I was catching up on my RSS posts today (while procrastinating on my first day back at work) and I saw a few posts about people using coding agents to spin up projects in less than an hour. I spent a fair bit of my leave working on projects, and I can probably count on one hand the number of times I actually used an agent. And I don’t fully know why I haven’t embraced them as much as others have.

It’s not because I shun them deliberately, or see no value in using them. I think it’s probably because the finished product is only part of the reason of why I work on something. It’s probably even less than half. Knowing that any particular project would only be used by myself (if I use it at all), I don’t get the value that comes from having others appreciate something I finished. I need another source of motivation for working on something. Ben Werdmuller probably puts it best:

I also think we’re going to see a real split in the tech industry (and everywhere code is written) between people who are outcome-driven and are excited to get to the part where they can test their work with users faster, and people who are process-driven and get their meaning from the engineering itself and are upset about having that taken away.

Clearly I fall squarely in that second group who find the engineering more interesting than the finish product. That probably explains a lot about how I approach projects: always starting new ones, never polishing them up once the “interesting” bit of the development work has been solved, never releasing them to anyone else.

Of course there are exceptions to these feelings, and maybe I’m more likely to use agents then. It probably also explains why I turn to the agents when there’s something “boring” that needs doing: there’s no fun in coding up DB marshalling logic for the eighth time.

But using a coding agent for an entire project without getting my hands dirty? Not sure I see myself doing that anytime soon.