A shift in what I’m writing about, and the assumptions I’m carrying across. The push that stopsEarlier this month my personal-assistant work...

Last time I wrote that the DAG wasn’t running yet. It runs now. This is what it turned out to be, and what it actually changed. I asked for ...

A progress update on the AI-driven DAG project, and a few things I’ve been thinking about while building it. This one is less of an essay th...

AI makes software changes cheaper to produce, but harder to understand, verify, and govern at scale. Here is a scenario most teams working w...

There are two familiar ways to run an agent over real work. In model-driven execution, the model organizes operations and decides what happe...

In my previous article, I introduced an agent harness built around Pi Core, with one important design decision: a two-stage execution flow. ...

I recently integrated Pi Core into an agent system I use in a work environment. This was an interesting choice for me because, in my persona...

I’ve just finished building the first working version of my LinkedIn operation harness. This is also the first post coming out of it. The id...

JessicaWhen I learned with Jessica last weekend, leaned a new useful term: Competitive Edge or Competitive Advantage. I think I can recog...

Why the title is like this? Because I never know this grammar. Or, I learned it but forgot it. I really like the cake of heating up to 300 ...