Skip to main content

Writing

Case studies and blog posts on architecture, operations, and delivery: what worked, what failed, and what is reusable.

Product OverviewOpen PlaygroundContact

Method

The unified perspective behind everything else: six principles, four playbooks.

Open the method →
Principles
Six cross-cutting ideas

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

Playbooks
Four adoptable processes

AI-Assisted Dev Adoption Loop · AI Infrastructure Readiness Audit · Healthcare Integration Onboarding · Agent Rollout With Guardrails

Reading paths
Four curated sequences

Introducing AI-Assisted Dev to a New Team · Auditing and Stabilizing GPU Infrastructure · Healthcare Integration From Scratch · Rolling Out Production Agents

Browse by topic
The archive, mapped

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.

All case studies →
Operating a Kubernetes LLM Platform on Consumer GPUs
Updated 6 min read
AI InfrastructureIn ProgressFeatured

Operating a Kubernetes LLM Platform on Consumer GPUs

How I evolved a small AMD GPU cluster into a CRD-driven inference platform with an OpenAI-compatible boundary, evidence-based model promotion, and safe rollouts.

OpenAI-compatible
Serving Contract
2 replicas
Production Lane
CRD + GitOps
Delivery Model
  • FlexInfer
  • Kubernetes
  • Flux
  • vLLM
  • +3 more
Read case study
fi-fhir: Profile-Driven Healthcare Integration
Updated 5 min read
HealthcareIn ProgressFeatured

fi-fhir: Profile-Driven Healthcare Integration

How fi-fhir separates feed-specific variance from parsing, semantic events, durable delivery, and workflow policy—and where the pre-1.0 platform still has work to do.

4
Input Families
3
Ingress Paths
Pre-1.0
Release State
  • Go
  • PostgreSQL
  • YAML
  • CEL
  • +5 more
Read case study
Patient Matching When the API Contract Is Ambiguous
Updated 5 min read
Healthcare

Patient Matching When the API Contract Is Ambiguous

A de-identified field pattern for containing patient-match risk when filter and mode parameters interact in undocumented ways.

2 parameters
Observed Conflict
Fail closed
Auto-link Policy
Pinned fixtures
Regression Proof
  • REST API
  • Go
  • PostgreSQL
  • Prometheus
Read case study
Building an Operator-Focused Kubernetes Dashboard
Updated 6 min read
DevOpsIn Progress

Building an Operator-Focused Kubernetes Dashboard

How FlexDeck combines Kubernetes, Flux, CI, observability, and model state without hiding freshness, access boundaries, or the limits of a homelab control surface.

K8s + GitOps
Operator Surface
Go + SolidJS
Application Shape
Read-only
Public Boundary
  • Go
  • SolidJS
  • Kubernetes
  • Flux
  • +3 more
Read case study

Blog

Technical notes, implementation updates, and deeper dives.

All posts →
The Factory Files a Ticket Against Itself: Two Repos, One Session, Three Gaps
·9 min read
Professional

The Factory Files a Ticket Against Itself: Two Repos, One Session, Three Gaps

I put fi-fhir and edilint through Mills for the first time. It merged work I did not write, then exposed a test gate passing on the wrong tree and fixed it against itself.

ai-agentsmillsloomfi-fhir+3 more
Read post
The Factory Upgrades Its Own Foundation: An MCP Spec Marathon
·6 min read
Lab

The Factory Upgrades Its Own Foundation: An MCP Spec Marathon

MCP shipped its first deliberately breaking spec revision. I wrote the gap analysis, filed it as factory backlog, and Mills started rebuilding the SDK it runs on.

mcpai-agentsloommills+2 more
Read post
Writing | FlexInfer