Writing
Articles on engineering decisions, implementation details, and the tradeoffs behind reliable production systems.
6 articles
Retrying an external write is a guess about which of three worlds you are in. Idempotency keys, business-key deduplication, and the database invariants that make the guess unnecessary.
Read articleCorrelating one job across TypeScript, a queue, and Python — without turning routine telemetry into a second copy of the sensitive payloads it describes.
Read articleEvery model call in a routing path converts a fact into a guess. What I learned about spending probabilistic routing only where the ambiguity is real.
Read articleWhy a model-generated Mermaid diagram or ECharts spec is a program, not data, and the two-tier validation and bounded repair pipeline I built around it.
Read articleTwo and a half years of building agent systems, and what I got wrong about architecture, context, evaluations, model routing, permissions, and recovery.
Read articleHow leases, checkpoints, ownership-safe writes, and tool-history repair made Research-AI recoverable — and what the design still does not guarantee.
Read article