Engineering methodology for deploying AI systems with operational discipline.

A system that ships predictably beats one that demos brilliantly.

I write The Human Stack — a living engineering reference for deploying, operating, and evaluating AI systems in production. Everything in this profile is evidence supporting that methodology: eval frameworks that catch regressions before they ship, cost observability that surfaces spend anomalies in real time, and MCP tooling that standardizes how AI agents connect to the world.

Before software I spent 17 years running manufacturing and logistics systems (IBM, Toyota Production System) — standard work, visual management, error-proofing. That discipline shows up in every codebase: ADL-governed decisions, adversarial test gates, evidence-graded maturity.

Building toward a world where every engineering team ships AI systems with the same operational discipline they apply to production infrastructure.

Substack · LinkedIn · jamesyng79@gmail.com

These are the repos I maintain to production quality — evidence, tests, and documentation first.

Hobby projects (EVE Online lore, personal context servers) are kept private. What you see here is what I ship.

The fastest way to understand the methodology is to use it. These repos are arranged as an onion — start at the outer layer and peel inward.

Animus is the primary reference implementation — a personal AI operating environment with local-first control and evidence-graded maturity tracking.

Key design decisions (visible in the code):

• Evidence Framework — Six-stage maturity model (Concept → Self-improving) with Coverage KPI. Makes "documented but unverified" into "inspectable evidence."
• ADL-governed architecture — Every major decision is append-only, dated, and cross-referenced. No tribal knowledge.
• Quality gates before merge — Deterministic scoring (tool/completeness/structure) with adversarial test harness. Features don't ship without gate passage.

• Decision logs, not memory. Every architectural choice is an ADL entry — rationale, rejected options, tradeoffs, kill criteria.
• Tests are deliverables. Not an afterthought. Adversarial tests prevent regression of quality-gate contracts.
• Local-first where possible. RX 7900 XTX inference stack (Ollama, 4-model tiered) for zero-cost eval calibration.
• Ship, measure, error-proof, repeat. Kaizen learned from scaling an ice-cream line 6× — applied to software.

Direct entry points for "what does the code actually look like":

• Animus Kernel — bitemporal memory + adversarial tests — v2.3 scaffold: valid-time / transaction-time axes, quality-gate contracts enforced before any feature ships. Architect Citizen produces ImprovementProposals from codebase observation.
• ai-spend — OpenRouter provider — GET /api/v1/generations pagination with native_cost fallback to token-based estimates. Pattern: provider registry ABC with side-effect registration.
• Animus Session Controller — Token-budgeted session lifecycle (96% utilization trigger), graceful finalization with model-generated summary, checkpoint + auto-restart. 22 tests, 83 existing head core tests green.
• Animus P5 Discovery — MCP scanner, OpenAPI ingestion, annotated script discovery, 4-dimension schema validator, hash deduplication. 41 tests, 194 total P0–P5 tests green.

17 years in manufacturing and logistics operations (IBM, Toyota Production System). Scaled an ice-cream production line from 740 pints/day to 4,800/hour using Kaizen. Now apply the same discipline to AI infrastructure: standard work, visual management, error-proofing, continuous improvement.

See it through. Do it better. Leave something real.