Three weeks ago I introduced Open Delivery Spec (ODS), my side project for governing AI-assisted code in CI. Since then the CLI has shipped 5 releases and grown two new pillars: deterministic merge-confidence signals that answer “is this AI PR safe to merge?”, and an auto-generated, standards-based evidence document on every PR. As always, this post sticks to what actually ships — no hype.
Recently, my attitude towards GitHub Copilot has undergone a significant change: from “praising” to “bashing.” After comparing it with Claude Code, I’ve found that Copilot has clear deficiencies in cross-repository support and “senior engineer” awareness, to the point where I’m no longer willing to discuss problems with it.
Over the past few months, I’ve been working on an open-source organization called Open Delivery Spec (ODS) in my spare time. The initiative stemmed from the increasing volume of AI-generated code and the lack of reliable governance mechanisms within teams. This article records the thought process, progress, and boundaries based on the project’s real-world status, without any exaggeration.
The Conventional Branch specification receives its first major update. Version 1.1.0 adds support for AI Coding Agent branch prefixes (ai/, copilot/, cursor/, claude/, codex/), and provides a machine-readable spec.json and agent registry, making the specification useful not only for humans but also for tools.
AI tools like Claude Code by default embed signatures in commits, something many people don’t even notice. Commit Check v2.11.0 introduces AI Attribution Governance, allowing a single line of configuration to reject commits with AI signatures at the CI level. This article also discusses the boundaries of this feature and other pain points Commit Check has solved in the past six months.
This article breaks down an architectural approach for enterprise-grade Agentic Applications from eight dimensions: Agent boundary design, Tool Engineering, observability, evaluation framework, Memory layering, Human-in-the-Loop, cost control, and security.
Many people have asked how to build a GitHub Copilot-like AI Agent inside Jira. This post shares my hands-on experience building one — covering account setup, Jira Automation triggers, webhook integration, and a Skills-based capability system. The core philosophy: leverage existing infrastructure to get it running fast and cheap.
Codex auto-renewed this month. I hadn’t really planned on continuing my subscription, but this renewal prompted me to re-evaluate the actual experience with Codex, DeepSeek V4 series, and Copilot. For me, the core difference among AI coding tools is no longer just model capability, but rather which one can help me write code more stably, affordably, and consistently.
Over the past ten days, I’ve made over a hundred commits to RepoKeeper, evolving it from a proof-of-concept to v1.2.0. It now boasts six modules, two backends, supports DeepSeek/OpenAI/Claude, and can even develop itself—this post will explain what it has evolved into.
After reading Mario Zechner’s “I’ve sold out” and then reviewing AGENTS.md and CONTRIBUTING.md in the pi repository, I found that this project differs from common open-source collaboration methods in many ways. New contributors’ issues and PRs are closed by default, no reviews on weekends, and don’t submit PRs if you don’t understand the code. It seems tough, but behind it is a serious attempt to address a problem: how open-source projects can avoid being bogged down by low-quality contributions in the AI era.
Codex’s $22 monthly subscription fee and usage limits prompted me to seek a cheaper, stable, and always-ready backup solution. After an unsuccessful attempt with OpenCode, I turned to the Pi + DeepSeek combination. The result was a bit unexpected: writing an entire blog post cost only 0.24 RMB.
The Explain Error Plugin has recently received several important updates: AI Auto-Fix for automatically creating fix PRs, usage statistics and quota management, and added support for four new AI providers: DeepSeek, Qwen, Azure OpenAI, and Custom Okta.
In today’s era of rapid AI technological advancement, many companies are chasing the AI wave. But do we truly understand the distinction between “Automation” and “AI Agent”? This article will explore, from a practical application perspective, in which scenarios deterministic automation should be used, and in which scenarios AI Agents should be introduced. Through comparative analysis, we hope to help readers make more informed technical choices in this “all-in-AI” era.
The Explain Error Plugin introduces two significant updates: support for custom context information and folder-level AI provider configurations. These two features make the plugin more flexible and robust for use in enterprise environments.
Recently, I received some user feedback, and I immediately enhanced the Explain Error Plugin, adding two very practical features: support for specifying the language of the explanation content output and support for obtaining AI return values in Pipeline.
This article provides a detailed explanation of GitHub’s AI-related concepts and their hierarchical relationships through fact-based explanations and analogies, helping readers clarify the meaning and function of terms like Models, Agents, Spaces, and Spark.
This article introduces the new feature of Jenkins Explain Error Plugin, which is the support for Ollama local models, helping users more efficiently analyze and resolve build errors.
This article introduces a new feature of the Jenkins Explain Error Plugin that supports for Google Gemini model for error analysis. It provides configuration methods and an example video.
Introducing my first Jenkins plugin: Explain Error Plugin. It automatically analyzes build failure log information and generates readable error explanations, helping developers locate and solve problems faster.
