to be green, fix the flakes.
If there are any merge upstream, if the PR comes into conflict, wait for everything to pass, put it in the merge queue, deal with flakes until it's in main.
And this is what it means to delegate fully, right?
This is in a very large model repo, probably a significant tax on humans to get PRs merged, but the agent is more than capable of doing this.
And I really don't have to think about it other than keep my laptop open.
I used to be much more of a control freak, but now I'm like, yeah, actually you could do a better job with this than me.
With the right context.
Yes.
Anything else in HarnessEng in general?
Just this piece.
I just want to make sure we...
I think one thing that I maybe didn't make super clear in the article that I heard on Twitter as an interesting...
Let's respond to them.
What's the chatter and then what's your response?
Ultimately, all the things that we have encoded in docs and tests and review agents and all these things are ways to put...
Yeah.
All the non-functional requirements of building high-scale, high-quality, reliable software into a space that prompt injects the agent.
We either write it down as docs, we add lints where the error messages tell how to do the right thing.
So the whole meta of the thing is to basically tease out of the heads of all the engineers on my team, what they think good looks like, what they would do by default, or what they would coach a new hire on the team to do, to get things to merge.
Yeah.
And that's why we pay attention to all the mistakes, mistakes that the agent makes, right?
This is code being written that is misaligned with some as-yet-not-written-down non-functional requirement.
Sorry, what did the online people misunderstand or...
No, somebody just literally said that.
I was like, oh, yeah.
Okay.
This is the thing.
This is what I've been doing.
Oh, I see.
Interesting.
One other neat thing, which I totally did not expect, is folks were just taking the link to the article and giving it to Pi or Codex and say, make my repo this.
You can achieve a whole recursion.
And it was wildly effective.
Really?
It was wildly effective.
No way.
It just actually is something I tried with 5.4 yesterday.
I didn't have that much time.
I was like out speaking at something, and this is one of my things.
I was like, okay, I have this article.
Can we just scaffold out what it would be like to run this?
And I did it first as that.
And then I was like, okay, let me take another little side repo and say, okay, if I was to fully automate this like this, because I haven't written a line of code, it's like...
It's just a side thing.
I'm doing voice, TTS.
I'm just like slobbing out, whatever.
It's nothing production.
I'm like, how would I make this like this?
And it's actually like a really good way.
It's like a good way to learn what could be changed.
What could be like, it's just a good analyzing, right?
You give it all the code, you give it all the context, you give it the article and it walks you through it very well.
That's right.
That's right.
I guess one more thing before we go to Symfony is I wanted to cover Brett Taylor's response.
We had him on the show.
He is your chairman, which is wild that he's reading your articles as well and like getting engaged in it.
He says, software dependencies are going away, basically.
They can just be like vendored.
Yes.
Response.
A hundred percent.
A hundred percent agree.
You still have PromQL.
You still pay Datadog.
You still pay Temporal.
Thank you.
Yep.
The level of complexity of the dependencies that we can internalize is, I would say, low medium right now, just based on model capability.
What is medium?
I would say like a couple thousand line dependency is a thing that we could in-house, no problem, in an afternoon of time.
One neat thing about it is like probably most of that you don't even need, like by in-housing and abstraction, you can strip away all the generic parts of it and only focus on what you need to enable the specific thing you're building.
I've been calling this the end of bullshit plugins.
Yeah.
Because it's so much, when I publish an open source thing, I want to accept everything and be liberal.
I want to accept this is Postel's law, but that means there's so much bloat.
There's so much overhead.
One other neat thing about this too is when we deploy Codex security on the repo, it is able to deeply review and change the code.
Change the internalized dependencies in a much lower friction way than it would be to like push patches upstream, wait for them to be released, pull them down, make sure that's compatible with all the transitives I have in my repo and things like that.
So it's also much lower friction to internalize some of these things if code is free because the tokens are cheap sort of thing.
I think like the only argument I have against this is basically scale testing, which obviously the larger pieces of software like Linux, MySQL, he calls that, but even the data dollars and temporals.
And then maybe security testing where classically, I think, is it Linus Torvalds who said open source is the best disinfectant?
Many eyes.
Many eyes.
And if inline your dependencies and code them up, you're going to have to relearn mistakes from other people.
Yep.
And to internalize that dependency, you're back to zero and you have to start reassembling all those bits and pieces to have high confidence in the code as it is written.
Yeah.
Even part of the first intro of this, you basically mentioned like everything was written by Codex, including internal tooling, right?
Yes.
So internal tooling, like when you're visualizing what's going on, it's writing it for itself.
Yeah.
I built internal tooling for AI now and like I just showed them off and they're like, how long did you spend?
And I didn't spend any time.
I just prompted it.
Very funny story here.
Yeah.
Go ahead.
We had deployed our app to the first dozen users internally.
I had some performance issues, so we asked them to export a trace for us, get a tarball, gave it to our on-call engineer.
And.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
He did a fantastic job of working with Codex to build this beautiful local dev tool, Next.js app that you drag and drop the tarball in and it visualizes the entire trace.
Oh, it's fantastic.
It took an afternoon, but none of this was necessary because you could just spin up Codex and give it the tarball and ask the same thing and get the response immediately.
