PROCESS MINING FOR AI AGENTIC WORKFLOWS, PART 4: IN PRODUCTION
Part 4 of 4 in the series Process Mining for AI Agentic Workflows. Previous: Part 3, Engineering and the Agent. Start at Part 1, A Field Guide.
Read moreFROM WARM-UP TO THE HARD CLIMB: CONTRIBUTING ACCRINTM AND ACCRINT TO A RUST SPREADSHEET ENGINE
The warm-up: shipping ACCRINTM Last spring I set out to add two functions to IronCalc, an open-source spreadsheet engine written in Rust. Both compute accrued interest on bonds. One took a couple of focused sessions. The other turned into a multi-week investigation that ended in a public discussion with the maintainer about which of two Microsoft documents is “correct.” This is the story of both, and of the working method that let the hard one span weeks without losing the thread.
Read moreHOW TAKE AI BITE LEARNED TO BOOTSTRAP ITSELF
It is curious how AI, in this case Claude Code, will embark on a quest with topics not entirely explored. That would write the fate for an explorer in counted minutes. However, we humans sometimes think that an AI suggests acting on something based on training, as if training is equivalent to knowledge. Try entering the Amazon jungle without knowledge and see if you walk out at all.
Read moreRUNNING A PMO FOR AN AI-AGENT WORKFORCE
I closed my last post by saying there was a word for the role behind the methodology and that a next post would get to it. This is that post.
Read morePROJECT 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 more147 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 more- 1
- 2