LT

Lauren Tan

Things Lauren Says on Podcasts

Where to Find Them

Lauren Tan has been a guest on Front End Happy Hour (3 times) , The Changelog and Y Combinator Startup Podcast .

Recently: “The Rise Of AI Coworkers” on Y Combinator Startup Podcast (November 2026); “Engineer to manager and back again (Interview)” on The Changelog (March 2020); “Episode 089 - Hollywood Martinis - Netflix Studio Engineering” on Front End Happy Hour (October 2019); “Episode 070 - Senior Engineer - Master Brewer” on Front End Happy Hour (November 2018); “Episode 066 - Type systems - a static drink list” on Front End Happy Hour (September 2018).

What They Said

“Even though you can go really fast, it doesn't mean you should ship every feature you can think of. This is where human judgment and taste comes in. … Even for my own factories, I don't turn them towards feature development. I turn them towards software maintenance, which used to be a full-time job for someone. Now I've given that to a lot of agents.” — Lauren Tan, Y Combinator Startup Podcast

The discussion was about saying no to features and keeping product taste when anyone can build anything. She says she points her agent "factories" at bugs and performance rather than new features.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 54:49 into the episode
Speaker 3

would be made that way. I wish Apple, Apple, people who work at Apple, could you do this? Because, hey, I have a calendar team in particular. I have some problems with you.

Speaker 1

…sitting with a change for longer than feels comfortable before we ship it. And the default is if something doesn't get internal product market fit, we don't ship it. Even if it gets Like mixed internal product market fit, we don't ship it. And so, as a team, we really try to keep a high bar. Yeah,

Speaker 4

I think that's actually one of my favorite parts of working on the GraphPot team is that, you know, despite the great velocity that we have, we still have a lot of intention and care for the user experience. And, you know, even though you can go really fast, it doesn't mean that you should just ship every feature you can think of. And this is where human judgment and taste, I think, comes in. I don't think that's going to go out of style personally. I think as long as we're building software for humans, humans should really be thinking about the, you know, be an intentionally designed experience because we know each other the best, right? You know, if you're building software for agents, that's a different story. That, you know, you can certainly probably go as fast as possible. But I think, yeah, for humans, you do want to have put intentional care and thought into the stuff that you develop. So even for my own factories, I don't turn them towards like feature development. I turn them more towards the software maintenance side of things because I care a lot about performance. I care a lot about fixing bugs that our users encounter…

Lauren Tan

One thing that's very inspiring about your journey, Lauren, I don't know if many people know, is you grew up in Singapore and you studied a non-technical degree. You did a bachelor's in accounting and finance from Onash in Australia. Then somehow you ended up becoming one of the now best AI…

Speaker 4

Yeah.

Lauren Tan

How did that happen? I think sometimes people think it's like it's very hard to get into tech, but you did it. And you also worked on the React compiler, which is one of the hardest things as well.

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“It took us quite a while to get to that point. It involves making sure your code base has good guardrails and constraints, so that the time you'd otherwise spend on human code review is encoded into your code base and your static analysis and tooling. When you have that much trust in your agent's ability to write good code, I've gotten to a point where I essentially have my agents merge their own pull requests.” — Lauren Tan, Y Combinator Startup Podcast

She had just described building a whole feature in one Slack thread without opening her editor, and a host said very few engineers work this way. She explains what has to be in place before you stop reading the PR.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 30:03 into the episode
Speaker 4

And so the whole feature was built end-to-end in that one Slack thread with you and Samantha and Potato building it.

Speaker 3

…the gold standard for how to do it. And then I would say maybe like five or 10% of engineers or maybe 1% of engineers in the world are doing this right now. So this is literally something that should grow by a hundred axes. I'm unbelievable that like so few people are doing feature work this way.

Lauren Tan

Yeah, I'll say that, you know, it took us actually quite a while to get to that point. I feel like it's actually quite hard to get to that point overnight. It involves investment into making sure you have the right skills, your code base has good guardrails and constraints so that the time that you would otherwise have to spend on human code review is encoded into your code base and your static analysis and your tooling so that the engineer's time, yeah, like PSAC. And so your engineer's time is freed up to actually focus on the actual product, the user experience and the operational execution part of the job. When you have so much more trust in your agent's ability to write good code because you've set up those systems, I've gotten to a point where I essentially have my agents merge their own pull requests. So in that Slack thread example, that was an example of me not reading the PR. And we just looked at the artifacts that came out of it. So

Speaker 3

this cursor environment, does it already have PSTAC? And is that the way it sort of creates, you know, decides how to build it?

