I was worried AI would take the fun out of engineering. My early experiences felt a bit like “autocomplete on steroids” — faster, but less satisfying.
It’s gone the other way. I feel energised.
The work is more playful now: I give it context, tighten constraints, adjust guardrails, and see what it comes back with — then steer, test, and refine. As it proves capability, I’m gradually delegating more of the execution to the agents, while I stay focused on intent, validation, and the tricky trade-offs.
And when something becomes fun/playful, it usually leads to better outcomes — you explore more, iterate more, and care more about getting it right.
The big shift is feasibility. Things that used to feel too heavy now feel doable:
- big refactors (in small slices)
- closing knowledge gaps quickly
- exploring multiple approaches without burning a day
It’s not “ship anything faster”. It’s “make more of the right work possible”.