AI & UI/UX Design Blog
Latest AI tools and news for designers, plus classic UI/UX articles on research, systems, mobile, and Hong Kong product work.
How to Present AI Work in Your UX Portfolio
Case studies are changing — here's how to document AI-assisted research, generative workflows, and human judgment so clients trust the process, not just the output.
Designing Interfaces for AI Products Users Actually Trust
Patterns for chat UIs, confidence, errors, and human takeover — what changes when the product is not just software, but software that guesses.
UX Writing for AI Assistants: Prompts, Replies, and Guardrails
How to write system prompts, suggested starters, and in-thread copy so AI features feel helpful — not creepy, vague, or overly corporate.
Claude Code in 2026: What UI/UX Designers Should Know
Anthropic's agentic coding tool now runs in VS Code, ships checkpoints, and uses Sonnet 4.5 — here's what changed and how it affects design–dev collaboration.
AI Features vs. AI-Native Products: A UX Strategy Guide
When to bolt on a copilot, when to rebuild the core journey around AI, and how Hong Kong startups can avoid shipping novelty without retention.
Mobile UX for AI Copilots: Small Screens, Big Expectations
Thumb-friendly chat, voice input, streaming replies, and battery-conscious patterns for AI on iOS and Android.
How to Usability-Test AI Features Before You Ship
Test plans for probabilistic UI — task scripts, trust questions, and what to measure when every session can feel different.
Cursor in 2026: Why Designers Are Paying Attention
Rules, skills, multi-model support, and agent mode — how the AI-native IDE fits design–dev workflows alongside Claude Code and Codex.
OpenAI Codex App & GPT-5.3-Codex: The Latest in Agentic Coding
OpenAI's desktop Codex app, parallel agents, and GPT-5.3-Codex — billed as its most capable coding model yet — and what product designers should watch.
Microsoft Copilot in the Workspace: Notes for Product Designers
Copilot across Windows, Edge, M365, and GitHub — what it means when your users and stakeholders already live in Microsoft's stack.
GPT-5.5: What OpenAI's Latest Model Means for Builders
Higher intelligence at GPT-5.4-class latency, stronger coding benchmarks, and fewer tokens on Codex tasks — a quick breakdown for designers and PMs.
ChatGPT Agent Mode: What OpenAI's Agent Direction Means for UX
Longer-horizon tasks, tool use, and computer control — how agent-style ChatGPT shifts expectations for assistant UX.
Claude Code vs. OpenAI Codex vs. Cursor: A 2026 Comparison
Three agentic coding paths — Anthropic, OpenAI, and Cursor — compared for product teams choosing tools in 2026.
Designing Mobile-First Experiences That Actually Convert
How thinking small leads to bigger results — practical principles for crafting mobile experiences that respect attention, context, and intent.
Figma AI Features in 2026: Acceleration, Not Autopilot
First drafts, rename layers, generate content — how to use Figma's AI without eroding system quality.
Google Gemini & AI Overviews: What Changed for Product Teams
How Google's AI search features affect marketing sites, portfolios, and content structure in 2026 — without separate 'AI-only' pages.
Perplexity for UX Research: Faster Scans, Same Verification Rules
Using cited AI search for competitive reviews and landscape scans — without treating summaries as user evidence.
AI-Assisted User Research: 5 Methods That Stay Rigorous
Use LLMs to speed synthesis and tagging — without replacing real users or inventing insights you never heard.
Anthropic Skills & MCP: Extending Claude Beyond Chat
Skills, MCP servers, and agent teams — why Anthropic's extensibility model matters for design systems and product ops.
AI Coding Agents Changed Design Handoff — Here's the New Playbook
When Claude Code or Codex implements your Figma in hours, handoff becomes continuous review — not a one-time spec dump.
Remote Usability Testing When You Only Have a Week
A lightweight remote test plan — recruit, script, run, synthesize — for product teams that need signal before the next sprint, not a month-long study.
Figma Handoff Checklist: What Developers Wish Designers Documented
A practical pre-handoff list — spacing, states, edge cases, and tokens — so engineering can build your UI without guesswork or Slack archaeology.
AI Industry News Designers Should Track in 2026
A short list of sources and themes — models, agents, regulation, and UX patterns — so you stay informed without doom-scrolling.
Building a Design System from Scratch (Without Burning Out)
What I learned shipping a design system to a 12-person product team — what to build first, what to skip, and how to keep designers and engineers shipping in parallel.
Working as a UI/UX Designer in Hong Kong: What Clients Actually Need
What startups and agencies in Hong Kong look for when hiring UI/UX — and how to position your portfolio, process, and communication for local product work.
How Hong Kong Product Teams Are Adopting AI Coding Tools
Practical adoption patterns for startups and agencies — pilots, governance, and design–dev alignment in 2026.
Web Design vs. App Design: How Startups Should Choose Where to Invest
Not every product needs a native app on day one. A simple framework for deciding between responsive web, PWA, and mobile app design when budget and time are limited.
How to Structure a UX Case Study for Your Portfolio
A repeatable outline — context, research, decisions, and outcomes — so hiring managers and clients can scan your work in minutes.
User Research on a Budget: 5 Methods That Punch Above Their Weight
You don't need a research ops team or a six-figure tooling stack. Here are the lean techniques I reach for when timelines are tight and stakes are high.