Course Objective & Scope
Even a frontier model will frustrate users if poorly designed: it outputs walls of text, guesses when information is missing or hits dead ends on errors. This programme teaches modern conversation design principles for moving from rigid decision trees to flexible LLM-powered dialogues.
Participants define brand voice and system instructions, design slot collection, disambiguation, error repair and context-preserving human handoff flows for both chat and voice channels, and produce a conversation design style guide and working prototype for their organisation.
Who Should Attend?
- Conversation designers, UX writers and product designers
- Customer experience (CX), contact centre and digital channel managers
- Product managers and prompt designers building assistants and chatbots
- No technical prerequisites
Key Takeaways
- Write persona and conversational guidelines suited to brand identity and channel (chat versus voice)
- Structure hybrid dialogue flows that balance natural language flexibility with mandatory business steps
- Design clarifying questions that resolve missing or ambiguous user intents without friction
- Craft graceful repair patterns for misunderstandings, out-of-scope requests and system failures
- Evaluate dialogue quality using table reads, Wizard-of-Oz testing and rubrics
Curriculum
From Decision Trees to LLM Dialogues
- Differences between classic NLU/intent flows and generative dialogue management
- Chat versus voice: brevity, cognitive load and spoken pacing
Persona, System Instructions and Voice Guidelines
- Role definition, boundaries, form of address and response length rules
- Principles for empathy, clarity and avoiding over-apologising
Multi-Turn Flows, Slot Collection and Steering
- Conversational slot filling and confirmation within natural dialogue
- Disambiguation, handling digressions and returning to the task
Conversational Repair, Safety and Human Handoff
- Managing out-of-scope queries, repeated failures and frustrated users
- Warm handoff to human agents with a structured conversation summary
Dialogue Testing and Quality Metrics
- Table reads, persona simulations and conversation evaluation rubrics
- Task completion rate, turn count and user satisfaction metrics
Other Courses in This Category
-
Designing AI customer service agents and human-agent assist systems powered by knowledge bases (RAG), CRM/order tools and policy guardrails, from contact centre architecture to production rollout.
- Live Course
- 5 modules
-
Speech-to-Text (STT), LLM and Text-to-Speech (TTS) pipelines for enterprise voice AI: low-latency audio processing with Whisper, Deepgram, ElevenLabs and Cartesia, acoustic challenges and telephony integration.
- Live Course
- 5 modules
-
Real-time AI assistants that interact instantaneously over voice, camera and screen sharing: full-duplex streaming, barge-in handling, live visual context, in-flight tool calling and resilient session management.
- Live Course
- 5 modules
-
Computer-use systems that operate desktop and browser environments via screenshot perception, coordinate grounding and keyboard/mouse actions: Claude Computer Use, OpenAI CUA, sandboxed VMs and safe execution.
- Live Course
- 5 modules
-
UI agents that execute workflows across web portals and legacy enterprise screens without APIs: DOM plus visual grounding (Set-of-Marks) with Playwright, Stagehand and Browserbase, session handling and resilient automation.
- Live Course
- 5 modules
-
User control and confirmation UX in voice, multimodal and UI-acting agents: action previews, tiered permissions, live takeover/handback, undo mechanisms and UI safety patterns.
- Live Course
- 5 modules
Get in touch
