Frameworks and thinking about AI systems, deployment, and the organizational dynamics that shape what gets built.
When Production Disagrees with the Architecture
A caller answered two questions when our voice agent had asked one. That small production failure exposed a larger problem: evals can preserve counterexamples without preserving what they should teach us about architecture. Production evals → architectural assumptions → prospective evidence → earned autonomy.
Reality-graded architecture loop · What exists today, and what is proposed · References & intellectual lineage
The Bottleneck Moves
Coding agents made implementation cheap, so the bottleneck was supposed to move upstream into specification and architecture. Some of it did; more of it accumulated downstream in convergence — restoring mergeability, asynchronous review round trips, serialized resources, and acceptance criteria the executor cannot verify. Drawn from a retrospective of twenty merged changes in a production system, none of which a reader can check.
Why none of these figures can be checked · What the sample could not have shown · Convergence topology
The Archive That Cites Itself
Persistent AI advisors, the people they model, and the limits of “more context”—why a user model should preserve the history of its claims rather than a polished conclusion.
Interactive mirror · Event-sourced state, applied · References
HALA: Human-AI Layered Architecture
Pattern language for human-AI role allocation: 28 patterns across 5 layers. Inspired by observations from production AI work, where organizational dynamics—not technical capabilities—were the binding constraint. A design proposal; none of the patterns have been deployed.
Agentic Delivery: Specs, Supersession, and Eval Gates
How this site’s content was written by an AI coding agent under a written spec with supersession rules, a fact inventory, and eval gates—including the defect the process found in its own verification record.
Strategy Tournament
An unimplemented design specification for a backtesting framework: how systematic strategies would be compared under realistic execution constraints—slippage, latency, partial fills—and robustness stress tests, so a strategy that only looks good against a frictionless backtest gets caught before capital does. Addresses evaluating adaptive systems when the evaluation itself can be gamed. No code was written and no repository exists.