Essays and posts. Longer-form thinking built on top of the wiki.
A structured course on AI engineering and agentic patterns, distilled from the wiki: foundations, context, evals, verification, harnesses, and the software factory.
2026-08-28Why Rust-speed, error-only lint gates like Oxlint are the Tier 1 backpressure layer that keeps autonomous coding loops honest — with the failure modes they mechanically close.
2026-08-27Dissecting OpenAI's Codex harness: JSON-RPC app-server decoupling, multi-platform OS sandboxing, bounded context streams, and the lessons of production agent design.
2026-08-27Why probabilistic coding generators accumulate intent, semantic, verification, architecture, and authorization debt—and how risk-conditioned systems keep autonomous loops releasable.
2026-08-25How Uncle Bob's 2012 Dependency Rule and boundary isolation principles solve the durability, containment, and testability crises in modern AI agent harnesses.
2026-08-24How evaluation methodology shipped as installable skills and GAN-inspired generator-evaluator loops are advancing AI agent reliability beyond prompt tweaks.
2026-08-24Why single-agent prompt loops degrade past the smart zone, and how graph orchestration provides the structural partition needed for production AI systems.
2026-08-22The first post on pyweb.dev
2026-08-22A practitioner's architectural guide to building reliable AI coding agents: avoiding context rot, operating in the smart zone, and enforcing tight engineering loops.