Ux
12 articles about ux.
Is Claude Deliberately Increasing Dialog? Clarifying Questions vs Guessing
When should AI agents ask clarifying questions versus just attempting the task? The tradeoff between getting it right on the first try and wasting time on
Using AI Agents to Gather and Analyze App Feedback
The hardest part of building an app is knowing if the UX works. AI agents can help collect, organize, and surface feedback patterns from real users - so you
The Counterintuitive Math of Shutting Up
The most useful agent is the one that only speaks when something unexpected happens. Silence is not inaction - it is a signal that everything is working as
The End of User Error
AI agents can eliminate user error by interpreting intent rather than literal input. But the real version of this is harder and more nuanced than it sounds.
Against Frictionlessness - Why AI Agent UX Needs Friction
Removing confirmation dialogs let an AI agent click delete-all. Learn why intentional friction in AI agent UX prevents catastrophic mistakes and protects users.
Intent Disambiguation in AI Agents: When Commands Are Ambiguous
When you tell an AI agent to 'walk the dog,' it might start a business instead. Intent disambiguation is the difference between useful agents and chaotic ones.
Running 5 Claude Code Instances in Parallel - Ctrl+C Muscle Memory
The UX realities of running five Claude Code instances simultaneously - ctrl+c muscle memory, process management, and why the goodbye message feels passive
Managing Multiple Agent Windows Is a UX Nightmare - Voice Solves It
Instead of switching between agent windows and your work, just talk. Voice commands let you direct the agent while your hands and eyes stay on your actual task.
Every Platform Is Broken in Ways Users Pretend Not to Notice
Honest takes on AI tooling - every platform has broken workflows that users work around instead of fixing. Why acknowledging the cracks matters.
Voice Computer Control Gets Better with Persistent Memory
Voice-first desktop agents are the right interface, but voice without memory means repeating yourself every session. Persistent memory makes voice control
Voice Should Be the Default Input for AI Agents, Not an Add-On
Why designing an AI agent with voice as the primary input from day one creates a fundamentally better interaction model than bolting it on later.
How to Build AI Agents You Can Actually Trust - Bounded Tools and Approval UX
Giving AI agents broad system access is a recipe for disaster. How bounded tool interfaces and smart approval flows make desktop agents safe to use.