Daigle: Domain-specific prompt permutations are essential to avoid obvious AI output
Kyle Daigle · GitHub’s Agent Era: 14x Commits, 200M Developers, Copilot’s Next Act — Kyle Daigle · Jun 2, 2026 · at 15:17
GitHub COO Kyle Daigle discusses how core AI operations like summarization require distinct phrasing and contextual lenses depending on whether the audience is an analyst, marketer, or engineer.
0:00 / 0:29exact quote · 29.0s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“The interesting matrix problem when we go from like a developer set of concerns to all kinds of different professions is that what that word means to me is different than it means to you is different than it means to the, you know, analyst or the salesperson. And that's where I think the matrix mess is that we're starting to like, still starting to find. It's not these mega skills, but they're all just slightly Permutations, but those permutations are really important. It's the difference between someone reading this and going, did AI make this?”
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: Replacing pull requests is hard because code review codifies social trust
“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 w…”
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…”