The archive, mapped
Every blog post and case study on the site with the principles and playbooks each piece argues for. Filter by any principle or playbook to see just the evidence behind it.
All content
19 itemsI 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.
- The Agent Gets Read-Only Credentials: A Trust Ladder for AI in Regulated SystemsAug 29, 2026 · 4 min
A design pattern for supervised AI investigations: scoped read access, reviewed drafts, and failure tests before expanding permissions.
- The Factory Upgrades Its Own Foundation: An MCP Spec MarathonAug 29, 2026 · 7 min
MCP shipped a breaking specification revision. I wrote the gap analysis and filed it as backlog for Mills, which merged the SDK half of the migration on August 26.
- A Green Run That Checks Nothing: Seven Silence Modes, Seventy Repos, One DayAug 16, 2026 · 16 min
A fleet-wide maintenance day exposed seven ways CI can report success without useful work—and the merge-queue discipline and recurring checks built to catch them.
- The File That Failed With Zero Errors: A Field Guide to Invisible EDI DefectsAug 14, 2026 · 5 min
Four defect classes that healthcare interchange parsers can accept silently, with synthetic samples, real linter output, and the pre-send gate that catches them.
- Twin Life on a Doubled Pool: One Day of Canary-Driven Inference EngineeringJul 26, 2026 · 12 min
A twin-lane canary promoted prefix caching, FP8 KV cache, and a larger context pool while catching five regressions before they reached the primary workload.
- Finding the Real Context Ceiling: Needle-Benchmarking Forced RoPE ExtrapolationJun 25, 2026 · 5 min
Needle-retrieval tests on a 35B model passed near 63,000 prompt tokens and failed at longer contexts, even when vLLM loaded without a memory error.
- A One-Page AI Usage Policy for an Engineering TeamApr 20, 2026 · 4 min
A short, adoptable AI usage policy for engineering teams: what to put on the page, what to leave off, and why the policy matters less than the habits it makes explicit.
- The First 90 Days: Introducing AI-Assisted Dev to a New TeamApr 20, 2026 · 8 min
A 90-day rollout for AI-assisted development: start with bounded habits, measure the work, and standardize only after the team has evidence.
- Build Your Own Legs Before the Crutches FailMar 9, 2026 · 5 min
Two cases where an AI draft looked right and was wrong, and the generated checks that replaced my having to remember.
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.
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.
- Standing Up a GPU-Ready Private AI Platform (Harvester + K3s + Flux + GitLab)Dec 29, 2025 · 6 min
Field notes from building and operating a small private GPU platform with Harvester, K3s, and a GitLab -> Flux delivery loop.
- Optimizing Real-Time Kubernetes VisualizationsDec 25, 2025 · 8 min
What the current FlexDeck code does to keep Canvas 2D and Three.js cluster views responsive, and how its performance harness avoids unsupported frame-rate claims.
- A Production Playbook for Healthcare API IntegrationsDec 19, 2025 · 7 min
A practical operating model for healthcare integrations: explicit contracts, safe delivery, observable decisions, and support loops that improve the product.
- Healthcare Interoperability: From SMART Apps to TEFCA-Scale ExchangeDec 19, 2025 · 7 min
What changed since Meaningful Use, what SMART and TEFCA each solve, and why production interoperability still needs explicit contracts.
- Case Study: The Patient-Matching Parameter TrapDec 19, 2025 · 5 min
How one undocumented precedence rule turned a patient-matching threshold into an unsafe assumption—and how I design the contract now.
A de-identified field pattern for containing patient-match risk when filter and mode parameters interact in undocumented ways.
How FlexDeck combines Kubernetes, Flux, CI, observability, and model state without hiding freshness, access boundaries, or the limits of a homelab control surface.