AI Voice Guide Experience
Guide Voice is a demo prototype that explores how AI and voice-first experiences can radically simplify access to large, layered content ecosystems.
Designed to be scalable and adaptable, it proposes a conversational model that could be applied across education, onboarding, customer service, and more.
The goal: create a seamless, voice-driven guide that understands user intent and delivers structured, meaningful suggestions in real time.
Category
Dynamic Content Guide
Skills
UX Writing
Prompt Design
Accessibility-first Design
Conversation Flow
Microinteraction & Feedback Design
My role
Lead UX & Concept Designer
Timeline
1 month
My role & resposabilities
I led the end-to-end design of the voice assistant experience—shaping the flows, behaviors, and visual touchpoints. The project was completed in a 4-week sprint, collaborating with developers and strategist.
Today’s information-heavy experiences — whether in culture, learning, or service — are often fragmented. Users jump across pages and formats without continuity or narrative. Traditional interfaces require too much searching; AI assistants remain generic.
The challenge was to design a conversational AI model that guides users through large volumes of content in a personalized, intelligent, and low-friction way.
The experience needed to be scalable, modular, and intuitive enough to serve use cases far beyond cultural content — from e-learning to onboarding journeys.
The journey is powered by an LLM/AI engine that organizes and contextualizes content in real-time.
Start: The user enters a neutral scenario.
Query: The AI asks the user to choose between typing, speaking, or being guided.
Iteration: The AI provides up to 5 content suggestions, then re-prompts for refinement.
Thematic Shift: If a clear theme emerges, the background scenario adapts visually.
Loop: When content is exhausted, the conversation resets, evolving with the user's curiosity.
Max 5 contents per interaction
Scenario evolves based on thematic density
Each “ask” is context-aware, never redundant
Voice and keyboard input allowed
As AI tools reshape user expectations, especially among Gen Z and Gen Alpha, there's growing demand for experiences that are:
Curious Cultural Explorer – wants light yet meaningful storytelling
Student in a Hurry – needs fast, smart topic breakdowns
Museum Visitor – uses voice to navigate content on-site
Educator/Parent – curates safe, thematic content for others
The UI was intentionally minimal with whitespace, simple gestures, large typography, and no visual clutter. No UI overload: just one button to start, one to stop, and AI does the rest.
To visualize the dynamic experience, here’s a hypothetical user journey.
The AI continuously adapts based on topic focus, content suggestions, and semantic structure, offering a highly flexible and evolving interaction.
AI-Led Guidance:
If the user doesn’t know what to ask, the AI proactively suggests new topics to keep the experience moving forward and spark curiosity.
Contextual Suggestions:
At the end of each content context, the AI offers carefully curated suggestions to seamlessly extend or shift the journey, inviting users to dive deeper or explore adjacent topics.User Choice (Voice or Keyboard):
At any moment, the user can choose their preferred input mode — either speaking naturally or typing — to interact with the AI, ensuring maximum comfort and accessibility.
This project reimagines user interaction by blending intuitive design with adaptive AI, creating a seamless and personalized experience. It emphasizes clarity, accessibility, and meaningful engagement, setting a new standard for digital interfaces.
Guide Voice reimagines how users navigate complex topics through conversational, adaptive guidance — merging AI intelligence with human curiosity.
The result is a scalable model that feels intimate, purposeful, and fluid — ready for museums, educational platforms, or cultural discovery tools of the future.
