Code Reviewing AI-Generated JavaScript: What I Found
This post was published on
What I learned reviewing AI-generated JavaScript: real-world issues, code review tips, and ways to ensure robust, production-ready code.
Posts tagged with ai
-
-
Preventing Common Issues When Working with AI-Generated Code
This post was published on
AI coding agents have made me significantly more productive as an engineer, but they have a systematic problem: as context fills, they drift from explicit guidance and violate documented patterns. This examines AI limitations and the workflow adaptations that help while labs address the underlying issues.
-
Part 2: Organising Reference Materials for AI Agent Sessions
This post was published on
How to structure a self-contained folder of specifications, screenshots, and Figma links that an AI agent can reference throughout an implementation planning session.
-
Part 3: Running an AI Agent Implementation Planning Session
This post was published on
How to structure an AI agent session with sequential tasks, review checkpoints, and explicit deliverables—turning a handoff document into actionable state machines, gap reports, and implementation plans.
-
Part 1: Structuring Feature Specifications for AI Agents
This post was published on
How to structure a handoff document that enables AI agents to perform gap analysis and implementation planning—with traceable acceptance criteria, UI state inventories, and explicit business logic.
-
What AI Agents Get Wrong About VRT, And How to Fix It
This post was published on
Exploring common misconceptions AI agents have about Visual Regression Testing and practical solutions to address them.
-
AI Gave Me Working Code. Questioning It Gave Me Better Code.
This post was published on
Working code isn't understood code. When AI-generated code feels hard to parse, that's a signal to ask questions, and sometimes, the answer leads to something better.
-
Writing Cross-Platform Hooks for AI Coding Agents
This post was published on
How to write a single hook script that works across Claude Code and Cursor, giving you deterministic control over agent behaviour when it matters most.