August 30, 2026
· 18 min read
Why choosing a model per workload belongs in configuration, why the routing table has to be benchmarked through the full harness rather than guessed, and why it needs to be rebuilt on a cadence rather than trusted forever.
August 13, 2026
· 6 min read
A field note on treating a garden as a living operating system with explicit zones, recurring checks, and practical feedback loops.
August 11, 2026
· 9 min read
A comparison between infrastructure testing and agent evaluation, focused on hidden state, behavioral contracts, and feedback loops.
August 2, 2026
· 9 min read
A field note on treating overlanding plans as operational reviews with explicit assumptions, risk budgets, and verification timing.
July 26, 2026
· 6 min read
How a personal LLM wiki can separate raw evidence, curated memory, context packs, privacy boundaries, and evaluation loops.
July 18, 2026
· 6 min read
A reliability note on why incident categories matter only when they change prioritization, learning, and operational follow-through.
July 10, 2026
· 6 min read
A close look at reef-pi's hardware abstraction layer as the line that turned a controller project into a small open-source platform.
July 5, 2026
· 6 min read
A systems-through-line from Chef, infrastructure automation, and TDD in operations to context engineering for agentic AI.
June 28, 2026
· 6 min read
Why reusable prompts and context packs deserve versioning, review, privacy boundaries, failure modes, and evaluation loops.
May 31, 2026
· 3 min read
Lessons from reef-pi as a public engineering artifact that must survive real users, hardware variation, and community support.
May 31, 2026
· 3 min read
How automation, testing, and platform thinking connect infrastructure-as-code work with later production engineering practice.
May 31, 2026
· 1 min read
What this website collects, how public material is selected, and where to find broader profile and project links.