As AI agents become autonomous decision-makers rather than passive tools, the way humans interact with them must evolve. This session explores the interaction models, UX patterns and interface primitives that will define human–AI collaboration in 2026 and beyond. We will examine how autonomy, reversibility, transparency and memory control reshape UI design, and why traditional chatbot and static website paradigms are no longer sufficient.
Using production examples from modern agentic systems, we walk through practical design patterns for proactive agents, multi-step collaborative workflows, alignment-aware interfaces and safety-centred feedback loops. Each pattern is paired with concrete implementation guidance developers can apply immediately to their own applications.