So in a way, optimizing for human legibility of that debugging process was wrong.
It kept him in the loop unnecessarily when instead he could have just like, Codex cooked for five minutes and gotten the same.
Yeah, you have to fight your instincts here.
This is how we used to do it.
Or this is how I would have used to solve it.
Yeah.
In this local observability stack, like, sure, you can deploy Jaeger to visualize the traces, but I wouldn't expect to be looking at the traces in the first place because I'm not going to write the code to fix them.
Yeah.
So basically it needs to be like this kind of house stack and owning the whole loop.
I think that is very well established and it sounds like you might be like sharing more about that in the future.
Right?
Yeah.
We're going to talk about Symfony in a little bit, but like the way we distributed it as a spec, which I think folks are calling ghost libraries on Twitter.
This is like a, such a cool name.
It does mean it becomes much cheaper to share software with the world, right?
You define a spec, how you could build your own specifying as much as is required for a coding agent to reassemble it locally.
The flow here is very cool.
Like we have taken all the scaffolding that has existed in our proprietary.
Repo spun up a new one, ask Codex with our repo as a reference, write the spec.
We tell it spin up a Tmux, spawn a disconnected Codex to implement the spec, wait for it to be done, spawn another Codex and another Tmux to review the spec or review the implementation compared to upstream and update the spec.
So it diverges less.
And then you just loop over and over Ralph style until you get a spec that is with high fidelity able to reproduce the system.
As it is.
It's fantastic.
And you're basically, you're not really adding any of your human bias in there, right?
That's correct.
A lot of times people write a spec and be like, okay, I think it should be done this way and you'll riff on something and it's no, that agent could have just handled it.
Like you're still scaffolding in a sense, right?
I want it done this way.
It can determine that spec better.
That's right.
That's right.
Part of me, I've been working a lot on evals recently.
And part of me is wondering if an agent can produce a spec that it cannot solve.
Is it always capable of things that it can imagine?
Or can you imagine things that it is?
It's impossible to do.
I think with Symfony, we there's like this, there's this axis where you have things that are easier, hard or established or new.
Right.
And I think things that are hard and new is still something that the models need humans yet drive.
But I think those other quadrants are largely salt given the right scaffold and the right thing that's going to drive the agent to completion.
It's crazy that it's all, but it means that the humans, the ones with limited time and attention get to work on the hardest stuff.
Like the problems where it's pure white space out in front or like the deepest refactorings where you don't know what the proper shape of the interfaces are.
And this is where I want to spend my time because it lets me set up for the next level of scale.
Yeah.
Yeah.
Amazing.
Let's introduce Symfony.
I think we've been mentioning it every now and then.
Elixir.
Interesting option.
Yeah.
Yeah.
Again, like the Elixir manifestation here is just a derivative.
Is it a model chosen?
Yeah.
And it chose that because the process supervision and the gen servers are super amenable to the type of process orchestration that we're doing here.
You are essentially spinning up little daemons for every task that is in execution and driving it to completion, which means the model gets a ton of stuff for free by using Elixir and the Beam.
I had to go do a crash course in Beam and Elixir.
And I think most people are not operating at that scale of concurrency where you need that.
It's a good, good mental model for resumability and all those things.
And these are things I care about.
But tell me the story, the origin story of Symfony.
What do you use it for?
Is this, how did it form?
Maybe any abandoned paths that you didn't take?
At the end of December, we were at about three and a half PRs per engineer per day.
So it was before 5.2 came out.
In the beginning of January, everyone gets back from holiday with 5.2 and no other work on the repository.
We were up in the five to ten days.
Yeah.
Up to 10 PRs per day per engineer.
And I don't know about y'all, but like it's very taxing to constantly be switching like that.
Like I was pretty tapped out at the end of the day.
Again, where are the humans spending their time?
They're spending their time context switching between all these active TMUX panes to drive the agent forward.
Yeah.
So let's again, build something to remove ourselves from the loop.
And this is what Frantic sprinted after here to find a way to remove the need for the human to sit in front of their terminal.
So a lot of experimentation with dev boxes and automatically spinning up agents.
Like it seems like a fantastic end state here where my life is beach.
I open live twice a day and say yes, no to these things.
And this is again, a super, super interesting framing for how the work is done because I become more latency insensitive.
I have way less attachment to the code.
Yeah.
