Personal concept · 2 months · UX/UI & conversation design

Aunty Sip

Herbal knowledge,
in the moment.

A voice-first wearable concept that pairs timely guidance on smart glasses with a phone companion for images, ingredients, and detail.

Speculative concept · Educational guidance only · Not medically validated

Listening
Aunty Sip phone companion showing tea information and ingredients
Sip
Project
Future wearable concept
My role
End-to-end designer
Ownership
Personas · journey · conversation · UI
Prototype
Storyboards · two scenario films

The opportunity

The request for tea is only one moment in a longer experience.

Information can become fragmented between learning what an ingredient is, deciding whether it feels relevant, finding it, preparing it, and remembering what to do next. I used that broader journey to frame the concept and its boundaries.

Botanical illustration of medicinal plants
How might a future wearable make herbal-tea knowledge easier to understand while preserving context, care, and user control?

Find

Make unfamiliar knowledge easier to approach.

Consider

Help someone judge what feels relevant without hiding uncertainty.

Source

Connect recognition with a practical way to find ingredients.

Prepare

Keep instructions available while both hands are busy.

Remember

Carry the routine into the rest of the day.

Learn

Leave the person with knowledge they can use again.

Designed personas

Two ways into trust.

These are scenario models created to explore different needs. They are not presented as research-validated personas.

Returning user · Tai

A clear need, limited time.

Tai already has a routine. The experience needs to move from a contextual request to sourcing, hands-free preparation, and a thoughtful check-in.

Newcomer · Ke

Curiosity before confidence.

Ke first needs to recognize what they are seeing, understand it in plain language, and learn how to prepare it without being overwhelmed.

Bot persona and visual language

Warm, wise, and clear about what the interface is doing.

Aunty Sip was written as a caring guide, not an authority that always has the answer. Its visual states make an otherwise invisible voice interaction legible while keeping the view quiet.

Aunty Sip circular tea mark
Aunty Sip standby state

Standby

A quiet tea swirl shows that Aunty Sip is available.

Aunty Sip listening state

Listening

A breathing water ring makes the microphone state clear.

Aunty Sip speaking state

Speaking

Tea leaves move outward while the assistant responds.

Two scenario stories

The same assistant behaves differently when the starting point changes.

Each scenario connects the dialogue, timing, device handoff, and preparation routine. The videos are user-controlled.

Tai · Returning user

Guidance across a full routine.

A request becomes a multi-turn conversation, an ingredient handoff, hands-free preparation, and a next-day feedback moment.

AskClarifySourcePrepareFollow up
Tai starts a conversation with Aunty Sip
Ask
Tai receives contextual guidance
Consider
Tai follows hands-free brewing guidance
Prepare
Open Tai’s full scenario flowTai scenario flow from request through preparation and follow-up
Ke · Newcomer

Recognition that becomes learning.

Curiosity in context leads to recognition, a richer phone explanation, and voice-guided preparation.

NoticeRecognizeLearnPrepare
Ke notices an unfamiliar herb
Notice
Aunty Sip explores recognition in context
Recognize
Ke learns through the companion experience
Learn
Open Ke’s full scenario flowKe scenario flow from recognition through learning and preparation

Cross-device strategy

Put the right amount of information in the right place.

The glasses keep attention in the world. The phone becomes a deliberate handoff for images, ingredients, sourcing, and longer explanations.

Smart glasses

Immediate and low-attention.

Voice, recognition, short prompts, timers, and step cues appear at the moment of action.

Herb recognition shown in the smart-glasses concept
Aunty Sip phone detail screen showing a tea overview and ingredient list
Phone companion · content designed for reading and revisiting
Companion phone

Detailed and reviewable.

Images, ingredient information, and saved content move to a surface better suited to focused reading.

Aunty Sip phone companion handoff in context
Traditional illustration showing herbal ingredients being prepared and exchanged

Conversation architecture

Design the repair before the happy path.

Wearable conversation cannot depend on perfect recognition or on a person following one script. Clarification and recovery are part of the experience, not edge cases.

Ask before assuming

When information is unavailable, Aunty Sip asks a short, explicit question instead of pretending the system already knows.

Keep uncertainty visible

If recognition fails, the conversation moves to observable details such as color, shape, and distinctive features.

Make the next step recoverable

If ingredients are missing, the experience offers a sourcing path rather than forcing the original routine.

Use the right surface

When the explanation needs an image or more detail, the glasses hand the moment to the phone.

View the full conversation design artifactConversation design sheet with multi-turn prompts and fallback responses

Prototype in context

The films made timing and attention visible.

I wrote, designed, edited, and produced both scenario films to make the proposed experience discussable before working hardware existed.

Voice-guided brewing in the Aunty Sip concept
Hands-free brewing guidance
The final pouring step in the Aunty Sip scenario
The routine returns to the physical world

Prototype credit note: the videos include selected footage from the Bilibili video “广东人为啥自讨苦吃 (Why do Cantonese Seek Bitterness?)”; a delivery icon from Iconfont; and journey illustrations created with MidJourney. Concept direction, conversation design, interface, storyboards, editing, and video production are Yazmin Wang’s work.

Botanical garden illustration

Reflection and limits

This remains a conversation concept.

Aunty Sip was not clinically validated, did not diagnose or treat conditions, and did not test live health data or recognition accuracy.

What the work demonstrates

Cross-device product thinking, conversation architecture, scenario design, visual states, interface design, and video prototyping within one system.

What I would change

The original doctor-like persona risks over-trust. A future version should show uncertainty clearly, separate education from medical advice, and provide an obvious safety escalation path.

What comes next

Run Wizard-of-Oz sessions, test comprehension and recovery, define consent and privacy, and explore recognition confidence, cultural accuracy, and hardware feasibility.

All case studies are open

Explore all work