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 examines the challenges of applying generative AI to real‑world software development, proposes a collective‑wisdom Copilot that blends team knowledge, AI agents, and IDE integration, and details how Shire’s new version enables sharing, installing, and executing AI‑driven agents across diverse development workflows.
The article explores how prompts have evolved from simple text cues into executable, shareable agents, outlining engineering best practices, DSL‑plus‑runtime architecture, and the Shire Run platform that enables downloading, sharing, and future online execution of AI‑driven smart agents.
This article analyzes the current state and challenges of AI‑assisted development tools, proposes strategies to integrate cloud‑based and IDE‑embedded intelligent agents, and presents practical examples—including Shire language scripts and tool orchestration—to improve end‑to‑end software engineering efficiency.
Shire 0.5 introduces SonarQube issue support, Git‑enabled ShireQL queries, a reranking function for RAG, and new data‑guarding capabilities like the redact function and customizable secret‑pattern YAML, enabling developers to securely build AI‑powered coding agents that leverage IDE assets while protecting sensitive information.
This article provides a comprehensive, step‑by‑step guide to designing, prototyping, and continuously improving an AI‑assisted software engineering (AI4SE) framework, covering goal definition, pain‑point identification, technology selection, cross‑disciplinary team building, metric evaluation, and real‑world examples for teams of all sizes.
This article explains how to use the Shire language to create reliable coding agents by defining custom RAG workflows, leveraging IDE APIs, code verification functions, and vector‑based search, with detailed examples, configuration snippets, and a roadmap for future enhancements.
From 2023 to 2024, AI has expanded from simple developer assistance to comprehensive, lifecycle‑wide support, evolving through individual, team, and organizational layers and shifting from local IDE plugins to domain‑specific intelligent code generation tools.
This article examines the open‑source AutoDev AI‑driven programming tool, outlining its three maturity stages—from chat‑based assistance to fully automated generation, verification, and execution—and detailing new features such as automatic refactoring, API test execution, bulk test creation, and batch prompting to improve developer productivity.
AutoDev for VSCode extends the AI-driven coding assistant from IntelliJ IDEA to the VSCode ecosystem, detailing its unified architecture, dependency-inverted plugin system, event-driven UI, core interfaces, test-generation prompts, and the 0.1.0 release features such as custom AI commands, test and comment generation.
AutoDev 1.8 introduces AI‑driven refactoring, commit‑message generation, CLI assistance, and Chinese prompt support, combining software‑development best practices with knowledge‑engineered AI to streamline code changes, improve code quality, and integrate seamlessly into modern DevOps pipelines.
