# A six-week agent build shipped without Gill reading the code

Markdown copy of https://realalpha.app/s/a-six-week-agent-build-shipped-without-gill-reading-the-code/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Harjot Gill](https://realalpha.app/builders/harjot-gill/) · Harjot Gill is founder and CEO of CodeRabbit. · Co-founded CodeRabbit, the AI code review company that became the most installed AI app on GitHub and GitLab.
- Host: [Gergely Orosz](https://realalpha.app/people/gergely-orosz/) · Host, The Pragmatic Engineer · Spent four years at Uber heading mobile, web and backend teams; shipped part of its payments system.
- Show: The Pragmatic Engineer
- Episode: [Software factories and code reviews with Harjot Gill](https://realalpha.app/v/4Cjb7691GJ8/), Nov 18, 2026
- Moment: 15:37 to 18:29 of the episode (3 min), playing on https://realalpha.app/s/a-six-week-agent-build-shipped-without-gill-reading-the-code/; the episode from there: https://realalpha.app/v/4Cjb7691GJ8/?t=937

## Quote

> “it just **hill-climbed over time** on its own, all written in Rust”
> — [Harjot Gill](https://realalpha.app/builders/harjot-gill/) at [16:14](https://realalpha.app/v/4Cjb7691GJ8/?t=974) · The Pragmatic Engineer

## Takeaways

1. An agent ran for six weeks on a Rust storage implementation.
2. TLA+ and simulations helped catch race conditions.
3. Multiple test environments gave agents ways to verify their work.

## About this segment

Harjot Gill says an agent spent six weeks building a Rust write-ahead log for object storage, which shipped without him reading the code. He explains the simulations and formal models used to verify its work.

From “Software factories and code reviews with Harjot Gill”, Nov 18, 2026. [Watch the full episode](https://realalpha.app/v/4Cjb7691GJ8/)

## Transcript

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

[15:44](https://realalpha.app/v/4Cjb7691GJ8/?t=944) I'm still doing software development. It's not like I'm not doing software engineering, but now what I'm focusing on is a lot more fun than figuring out the syntax and autocomplete. I mean, my agents are writing Rust code. I have zero idea how Rust works. We recently had an agent goal running for six weeks to... Six weeks. Yeah, so for running, so building like Git write-head log on object stores.

[16:08](https://realalpha.app/v/4Cjb7691GJ8/?t=968) Yeah, write-head log. When Cursor's origin blog post came out, I appointed the agent, it ran for six weeks, and now we have that in production, powering a lot of the knowledge bases at CodeRabbit. So I didn't even have to have the real implementation, it just hill-climbed over time on its own, all written in Rust, and I have not read a single line of it. And for those of us who are not as familiar with this specific term, what does hill-climbing mean for agents?

[16:34](https://realalpha.app/v/4Cjb7691GJ8/?t=994) Yeah, so it's some sort of a loop. Like, it all starts at a very basic that agent can verify its work against something. Yep. And these loops are like inner loops, outer loops, multiple types. So when you're looking at software development, you want to provide agents means to verify its work close to where it's doing the software development. So we do a lot of... or not, a lot of formal methods. So when we first did the Slack bot product like eight months back, we invested a lot in like first modeling what this distributed system is going to do in DLA plus, then implementing it.

[17:07](https://realalpha.app/v/4Cjb7691GJ8/?t=1027) And also investing a lot in simulations. So the way we are scaling code development, code review is just one piece, which we of course market, but there were like a hundred other things you have to do, right? So we invested a lot in local deterministic simulations, right? very recently we started investing in lean theorems as well so a lot of that is lean is another form of formal methods yeah like you have theorems and it even like used for mathematical proofs where you can also try to build probably correct software things like billing service and all we have got like a bunch of lean theorems i can actually show you after the podcast it's pretty cool what we're doing there so what we have been doing is like these are all like hill climbing like you're first making them hill climb locally then you're going to the next environment

[17:49](https://realalpha.app/v/4Cjb7691GJ8/?t=1069) where, let's say, emulators is another thing we have invested a lot in our own 12. So you can now very quickly mock a real emulator, like the real APIs, like Google Cloud APIs or whatever, right? Then you are actually testing against a real Google Cloud or Vercel environment. Those are the cloud providers we have. In dev, you can have the agent actually spin up services, actually test them, right?

[18:11](https://realalpha.app/v/4Cjb7691GJ8/?t=1091) I mean, this is all hill climbing. And then in production as well, like the thing is that I kind of see each release. So we release multiple times a day, right? every 30 to 45 minutes, we ship code. And each release is almost like a turn in a strategy game.
