2,161 commits later, here is what I measure
The Git history is busy. The harder question is how much of that activity becomes a result worth keeping.
The Git history is busy. The harder question is how much of that activity becomes a result worth keeping.
I can keep several agents busy. The harder job is making sure their work adds up to a product I actually want.
An organization chart can change quickly. Rebuilding clarity about priorities, ownership, and growth takes more deliberate work.
Owning quality and automation alongside firmware changes the question from who checks the work to how quickly the system reveals a bad assumption.
Accuracy is one target. Latency, power, compute, reliability, and the cost of the complete system belong in the same decision.
Staying technical is useful when it improves the questions I ask and the decisions I help teams make.
Leading Safety and Telematics means connecting firmware, quality, automation, data, and services around the behavior customers experience.
A busy session can keep producing work after it has stopped reducing uncertainty. I want to notice that before the diff gets bigger.
The biggest AI shift for me has not been technical.
I pay for the highest consumer-tier AI coding subscriptions I can justify.
One of the best uses of AI is not doing the known work faster.
AI makes it easier to create.
Running multiple AI sessions is not like having magic.
AI does not reduce the value of internal tools.
One of my most productive AI weeks had zero commits.
Token limits are usually discussed as a model constraint.
Prompting matters.
AI can make one person look like a small team.
The first wave of AI coding feels like a writing-speed upgrade.