Command Palette
Search for a command to run...
Preview-Before-Action: Trustworthy Agent Design
Core principle for responsible agentic product design: always preview before execute. Treating agents as unsupervised interns — managing risk through transparency and human checkpoints. Foundational pattern for trust in agentic systems.
More Articles(4)
7 Practical Tips for Designers: Boost Your Workflow Today
From the creators of Refactoring UI, this article shares seven concrete techniques for making designs look polished without being a design expert. Covers practical tips like using color and weight instead of font size, borrowing design decisions, and overlapping elements for depth.
Agent Experience (AX) Design Patterns
New design discipline emerging around Agent Experience (AX): preview patterns, override controls, and autonomy balance. Frames agents as 'unsupervised interns' — high-potential, high-risk collaborators that require thoughtful oversight interfaces.
AI Agents and the Natural Language UI Paradigm
Natural language replaces menu-driven navigation. Queries like 'Show me what I can afford next month' become first-class product interactions — an intent layer that rewrites how financial and consumer products are designed. Explores autonomy/automation balance and generative UI patterns for agent-first product surfaces.
AI Design Trends 2026 That Actually Matter
A signal-to-noise breakdown of which 2026 design trends are genuinely reshaping the discipline. Covers the shift from static design libraries to AI-driven intent-based systems, and what it means for designers to evolve from pixel-pushers to quality-control strategists.