Writing
Case studies and blog posts on architecture, operations, and delivery: what worked, what failed, and what is reusable.
Method
The unified perspective behind everything else: six principles, four playbooks.
Explicit Control Loops · Evidence First, Measure Before You Optimize · Warnings Over Errors, Graceful Degradation by Default · One Config, Many Surfaces · Contract-Driven Integration · GitOps as the Boring Substrate
AI-Assisted Dev Adoption Loop · AI Infrastructure Readiness Audit · Healthcare Integration Onboarding · Agent Rollout With Guardrails
Introducing AI-Assisted Dev to a New Team · Auditing and Stabilizing GPU Infrastructure · Healthcare Integration From Scratch · Rolling Out Production Agents
Every post and case study with its principle and playbook tags — filter by any of them.
Case Studies
Real implementations with metrics, stack details, and lessons learned.
Blog
Technical notes, implementation updates, and deeper dives.
Five Voices, 200K Tokens, One Consumer GPU: Giving Simulated Minds a Whole Life to Remember
We rebuilt our Jungian multi-agent lab so each archetype carries its entire life — every situation, everything heard, everything said — as an append-only journal that fills a 228K-token context window on a 24 GB Radeon. Prefix caching makes depth nearly free; when the window fills, the agents dream their oldest memories into a durable core. Here is the architecture, the numbers, and what broke along the way.
Gaming Mode: Turning an Inference GPU Node into a Moonlight Host — Declaratively
FlexInfer had a "gaming mode" that had never once run a game. I killed the stub, proved the substrate with a 30-minute kill-test, and rebuilt it as a declarative GamingSession CR that drains inference and streams a GPU-accelerated game over Moonlight.