kevin@escapecommand:~/blog$ ls -t
My task board runs models at three points in its pipeline, and none of them decide anything. The rule that fell out of building it: put the model where being wrong is cheap, and put deterministic code everywhere being wrong is permanent.
An instruction to an agent is not a control. Before I let anything act on my mail, I built the layer that does not depend on the agent behaving: a read-only, append-only, encrypted copy the agent cannot reach, and a gate it has to pass before it touches a message.
I run shadow jobs to grade my local inference stack against the cloud models. The first thing the harness caught was a cloud model fabricating an entire result. Reading output is not verification. A diff is.
AI is the fastest way to discover the shape of the tool you need. It is the wrong thing to call every time you use that tool. Once the shape is clear, graduate it off the AI runtime.
Someone, somewhere, has already solved your exact problem or close enough to it. The skill is learning to abstract your query until you can find them.
The operations reflex is to spot the friction you have stopped noticing and smooth it out. That reflex used to stop at the edge of software. AI moved the edge, and now it reaches the physical things in your house.
I left hardware for a decade. When I came back, the toolchain was unrecognizable but the architecture in my head still worked. AI rewards that survival.
AI tools commoditized the building. What survives is the skill that was always the hard part: holding the architecture of a system in your head and describing it well enough to get something useful out.
XKCD 1205 told us when automation was worth the time. AI collapsed that calculation. But the chart measured the wrong cost all along.
AI skills are the fastest way to prove an idea works. But when other people need what you built, it is time to think bigger.
The Google Sheet is the most popular application platform in enterprise. AI is finally changing that.