changisaac

We’re building developer tooling for AI coding agents. This means our customers are naturally those adopting AI coding tools now. There’s a much higher density of teams (a lot of which are startups) in SF. Again, not a necessity, but would definitely help.

>"Code review" as defined as a human in the loop getting the final say on whether a change will be made to the system will be the absolute last thing to go. That process may look very different as both the inputs massively increase in scale and the methods get disrupted by AI.

I know this is probably not something you can divulge but I look forward to how your team at Graphite plans to solve this! (Would also love your personal take!)

This is a great analysis btw, thanks for this!

My take away from this is that my startup should spend some time investing in some cost analysis with our LLM usage and context engineering (perhaps closely after some level of PMF). If it’s not happening anytime soon, might as well treat it as it’s not happening at all considering that startups die out pretty quick lol.

> and yet that you're only asking this question at all because you're still compute limited.

Very good point.

Haha nice one, took me a second there to understand this.

That’s true haha, even if obsolete for catching bugs, etc. one reason for human code reviews might just be accountability.

Surprised that’s your take considering Diamond is one of the code review bots that are ahead of the pack. Curious why you think that’s the case? Is it a technical limitation? Or something about human code review that is just fundamentally hard to copy?

Good points, I think I agree with your points here, really hard to search for and view more context. Assuming these can be remedied somehow though, is the prospect of doing mobile reviews while you walk around something you'd be want?