The archive, mapped

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.

A design pattern for supervised AI investigations: scoped read access, reviewed drafts, and failure tests before expanding permissions.

MCP shipped a breaking specification revision. I wrote the gap analysis, filed it as factory backlog, and Mills started rebuilding the SDK it runs on.

Four defect classes that healthcare interchange parsers can accept silently, with synthetic samples, real linter output, and the pre-send gate that catches them.

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.

How five simulated minds share one 24 GB Radeon, keep 200K-token life histories, reuse them through prefix caching, and compact old memories without erasing continuity.

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 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.

A 90-day rollout for AI-assisted development: start with bounded habits, measure the work, and standardize only after the team has evidence.

Field notes from serving Gemma 4 E4B on Radeon: the stable TRITON path, an experimental TurboQuant long-context lane, and the GPTQ work still in progress.

How I use AI drafts to build engineering judgment through inspection, regression tests, code review, and repeatable release checks.

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.

Field notes from building and operating a small private GPU platform with Harvester, K3s, and a GitLab -> Flux delivery loop.

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 practical operating model for healthcare integrations: explicit contracts, safe delivery, observable decisions, and support loops that improve the product.

What changed since Meaningful Use, what SMART and TEFCA each solve, and why production interoperability still needs explicit contracts.

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.