code as it is written like i've had close to zero investment in the actual authorship experience so if it's garbage i can just throw it away and not care too much about it in symphony there's this like rework state where once the pr is proposed and it's escalated to the human for review it should be a cheap review is either mergeable or is not and if it's not you move it to rework the elixir service will completely trash the entire work tree and pr and start it again from scratch and this is that opportunity again to say why was it trash right what did the agent do that was yeah yeah fix that before moving the ticket to the progress again yeah why is this not in codex app is i guess it's you guys are ahead of codex app yeah so the way the team has been working is basically to be as ai pilled as possible and spread the head and a lot of the things we have worked on have fallen out into a lot of the products that we have like we were in deep consultation with the codex team to have the codex app be a thing that exists right to have skills be a thing that codex is able to use so we didn't have to roll our own to put automations into the product so all of our automatic refactoring agents didn't have to be these hand-rolled control loops it has been really fantastic to be in a way unanchored to the product development of frontier and codex and just very quickly try to figure out what's works and then later find the scalable thing that can be deployed widely it's been a very fun way to operate it's certainly chaotic i have lost track very often of what the actual state of the code looks like because i'm not in the loop there was one point where we had wired playwright directly up to the electron app with mcp mcp is i'm pretty bearish on because the harness forcibly injects all those tokens in the context and i don't really get a say over it and i don't really get a say over it they mess with auto compaction the agent can forget how to use the tool there's probably only what three calls in playwright that i actually ever want to use so i pay the cost for a ton of things somebody vibed a local daemon that boots playwright and exposes a tiny little shim cli to drive it and i had zero idea that this had occurred because to me i run codex and it's able to so it's better yeah like no knowledge of this at all so we have had in human space to spend a lot of time doing synchronous knowledge sharing we have a daily stand-up that's 45 minutes long because we almost have to fan out the understanding of the current state i was going to say this is good for a single human multi-agent but multi-human multi-agent is a whole like explosion of stuff yeah and that this is fundamentally why we have such a rigid like 10 000 engineer level architecture in the app because we have to find ways to carve up the space so people are not trampling on each other sorry i don't get the 10 000 thing did i miss that the structure of the repository is like 500 npm packages it's like architecture to the access for what you would consider i think normal for a seven person team but if every person is actually like 10 to 50 then the like numbers on being super super deep into decomposition and sharding and like proper interface boundaries make a lot more sense yeah to me that's why i talked about microphone ends and an access from that world but cool it's just coming back to to this i don't know if you have other thoughts on orchestrating so much work coin going through this is this enough is this like at any aha moments it'll be interesting to see like where okay so right now you pick linear as your issue tracker right or it's like a li is it actually linear this is actually linear oh that's linear it's linear oh i never look at anymore video the demo video i had to download to run Because I'm a Slack maxi, but Linear is also really good.
Yes.
We do make a good use of Slack.
We fire off Codex to do all these low-sha-slash-ity fix-ups, the things that, like, sink that knowledge into the repository.
It's super cheap.
Just do it in Codex.
My biggest plug is OpenAI needs to build Slack.
You need to own Slack, build yours, turn this into Slack.
I did read...
You don't know how to do this?
I would say that if we think that we want these agents to do economically valuable work, which is, like, this is the mission, right?
We want AI to be deployed widely to do economically valuable work.
Then we need to find ways for them to naturally collaborate with humans, which means collaboration tooling, I think, is an interesting space to explore.
Yeah, totally.
GitHub, Slack, Linear.
Yeah, that was kind of my thing.
Okay, where do we see...
Right now, Codex has started Codex model, then CLI.
Now there's an app.
App can let me shoot off multiple Codexes in parallel, but there's no great team collaboration for Codex.
And it seems...
It seems like your team had some say into what comes out, right?
So you talked to them.
Codex kind of was a thing from there.
If you guys are on the bound, what stuff that, like, you might not focus on, but what do you expect other people to be building, right?
So people that are, like, 5X, 50Xing, should you build stuff that's, like, very niche for your workflow, for your team?
Should it be more general so other people can adopt this or a niche there?
Because part of it is just, okay, is everything just internal tooling?
Do we have everything our own way?
Like, the way our team operates has our own ways that we like to communicate?
Or is there a broader way to do it?
Is it something like an issue tracker?
Just thoughts, if you want to riff on that.
I think TBD.
We have not figured this out in a general way.
I do think that there is leverage to be had in making the code and the processes as much the same as possible.
If you think that code is context, code is prompts, it's better from the agent behavior perspective to be able to look in a package in directory XYZ and it not to have to page so deeply into directory ABC because they have the same structure, use the same language, they have the same patterns internally.
And that same, like, leverage comes from aligning on a single set of skills that you're pouring every engineer's taste into to make sure that the agent is effective.
So like in our code base, we have, I think, six skills.
That's it.
And if some part of the software development loop is not being covered, our first attempt is to encode it in one of the existing sites.
And that's how we set up skills, which means that we can change the agent behavior more cheaply than changing the human driver behavior.
Yeah.
Have you ever experimented with agents changing their own behavior?
We do.
Yeah.
A parent agent changing a subagent's behavior or something like that.
We have some bits for skill distillation.
So for example, there's one neat thing you can do with Codex, which is just pointed at it's on session logs to ask it to tell you how you can use.
The tool better introspection or ask it to do things better.
So can I do this session better?
What skills should I, I like the modification of you can do, just do things too.
You can just ask the agent to do things.
Yeah.
You can just Codex things.
This is like a, this is like a silly emoji that we have.
I, you can just Codex things.
You can just prompt things.
It's really glorious future we live in, but okay.
You can do that one-on-one, but we're actually slurping these up for the entire team into blob storage and running agent loops over them every day.
To figure out where as a team, can we do better?
And how do we reflect that back into the repository though?
Everybody benefits from everybody else's behavior for free.
Same for like PR comments, right?
These are all feedback.
That means the code as written deviated from what was good.
A PR comment, a failed build.
These are all signals that mean at some point the agent was missing context.
