Tag
code review
Code review is the checkpoint that keeps AI-generated changes aligned with engineering standards, from diff inspection and test validation to architecture consistency and risk control. As Cursor, Windsurf, and Claude Code speed up output, review becomes central to codebase readability and maintainability.
14 articles
Kubernetes sets rules for AI-assisted maintainership
Kubernetes has set guardrails for AI-assisted maintainership, keeping final code review, accountability, and disclosure in human hands.
Persistent-state AI agents open a new attack surface
A new benchmark shows AI coding agents can hide attacks across PRs and time their payloads to evade monitors.
Devin docs show where the AI engineer fits
Devin docs show 5 ways the AI software engineer helps teams ship code, fix bugs, and work faster.
AI should govern the SDLC before it writes code
AI belongs in PRD and review governance before it belongs in code generation.
Cursor data shows AI code review is fading
Cursor says more AI-generated code is reaching production without manual review, signaling growing trust in coding agents.
20 AI coding assistants, stripped down for 2026
I broke down Axify’s 20-tool review into a practical guide, with the tradeoffs, use cases, and a copy-ready evaluation template.
Open Code Review turns AI reviews into line-accurate checks
I break down Alibaba’s Open Code Review CLI and give you a copy-ready setup for reliable, line-level AI code reviews.
Anthropic’s code review tool turns AI code into reviewable work
Anthropic’s new review tool helps teams catch bugs and security issues in AI-written code before it ships.
Why JetBrains Is Right to Treat AI as an IDE Problem
JetBrains is right: AI coding quality depends on the IDE, not just the model.
Why AI coding assistants need tighter governance, not blanket bans
AI coding assistants are worth using, but only inside stricter governance, review, and security controls.
Why GitHub Copilot code review should count against Actions minutes
GitHub should bill Copilot code review against Actions minutes because the feature runs on shared runner infrastructure.
Cursor vs Windsurf: 4 Tasks, Same Prompts
Same prompts, four tasks, two AI IDEs. Cursor fit the codebase better; Windsurf moved faster but needed more cleanup.
AI coding is fast. Trust is the bottleneck
AI coding tools are shipping faster than humans can review them, pushing enterprises toward code governance, testing, and trust layers.
Superpowers Plugin for Claude Code: Seven-Step Workflow for Predictable Quality
Superpowers is an official Claude Code workflow plugin that enforces a seven-step development process: brainstorming, Git worktrees, implementation planning, subagent-driven coding, TDD, code review, and branch completion. Ideal for complex features exceeding 1000 lines, ensuring predictable quality and reusable workflows.