Not to be a curmudgeon, but why are they spending time on this? As an enthusiastic Raycast user, I would prefer to see them focus on making Raycast better, not finding new ways to jump on the AI bandwagon.
I think this is less about the projects themselves and more about distribution channels like HN and ProductHunt being dead. When the zone is flooded by vibecoded apps of all kinds, the "build it and they will come" era of getting your thing on a popular website's homepage is over.
But other distribution strategies exist. You just have to be smarter about finding and getting in front of your core audience.
Agent orchestration seems to be the new hot problem to be solved in the ecosystem. See also Steve Yegge's most recent posts [1]. Curious to see what tools emerge as the winners of the Cambrian explosion we're probably about to see.
I always liken it to using Uber in ~2012. It was fun to get around major metro areas for dirt cheap. But then prices rose dramatically over the next decade+ as the company was forced to wean itself off of VC subsidies.
Highly recommend A History of Modern Computing [1]. Starting with the ENIAC in the '40s through the successive generations of computing technology in the 20th century, it gives a fantastic overview of the field's history.
Sadly, now that I look into it, it looks like it's out of print. There are a few copies available on Amazon, so act now!
I think this is a good question, but that it falls prey to the same conceit that befalls those who claim they could "build Twitter in a weekend". A picture-perfect sketch of a system can illustrate one's knowledge of patterns and off-the-shelf solutions, but it won't cover the things that get in the way of a team building their way towards product/market fit.
You could lead with this question and then jump in with hypothetical roadblocks to see how the candidate reacts.
Ex:
- "A network of microservices _would_ be a clean way to implement this. How would you foresee the operational burden of this impacting a small team?"
- "Imagine that you build this and it works well, but the product it powers ends up not resonating with customers. The team now wants to pivot to X. What changes would you make to the system to address this new problem space?"
A former colleague of mine wrote a great article on this topic which summarized how the infrastructure group at Twitter thought/thinks about code review: http://glen.nu/ramblings/oncodereview.php
I've come across tools that claim to expose and measure potential technical debt, such as techdebt.org or SQALE (http://www.sqale.org/details). I'd be skeptical of any software that claims to provide an automated mechanism for paying down debt. The consequences of debt are too varied and subtle to be generalizable.
UI nit: You should add placeholder text for the signup text input. The fact that it's intended to field email addresses may not be obvious to everyone.