[pillsburycat]

This looks really cool. However, the current AI models are pretty good at designing UIs from prompts and even turning screenshots of mocks into full UIs. I'm not sure this visual design approach would save time vs simply prompting an AI agent.

That being said, I could see a niche market for a designer persona who is used to building in tools like figma.

[ajspig1]

also, this assumes humans are still the primary CLI consumers. With agents increasingly being the first-class users of command-line tools, building visual design tooling for terminal UIs feels like optimizing for a shrinking audience.

[pillsburycat]

Well you still need some human prompting the AI and looking at results, no? :)

Agents aren't picky with UI, so most effort will always be spent designing for humans, even if they are not the primary consumers.