Chapter iii · Writing

Field notes from a practitioner using AI systems for real work.

The main thread is Reflective Practitioner. Older academic publications sit underneath. No newsletter cadence theatre.

4 essays in 2026 · 12 academic papers · 1 provisional patent
Writing · Chapter iii
Reflective Practitioner · 2026

Recent essays.

  • Aug 2026
    No. 05

    When Your Agent Stops You and Nothing Is Wrong

    ~ 4,800 words · 19 minute read

    Your agents read prose that a human wrote, and some of it stopped being true. When one of them stops you, the alarm is faithful, the reasoning is sound, and the conclusion is wrong. What that does to the person who has to keep deciding, and the smallest thing that fixes it.

  • Aug 2026
    No. 04

    White Bears in My Constitution

    ~ 6,350 words · 28 minute read

    I replaced a creed with a constitution because the literature said to, and my agents started producing exactly the failures the constitution named. An experiment in constitutional AI governance, what went wrong, and the forty-year-old cognitive psychology paper that explained it.

  • Aug 2026
    No. 03

    The Grandmother and the Machine

    ~ 2,500 words · 11 minute read

    Fifty thousand years apart, two women do the same thing. A drought, an argument around a fire, and a direction the whole tribe has to bet on. What that tells us about AI, and about the one question that has always done the work: how do you know?

  • May 2026
    No. 02

    Your Agent Is Impersonating Itself

    ~ 2,750 words · 12 minute read

    Most “agent failures” are not the model losing competence. They are the model losing track of which agent it is supposed to be. Notes on identity drift from a panel system in daily production use, and the verification gate I built to stop it.

  • Apr 2026
    No. 01

    Why Your AI Apologizes Like a Sycophantic Politician

    ~ 2,250 words · 10 minute read

    On the difference between a model that has been trained to be agreeable and a colleague who tells you when you are wrong. Why you want the second one. How to ask for it. What it sounds like when you get it.

Clusters of orange mountain ash berries in the foreground, a distant ridge lit pink by late sun

Fig. 07 Mountain ash, first cold week. Flathead Valley, autumn 2024.

USPTO · April 2026

Patents.

i.

AIPassWeb

Comprehension-based verification mechanism for AI agent context integrity.

Provisional patent application filed with the USPTO on April 28, 2026. Sole inventor. The mechanism is now the verification gate at the boundary of BgARC: if a session cannot demonstrate comprehension of its assembled context, it does not start.

Filed 28 Apr 2026
Sole inventor
2010-2016

Academic publications.

Twelve peer-reviewed papers and reference works in the history and philosophy of science. Most are on counterfactual evolutionary theory between 1880 and 1920: what biology would have looked like had a few intellectual moves landed differently. The full list is available on Google Scholar; selected work below.

  • 2014

    Definitely Directed Evolution (1890-1926): The Importance of Variation in Major Evolutionary Works by Theodor Eimer, Edward Drinker Cope, and Leo Berg

    Doctoral dissertation · Arizona State University

  • 2012

    On the rhetoric of inevitability in evolutionary history

    Studies in History and Philosophy of Biological & Biomedical Sciences

If you read something here and it lands, or it lands wrong, write to me. I read everything.