Course Objective & Scope
Confronting users with an empty prompt box ('What am I supposed to type?') creates heavy cognitive load, and editing a monolithic wall of generated text often takes longer than writing from scratch. This programme teaches proven interface and interaction patterns for generative AI products.
Participants explore chat, inline command, sidecar copilot and collaborative canvas/artifact patterns, designing streaming states, scoped refinement controls, parameters and feedback components in a UX prototype and failure/fallback flow tailored to their product.
Who Should Attend?
- UX/UI designers, product designers and design system teams
- Product managers building generative AI features
- Frontend developers and design engineers
- No coding prerequisites
Key Takeaways
- Select the right surface—chat, inline action, autofill or canvas—for the user's task
- Eliminate blank-canvas paralysis with contextual starters, chips and structured input controls
- Design thinking/tool-progress indicators and streaming UI states that manage perceived wait time
- Enable users to highlight, refine, compare and branch specific parts of generated outputs
- Create a reusable UI pattern checklist covering failure, fallback and escalation states
Curriculum
Beyond the Chat Box: GenAI Interface Archetypes
- Choosing between chat, inline contextual menus, sidecars and split-screen canvases
- Generative UI: rendering interactive cards, tables and forms instead of plain text
Input Scaffolding and Reducing Prompt Effort
- Contextual starter chips, slash commands and structured parameter controls
- Visualising attached documents and active screen context with removable pills
Time, Streaming and Progress States
- Token streaming choreography, skeletons and multi-step tool progress indicators
- Backgrounding long-running tasks and notifying users on completion
Co-Editing, Scoping and Iteration Patterns
- Highlighting sections to rewrite, adjust tone/length and compare variations
- Inline diff accept/reject controls and keyboard-first review workflows
Failure, Fallback and Feedback UX
- Designing states for uncertainty, missing context, refusals and manual fallback
- Capturing implicit behavioural feedback alongside explicit user corrections
Other Courses in This Category
-
Calibrating user trust and preserving human control in AI products: confidence cues, editable drafts, undo and version history, privacy boundaries and escalation UX.
- Live Course
- 5 modules
-
Explainability design in LLM, RAG and decision-support products: inline citations, document/data provenance, reasoning summaries, decision factor breakdowns and auditable interfaces.
- Live Course
- 5 modules
-
Designing human-AI collaboration that amplifies human expertise: mixed-initiative workflows, preventing cognitive overload and skill atrophy, Microsoft HAX and Google PAIR guidelines, and co-creation loops.
- Live Course
- 5 modules
-
End-to-end metric architecture for AI products: North Star and task completion, acceptance rate and edit distance, offline/online eval correlation, retention and cost per successful task.
- Live Course
- 5 modules
-
Experimentation design for probabilistic AI products: moving from offline evals to online A/B tests, shadow deployments, interleaving, controlling for novelty effects and multi-metric ship criteria.
- Live Course
- 5 modules
-
Model behaviour and quality management for product teams: behaviour specifications (tone, boundaries, refusal style), systematic error analysis, domain-expert rubrics and continuous quality loops.
- Live Course
- 5 modules
Get in touch
