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.
What I learned reviewing AI-generated JavaScript: real-world issues, code review tips, and ways to ensure robust, production-ready code.
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.
How to structure a self-contained folder of specifications, screenshots, and Figma links that an AI agent can reference throughout an implementation planning session.
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.
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.
Exploring common misconceptions AI agents have about Visual Regression Testing and practical solutions to address them.
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.
How I built an eval-judge-improve loop to autonomously refine a semantic HTML agent skill, taking it from 2.46 to 2.89 out of 3.0 across four iterations and what I learned about the limits of automated improvement.
Timelapse is a progressive web app (PWA) with acollection of widgets that shows how much time has elapsed in the day, week, month, quarter, and year. Widgets and timezone are configurable.