Lauren Tan

Yeah. So for internal, PSAC is installed into our repo. There's an internal version of PSAC. Instead of calling it potato mode, it's Lauren mode. And it just started because I wanted a place to put my skills. And so yeah, everyone in the company can actually use PSAC. And my cloud agents that the…

Speaker 4

We haven't really explained what PSTA is. Can you explain what PSTAC is for people who don't know?

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“The new job of a software engineer is to figure out how to get agents to write good code by default. When you have a loop where the agent can check its own work, it doesn't guarantee the quality of the code is good, but it will be correct. Maybe it's very slow or very resource inefficient, and that's where the engineers come into play.” — Lauren Tan, Y Combinator Startup Podcast

A host asked for the smallest agent loop someone could start with. She says the first step is teaching the agent to run the code and measure it the way a real user would, so it can check its own work.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 42:41 into the episode
Lauren Tan

…translating user intent well into what the bots need to do Because I think that there's a big gap between the best AI builders to the so-so ones is really how you translate that intent super well. And there's a lot of tips and tricks of what you did, Laura. I mean, your video is pretty impressive.

Speaker 3

Is there like one super important, just like if you do this, you'll get started. Like, I think, was it like your, you know, what's the minimal form of a loop?

Speaker 4

This is the smallest loop, essentially. Like, so agents already are able to write code. Maybe it's not good. Let me scratch it out for now. So, like, you know, like naively, if you're using agents, you can definitely write code. You can run the code. And, you know, today that if you haven't spent a lot of time in your agent setup, you may be the person running the code. And so this isn't actually a loop, really, because right now, this is like the missing piece. The agent can't do this, but you were doing it. So the smallest loop I find is you can actually focus on this part. How do you teach your agent to run the code empirically, take CPU traces, performance metrics, run the code and run the application like a real user would. The reason why I think it provides a loop is because the agent now has the ability to check its own work. So it can find the issues with the code that it wrote. Then it can write better code or more correct code and then it can keep looping until it produces a result that you want. I took out the good part for a reason because I think that when you have a loop like this, it doesn't guarantee…

Speaker 3

I feel like since we have some of the world's experts at software factories here, I want to ask some like nitty-gritty questions that that's okay. Because I'm struggling with this right now with G-Stack. I have a bunch of agents that are struggling with the code review step. I have like a slash…

Speaker 4

No, I don't know. No plan mode. Yeah.

Speaker 3

So then, but PSTAC must have like a review step then. How do you, what's your philosophy on like how much review is enough versus too much? Like I'm literally in a debate with one of my happy captains right now where it's like, I wanted to go from 50 million tokens for review to like 10 million…

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.
“I think of your code base as a form of memory. It's much more token efficient if you refactor your architecture, your API design, or you have static analysis, lint rules, compilers. These all exist to help humans write good code, and unsurprisingly they also help agents.” — Lauren Tan, Y Combinator Startup Podcast

A host asked how much code review is enough, since his review step burns tens of millions of tokens. She answers that she has moved away from adversarial multi-model review and puts the effort into the code base and static analysis instead, so the agent gets it right the first time.

Y Combinator Startup Podcast · 2026-11-16 Permalink → Listen →
Y Combinator Startup Podcast Around 45:51 into the episode
Speaker 4

question. I think. So for me, actually, in PSTAC, I have tried to downplay some of the review skills a little bit. In PSAC, we have a bunch of skills. There's one called Interrogate, and that will spawn agents of different models. So across different families,

Speaker 3

which works really well, you can do like adversarial review.

Speaker 4

That was quite hot many months ago. I've actually kind of withdrawn a little bit from that because I've Find that when you do that, I mean, it's still valuable, but I think you run the risk of overfitting, where the sort of agent doesn't have the ability or maybe enough judgment to determine what's actually good feedback versus not good feedback. And it maybe doesn't have complete knowledge of your goals and your intents and your, you know, your wider product vision. It doesn't understand how you want the product to evolve, for example. And so you can get to a point where you are, you know, very abstractly, you know, it's kind of like imagine before agent, you have a bunch of engineers talking about the most perfect, ideal utopia way of doing this. But actually, you know, that doesn't even matter because in two months, we plan to deprecate this thing and build a completely new vision. And so I think there's some similar analogy there where I think some review is good, but I try to move more towards like on my screen here. I have this inverted pyramid…

Speaker 3

You just gave me a feature idea, which is like, because GStack has office hours and like the CEO review where you're like talking about the product, I can use that. I mean, because those are like product requirements that feed in. Right. Yeah. And those save to markdown in the project. So I could…

Speaker 4

Yeah, I think so I intentionally drew it this way. I guess it's not a very scientific chart, of course, but the way I imagined it when I drew it, I think this is in terms of where you should spend your time as an engineer. So for me, most of the investment I make is into the code base and then…

Speaker 1

Is somehow enforced in static analysis? Actually, like can know how long something will take to run?

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

Collections They Appear In