Writing

Notes from the seam of research, design, and engineering. They are about making AI trustworthy, and about designing with it as a material rather than bolting it on as a feature. Grouped by the ideas I keep returning to. Short pieces, mostly.

• POV2026 · ~6 min AI as a Design MaterialDesigning with AI as a probabilistic raw material. You understand its grain, then build the guardrails, evaluation, and human-in-the-loop around it.
• POV2026 · ~7 min Designing AI Behavior, Not AI ScreensThe real work in AI agents UX. Confidence caps, a critique-repair loop, hypothesis-blind generation, and a harness that makes the behavior predictable.
• POV2026 · ~7 min Building With LLMs: Designing the HarnessTreat the model as a probabilistic material and wrap it in a harness: an eval harness, guardrails, model routing, and audit journals.

• FLAGSHIP2026 · ~7 min Grounded Simulation: faithful, not just fluentA first-principles architecture for keeping LLM “synthetic users” faithful and auditable, not just fluent.
• POV2026 · ~6 min Auditable AI ResearchWhy AI-generated research has to be inspectable and defensible. Research you can audit in thirty minutes, plus the mechanisms that get you there.
• POV2026 · ~6 min Less Expertise, More CoverageFraming an LLM as a narrow expert can shrink the coverage of an analytical task. A broader prompt often surfaces more of the real answer space.

• POV2026 · ~6 min Research → Product → CodeOne continuous loop with minimal handoff loss. What you gain when the person who frames the question also ships the code.