Web Developer
New web development articles are posted weekly, mainly focused on frontend topics.
Void is VoidZero's toolkit for building full-stack Vite apps and deploying them to Cloudflare. It infers resources from imports like void/db. This article builds a React memo app on D1 and deploys it with a single void deploy command.
Tags and branches in GitHub Actions can change the code that runs without any workflow change. Workflow dependency lockfiles pin dependencies to commit SHAs while keeping readable tags. This article shows how to use them.
A document can run only one `document.startViewTransition()` at a time, drawn over the whole page. `element.startViewTransition()` scopes a transition to an element so several can run at once. This article shows the basics by animating two lists.
Void is VoidZero's toolkit for building full-stack Vite apps and deploying them to Cloudflare. It infers resources from imports like void/db. This article builds a React memo app on D1 and deploys it with a single void deploy command.
Tags and branches in GitHub Actions can change the code that runs without any workflow change. Workflow dependency lockfiles pin dependencies to commit SHAs while keeping readable tags. This article shows how to use them.
A document can run only one `document.startViewTransition()` at a time, drawn over the whole page. `element.startViewTransition()` scopes a transition to an element so several can run at once. This article shows the basics by animating two lists.
azukiazusa
azukiazusa
azukiazusa
azukiazusa
Improve memory and skills with the Boy Scout Rule
A talk about gradually improving an agent's memory and skills through everyday tasks, so it can accomplish work more efficiently.
The frontend's audience has changed: designing new web interfaces in the age of AI
Frontend engineers have always built for humans — but AI is changing that assumption. This talk examines two shifts: AI as a producer of web output (streaming UI, MCP Apps) and AI as a consumer of the web (Markdown delivery, WebMCP), exploring what these changes mean for how we design web interfaces in the AI era.
How should we give feedback when coding agents write frontend code?
LLM-based coding agents (such as Claude Code and Codex) are spreading rapidly, and feedback from code execution results is essential in iterative improvement loops. Backend development can get immediate feedback through execution and tests, while frontend development has unique challenges. This talk focuses on the feedback-loop problem in frontend code generation and discusses practical solutions and trade-offs.
