Multi-agent coordination through verifiable behavioral contracts. Agents commit to observable behaviors rather than inferred mental states, so a third party can check compliance without access to internal representations. The framework is formalized against Hart-Moore incomplete contracts theory; nearly all of the evidence below is simulation, and the two figures from real LLM agents are listed first.

4/4 agents better calibrated by external assessment than self-report (real LLMs) · +0.017 motivation effect in real LLMs — a null, p = 0.56, CI excludes the predicted +0.065 · 40.4% hold-up reduction in simulation (95% CI: [37.2%, 43.5%])

Corrected in place repeatedly, most recently September 2026: several published figures were traced to hardcoded chart constants rather than experiment output, and the self-selection result was falsified by an adversarial re-audit, re-measured, and then failed to reproduce in real LLM agents. The original wording and the defect are kept on the page. Only thirteen of the experiment scripts import the GCL package; everything from 19 onward is a standalone simulation.

derive_real_headline_stats.py · Re-derived by CI · What currently survives · Correction record · Repository

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.

The evaluation machinery described in Act I is deployed. The architectural-learning loop the essay argues for is a proposal — nothing in Act III has been built.

Reality-graded architecture loop · What exists today, and what is proposed · References & intellectual lineage

Grounded RAG chatbot over this site, red-team hardened. Published eval-gate numbers including the bars still unmet, and the real defects the harness found and root-caused—rate limiter, citation injection, retrieval crowding.

Eval runs · golden_harness.py · Try it

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.

The only entry here with no checkable evidence. The underlying sample is employer work product: the repository is not public and the methodology note is not mine to publish, so every figure in the essay rests on my word alone. Stated at the top of the page rather than at the bottom.

Why none of these figures can be checked · What the sample could not have shown · Convergence topology

Extension of Google Research’s nested optimization: 5 timescales with 9 bidirectional knowledge bridges. Addresses catastrophic interference where fast learning degrades slow-learned representations, via normalization constraints that preserve component distinctiveness during optimization.

+89% accuracy at high regularization, where baseline collapses

Bridge ablation, re-derived weekly by CI · Reproduce in Colab · Repository

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

Systems-architecture layer beneath agent frameworks: durability, verification, and policy—not orchestration. Event-sourced state for resume/replay from any checkpoint, a tool gateway enforcing policy at invocation time, and GCL commitments as first-class objects with explicit failure modes.

303 tests passing

Single-node only. No performance benchmarks yet, and no production deployment.

What the 303 tests cover — and what they don't · Built on GCL's verifiable-behavior contracts · Repository · Event-sourced state applied to models of people

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.

Interactive demo · PDF

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.

Process artifacts · Eval runs

Production extraction with multi-provider LLM routing and human-in-the-loop validation, shipped at HCA Healthcare. HIPAA-compliant architecture prioritizing audit trails over model optimization; corrections captured as reward-shaped labels for offline fine-tuning.

Repository

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.

Why this page has no code behind it

A working voice-first MERN record system for beekeepers — speech capture, LLM extraction of structured observations, and a full apiary/hive/inspection domain model — plus three decision-support models specified in detail against it. None of the models are trained: the prediction endpoint is wired but its predictor is a stub, and no labelled dataset has been assembled.

Repository

A personal design specification for governing autonomous agents in high-stakes domains: frozen constitutional constraints beneath a human-supervised strategic layer and an autonomous tactical layer. Nothing was implemented.

Corrected September 2026: this entry previously read as a deployed system built in the current role, was tagged Production, and cited employer confidentiality for its lack of evidence. It is a personal design predating that role. Nothing was implemented and no repository exists.

A personal design specification for a real-time voice-AI agent for high-stakes adversarial contexts, combining streaming speech recognition with retrieval over domain corpora. Nothing was implemented.

Corrected September 2026: this entry previously read as a deployed system built in the current role, was tagged Production, and cited employer confidentiality for its lack of evidence. It is a personal design predating that role. Nothing was implemented and no repository exists.

Production agentic workflow coordination.

Three flagship claims—the punishment paradox, Hart-Moore hold-up reduction, and the CNL bridge ablation—re-derived by the source repos' own CI: the GCL pair on every push, the CNL bridge weekly at full scale. Not a promise that a number cannot change; a standing invitation to check whether it still holds.

The three claims