Houselights — Spatial Concert App
Project Overview
Houselights is a high-definition spatial video app for VR that puts viewers in the “best seat in the house” for live sports, concerts, comedy specials, and theatrical performances — from home. Alongside the live calendar, pre-recorded performances run all day across a mix of artists and formats, so the room is never empty. The app is eyes-and-hands: no controllers, no voice input. Your gaze aims, a pinch confirms. Users browse by genre, open an artist, unlock a show, and watch it on a floating screen with the setlist at their side.
The work was self-directed in that I made every UX, UI, and content call on the prototype — but it wasn’t built in a vacuum. I presented to stakeholders through the project and folded in feedback as the direction took shape alongside the pitch they were building for the parent company. I designed the spatial layout, the interaction model, the component system, and the brand. I directed an AI model — Claude, connected to my Figma file through the Figma connector — to do the building. The result is a fully playable prototype of about 90 boards, a 49-component library whose states double as the engineering spec, a rendered logo animation, and a complete record of how the direction happened.
Role & Responsibilities
Art director and designer. I set the visual language, the spatial layout and the interaction rules, chose the content, and made every call on what stayed and what went. Claude worked inside my Figma file as the builder — created boards and components, wired the prototype, and rendered video from code — all to my direction.
This case study is doing three jobs at once: it shows the visual identity I built from scratch, the UX calls I made about how people move through the app, and how I worked with AI as a co-worker to get it built — without handing any of the design decisions over to the model.
Key Contributions
- Presented to stakeholders across the project — walking them through design and user-experience decisions, fielding feedback, and defending the calls that stayed
- Created a new à la carte purchasing model for individual concerts, replacing a subscription-first assumption with pay-per-show economics
- Set the design direction for integrating the spectrum motif into the app’s visual language — applied holistically across brand, interaction feedback, and navigation
- Established the spatial layout, interaction model, and component system for a hands-and-eyes VR input scheme with no controllers or voice
- Built and oversaw a prototype of ~90 boards, a 49-component library, ~2,300 component instances, and ~950 prototype links — every design decision mine
- Produced pitch videos walking stakeholders through the prototype’s capabilities and the core user journeys
- Directed an AI model (Claude, via the Figma connector) as the builder — and maintained the full co-work chat as an auditable record of how every direction was given and received
- Directed the logo and intro animation through six font-only options and twenty-plus revisions
Working With AI
Claude was connected to the Figma file through Figma’s connector. That gave it the ability to read the file’s structure, run scripts against it (create frames, components and variants; set prototype links and timings; rename, move and restyle layers), and take screenshots of boards to check its own work. It also had a separate workspace where it could write code to render video.
I worked in Figma and in the prototype at the same time, reviewing each change, and gave direction in plain language. Nothing went into the file that I didn’t ask for, review, and approve. When something missed, I rejected it — sometimes after it had been built out at scale — and asked for the reversal.
What I did
- Set the concept, product scope and user flow
- Defined the visual language — glass panels, dark room, one accent colour, spectrum motif
- Wrote the interaction rules for gaze and pinch, including the 90 / 120 / 220 ms hover timing
- Chose between options by trying them in the live prototype — not from static mockups
- Made every content decision: artists, shows, setlists, what got featured
- Directed the brand and logo: picked the typeface direction, specified every option I wanted to see drawn, and called every animation revision by hand
- Gathered reference, judged what was worth borrowing and what wasn’t
- Had the final say on every change — including rejecting and reversing work that missed
- Placed every image and video into Figma by hand
- Recorded the prototype myself
What Claude did
- Built boards and overlays to the layout I described
- Applied the visual language consistently across ~90 boards
- Encoded the gaze timing as real prototype reactions on every component
- Built the options I needed to compare as live, hoverable components — not static comps
- Populated boards with content and corrected them when I flagged errors
- Drew every logo option I specified and rendered each animation revision from code
- Analysed reference material I provided and proposed layouts for me to react to
- Reworked or reverted on instruction, at any scale
- Edited the recording I made into the walkthrough video and looping clips
Where AI helped
- Scale and repetition. Changing the show view meant repointing 111 prototype links across the file — one instruction, one pass, links read back to confirm none were missed.
- Options as working things. Hover treatments and logo directions arrived as live components, so choices were made by trying them.
- Consistency. A timing rule or a colour rule, once stated, was applied to every instance without drift.