We've got to figure out how to slurp it up and put it back in the reboot.
By the way, I do this exactly right.
I used to, when I use cloud code for.
A lot of cool work is like a nice product, right?
And I think you would agree.
I always have it tell me what do I do better next time?
And that's the meta programming reflection thing.
So I was thinking like you have six reflection extraction levels in Symfony and almost like the zeroth layer.
So the six levels are policy, configuration, coordination, execution, integration, observability.
We've talked about a couple of these, but the zeroth layer is like the, okay.
Are we working well?
Can we improve how we work?
Yes.
Can I modify my own workflow.md or something?
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
I don't know.
Yeah, of course.
Yeah.
Of course you can.
Like this thing is also able to cut its own tickets because we give it full access.
You can make a ticket to have it cut tickets.
You can put in the ticket that you expect it to file as a follow up work.
Like.
Self-modifying.
Yeah.
Yeah.
Put, don't put the agent in a box.
Give the agent full accessibility over its domain.
I had a mental reaction when you said don't put an agent in a box.
So I think it should put it in a box.
Like it's just that you're giving the box everything it needs.
Yeah.
Contacts and tools.
But we're like, as developers, we're used.
To calling out to different systems.
But here you use the open source things like the Prometheus, whatever.
And you run it locally so that you can have the full loop.
I assume.
Yep.
I think like.
Another thing.
You want to minimize cloud dependencies.
You also want to make sure that you think about what the agent has access to.
What does it see?
Does it go back into the loop?
Like from the most basic sense of you let it see its own like calls, traces.
It can determine where it went wrong.
But are you feeding that back in?
So, you know, just the most basic level, if you want to see exactly what's input output, like.
Does the agent have access to what is being outputted, right?
It can self-improve a lot of these things.
It's all text, right?
My job is to figure out ways to funnel text from one agent to the other.
It's so strange.
Like way back at the start of this whole AI wave, Andre was like, English is the hottest new programming language.
It's here.
It's here.
Yeah.
The features.
Yeah.
A lot of, okay.
Like a lot of software, a lot of stuff.
There's a GUI.
It's made for the human.
We're seeing the evolution of CLIs for everything, right?
All tools have CLIs.
Your agents can use them well.
Do we get good vision?
Do we get good little sandboxes?
Like right now it's a really effective way, right?
Models love to use tools.
They love to bash.
They love to read through text.
So slap a CLI, let it go loose.
That works for everything?
It does.
Yeah.
We've also been adapting non-textual things to that shape in order to improve model behavior in some ways, right?
We want the agent to be able to see the UI.
Agents do not perceive visually in the same way.
That we do.
They don't see a red box.
They see red box button, right?
They see these things in latent space.
So if we want.
Hey, Alejandro, we have a thing that goes off every time you're sitting in space.
Ding.
Anyway, if we want to actually make it see the layout, it's almost easier to rasterize that image to ASCII Arc and feed it in to the agent.
And there's no reason you can't do both, right?
To like further refine how the model perceives the.
Object it's manipulating.
Cool.
Can we, you want to talk about a couple more of these layers that might bear more introspection or that you have personal passion for?
I will say that the coordination layer here was a really tricky piece to get right.
Let's do it.
Yeah.
I'm all about that.
And this is temporal square thing.
This is where, when we turn the spec into Elixir, where like the model takes a shortcut, right?
It like is, oh, I have all these primitives that I can make use of in this lovely runtime that has native.
Process supervision, which is I think a neat way to have taken the spec and made it more achievable by making choices that naturally map to the domain.
Right.
In the same way that like you would prefer to have a TypeScript model repo if you are doing full stack web development, right?
Because the ability to share types across the front end and back end reduces a lot of complexity and because it's what GraphQL used to be.
That's right.
And.
I don't know.
I don't know if it's still alive, but it's.
No humans in the loop here.
So like my own personal ability to write or not write Elixir doesn't really have to bias us away from using the right tool for the job, which is just wild.
Love it.
I love it.
Yeah.
I wonder if any languages struggle more than others because of this.
I feel like everyone has their own abstractions that would make sense, but maybe it might be slower.
It might be more faulty where like, you'd have to just kick the server every now and then.
I don't know.
I think observability layer is really well understood.
Integration layer, MCP is dead.
I think all these are just like a really interesting hierarchy to travel up and down.
It's common language for people working on the system to understand.
The policy stuff is really cool, right?
Yeah.
You don't really have to build a bunch of code to make sure the system waits for CI to pass.
It's your institutional knowledge.
Yeah.
You just give it the GH CLI with some text to say, CI has to pass.
It makes the maintenance of these systems a lot easier.
Do you think that CLI has to pass?
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
Yeah.
glance at the diff and be like sure thing send it but the clis are nice because they're super token efficient and they can be made more token efficient really easily like i'm sure you all have seen like i go to build kite or jenkins and i could just get this massive wall of build output and in order to unblock the humans your developer productivity team is almost certainly going to write some code that parses the actual exception out of the build logs and sticks it in a sticky note at the top of the page and you basically want clis to be structured in a similar way right you're going to want to pass dash silent to prettier because the agent doesn't care that every file was already formatted it just wants to know it's either formatted or not so it can then go run a write command similarly like in our pmpm distributed script runner we're we had one when you do dash recursive like it produces a absolute mountain of text but all of that is for passing test suites so we ended up wrapping all of this in another script to suppress the which you can vibe the one channel output the failing parts of the test you make a pipe errors versus the standard send it out i i don't know okay whatever i used to maintain a cli for my company Yeah, this is like very core to my heart, but you're vibing my job.
