Post

Jamon
@jamon.dev

I have developed a rule of thumb for when it's best to code by hand. If I don't understand the problem super well, I'll start digging in with an agent and gaining familiarity. If the solution after 10-15m isn't something that I feel I could implement myself, it's time to go do it by hand.

Jamon
@jamon.dev

I do it the way I did pre-AI. Finding the relevant code, reading and understanding it, and trying out various ideas. Usually when I'm about 30-50% done, the system is mapped out really well in my mind, and all that remains is execution.

Jamon
@jamon.dev

Then I'll write up a detailed spec and ask the agent for feedback. It almost always finds edge cases I didn't consider and "gets" where I'm going with it. I let the agent take it forward and also have it do the things I usually don't have patience for, like TDD. The grunt work.

0 reposts1 like

Matt Green
@mattgreenrocks.bsky.social

Agents are amazingly good rubber ducks, especially when talking through various approaches. Been meaning to try an experiment where I create the bones of the architecture (interfaces, high level code, etc) and then the agent fleshes it out against property-based tests I write and it can't modify.

Jamon
@jamon.dev

What's nice is that I am fully qualified to review the code afterward and, not only that, any future agentic work on that system is easier. I understand it better because I did the manual work.

Jamon
@jamon.dev

It's still really fast and it makes future work faster. It's this kind of hybrid human + agent workflow that makes me feel superhuman.