- Rendering from code. The logo animation was drawn frame by frame from the same letter geometry as the Figma file, which is why the last video frame matches the first prototype board exactly.
Where AI didn’t help
- Taste. First attempts were often rejected — the first logo, the angled side panels, the combined depth effect. The AI proposed; it couldn’t tell which proposals were good.
- Material language. Liquid glass never fully landed from description alone. “Translucent panel over passthrough” came back as a flat fill or a hard frosted plate more often than not — the refraction, the way light bends through the edge, the soft lift under gaze — I had to show it a reference and point at the specific quality I meant before it stuck.
- Spacing. It struggled to judge space the way a designer does. A rule stated in prose (“20px gap”, “align the icon to the baseline”) didn’t always translate to what the board actually looked like. The fastest fix was to take a screenshot, draw the correction right on top in markup, and inject that back — it needed to see the gap I meant before it could close it.
- Feel. It couldn’t play video inside the prototype or judge how a hover feels under a hand or an eye. I did that by using the prototype.
- Media. It couldn’t place images or video into Figma. I placed every one by hand.
- Accuracy. Content errors — wrong show details, a stray label — were caught by me, not by the AI.
Design Language
The interface is liquid glass on the user’s own home, simulating passthrough within the VR headset. Panels sit at a fixed distance and behave like physical surfaces — they refract light, lift subtly under gaze, and settle back when you look away. The dark room behind them isn’t a static backdrop: it’s a generated passthrough feed, standing in for what the user sees through their HMD. Your living room becomes the venue. The app doesn’t pull you out of your space to watch a show; it places the show inside it.
The spectrum strip is the brand’s signature motif. A multi-colour sweep runs through the Houselights wordmark and reappears throughout the interface: it circles an artist card the moment you gaze at it, underlines any element that leads to live content, and marks the current selection in menus. Every colour in that spectrum stands for a different flavour of content — pop, hip-hop, rock, electronic, and everything between — so the strip isn’t decoration, it’s a visual promise that whatever you’re after, Houselights has a strip for it.
Interaction Model — Eyes and a Pinch
Eyes dart and lock. Cursors glide. A hover tuned for a mouse lags the eye and lights up everything you glance across. I set a simple contract for every gaze-reactive element: wait 90 milliseconds before reacting, arrive in 120, release in 220. The target shouldn’t move under a fixating eye, so the lift is small and the depth cue comes from the shadow and the ring.
Component System — States Are the Spec
Every component holds its own states and the motion between them, so the library is the spec. When I wanted to choose a hover treatment I didn’t compare stills — I had six options built as live components on one board, hovered each of them, shipped one, tried a second across the whole prototype and took it back out when it was too much.
The prototype grew to about 88 live boards, a 49-component library, roughly 2,300 component instances, and ~950 navigation links — all consistent because a rule, once stated, was applied everywhere.
The Show View — Theater at Home
Full-screen mode is the point of the app. The show lives on a floating screen, the room goes dark around it, and the space behaves like a theater built just for you. Now Playing and performer info sit in a panel to the left; the setlist sits in a panel to the right — close enough to reach with a glance, far enough not to crowd the performance. The playback controls run across the bottom and stay out of the way until you want them.
A pinch, or a quick palm-down gesture, clears every panel and leaves just the music and the stage. Another pinch brings it all back. The interface is there when you want context, gone when you want to disappear into the show.
Taking It Into Shapes XR
Figma’s prototype can tell me whether the interactions read right. What it can’t tell me is whether the panels feel right in space — sitting at a real distance in a real room, with passthrough behind them. So I pulled the prototype into Shapes XR to check that the direction was holding up spatially before going any further: Were the panels at a comfortable distance? Did they float or did they feel glued on? Was the room behaving like a venue or a backdrop?
Brand & Motion
The logo is two weights of one typeface and a strip of concert footage. HOUSE in a light weight, LIGHTS in a black weight, with the footage playing inside the heavy letters. The intro animation was rendered from code frame by frame, and its last frame matches the sign-in board in the prototype pixel for pixel — so the video hands off to the interactive prototype without a visible seam.
Brand and motion direction leaned on a multi-AI pipeline: Claude for layout and code-rendered animation, Manus and Gemini for logo exploration, type pairing, and motion reference. I directed the choices and judged every output — the AI tools expanded the option space; the final call was mine.
Detail Gallery









