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.
I’m a Director of Engineering at Samsara, working across Safety and Telematics. I write about edge AI, firmware-to-cloud systems, engineering leadership, and the practical systems I build around coding agents.
Read the AI engineering series · About my leadership scope
This site is a record of the work behind the outcomes: the decisions, experiments, tools, failures, and operating practices that make the next result more trustworthy.
Recent writing
The guardrails that let me run multiple AI agents
One agent per level worked well. Eight agents assigned broad themes across the same codebase did not. The difference was ownership.
AI gives me speed. My job is to give it direction.
I can keep several agents busy. The harder job is making sure their work adds up to a product I actually want.
Keeping teams steady while the organization changes
An organization chart can change quickly. Rebuilding clarity about priorities, ownership, and growth takes more deliberate work.
Quality engineering belongs inside the development loop
Owning quality and automation alongside firmware changes the question from who checks the work to how quickly the system reveals a bad assumption.
What an AI agent has to prove before I call it done
A clean compile answers one question. It does not tell me whether the right screen opened, the interaction worked, or the browser ran the new build.
Some experiments should stay experiments
The value of a prototype can be the decision it makes possible, even when none of its code belongs in the product.
I build tools so the next iteration costs less
The useful tool is the one that lets me answer the next product question without rebuilding the entire experiment.