"When I work on something, whether it's at Interfere or my personal projects, I like to experiment a lot. Design engineering is a lot about trial and error, and I often spend hours trying to find the "this feels right" moment. This is where AI helps. Instead of spending hours on a concept that I'm unsure of, I try that concept out in a matter of minutes, and throw it away if it doesn't feel right."
"There is an important distinction to make here though. I don't use AI to come up with ideas or to replace my own thinking. I use it to accelerate my workflow. It's also very important to understand what the agent is doing. AI works best if the user is in charge and not the other way around. Don't just blindly follow whatever the agent gives you."
"Whether you are using Claude Code, Codex, Cursor or any other agent, one of the most important things is the setup. I personally use Cursor for most of my work, so I'll use that as an example. The first thing I do when starting a project is create a set of rules for the codebase. You already have a pretty good idea of how you want to do certain things."
A design engineer remains skeptical of AI because AI is not particularly strong at craft, thoughtfulness, or creativity. AI accelerates experimentation by allowing fast trials and quick discarding of concepts that don't feel right. AI should not replace idea generation or personal thinking; it should speed workflows while the user stays in control. Understanding what the agent is doing and avoiding blind acceptance of outputs is essential. Proper setup and concise, referenced rules for the codebase improve agent behavior. Copying rules without understanding them is discouraged. Tool choice and conversational context management matter.
Read at Jakub
Unable to calculate read time
Collection
[
|
...
]