Claude Code can code nice UI. But nice UI doesn't mean good UI.
Manual UI testing is becoming one of my biggest bottlenecks when coding with AI now.
Tap a slide to expand
Manual UI testing is becoming one of my biggest bottlenecks when coding with AI now.
For any new feature, I find myself usually spending 80% of time doing manual UI testing.
These are two common issues I see:
- LLM sometimes makes poor judgment of what UI component to use.
When I asked Claude Code to add a feature to allow users to toggle the AI mode, image 1 is what it coded. It used an on/off switch for a choice between two modes. It looks decent, but ambiguous. What does ON mean? Turn ON Learning Mode or Explore Mode?
One way to solve this is probably giving it best practices on how to choose components as a skill?
- LLM can’t see layout issue.
After prompting it about the ambiguity, I asked it to use a segmented control. But it introduced a layout issue.
It took additional prompt to finally get it fixed.
—
This invites a question.
If the LLM could see what it coded, could it catch these obvious issues on its own?
This is something I just started to explore. Does anyone know of a solution that lets Claude Code (or similar tools) see its own UI output for a mobile app during the agentic loop?
Would love to hear how others handle this.
#AI #CodingWithAI #ClaudeCode #UITesting #UXDesign #DeveloperExperience #LLM
Enjoyed this? Subscribe for more.
Practical insights on AI, growth, and independent learning. No spam.
More in Vibe Coding
I finally concede that AI is smarter than me.
For 2 years, I held onto reasons like “AI can't solve my kid's homework” or “It can't play tic-tac-toe” to believe I was still smarter.
AI Agents are not plug-and-play. 5 ways to add useful skills to your AI agents.
Most of them came thinking AI agents are plug-and-play. Set it up, and it becomes extremely helpful immediately.
Why you should learn Claude Code before OpenClaw
If that is what you heard about the recent IMDA advisory, you only got half the picture.
10 Ways to Reduce the Risk of Running OpenClaw (or Any AI Agent)
The safe answer comes from Peter Steinberger, OpenClaw's creator himself. He said OpenClaw is designed as a personal assistant - one user to one or many agen...
Most marketers know Inbound and Outbound Marketing. But have you heard of... Rebound Marketing?
No? That’s because I just coined it.
💡 Little-known hack to get the most out of Cursor for FREE
If you're using Cursor on the free plan, you will eventually hit the dreaded "servers overload" screen.
I finally concede that AI is smarter than me.
For 2 years, I held onto reasons like “AI can't solve my kid's homework” or “It can't play tic-tac-toe” to believe I was still smarter.
Why you should learn Claude Code before OpenClaw
If that is what you heard about the recent IMDA advisory, you only got half the picture.
Most marketers know Inbound and Outbound Marketing. But have you heard of... Rebound Marketing?
No? That’s because I just coined it.
AI Agents are not plug-and-play. 5 ways to add useful skills to your AI agents.
Most of them came thinking AI agents are plug-and-play. Set it up, and it becomes extremely helpful immediately.
10 Ways to Reduce the Risk of Running OpenClaw (or Any AI Agent)
The safe answer comes from Peter Steinberger, OpenClaw's creator himself. He said OpenClaw is designed as a personal assistant - one user to one or many agen...
💡 Little-known hack to get the most out of Cursor for FREE
If you're using Cursor on the free plan, you will eventually hit the dreaded "servers overload" screen.