Daigle: Replacing pull requests is hard because code review codifies social trust
Kyle Daigle · GitHub’s Agent Era: 14x Commits, 200M Developers, Copilot’s Next Act — Kyle Daigle · Jun 2, 2026 · at 36:16
GitHub COO Kyle Daigle discusses why AI code generation and automated review tools fail to fully displace the traditional pull request model.
0:00 / 0:51exact quote · 51.6s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“I think the reason why there's not a single answer is ultimately we're trying to codify trust. We're trying to say like, okay, if Sean reviews this, I'm going to trust it because you're Sean or you're the senior dev or you're the whatever. And right now when we are working in a flow where an agent writes code and another agent reviews code, and then Kyle goes and looks at it. The trust is kind of diffuse. In most of the tools that we're talking about are talking more about verification flows. We have more assets to look at. So I can probably say whether this is a good PR or not, but that still doesn't solve. I think the human problem of I'm looking at a PR and I want to know if I can trust it. And we're still, we still tend to use human signals for that, you know Mitchell approving it or Kyle approving it or whatever. And so I, Think that's, I think that's why most of these options haven't really solved it is because it's a social problem.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Kyle Daigle
Daigle: The era of massive, monolithic AI skills is ending
“First is I think that we're ending the era of these like massive, beautiful, perfect skills that are just like not any of those things, you know?”
Daigle: AI code vendoring will not solve supply chain vulnerabilities
“And so I do think there's something true there where having like either taking only what you need or the dependencies just getting incredibly small over time, I think will help to some degree, but it's not going to solve the fundamental problem. I don't think …”
Daigle: Using AI to build running apps qualifies you as a developer
“If you create code, if you have an idea and you create it into some way of like, I'm going to run it and use the app right now, you may still use AI in that moment, but that's okay. At some point you're going to do the next thing.”
Daigle: The real value of AI agents is full software lifecycle automation
“What we think is that it's not solely about the code generation. It's really about having the ability to use these you know, coding agent brained harnesses or runtimes across, not just. The coding experience where I'm going to like send a bunch of tasks out, o…”
Daigle: Operating systems must evolve because autonomous AI agents now use them
“Operating systems need to look different than they looked five years ago because it's not just you using them anymore.”
Daigle: LLMs are most valuable for retrospective workflow analysis
“I find AI in like what most of this like launch here is, is actually like less building forward. It's actually like. A recursive loop backwards. I'm always looking at what had happened first, like go back through the week and tell me what we did, what worked, …”