Tagged articles
AI code review
49 articles · Page 1 of 1
The author shares a practical workflow for escaping Claude Code's bug-regression loops by integrating GPT-5.2 via OpenAI's Codex CLI as a second-opinion reviewer, detailing configuration, command patterns, sandbox modes, and background execution tips for complex backend projects.
AI code reviewAI-assisted developmentClaude Code
0 likes · 7 min read

The article explains why simply adding a reviewer AI agent after a developer agent fails when both share requirement misunderstandings, and proposes a structured multi-agent review process: independent judgment against acceptance criteria first, automated mechanical checks, risk-based review division, actionable findings with trigger conditions and verification steps, reverse test validation via mutation and negative testing, and review conclusions tied to specific commits with expiration tracking.
AI code reviewGoogle engineering practicescode review best practices
0 likes · 10 min read

The author used AI to audit the Feat framework, uncovering 9 issues including connection reuse state leaks and security vulnerabilities, all fixed with automated tests, while reflecting on AI's role as a tireless code reviewer and the importance of invisible stability in foundational frameworks.
AI code reviewFeat frameworkautomated testing
0 likes · 6 min read


TonyBaiOct 1, 2026 · R&D Management
Haskell core developer turion shares a practical workflow for using LLMs without losing programming satisfaction: humans write code while AI handles planning, research, and automated review via a GAN-like pipeline, avoiding over-reliance on frontier models and token anxiety, and preserving code ownership and mental well-being.
AI code reviewLLM-assisted programmingcode ownership
0 likes · 26 min read

Cloudflare open-sources a six-phase security audit skill that transforms coding agents into structured auditors using adversarial validation, machine-readable findings, and a coverage ledger to make AI-driven vulnerability detection reproducible and trustworthy.
AI code reviewCloudflareCoding Agent
0 likes · 13 min read


Geek LabsSep 21, 2026 · Artificial Intelligence
clawpatch orchestrates local coding agents like Codex CLI and Claude Code as subprocesses to review, fix, and revalidate AI-generated code through a six-stage pipeline (init, map, review, fix, revalidate, open-pr) with semantic slicing, evidence-backed findings, read-only sandboxes, and explicit human approval — without ever calling model APIs directly.
AI code reviewCI integrationCodex CLI
0 likes · 14 min read

Alibaba's OpenCodeReview adopts a hybrid deterministic-engineering-plus-agent architecture for code review, cutting token usage by ~9x versus generic coding agents by constraining agent autonomy with hard-coded filters, token guards, and line-resolution modules, trading lower recall for higher precision and reliability.
AACR-BenchAI code reviewAgent Architecture
0 likes · 16 min read

Alibaba open-sourced Open Code Review, an AI code review tool used internally for two years, which combines a deterministic rule engine for file selection and line positioning with LLMs for judgment only, achieving higher precision and 9x lower token consumption than Claude Code on a benchmark of 200 real PRs.
AACR-BenchAI code reviewAlibaba
0 likes · 8 min read

This tutorial shows how to set up an AI-assisted pre-commit code review for Laravel projects by exporting environment details, route lists, and staged diffs into a structured prompt that checks for missing authentication, validation, transactions, queue retries, cache conflicts, and test coverage.
AI code reviewLaravelautomation
0 likes · 4 min read

A technical management team discovers that AI code reviews approve bug fixes that violate architectural intent because AI cannot grasp unwritten team conventions, revealing that AI's limitations mirror human failures in documenting context, standardizing processes, and managing knowledge.
AI code reviewAI limitationsR&D management
0 likes · 8 min read


TonyBaiAug 10, 2026 · Artificial Intelligence
Cloudflare built a three‑layer AI engineering stack—platform, knowledge, and governance—that lets 3,600 engineers (95% of R&D) use AI tools at scale, reduces inference cost by 77% with Workers AI, intercepts over 240,000 standard violations, and keeps per‑review cost under $1 while maintaining high security.
AI EngineeringAI code reviewAgents
0 likes · 23 min read

