# Code review can fade as teams build stronger guardrails

Markdown copy of https://realalpha.app/s/code-review-can-fade-as-teams-build-stronger-guardrails/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Walden Yan](https://realalpha.app/builders/walden-yan/) · Walden Yan is co-founder of Cognition. · Co-founder and chief product officer of Cognition, the company behind Devin; an IOI gold medalist in competitive programming.
- Host: Madison Kanna
- Show: MTS
- Episode: [One Founder Now Runs a Game Studio With 20 AI Bots | Walden Yan](https://realalpha.app/v/fFS4bs2Q9_c/), Nov 18, 2026
- Moment: 24:33 to 27:07 of the episode (3 min), playing on https://realalpha.app/s/code-review-can-fade-as-teams-build-stronger-guardrails/; the episode from there: https://realalpha.app/v/fFS4bs2Q9_c/?t=1473

## Quote

> “And if you step back a little bit, the problem of how do I get my AI to not need me to review my code is actually a **pretty fun engineering problem**.”
> — [Walden Yan](https://realalpha.app/builders/walden-yan/) at [24:44](https://realalpha.app/v/fFS4bs2Q9_c/?t=1484) · MTS

## Takeaways

1. Design systems so whole areas of code are safe to auto-merge.
2. Use testing and formal verification to build trust in agents.
3. Set thresholds for which changes need human review.

## About this segment

Walden Yan argues that less code review depends on better architecture, tests and guardrails—not simply ignoring AI-written code. He describes bots testing prompt changes and escalating only riskier edits.

From “One Founder Now Runs a Game Studio With 20 AI Bots | Walden Yan”, Nov 18, 2026. [Watch the full episode](https://realalpha.app/v/fFS4bs2Q9_c/)

## Transcript

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

[24:38](https://realalpha.app/v/fFS4bs2Q9_c/?t=1478) Yeah, you know, I've really I've actually been pushing my bots to find more ways to lean off of my code review because that is the part that I enjoy the least. And if you step back a little bit, the problem of how do I get my AI to not need me to review my code is actually a pretty fun engineering problem. You're thinking now less in terms of individual lines of code and debugging, but you're actually thinking about high-level guardrails.

[25:05](https://realalpha.app/v/fFS4bs2Q9_c/?t=1505) Like, oh, how can I architect my code base so that all the code over here, it's impossible to introduce security vulnerabilities? Okay, whoa, if I do that now, then all this can be auto-shipped and merged and auto-fixed by the AI, and I don't have to be worried about it. Can I add interesting new technologies like formal verification or better testing infrastructure so that I trust my agents more?

[25:27](https://realalpha.app/v/fFS4bs2Q9_c/?t=1527) If you spend more time on these meta problems, I've found that you can actually let your dev and bots run even more autonomously. And really, that's where you need to get to, to the point where you can be merging thousands of PRs without any human intervention. So actually, your early question was, where's the technology going from here? I really think that code review is going to be a thing of the past very soon.

[25:49](https://realalpha.app/v/fFS4bs2Q9_c/?t=1549) But it's not because we're just going to turn our heads away and say, I don't care to review code anymore. I think it's because we're actually going to spend time thinking about how do we engineer our code bases and set up our Devon bots so that I don't have to be in the weeds and reading every line of code. Okay, so that's a problem you're kind of currently working on is how can I review less of the code, trust my bots more to do this for me? Yeah, 100%. For example, we have Devon bots that are going in and changing the prompts for Devon continuously, but they're not just YOLO shipping them. We actually tell them any change you make, you have to run it, you know at least 10 times with like various models and you know with certain guardrails um changes beyond a certain length need human review but changes below a certain length that

[26:35](https://realalpha.app/v/fFS4bs2Q9_c/?t=1595) don't need it uh and you give it all these tools and systems where you can point in the right direction and give it the guardrails where you know it can be safe and then you get i can just turn away i like come back later and i find out oh devin like made like five or six prompt changes based off of you know human bug reports that's like an amazing feeling and that's like super rewarding that's kind of like the feeling that i i set out to do when when i came in and started coding and doing engineering yeah it's starting to feel like more fun again like i feel like i
