AI UX: The Limits of Declarative Interfaces - Sara Du
saradu.substack.com · 895 words · saved by 2 readers
Why we'll still be clicking in 2030
AI UX: The Limits of Declarative Interfaces Why we'll still be clicking in 2030 Sara Du Jan 08, 2026 36 6 Share The magic of LLM-powered interfaces is the shift from procedural interactions (“click A, then B, then C”) to declarative ones (“do this for me”). Photo editing tools are a canonical example of this. In 2015, removing an object from an image required learning a multi-step procedure: lassoing the object, feathering edges, clone-stamping the background, and hoping it looked natural. Today, you select an area and type “remove.” The interface, instead of teaching you how to do something,
saved by
related reading
- AI Design Field Guideaidesignfieldguide.com
- The case against conversational interfaces << julian.digitaljulian.digital
- Why Chatbots Are Not the Future of Interfaceswattenberger.com
- The State of UX in 2025trends.uxdesign.cc
- Designing AI experiences people actually usebuzzusborne.com
- Malleable software in the age of LLMsgeoffreylitt.com
- Natural Language Is an Unnatural Interfacevarunshenoy.substack.com
- Doomprompting Is the New Doomscrolling.workingtheorys.com
- Design for the AI agelinear.app
- Design for the AI agelinear.app
- 2025 was the AI feature era. 2026 is the trust era. | by Yulia Lápicus | Mediummedium.com
- Mediumuxdesign.cc