Stay Sassy PM: Managing multiple AI agents exhausts engineers reviewing critical code
Stay Sassy PM · ⚡️ The best engineers don't write the most code. They delete the most code. — Stay Sassy · Apr 13, 2026 · at 48:09
Stay Sassy PM, an anonymous product manager and tech writer, discusses cognitive overload and review risks in AI-assisted software engineering on Latent Space.
0:00 / 0:52exact quote · 52.7s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“One of the things that people quietly talk about is that that's very fatiguing. And I know some people who are operating that way. I've met these people and it is fatiguing. And what is fatigue really going to hit you on? Fatigue is really gonna hit you when now it's the end of the day, you have been tending to this herd of agents that you, that you've named and are chatting with constantly, and now someone from another team hits you with a pull request that's very, very complicated, that touches many different systems where you need to basically cage all of this context into your brain in order to review it. That starts to become very risky, like, to somebody who is, you know, Accountable, at least partially accountable to a system being sustained. That's very risky to know that somebody who's that exhausted is going to be reviewing really mission critical code.”
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 Stay Sassy PM
Stay Sassy PM: AI cognitive offloading will boost convenience services
“I would say, I think that this could be really good for any sort of service that makes, that allows people to be kind of lazy, because I think that AI has a very strong ability to just sort of reduce people's willingness to do work. It's like you could offload…”
Stay Sassy PM: Leaders know what to do 99% of the time
“From what I've seen, 99% of the time, you know exactly what to do. The number of truly, truly difficult questions that require you to know some sort of advanced theory, or advanced philosophy, or run some huge amount of calculations that are very non straightf…”