This is where I document the ways I'm using AI in both my personal and professional workflows. Not as a list of tools. As specific systems I've built to do specific kinds of work — and the patterns I've found in using AI well versus using it poorly.
I use AI to do the work on me — to force the reps I'd skip, call out the flinches I can't see, and grade me fuzzy when I want to be graded clean. The first article is the one I lean on most: a Claude skill I built before opening Manning's IR textbook, grounded in Justin Skycak's Advice on Upskilling. The premise: learning is a positive change in long-term memory. If I can't retrieve it cold without help, I haven't learned it.
More articles will follow as I build new systems and find new patterns worth writing about.
A walkthrough of the learning system: a Claude skill grounded in Skycak's framework, three modes (Diagnose, Plan, Coach), eight non-negotiable rules, five grading categories where peeked ≠ clean. Four files that hold the strategic, tactical, and operational layers — and a rep loop that adapts to how the rep was graded.