LT Lauren Tan On Y Combinator Startup Podcast

“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.”

Y Combinator Startup Podcast · Startups & Venture · November 2026

“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

Context

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.

Transcript

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.

More from Y Combinator Startup Podcast