Method · Browse by topic

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.

Back to principles Reading paths

PrincipleAll 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

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

Matching the filter

2 items

Building a Multi-Model LLM Platform on Consumer GPUsCase studyJan 15, 2026
How I run multiple OpenAI-compatible LLM endpoints on a small K3s cluster with AMD Radeon GPUs, and what I had to do to make it stable.
Evidence First, Measure Before You Optimize GitOps as the Boring Substrate Playbook: AI Infrastructure Readiness Audit
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.
One Config, Many Surfaces GitOps as the Boring Substrate Playbook: AI Infrastructure Readiness Audit