PROJECT MANAGEMENT FOR THE AGENTIC STAKEHOLDER
I was reading my own inbox folder when it clicked. Not the email kind, the one that lives at _inbox/ inside all projects developed with Take AI Bite, where messages from one repository land for another to pick up at the next session start. I had built it months earlier to stop losing observations between projects, populated it without ceremony, processed it without ceremony, moved entries to done/ when finished. It worked. I had not given it a name beyond “the inbox,” and I had not asked where the pattern came from.
Read moreHOW A METHODOLOGY LEARNED TO THINK AHEAD
There is a moment in every growing project when the backlog starts feeding itself. You fix something, and the fix reveals two things you had not noticed. You build a feature, and three people ask for the feature next to it. The work produces more work, and the question stops being “what can we build?” and becomes “what should we build next, and why?”
Read morePROTOCOL EXISTENCE IS NOT PROTOCOL VISIBILITY: DSM V1.4.5
Session 8 of the efficientnet-flower-classification-transfer-learning project. A spoke agent wrote a feedback file directly into the Hub’s repo. It did not show me the content first, did not ask, did not pause. The write just happened.
Read moreTHE TRAINER AND THE AGENTS
I did not plan to become a trainer. But here I am, 15+ projects in, with a system of AI agents I built from scratch. Each one shaped by the projects that tested them. 20,000 lines of methodology, a feedback loop that runs both ways, and a system that learns for itself and remembers what I learned even when I forget. Also, very stubborn sometimes, but that’s on me, and that’s why I keep refining how we work together.
Read more90 FEATURES ACROSS THREE DIMENSIONS
Most AI coding tools are built to reduce human involvement. DSM is built to make human involvement worth the time: the human and the AI produce better work together than either would alone, and what they learn carries forward.
Read moreTAKE AI BITE: A FRAMEWORK FOR HUMAN-AI COLLABORATION
AI tools generate faster than humans can review. When the output exceeds what a person can meaningfully engage with, the collaboration quietly breaks: the human stops reading and starts clicking “approve.” The human in the loop becomes decorative, and what they actually bring, direction, judgment, style, goes missing from the work.
Read moreTAKE A BITE
Deliver only what the reviewer can chew. Someone offers you a bite of a cookie. You take a bite the size you will enjoy. Too small and you won’t taste the cookie; too much and it will cause a lot of issues. AI collaboration works the same way.
Read more