That's right.
Cool.
Any other things?
This is a long spec.
I appreciate that.
It's got a lot of strong opinions in here.
Any other things that we should highlight?
I think obviously you can spend the whole day going through some of these, but I do think that some of these have a lot of care or some of this you might want to tell people, hey, take this, but make it your own.
Yeah.
Fundamentally, software is made more flexible when it's able to adapt to the environment in which it is deployed, which means that things like linear or GitHub even are specified within the spec, but not required pieces of it.
There's like a more platonic ideal of the thing that you could swap in like Jira or Bitbucket, for example.
But being able to tightly specify things like the ID formats or how the...
Ralph loop works for the individual agents basically means you can get up and running with a fully specified system quickly that you then evolve later on.
I think we never intended for this to be a static spec that you can never change.
It's more like a blueprint to get something up and running for you then to vibe later till your heart's content.
You have like code and scripts in here where it's all...
I think this is a really good prompt.
It's just a very long prompt.
Fundamentally, the agents are good at following instructions, so give them instructions and it will improve the reliability of the result.
Much like the way we use Symfony, we don't want folks to have to monitor the agent as it is vibing the system into existence.
So being very opinionated, very strict around what the success criteria are means that our deployment success rate goes up.
Yeah.
It means we don't have to get tickets on this thing.
I think it all goes back to that, like go to disposable, right?
Like early on when you had CLIs or you'd kick off a Codex run, it would take two hours.
You would want to monitor, okay, I'm in the workflow of just using one.
I don't want it to go down the wrong path.
I'll cut it off and then just shoot off four.
Like that was my favorite thing of the Codex app, right?
Just four exit, like it's okay.
One of them will probably be right.
One of them might be better.
Stop overthinking it.
Like my first example is probably like deep research.
When you put out deep research and I'd ask it something like I asked it something about LLM, it thought it was legal or something and spent an hour, came back with a report.
I was completely off the rails and I was like, okay, I got to monitor this thing a bit.
No, don't monitor it.
Just, you want to build it so that it goes the right way.
And you don't want to, you don't want to sit there and babysit, right?
You don't want to babysit your agents.
With that deep research query that you made, looking at the bad result, you probably figured out you needed to tweak your prompt a bit, right?
That's that guardrail that you fed back into the code base for the task, your prompt to further align the agent's execution.
Same sort of concepts apply there too.
When you talk, how are the customers feeling?
For Symfony, I think we have none, right?
This is a thing we have put out into the world.
Symfony is internal, right?
As long as you're happy, you're the customer.
That's right.
Just what's the external view?
I'd say folks are very excited about this way of distributing software and ideas in cheap ways.
For us as users, it has again pushed the productivity 5x, which means I think there's something here that's like a durable pattern around removing the human from the loop.
And figuring out ways to trust the output.
The video that is shared here is the same sort of video we would expect the coding agent to attach to the PR that is created.
That's part of building trust in the system.
And that's, to me, like fundamentally what has been cool about building this is it more closely pushes that persona of the agent working with you to be like a teammate.
I don't shoulder surf you like for the tickets.
You work on during the week.
I would never think that I would want to do that.
I wouldn't want a screen recording of your entire session in Cursor or Cloud Code.
I would expect you to do what you think you need to do to convince me that the code is good and mergeable and compress that full trajectory in a way that is legible to me, the reviewer.
It's stuff.
And you can just do that because Codex will absolutely sling some FX around.
It's great.
Oh, everything.
FFmpeg is the OG, like, god CLI.
Yeah, Swiss army chainsaw.
I used to say there's a SaaS, micro SaaS, let's call it, in every flag in FFmpeg.
Oh, for sure.
You know what I mean?
For sure.
Just host it as a service, put a UI on it.
People who don't know FFmpeg will pay for it.
When we were first experimenting with this, it was a wild feeling to be at the computer with just like windows just popping up all over the place and getting captured and files appearing on my desktop.
Like, very much.
Felt like the future to have a thing controlling my computer for, like, actual productive use.
Like, I'm just there keeping it, like, awake, jiggling the mouse every once in a while.
That's what some office workers do.
So they buy a mouse jiggler.
That's right.
One thing I wanted to ask, okay, as stuff is so code is disposable, async, shoot off a bunch of agents, one question is, okay, are you always like a extra high thinking guy?
And where do you see Spark?
So 5.3 Spark.
There's a lot of me wanting to make quick.
Quick changes.
I'm not going to open up a ID.
I'm not going to do anything, but I will say, okay, fix this little thing, change a line, change a color.
Spark is great for that.
But am I still the bottleneck?
Like, why don't I just let that go back and like, just riff on that?
Is there.
Spark is such a different model compared to the, the extra high level reasoning that you get in these.
Yeah.
To be fair for people, it is a different model, different architecture, different, like doesn't support it.