In a FastAPI project I deliberately introduced five hidden bugs and ran Claude Code's /code-review, which identified every injected issue, confirmed them, and even discovered an old real bug, while the article details the tool's multi‑phase pipeline, performance metrics, and speed‑up tricks.
AI code reviewClaude CodeFastAPI
0 likes · 11 min read

The code‑review‑graph tool parses a codebase into a local SQLite graph, lets AI reviewers query only the affected files, and achieves a median 82‑fold token reduction across six real‑world projects while supporting incremental updates and dozens of languages.
AI code reviewMCP Protocolcode-review-graph
0 likes · 11 min read

code-review-graph builds a local AST‑based knowledge graph with Tree‑sitter, exposes MCP query tools to AI editors, and in benchmark tests reduces token consumption by up to 82 times while raising review quality scores from 7.2 to 8.8, especially for large monorepos.
AI code reviewMCP ProtocolSQLite
0 likes · 16 min read

The article analyzes how AI‑driven code review becomes a new bottleneck after coding acceleration, proposes a three‑layer capability model—context construction, multi‑round consensus, and feedback loops—plus four core insights, and illustrates the approach with real‑world data from Snap's CodePal.
AI code reviewLLMautomation
0 likes · 13 min read

With AI coding accelerating development, code review becomes the new bottleneck; this article outlines a three‑layer capability model—context construction, multi‑round consensus, and feedback loops—plus four key insights to help you design a truly usable AI code‑review tool.
AI code reviewLLMcontext construction
0 likes · 13 min read

The article introduces the open‑source code‑review‑skill for Claude Code, explains its progressive loading of language‑specific guides, four‑stage review process, severity tagging, security checks, collaborative tone, and automation, and shows how installing the skill dramatically improves AI‑driven code review accuracy across multiple languages.
AI code reviewClaude CodeMulti-language
0 likes · 8 min read

With AI‑generated code now accounting for 55.87% of the 2,000 monthly change requests in the cloud‑storage front‑end team, traditional code review pressure has surged, prompting the team to embed a multi‑agent AICR gate into the CI/CD pipeline that automates context extraction, parallel AI inspections, verification, and feedback while controlling latency and mis‑reports.
AI code reviewAICRCI/CD
0 likes · 32 min read

Autoreview is an AI‑driven skill that automatically reviews code before a PR, addressing volume, blind‑spot, and boredom problems by repeatedly running until the code is clean, using a Scope Governor, multi‑engine panels, and strict isolation to enforce quality without manual bottlenecks.
AI code reviewCI workflowScope Governor
0 likes · 16 min read

GitHub Copilot Code Review now uses grep, rg, glob and view to actively explore related files in Java pull requests, shifting AI code review from merely commenting on changed lines to investigating the broader impact on transactions, caches, messaging, database queries and system compatibility.
AI code reviewGitHub CopilotJava
0 likes · 20 min read

Alibaba’s Open Code Review (OCR) combines deterministic engineering with LLM agents to deliver a battle‑tested, repository‑aware AI code review CLI, addresses coverage gaps, position drift, and instability, and introduces the AACR‑Bench benchmark for hidden‑defect detection.
AACR-BenchAI code reviewClaude Code
0 likes · 17 min read


TonyBaiJun 4, 2026 · Industry Insights
The article examines how the hidden social contract of open‑source development is breaking under a flood of unreviewed pull requests, explores AI‑generated code and reviews, questions what protected branches actually safeguard, and reflects on the responsibility and community impact of relying on AI tools.
AI code reviewGitHubmaintainer dilemma
0 likes · 15 min read


转转QAMay 28, 2026 · Operations
In the AI coding era, traditional test‑after‑code practices cause missed bugs, so a recycling‑service QA team adopts intent‑driven testing, business‑view AI code review, and risk‑focused automation to transform testers into AI‑assisted quality strategists.
AI TestingAI code reviewQA automation
0 likes · 10 min read

The article describes how an AST‑based code‑context service, wrapped by an MCP middleware and built with Spring AI and Eclipse JDT, supplies structured Java code information to large models, addressing the context gaps of diff‑only AI code review and improving accuracy through concrete examples and evaluation.
AI code reviewASTEclipse JDT
0 likes · 16 min read

