I'm every bit as immersed in this as you are. I've been developing my own custom claude code plugins that allow me to delegate more and more the agents. But the one thing the agent is not reliably doing for me is making sound architectural choices and maintaining long term business context and how it intersects with those architectural choices.
I tried teaching all of that in system prompts and documentation and it blows the context window to an unusable size. As such the things that as a high level experienced senior engineer I have been expected to do pre-agents I am still expected to do.
If you are eliminating those people from your business then I don't know that I can ever trust the software your company produces and thus how I could ever trust you.
I'd try a different approach - mechanical engineering isn't that hard and it can benefit greatly from developing some specialized agents and fine-tuned LLMs for it. As a side benefit, that approach happens to create some software jobs too, open source for best results.
> making sound architectural choices and maintaining long term business context and how it intersects with those architectural choices.
I completely agree with you, but this is rapidly becoming less and less the case, and would not at all surprise me if even by the end of this year its just barely relevant anymore.
> If you are eliminating those people from your business then I don't know that I can ever trust the software your company produces and thus how I could ever trust you.
I mean thats totally fine, but do realize many common load bearing enterprise and consumer software products are a tower of legacy tech debt and junior engineers writing terrible abstractions. I don't think this "well how am I going to trust you" from (probably rightfully) concerned senior SWEs is going to change anything.
s
"Im not even sure we will need maintain software" (sic) - I'm not sure what your specific background is, but with a statement like that you lose all legitimacy to me.
Yes, I'd like to hear more of their background, because they seem very naive about writing software, adding to it, testing it, etc.
You can't just whip up a replacement for salesforce using claude code. Who's going to fix the bugs, who is going to have tests, manage performance testing? People will still pay for software that is tested and performant. I could get a replacement for an online spreadsheet, google docs like thing. Suppose you tell it to copy the google docs or whatever programming language. You won't know if it's buggy because you won't haev the same test coverage. You'll never know about bugs that took a long time to reveal in some combination of features.
You can create a new system with a few features together to do something. Again, not tested, not perf tested, isn't away of a compiler bug you had to work around.
But lots of simple things can be claude coded and replaced. Say something that took a photo of a person, centered it, then say put some kind of log on the pic. Something you paid $5 a month to do.
Writings on the wall, it is true, tech debt will no longer be a thing to care about.
"but who will maintain it?" massive massive question, rapidly becoming completely irrelevant
"but who will review it?" humans sure, with the assistance of ai, writing is also on the wall: AI will soon become more adept at code review than any human
I can understand "losing all legitimacy" being a thing, but to me that is an obvious knee jerk reaction to someone who is not quite understanding how this trend curve is going.
And the human downstream of this random reorganization of things at will, how do they manage it?
If its AI agents all the way down its commoditization all the way down, if humans have to deal with it there's some sort of cost for change even if its 0 for code.
I know... I know buddy. The world changed and I don't know if I'm going to have a job.