It's just, it's incredibly fast.
Smaller model.
I have not quite figured out how to.
Use it yet.
To be honest, I use faster.
I was adapting it to the same sorts of tasks I would use X high reasoning for.
Yeah, I know.
And it would blow through three compactions before writing a line of code.
And that's another big thing with 5.4, right?
Million coking context, which is huge in agentics, right?
Like you can just run for longer before you have to compact the more tokens you can spend on a task before compacting, like the better you'll do.
That's right.
That's right.
I'm not sure how to deploy Spark.
I think your intuition is right.
That.
It's very.
Great.
For spiking out prototypes, exploring ideas quickly, doing those documentation updates.
It is fantastic for us in taking that feedback and transforming it into a lint where we already have good infrastructure for ES lints in the code base.
These sorts of things it's great at, and it allows us to unblock quickly doing those like anti-fragile healing tasks in the code base.
Yeah.
That makes sense.
So you're pushed, you guys are pushing models to the fricking limit.
What can cart models not do well yet?
They're definitely not there on being able to go from new product idea to prototype single one shot.
This is where I find I spend a lot of time steering is translating end state of a mock for a net new thing, right?
Think no existing screens into product that is playable with similarly, while this has gotten better with each model release, like the gnarliest refactorings are the ones that I spend.
My most time with right.
The ones where I am interrupting the most, the ones where I am now double-clicking to build tooling, to help decompose monoliths and things like that.
This is a thing I only expect to get better, right?
Over the course of a month, we went from the low complexity tasks to like low complexity and big tasks in both these directions.
So this is what it means to not bet against the model, right?
You should expect that it is going to push itself out into these higher and higher complexity spaces.
Yeah.
So the things we do are robust to that.
It just basically means I'll be able to spend my time elsewhere and figure out what the next bottleneck is.
I do think it's also a bit of a different type of task, right?
Codex is really good at code base, understanding, working with code bases, but companies like lovable bolt replant, they solve a very different problem.
Scaffold of zero to one, right?
Idea at a product.
And it's there, there are people working on that and models are also pushing like step function changes there.
It's just different than the software engineering agents today.
Right?
Like I said, the model is isomorphic to myself.
The only thing that's different is figuring out how to get what's in here into context for the model.
And for these white space sort of projects, I myself, I'm just not good at it.
Which means that often over the agent trajectory, I realized the bits that were missing, which is why I find I need to have the synchronous interaction.
And I expect with the right harness, with the right scaffold, that's able to tease that out of me or.
Refine the possible space, right?
To be super opinionated around the frameworks that are deployed or to put a template in place, right?
These are ways to give the model all those non-functional requirements, that extra context to anchor on and avoid that wide dispersion of possible outcomes.
Thank you for that.
I want to talk a little bit about Frontier.
Yeah, sure.
Overall, you guys announced it maybe like a month ago and there's a few charts in here and it's basically like your enterprise offering is what I view it.
Is there one product or is there many?
I can't speak to the full product roadmap here, but what I can say is that Frontier is the platform by which we want to do AI transformation of every enterprise and from big to small.
And the way we want to do that is by making it easy to deploy highly observable, safe, controlled, identifiable agents into the workplace.
We want it to work with your company native IAM stack.
We want it to.
We want it to be able to plug into the security tooling that you have.
We want it to be able to plug into the workspace tools that you use.
So you're just going to be stripping specs, right?
We expect that there will be some harness things there.
Agents SDK is a core part of this to enable both startup builders as well as enterprise builders to have a works by default harness that is able to use all the best features of our models.
From the ship.
Shell tool down to the codex harness with file attachments and containers and all these other things that we know going to building highly reliable complex agents.
We want to make that great and we want to make it easy to compose these things together in ways that are safe.
For example, right, like the GPT OSS Safeguard model, for example, one thing that's really cool about it is it ships the ability to interface with a safety spec.
Safety specs are things that are bespoke.
To enterprises, we owe it to these folks to figure out ways for them to instrument the agents in their enterprise to avoid exfiltration in the ways they specifically care about, to know about their internal company code names, these sorts of things.
So providing the right hooks to make the platform customizable, but also mostly working by default for folks is the space we are trying to explore here.
Yeah.
And this is the snowflakes of the world just need this, right?
Yeah.
Brexit of the world stripes.
Yeah.
It makes sense.
I was going to go back to your, I think the demo videos that you guys had was pretty illustrative.
It's like also to me, an example of very large scale agent management.
Yes.
Like you give people a control dashboard that if you play, if you like play any one of these, like multiple agent things, you can dig down to the individual instance and see what's going on.
Yes, of course.
Well, who's the user?
Is it like the CEO, the CTO, CIO, something like that?
At least was my personal opinion here.
The buyer that we're trying to build product for.
Yeah.
I mean, I think that's, I think that's one of the things that we're trying to explore here is one, and employees who are making productive use of these agents, right, that's going to be whatever surfaces they appear in, the connectors they have access to, things like that, something like this dashboard is for IT, your GRC and government's folks, your AI innovation office, your security team, right?
The stakeholders in your company that are responsible for successfully deploying into the spaces where your employees work, as well as doing so in a safe way.
