Standby
A minimal, quiet state keeps the phone from becoming the center of the visit.
AI experience design · Museum UX · Accessibility
A quiet AI companion for first-time and occasional museum visitors that offers one helpful next step—then fades back so attention can return to the art.
My roleConcept originator, product strategy, PRD, interaction model, and early prototyping
TeamFive-person student team
TimelineSpring 2026
ToolsFigma, FigJam, Figma Make
My contribution
I originated the MusePilot concept, wrote the PRD, defined the product’s core behavior, and contributed to the early prototype. My teammates led much of the final visual system and high-fidelity motion prototype.
Solution
MusePilot supports moments of uncertainty without managing the entire visit. It stays quiet while visitors explore, responds when they need help, and returns to Standby when the task is complete.

A minimal, quiet state keeps the phone from becoming the center of the visit.
MusePilot offers one nearby suggestion and explains why it may be relevant.
Brief directions include useful access context, then return the visitor to the art.
A closing moment
At the end of the visit, MusePilot creates a personal recap that visitors can save or share.
The challenge
First-time and occasional visitors often have limited time, energy, and familiarity with the collection. They want reassurance without losing conversation, attention, or spontaneous discovery.
Visitors need
Visitors want
Our opportunity was not to design a smarter tour. It was to design a quieter form of guidance.
How feedback changed the product
Before
Our early concept centered a complete route, progress tracking, frequent next-stop instructions, and a prominent Replan action.
Feedback
Critique surfaced a central concern: visitors come to museums to look, talk, and explore—not to spend the experience following a phone.
After
We changed MusePilot from a managed route into a Standby companion that helps briefly and then fades back.
Offer one nearby option instead of planning the entire visit by default.
Let visitors stop or wander without making the experience feel broken.
Help at moments of uncertainty, then return attention to the museum.
This changed the product goal from route completion to visitor confidence, attention, and freedom.
What we learned
Museum observations, interviews, critique, and a four-participant qualitative prototype round helped us focus the final concept.
Visitors wanted to stop or wander without feeling that they had failed to follow the experience.
People needed to understand whether MusePilot considered the visit active, paused, exploratory, or finished.
Seating, stairs, water, restrooms, distance, and fatigue shaped what visitors could realistically do next.
A personal record extended the experience and created a natural opportunity for sharing.
What changed
Reflection
We initially treated better guidance as more guidance. This project taught me that in an attention-sensitive environment, the strongest AI behavior may be restraint.
MusePilot became more useful when it stopped trying to manage the entire visit and began supporting specific moments of uncertainty. My most important contribution was defining this product direction.
Interactive prototype
Move through the final concept as a visitor. The prototype demonstrates quiet guidance, rest support, and the end-of-visit recap.
Open full-screen in Figma ↗