Instead, I'm stripping back to basics, building small tools to solve specific problems, and find myself vastly preferring established software with a track record of keeping feature-bloat down and the problem-space focused.
Instead, I'm stripping back to basics, building small tools to solve specific problems, and find myself vastly preferring established software with a track record of keeping feature-bloat down and the problem-space focused.
The cool part is building smaller tools to solve your problems also allows you link those all together (MCP/CLI/API) in ways that weren't possible in the past using LLMs as a glue layer.
It’s extremely hard to do, even on a basic level. And the worst part is actually the UI. You can go the Wordpress/shopify route where you allow client templates and it’s a huge cost for you to maintain. Or you can do some sort of automatic field generation and no-one’s happy.
Not only that, but your product ends up in a straight jacket, where you can’t fix any fundamental data structure mistakes because half your client integrations will break.
I decided that I don't want a private life that needs GANTT charts or org mode for interesting projects. After half a dozen of time management books I realized that this is just another form of procrastinating: * reading a lot about time management * overcomplex tooling * shuffling time slots in a calendar
The solution is a simple (check) list as a reminder. Calendar only for hard deadlines. Plus "just do it" attitude. The rest will follow. Or not, if life is otherwise too busy -- which I simply accepted.
The results don't differ much from before. Except: less time wasted with software.