That is consistent with all the regulatory requirements that you have and customer attestations and things like that.
So it is a iceberg beneath the actual end.
It's great.
Yeah.
You jump every, I guess, layer in the UI is like going down the layer of extraction in terms of the agent, right?
Yep.
Yeah.
I think it's good.
Yeah.
The ability to dive deep into the individual agent trajectory level is going to be super powerful, not only for, from like a security perspective, but also from like.
Someone who is accountable for developing skills.
One thing that was interesting that we also blogged about shipping was an internal data agent, which uses a lot of the frontier technology in order to make our data ontology accessible to the agent and things like that to understand what's actually in the data warehouse.
Yeah.
Semantic layer type things.
I was briefly part of that, that world.
Is it salt?
I don't know.
It's actually really hard for humans to agree on what revenue is.
Yes.
Yes.
What is it?
What is it?
What is it?
What is it?
It is a data agent.
It's a data agent.
It's an active user.
There's what, five data scientists in the company that have defined this golden grid.
They are different.
Yeah.
And no, there's also internal politics.
Yes.
As to attribution of, I'm marketing, I'm responsible for this much and sales is responsible for this much, and they all add up to more than a hundred.
And I'm like, you guys have different definitions.
And if you're a startup, everything is ARR.
So I think that's cool.
Oh, you guys blogged about this.
Okay.
I didn't see this.
Yeah.
Is this the same team?
I don't know.
Is this what you're referring to?
Yes.
Okay.
We'll send people to read this.
Yeah, I don't know if you have any highlights.
In general, from the point of view, there's a lot of good things to read.
Yeah, lots of homework for people.
No, but like data as the feedback layer, you need to solve this first in order to have the product's feedback loop closed.
That's right.
So for the agents to understand.
And this is not something that humans have not solved this.
This is how you build agents that are artists that do more than coding, right?
Yeah, yeah.
To actually understand how you operate the business.
You have to understand what revenue is, what your customer segments are, what your product lines are.
Like one thing that's in looping back to the code base that we described here for harnessing.
One thing that's in corebeliefs.md is who's on the team, what product we're building, who our end customers are, who our pilot customers are, what the full vision of what we want to achieve over the next 12 months is.
These are all bits of context that inform how we would go.
So we have to give it to the agent, too.
I'm guessing that stuff is like pretty dynamic and it changes over time, too, right?
Like part of it was it's not just a big spec.
You have it as one of the things and it will iterate.
One thing that I think is going to break your mind even more is we have skills for how to properly generate deep fried memes and have Reagy culture in Slack.
Because with the Slack chat GPT app that you're able to use and Codex, like I can.
Get the agent to shitpost on my behalf.
Honestly, it's just it's part of humor.
Humor is part of AGI.
Is it funny?
It's pretty good.
Yeah.
Okay.
Yeah, it's pretty good.
It makes a lot of I think humor is like a really hard intelligence test, right?
It's like you have to get a lot of context into like very few words.
This is why references why five four is such a big uplift for our viewers.
It's the meaning.
Yeah, for sure.
Yeah, yeah, it's very cool.
So five four can chip us.
So let's take a look.
Yeah, maybe.
Maybe when y'all are.
Done here today.
Ask Codex to go over your coding agent sessions and to roast you.
Love it.
I'll give it a shot.
Coming back to the final point I wanted to make is, yeah, I think that there are multiple other like you guys are working on this, but this is a pattern that every other company out there should adopt regardless of whether or not they work with you.
To me, this is I saw this.
I was like, fuck, every company needs this.
This is multiple billions.
This is what it takes to get people to yes.
Yeah.
Actually realize the benefit.
Yeah.
Yes.
And distribute.
Build it.
And I think it sounds boring to people like, oh, it's for safeguards and whatever.
But I think you to handle agents at scale, like you're envisioning here, I don't know if it's like a real screenshot, like a demo, but this is what you need.
This is my original sort of view of what temporal was supposed to be that you've built this dashboard and you basically have every long running process in the company and one dashboard and that's it.
That's right.
Yeah.
I think it's pretty customized towards every enterprise, right?
Like you care about.
Different things.
There's a lot of customization, but there'll be multiple unicorns just doing this as a service.
I don't know.
I'm like a very frontier pill if you can tell.
Amazing.
It only clicked because obviously this came out first, then harness and then symphony.
And it only clicked for me that like, this is actually the thing you ship to do that.
Yeah.
Yeah.
There's a set of building blocks here that we assembled into these agents and the building blocks themselves are part of the product, right?
Yeah.
Ability to.
Steer revoke.
Authorization.
If a model becomes misaligned, like all of this is accessible through frontier and there's going to be a bunch of stakeholders in the company that have the things they need to see in the platform to get to yes.
So we'll build all of those in the frontier so that we can actually do the widespread deployment.
That's the fun part.
Yeah.
I'm also calling back to there's this like levels of AGI.
I don't know if OpenAI is still talking about this, but they used to talk about five levels of AGI and one of it was like, oh, it's like a intro.
And the coding software.
And at some point it was AI organization.
And this is it.
That's right.
Like this, this is level four or five.
I can't remember which, which level, but it's somewhere along that path was this.
