Invisible Users, Invisible Interfaces: Accelerating Design Iteration with AI Simulation
summary
Argues that using AI simulation speeds needfinding by turning data into active agents: a live data platform feeds Intelligent Twins that run 72 simulated actions across navigation, information architecture and engagement to audit three sports sites, finding navigation mostly fine but content and engagement dropping off. Uses computer vision, human‑in‑the‑loop observation and plans a reproducible code repo; cites MCP protocol from Anthropic for Figma‑to‑code integrations.
AI-written summary · about
chapters (8)
- 0:00AI-driven design acceleration
- 1:26AI trust gap and GenAI UX
- 2:50AI simulation for invisible needs
- 4:12Accelerated need finding with AI
- 6:39Global audit of sports websites
- 8:47Repairing AI trust gap with UX
- 10:13Future of design tools
- 11:38Conclusion
related talks
19mBeyond agents: AI as a creative partner
06mInterview
40mAI for UX: Using AI to Cut Costs and Time in UX
25mArtificial intelligence & design: imagining the future of UX
25mPrototyping at the speed of thought: AI as a discovery accelerator
32mThe product design assembly line - Ivan Dalmet
39mAI & Creativity: A Designer's Journey Into the Future
26mData, AI and design