A prolific open-source contributor who constantly starts new projects. Passionate about sharing software development insights to help developers improve their KPIs. Currently active in IDEs, graphics engines, and compiler technologies.
The article argues that in the AI‑first software era, managing multi‑agent teams requires a Kanban‑style control plane that visualizes runtime facts, concurrency, repository context, and execution history, turning the board from a simple task list into a robust engineering harness for reliable delivery.
An in‑depth analysis of Codex Security’s scans shows that AI‑assisted code production doesn’t create new bug types but dramatically speeds up the spread of existing flaws, prompting a shift toward automated, engineering‑driven defenses for large‑scale code generation.
The article analyzes how generative AI is reshaping software development, exposing the mismatch between AI's rapid code generation and traditional human‑centric engineering processes, and proposes a new "Harness Engineering" model that emphasizes system readability, defensive boundaries, and continuous feedback loops for safe AI‑assisted coding.
Routa is an engineering‑focused multi‑agent framework that separates tasks, state, events, and execution into controllable modules, enabling open‑ecosystem AI coding agents to collaborate through structured specifications, event‑driven coordination, and verifiable tool interfaces rather than fragile prompt stitching.
This article examines a recent real‑world experiment that shows how generative AI can compress a month‑long manual technical‑analysis workflow into minutes, reshaping the core skill set from information gathering to structured modeling and hypothesis‑driven insight in the financial technology sector.
The article analyzes six emerging trends in Chinese AI coding tools—model capability parity, open tool integration, spec‑driven development, lower entry barriers, self‑validation, and full‑stack automation—arguing that future success depends on end‑to‑end engineering reliability rather than mere code generation or emotional support.
As AI agents shift from assistants to autonomous executors, traditional GUIs become bottlenecks, prompting a redefinition of frontend architecture into a contract‑driven, observable, and controllable execution interface built on DSLs, NanoDSL, and a clear migration path.
This article explains how AutoDev builds an Agentic Retrieval‑Augmented Generation system with a Document Query Language (DocQL) that lets LLM agents navigate hierarchical code and documentation structures using JSONPath‑like queries, detailing implementation, multi‑level keyword expansion, and experimental findings.
AutoDev leverages a multi‑agent architecture and comprehensive information aggregation to turn traditional, fragmented code review into an intelligent, end‑to‑end process that not only detects issues but also generates and applies corrective patches automatically.
The article explains how the new AutoDev MPP architecture and its CLI, built on MPP Core, solve testing difficulties of previous IntelliJ‑based agents by tightly binding UI events, leveraging AI‑generated prompts, iteratively constructing a TUI/CLI, automating test framework generation, and integrating CI/CD for robust, portable AI‑driven development.