You know how I mentioned that my team is having fun sprinting ahead here.
And we do this thing where we're collecting all the agent trajectories from Codex to slurp them up and distill them.
This is what it means to build our team level knowledge base.
Happen to reflect it back into the code base, but it doesn't have to be that way.
And it doesn't have to be bound to just Codex.
I want ChatGPT to also learn Armenian culture and also the product we are building and how, so that when I go ask it, it also has the full context of the way I do my work.
And I'm super excited for Frontier to enable this.
Yeah.
Amazing.
What did the model people say when they see you do this?
Like you have a lot of feedback, obviously you have a lot of usage.
You have a lot of trajectories.
I don't, I don't imagine a lot of it's useful to them, but some of it is.
You have this too.
You deploy a billion tokens.
Yeah.
Yeah.
You have a lot of intelligence a day, and this was, this was at the beginning of 2086.
You're, you know, cooking.
Yeah.
There's this fundamental tension, which I think you have talked about between whether or not we invest deeper into the harness or we invest deeper into the training process to get the model to do more of this by default.
Yeah.
And I think success for the way we are operating here means the model gets better taste because we can point the way there.
And none of the things we have built actively degrade Asian performance because really all they're doing is running tests and like running tests is a good part of what it means to write reliable software.
If we were building an entire separate Ross scaffold around codecs to restrict its output, that I think would be like additional harness that would be prone to being scrapped.
But yeah, if instead we can build all the guardrails in a way that's.
It's just native to the output that codecs is already producing, which is code.
I think no friction with how the model continues to advance, but also like just good engineering and that's the whole point.
Yeah.
So I've had similar discussions with research scientists where the RL equivalent is on policy versus off policy.
Yeah.
And you're basically saying that you should build an on policy harness, which is already within distribution and you modify it from there.
But if you build it off policy, it's not that useful.
That's right.
Super cool.
Any, any thoughts?
Any things that we have?
That we haven't covered that we should get it, get out there?
Just, I've been super excited to benefit from all the cooking that the codecs team has been doing.
They absolutely ship relentlessly.
This is one of our core engineering values, ship relentlessly.
And they, the team there embodies it to an extreme degree.
Yeah.
I have five, three and then spark and five, four come out within what feels like a month is just a phenomenally fast.
It's exactly a month ago.
It's five, three and yesterday was five, four.
Yeah.
I mean, it's do we have every month now is five, five next week.
I think so.
Uh, I can't say that the poly markets would be very upset.
I think it's interesting that it's also correlated with the growth.
They announced there's 2 million users, but like almost don't care about codecs anymore.
This is it.
This is the game, man.
It's like coding.
Cool.
Soft, like knowledge work.
That's right.
This is the thing to chase after.
Yeah.
And this is one of the things that my team is excited to support.
Get the whole like self-hosted harness thing working, which you have done in like the rest of us are trying to figure out how to catch up, but then.
Do things, you know, right with it, do things, that's right.
You can just do things.
That's the line for the episode.
That's it.
Any other call to actions you're based in Seattle, your team, I'm guessing new Bellevue office, new Bellevue office.
We just had the grand opening yesterday as of the recording date, which was fantastic, beautiful buildings, super excited to be part of the Bellevue community, building the future in Washington.
And I would say that there is lots of work to be done in order to successfully serve enterprise customers here in frontier.
We are certainly hiring.
And if you haven't tried the Codex app yet, please give it a download.
We just passed 2 million weekly active users growing at a phenomenally fast rate, 25% week over week.
Come join us.
Yes.
And I think that's an interesting, my final observation, opening has very San Francisco centric company.
I know people who have been, who turned down the job or didn't get the job because they didn't want to move to SF and now they just don't have a choice.
You have to open.
The London, you have to open the Seattle.
And I wonder if that's going to be a shift in the culture.
Obviously you can't say, but.
I was one of the first engineering hires out of our Seattle office.
So it was very natural success has been part of what I have been building toward.
And it is, it has grown quite well, right?
We have durable products and lines of business that are built out of there.
A ton of zero to one work happening as well, which is the core essence of the way we do applied AI work at the company.
So I think that's one of the things that we're trying to do as a company to sprint after it new, to figure out where we can actually successfully deploy the model.
Yeah.
Yes.
A hundred percent.
We also have a New York office too, that has a ton of engineering presence.
Yeah, exactly.
That's the, these are my roadmaps for AI.
Wherever people hire engineers, I will go.
That's right.
Azra.
It's a cool office too.
New York is a old REI building.
I believe the REI office.
It's just, no, you will never be as big.
New York is, you can't get the size of office that they need.
The New York office.
Seattle has a very.
Mad men vibe.
It's beautiful.
The Bellevue one is very green, gold fixtures, very Pacific Northwest is very cool.
It's a little bit localized.
Yeah.
A lot of people are like, therefore people like New York.
They want to be in New York.
Right?
Yeah.
Yeah.
We have a fantastic workplace team that has been building out these offices.
It really is a privilege to work here.
Yeah.
Excellent.
Okay.
Thank you for your time.
You've been very generous and you're you've been cooking.
So I'm going to let you get back to cooking.
It's been amazing chatting with you folks.
Happy Friday.
Happy Friday.