The End of the Static Screen: Architecting Intent-Driven UX — Gus Iwanaga, commercetools

By ai.engineer

Categories: AI, Tools

Summary

After 40 years of static UX, AI enables intent-driven interfaces that adapt to users rather than forcing users to adapt to software. Gus Iwanaga from commercetools demonstrates how generative UI protocols can eliminate cognitive load by auto-generating information architecture and components based on user intent, reducing onboarding friction that currently requires massive investment.

Key Takeaways

  1. Current SaaS apps create cumulative cognitive debt—users must learn 5+ different mental models and navigation patterns daily. Each app requires dedicated onboarding investment, yet users remain cognitively overloaded by information architecture decisions made by teams, not tailored to individual intent.
  2. Intent-driven UX flips the paradigm: AI auto-generates UI layouts, component selection, and information architecture in real-time based on user queries (e.g., 'Create a sales report for Q1'), eliminating the need for static screen design and reducing time-to-productivity.
  3. UI protocols are emerging as a foundational shift—they enable machines to dynamically decide on placement, information hierarchy, and component retrieval from catalogs, making software adapt to user intent rather than forcing users into predefined workflows.
  4. The commercial opportunity is massive: companies like Salesforce, Slack, and similar platforms invest heavily in onboarding to offset UI complexity. Intent-driven UX removes this friction point and could reshape how SaaS products compete on user experience and time-to-value.
  5. At an API-first company (300+ endpoints), the architecture enables generative UI—the backend provides data and components, while AI orchestrates presentation. This pattern is replicable for any platform-based business with well-structured APIs and component catalogs.

Related topics

Transcript Excerpt

[music] >> How's it going? The end of uh the end of the conference, how's everybody feeling? Tired, drinking from the fire hose as well? Are you guys a little bit tired of hearing loop engineering, harness engineering, software factory, evolves, pre-training, post-training data, and whatnot? Uh but anyways, those topics were more than valid, right? Uh hi. Some uh really uh common faces here. By the way, I'm super excited to be here and talk to you guys about this title. And And I'm sorry, when I was when I submitted the application, I was thinking of potentially a catchy title, but I don't like this at all. So, with all due respect to the organizers, I'll have to make a change. Uh and the actual topic that I want to focus here today is lessons learned uh from a team that is building proper…

More from ai.engineer

Featured in