Production Changed. UX Must Change Too.

I've been building with AI coding tools for the last eight months — not demos and prototypes, but real applications. Revenue-generating systems. Security-audited products. The speed is absurd. You can go from idea to working software in hours: architecture, components, dashboards, tables. After 15 years building software the old way, it feels like cheating.

AI has removed engineering bottlenecks. It has collapsed iteration time. It has reduced the cost of production to almost zero. That includes design production. Layouts are cheap. Exploration is cheap. Polish is cheap — cheap enough.

But cheap execution does not eliminate judgment.

Here's the distinction I keep coming back to: AI is good at UI. It is not very good at UX. UI shows users data and actions. UX shows users the right data and the right action at the right time. That guiding layer — prioritization, sequencing, hierarchy — is where senior product designers live.

AI doesn't naturally operate there. It builds page by page. Design builds systems.

That's why so many AI-built products feel “off.” They look modern. They feel clean. But something's wrong. Buttons change color between screens. Hierarchy shifts without reason. Status indicators are inconsistent. The same data is labeled differently in different places. Similar interactions behave differently across contexts. There isn't a system. Just the suggestion of one.

And then there's the deeper issue.

There's a principle in UX research called the Aesthetic–Usability Effect. When something looks beautiful, users assume it's easier to use. AI makes beautiful interfaces almost instantly — clean spacing, modern typography, polished components. The surface looks finished. So the first impression is strong. “This looks great.” Expectation is set.

But when the structure underneath is incoherent — when onboarding overwhelms, when flows skip necessary context, when primary actions compete for attention — the contrast becomes jarring. The polish amplifies the flaw. Because now the product feels like it should make sense, and it doesn't.

Pretty UI can disguise structural weakness. It cannot resolve it. Polish creates a promise. UX has to fulfill it.

This is where fast production exposes weakness. When shipping is cheap, features accumulate. And when features accumulate, structure decays unless someone deliberately maintains it.

In fast-moving products, common issues begin to surface: interfaces that function but aren't intuitive; mismatched interaction patterns; weak discoverability of critical actions; flat hierarchies where everything competes equally; over-informing instead of guiding; redundant or misleading context; UX copy written by default rather than intent; AI chat interfaces inserted without structural integration. None of these issues are catastrophic on their own. Together, they create friction. The product works. It just feels heavier than it should.

The real shift isn't that AI builds bad interfaces. It's that AI accelerates production. Code is cheap. Iteration is constant. Prototype and production blur together. Features move from idea to live in days.

In that environment, UX cannot remain a phase that happens upstream. It has to operate inside production. It has to move at the speed of production.

That doesn't mean less rigor. It means different rigor — less ceremony, more judgment; shorter cycles, stronger structural interventions.

AI can build almost anything now. But it still can't decide what matters. Products are defined by what matters.

In the age of AI, the constraint isn't building pages. It's maintaining coherence.

That's the work.