Line of inquiry
Inquiring lines›How can we ensure AI systems remai…›How should autonomy and oversight…›this line of inquiry
How does interface design shape effectiveness in human-AI collaboration?
A broader line of inquiry — a family of 91 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 91
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- How does agent design differ fundamentally from interaction design practice?
- Can interface design nudge users toward verification of AI responses?
- Should design systems prioritize verbs and actions over static UI elements?
- Can Amershi's human-AI interaction guidelines translate into concrete prompting strategies?
- How do context windows constrain AI agent interface design choices?
- Can interface design scaffold human participation in tools designed for hands-off autonomy?
- How much does interface design versus model capability drive perceived AI value?
- Do Amershi's human-AI interaction guidelines still apply when design moves upstream?
- Can traditional UX methods work for autonomous AI systems?
- Can interface design alone overcome lack of awareness about AI tool capabilities?
- Where does perceived control diverge from actual intervention capability in AI interfaces?
- Does agent experience design produce better outcomes than screen-first design?
- Can interface design better surface what an LLM has inferred about a user?
- How should designers make invisible AI state legible to users?
- How do interface patterns compare to organizational AI oversight processes?
- Should AI interfaces keep manual GUI controls as a fallback?
- Should XAI designers treat explanations as arguments for adoption?
- What are the new heuristics designed specifically for computer-use agents?
- Can the human-AI boundary be designed rather than predetermined?
- What usability heuristics need agent-specific adaptation for AI interfaces?
- How can interfaces support users who prefer hands-on versus hands-off control?
- How do design systems balance transparency with minimizing cognitive load?
- Should interface design organize by pattern type or by behavioral phase?
- How do interface layers differ from UX categories as a design organizing principle?
- How does the control modality affect how users understand AI model outputs?
- Can architectural design choices resist the automation of design work itself?
- How can designers make control feel available without constant user oversight?
- Does Atlassian's approach differ from other AI interaction design frameworks?
- Can designers hide AI context complexity behind a stable user interface?
- How do Salesforce's guidelines compare to Amershi's broader human-AI interaction phases?
- Do Nielsen's classical usability heuristics apply directly to computer-use agents?
- How does intent-based interaction differ from traditional direct-manipulation design?
- Can self-assessed design quality validate the actual value of AI-assisted designs?
- Does pairing visual previews with clarification reduce interaction rounds across domains?
- What specific design patterns characterize post-2023 AI as active communication participants?
- How should systems design transparency to make human-machine contribution boundaries visible?
- Which workplace AI design principles matter most to business users?
- What evidence supports splitting agent customization into identity and interaction decisions?
- Why do evaluation scenarios need to reproduce interaction mode dimensions?
- Why does context work differently in AI than in conventional software?
- What design discipline replaces navigation and layout in AI systems?
- How do multi-layer AI interfaces differ from single opaque model boundaries?
- How do Amershi's AI interaction guidelines compare to agent-specific UX frameworks?
- Which design choices boost engagement but increase user vulnerability?
- What design changes if we separate behavior description from adoption justification goals?
- What role does interface design play in clinician adoption of AI tools?
- Why should service design absorb agent design rather than keep them separate?
- Why do planning and execution need opposite interface designs for human oversight?
- Do users actually find intuitive modalities easier to learn than direct controls?
- Does prompt-to-design speed benefit depend on the type of design task?
- Why do text prompts and GUI interactions require separate representation in interaction models?
- What stops AI from helping users articulate preferences they cannot express?
- How do designers distinguish intentional anthropomimesis from user-perceived anthropomorphism?
- What interface controls best address retention concerns about inferred data?
- How do pre-action UX patterns prepare users for staged autonomy expansion?
- What makes evaluation easier than envisioning for users?
- Why do persistent AI systems require fundamentally different design than ad-hoc supporters?
- What interaction mechanisms help systems determine when to defer to humans?
- Do API-based agent interactions outperform GUI-based approaches in real healthcare systems?
- Can ease of building outpace a single builder's judgment about system architecture?
- Should agents use APIs or GUI interaction for efficiency?
- Do Nielsen's three-layer interfaces resolve tension between intent surfaces and direct manipulation?
- Do users abandon AI features because of placement or intent articulation friction?
- What evidence would prove agent design has achieved paradigm status?
- What interface controls best support mid-session initiative adjustment?
- What are the five types of human interactions in agentic AI systems?
- How does vendor-prescribed design doctrine compare to frameworks derived from user research?
- How do anthropomimetic design features trigger System 1 cognitive traps?
- Can design features trigger genuine rivalry or only frustration?
- Do just-in-time objectives require active designer judgment at every interaction?
- How do users' intentions mature during ambiguity resolution in spatial interfaces?
- Can a single visual component communicate AI presence across different product contexts?
- How does participatory design differ from co-design in granting stakeholder agency?
- What design factors determine when a provocation lands as useful friction?
- How can designers distinguish anthropomorphism from anthropomimesis in their choices?
- How do direct manipulation and cognitive load theory guide interface design choices?
- Where should AI integrate to avoid creating isolated product experiences?
- How does Nielsen's orchestration surface layer formalize invisible design work?
- How should designers expose systemic trade-offs to users of autonomous agents?
- Can rule-based logic replace AI in low-risk product workflows?
- How does feedforward design differ from feedback in human-computer interaction?
- What does context engineering look like in practice for real AI assistants?
- How do Amershi's interaction-phase guidelines compare to concern-based AI UX frameworks?
- How does context in AI differ from context in conventional software?
- How does runtime adaptation differ from scripted response design?
- How do style lenses and output shaping change how users interact with AI results?
- Why did product managers gain more from Figma Make than professional designers?
- How do role dynamics change when UX designers, engineers, and product managers prototype together?
- What makes value-sensitive design distinct from user-centered design approaches?
- What barriers prevent gesture and voice from being implemented in GenAI systems?
- Why did reviewers add themes to Consult's output much more than removing them?