#system-design

Fast code is easy. A codebase that survives its next hundred changes is harder.

A bilingual Claude Code skill set for diagram-first system understanding, with one main workflow skill and one companion orchestration/reference skill.

Build and operate production-grade AI agent systems through this 22-chapter technical course designed for collaborative learning with AI partners.

BeforeCode — Spec-first software planning toolkit for humans and AI coding agents.

ML system design interview guide: retrieval, ranking, sequential recommendation, and the classic production ML stack.

Diago turns engineering work into AI-powered, evidence-grounded software diagrams for Codex and Claude.

A self healing API service mesh, written in Rust on Tokio and Axum, that watches a topology of upstream services, detects failures with a debounced health checker, atomically reroutes traffic and rewrites its own routing config, and asks Claude (via the Anthropic Messages API with tool calling) to produce a structured incident report.