Essays
Long-form posts. Architecture, incidents, and the specific patterns that have earned their place. Every post is grounded in something concrete.
- Context as a first-class artifact: the /deep-context pipelineStop hoping that relevant information will fit in the context window. Start manufacturing a task-specific context file before the task begins. The mechanism, the receipts, and the benchmark that gates it shipping.
- "Email me when done": a persistent task runner with a delivery guaranteeLong-running tasks fail silently if the session dies before the result is ready. This is the runner I built to make "email me when done" actually mean that. Retry loop, fallback email paths, and a last-ditch file.
- Lessons as code: turning postmortems into pre-flight checksA file I read at the start of every session, twenty-three numbered patterns of how I have broken my own system, and the pre-flight skill that checks proposed work against them. The pattern is the most portable thing on this site.
- Memory that sleeps: a tiered memory architecture with daily consolidationA two-tier retrieval system (semantic plus keyword), canonical topic files as curated truth, and a nightly consolidation pass that promotes session insights into the canonical tier. Why each piece exists and what fails without it.
- One hour, one command: disaster recovery for a solo AI shopWhat backups, what intentional exclusions, and a sequence that reconstitutes the whole personal AI operating environment in under an hour. The honest version, including the accepted gaps.
- A personal AI operating environment: worked example and receiptsWhat happens when one person uses an AI coding assistant as the primary interface to a real physical and operational life, and systematically fixes every failure that occurs along the way.
- Five things I built to help my AI agent that I had to removeEvery automated helper I built to make my system more reliable ended up making it less reliable. Why, with dated incidents and what I run instead.
- Six layers of defence for an AI agent over a 3D printerThe printer-safety architecture I now run, the specific incidents that produced each layer, and why the pattern generalises beyond 3D printing.
- Three-way AI model debate as a pre-commit gate: receipts from several months of useRunning Claude, Gemini and GPT-5.4 on the same question in parallel, blind Round 0, informed from Round 1 onward. What works, what does not, and the confidence trap I did not predict.
- What it means to be AI-nativeThe difference between using AI a lot and being AI-native: infrastructure as the binding constraint, not model capability.