This article details the design and implementation of an AI‑powered automated code‑review system for GitLab Merge Requests, covering background problems, layered architecture, diff parsing, prompt engineering, comment management, rate‑limiting, concurrency control, and the measurable improvements achieved.
AI code reviewGitLabLLM
0 likes · 22 min read

This article reviews three hot open‑source projects—TurboQuant Plus for compressing LLM memory, a Claude‑Code plugin that leverages Codex for AI‑driven code review, and the Rust‑based WeCom CLI for terminal control of Enterprise WeChat—detailing their features, usage, and target users.
AI code reviewClaudeLLM
0 likes · 8 min read

OpenAI released the codex‑plugin‑cc on GitHub, turning Claude Code into a hybrid AI system that offloads code review to Codex, adds new commands, and reshapes the development workflow while offering practical guidance, usage scenarios, and cost considerations for developers.
AI code reviewClaude CodeCodex Plugin
0 likes · 10 min read

This step‑by‑step tutorial shows how to integrate Claude Code with GitHub, configure the required GitHub App, set up GitHub Actions workflows for Issue mentions and Pull Request reviews, add necessary secrets, customize prompts, and adapt the setup for GLM models, turning Claude into an automated code‑review assistant.
AI code reviewClaudeGitHub Actions
0 likes · 10 min read

This article outlines the challenges of manual frontend code review, compares AI-powered CR solutions, details a pipeline integration using Cursor Agent CLI, and provides practical guidelines, model selection tips, and built‑in prompt engineering to automate and improve code quality checks.
AI code reviewCI integrationCursor Agent
0 likes · 12 min read


AI WakaMar 13, 2026 · Artificial Intelligence
This article examines a three‑layer AI‑powered code review system built around Claude, comparing GitHub Action, a custom sub‑agent pipeline, and Anthropic's native review in terms of cost, detection depth, false‑positive rates, and practical deployment recommendations for mid‑size development teams.
AI code reviewClaudeGitHub Actions
0 likes · 13 min read

Claude’s newly launched AI‑powered code review uses multiple parallel agents to automatically scan pull requests, flagging issues with an internal consistency check that reduces false positives to under 1 %, while Anthropic reports detection rates of 84 % for large PRs and 31 % for small ones, though each review costs $15–25.
AI code reviewClaudemulti-agent
0 likes · 9 min read

This article explains Alibaba Group’s AI‑driven code review benchmark, the agent‑based assistant that understands repository context, its real‑world impact on reducing null‑pointer exceptions, and how the open‑source AACR‑Bench dataset provides a multi‑language, context‑aware evaluation standard for AI code review.
AACR-BenchAI code reviewAgent Architecture
0 likes · 19 min read

The article examines which parts of a React code review can be reliably automated by AI—such as detecting missing dependencies, unused variables, and test gaps—while emphasizing that architectural decisions, state‑management trade‑offs, and performance reasoning must remain under human control.
AI code reviewcode qualityfrontend best practices
0 likes · 9 min read

This tutorial walks through integrating the AI Hub client with a TypeScript‑based code review engine, adding a UI button in a Vue component, handling loading states, previewing MergeRequest data, and wiring the backend calls to GitLab and the AI model, complete with code snippets and screenshots.
AI HubAI code reviewGitLab
0 likes · 11 min read

The article explains how the single‑commit review mode in Alibaba Cloud Codeup uses AI to evaluate each commit individually, addressing the shortcomings of default bulk diff reviews, detailing configuration steps, recommended scenarios, observed benefits, and its performance trade‑offs.
AI code reviewContinuous IntegrationGit
0 likes · 6 min read

This article explains how to construct and manage various context data—such as historical review feedback, code diffs, file types, developer experience, commit messages, business scenarios, framework knowledge, and Git logs—to improve the quality of AI‑driven code reviews, and provides a concrete TypeScript implementation with modular context providers, prompt engineering, and integration with GitLab and OpenAI APIs.
AI code reviewContext ManagementGitLab
0 likes · 21 min read

