Sporaflow

I'm not going to lie, to me it's clear: the job has nothing to do with what it was. Developers used to write code by hand, and humans understanding the full logic of a system mattered a lot. Today, with AI, it's so much easier to produce or understand code that this barrier is gone. The new job that's taking shape is very far from where it started. I get that a lot of people find it hard to accept, and even see the change as a bad thing. That's normal: the job won't appeal anymore to people who were, and presented themselves as, technicians and experts.

As for me, yes, I clearly understand my codebase less. I'm sure of it, I've noticed it lately. What I tell myself is that my value is less there now, and more in my ability to organize the whole thing, on the human side as much as the machines and tools. So I focused on what actually brings value to my company or my role, and it's true that code counts for less there.

I completely understand people who feel lost. A lot of developers chose this job because they were comfortable with code, not to do marketing or sales. And the job that's taking shape asks them to code less and organize more, that's the real tragedy of this shift. Unfortunately that's how the world works: adapt or die. Let's be clear, a lot of people won't make the jump. They'll see their job as dead and may end up leaving it. That's normal, and a shame.

But on the other hand, I think believing you can do without AI is limiting yourself, even a bit illogical. As imperfect as it is, refusing to use it is a bit like refusing the printing press when it was invented. Lots of jobs died, that's a certainty: everyone who wrote texts by hand. Honestly, I see AI exactly like the invention of the printing press. It deeply changes how we produce content, and we know we're going to produce a lot of it.

With the printing press, as with AI, we produce a lot of imperfect stuff, maybe even pointless texts. We already see it: AI often produces code that isn't secure and leaves holes. But flip the question: what valid reason would we have today to abolish the printing press? It produced millions of mediocre books, and yet nobody wants to go back to scribes, because it put the written word in everyone's hands. I think it'll be the same for AI. The real question isn't that it produces bad code, it's what we'd be willing to lose by refusing to use it.

it depends a lot on the project. I used to make more plans, especially when the models weren't as good. for a simple task I wouldn't even make one. I'd switch to plan mode when I felt exploration alone wouldn't be enough and I was worried the agent might make something up. and even then, I'd skim the plan or read its summary, just to see if it was heading in the right direction and if it would do things I wouldn't have done myself.

today with frontier models it's not really necessary anymore. each agent works in its own worktree, on its own branch, so if it goes in the wrong direction it's just a branch to discard.

what matters now is the context you give the agent. I use skills a lot, and with a very good model, giving it direction through a skill changes everything.

Really interesting project. I'm working on something similar, and I had a lot of trouble making native CLIs work with tracking their state. So I'm curious how you handle it: how do you tell when a task is complete or a session is stuck, and how do you avoid burning tokens, for example in loops? I tried quite a few approaches before finding one that works and is efficient enough.

I had the same problem with messages between agents. Getting them to talk to each other isn't that simple, especially when they use different CLIs. How do you handle that?