This essay is a reflection on what it really means to build and use AI agents, framed around the mindset rather than the technology. At its core, I argue that automation is ultimately about control, clarity, and responsibility, not about tools or “hacks.”
The real skill is not coding agents, but thinking clearly enough about work and responsibility that you avoid building systems that impress on the surface but quietly fail or reverse‑capture your time.
I’m curious how others draw the line between useful automation and dangerous dependency. What do you refuse to automate?
I automated my meeting scheduling and I think I saved 3 hours a week, but I stopped preparing for calls because I wasn't blocking out the thinking time anymore...so.
One of the things I did was to detect on the calendar when there’s overlap meetings and send a suggestion to postpone to another available slot. I also add the question if the meeting can be done asynchronous.
This essay is a reflection on what it really means to build and use AI agents, framed around the mindset rather than the technology. At its core, I argue that automation is ultimately about control, clarity, and responsibility, not about tools or “hacks.”
The real skill is not coding agents, but thinking clearly enough about work and responsibility that you avoid building systems that impress on the surface but quietly fail or reverse‑capture your time.
I’m curious how others draw the line between useful automation and dangerous dependency. What do you refuse to automate?
I automated my meeting scheduling and I think I saved 3 hours a week, but I stopped preparing for calls because I wasn't blocking out the thinking time anymore...so.
Automation done right is invisible and you don’t notice it. But if you are constantly think you are missing something, time to reconsider.
One of the things I did was to detect on the calendar when there’s overlap meetings and send a suggestion to postpone to another available slot. I also add the question if the meeting can be done asynchronous.