The article tells of a developer whose code caused a CPU spike, shows how an AI code review tool caught an unnecessary database query, and then outlines sixteen practical ideas—including multi‑turn dialogue, diff analysis, domain fine‑tuning, CI/CD integration, template feedback, intent inference, automated test generation, security scanning, auto‑fix suggestions, performance analysis, readability scoring, and visual reporting—to improve AI‑assisted code review quality.
AI code reviewCI/CDPerformance Analysis
0 likes · 20 min read

This article explains why enterprises need a single gateway for multiple large‑model services, introduces the open‑source OneAPI tool and its features, and provides step‑by‑step Docker installation, UI setup, channel and token configuration, optional Nginx proxy, and integration into an AI code‑review project.
AI code reviewDockerNGINX
0 likes · 11 min read

This article walks through two real-world security flaws—a high‑risk SQL injection and a medium‑risk stored XSS—showing how the CodeBuddy AI assistant can automatically detect, analyze, and remediate them with prepared statements and CSP enhancements, while explaining the underlying concepts and best practices.
AI code reviewCodeBuddyContent Security Policy
0 likes · 13 min read

This tutorial walks through setting up a Node.js environment, creating a TypeScript project, writing a custom OpenAI client, and integrating either Zhipu AI or an Ollama‑deployed model to perform automated code reviews via GitLab CI, complete with build, run, and VS Code debugging steps.
AI code reviewGitLab CINode.js
0 likes · 21 min read


21CTOMar 20, 2025 · Artificial Intelligence
Graphite’s new AI‑powered code‑review tool Diamond aims to catch bugs, style issues, and security flaws in large pull requests, but its founders warn that AI cannot fully replace human expertise, highlighting the need for balanced adoption in software development.
AI code reviewcode qualitysoftware engineering
0 likes · 5 min read

This tutorial walks through upgrading Git on a GitLab server, using the Commit API to fetch recent changes, invoking an AI model for automated code review, posting the review as a commit comment, and notifying the team via a Feishu custom‑bot webhook.
AI code reviewCI/CDFeishu
0 likes · 12 min read

This tutorial shows how to modify a GitLab CI pipeline to fetch changed files via the Merge Request API, extract the diff with jq, build a JSON request for the glm‑4‑flash model, and use AI to review code changes, including prompt engineering and result interpretation.
AI code reviewCI/CDGitLab
0 likes · 11 min read

This tutorial walks through creating a personal GitLab access token, testing the GitLab API, configuring CI variables, importing a sample project, triggering a merge‑request pipeline, sending changed files to a Zhipu AI model, and writing the AI's review back into the merge request as comments.
AI code reviewAPICI/CD
0 likes · 16 min read

This article walks through installing Ollama, setting up environment requirements, pulling and running open‑source LLMs such as qwen2 and gemma2 locally, configuring API access and environment variables, and using the AI Hub client to perform AI‑assisted code reviews, highlighting cost‑saving and security benefits.
AI HubAI code reviewAPI
0 likes · 13 min read

Nova is an AI-powered code review system integrated with GitLab CI and SonarQube, offering full-project context, multi-language support, extensibility for models and search methods, easy Docker deployment, safety filters, and aims to improve review precision and provide customizable audit prompts.
AI code reviewCI/CDCode safety
0 likes · 3 min read

This article analyses the drawbacks of manual code review, explains why they arise, and presents a practical solution that embeds a large‑language‑model‑based AI reviewer into a CI/CD pipeline, detailing configuration steps, script examples, and the resulting efficiency and quality gains.
AI code reviewCI/CDlarge language model
0 likes · 8 min read


JD TechJun 5, 2024 · Artificial Intelligence
This article explains the drawbacks of manual code review, demonstrates how AI large‑model services can automate and improve review quality, and provides a step‑by‑step guide—including a Java script and CI pipeline configuration—to embed JD's Chatrhino model into a continuous integration workflow, resulting in higher efficiency, accuracy, and reduced development cycle time.
AI code reviewCI/CDJava
0 likes · 11 min read

The article explains how AI code reviews suffer from missing context, and improves them by embedding the codebase, using Retrieval‑Augmented Generation to fetch relevant snippets, and adding a function‑calling tool that lets the model autonomously request additional code, resulting in precise, bug‑detecting feedback.
AI code reviewEmbeddingFunction Calling
0 likes · 8 min read
