Author of the rpcx microservice framework, original book author, and chair of Baidu's Go CMC committee.
The article recounts a near‑automatic library‑development experiment that started from a PRD, split into 15 issues, executed by a Loop Engineering agent, and resulted in a fully functional Go RDMA library while exposing hidden costs, bugs, and lessons learned.
The author demonstrates Loop Engineering by feeding a PRD to Claude Code, triggering a /loop-it command, and in one hour automatically creating, implementing, reviewing, and shipping eight GitHub issues for the Kuiniu tool, while detailing the concept, history, workflow design, state management, error recovery, and practical insights.
Loop Engineering replaces manual prompting of AI coding agents with automated loops that schedule, coordinate, and verify work, detailing the five essential primitives, historical evolution, practical implementations, limitations, and a step‑by‑step guide for building a minimal, production‑ready loop.
The article examines goscapy, a pure‑Go network library that brings Scapy‑style stream‑builder APIs, automatic checksum calculation, protocol inference and zero‑copy serialization to Go, and compares it in depth with gopacket, showing code examples, performance tricks, and practical use‑cases such as ARP and TCP SYN scanning.
The article introduces Lidar, Baidu’s new open‑source TCP‑SYN based network monitoring system, explains why the classic PingMesh approach is unsuitable for large data‑center environments, and details Lidar’s design, implementation quirks across Linux and macOS, BPF filtering, source‑port rotation for ECMP coverage, and practical usage examples.
Baize is an open‑source, configuration‑driven Go tool that delivers millisecond‑granular, high‑frequency (up to 5 000 packets per second) network quality monitoring, covering full ECMP paths, one‑way packet‑loss detection without clock sync, and complementary bit‑flip checks, with simple JSON deployment and built‑in profiling.
The author describes creating a Go library called agent‑wrapper that unifies multiple coding agents—Claude Code, Codex, Pi, OpenCode—by providing a single registration interface, built‑in approval, budget control, context compression, session resume, and command‑line tools, turning disparate agents into a stable, production‑ready orchestration layer.
The article analyzes how AI agents have transformed software engineering over the past three years, redefining programming from hand‑written code to prompt‑driven development, and argues that engineers must shift from writing code to orchestrating intelligent agents to stay relevant.
The article introduces the open‑source /smell skill, an AI‑powered code‑analysis tool that scans a codebase, identifies architectural anti‑patterns, code‑level smells, and performance hotspots, and generates a detailed markdown report with severity rankings and refactoring suggestions.
The article introduces Matt Pocock's open‑source "skills" collection for AI coding agents, shows how it embeds traditional engineering practices such as alignment, domain modeling, TDD, and architecture governance into reusable command sets, and walks through a complete partial‑refund feature implementation using these skills.
