Sprint week

VibeCheck by Visa

A checkout-time check that shows Gen Z what an impulse buy costs in the things they care about, built in a five-day design sprint for Visa.

Company
LSE Sprint Week · Visa brief
Role
Led the research, UX spec and prototype build
When
Nov 2026
Length
3 min read
Stack
  • Kiro
  • HTML/CSS/JS
  • Mural
Open brief to clickable prototype
After5 days
Three phone screens: a VibeCheck welcome screen reading Spend on your vibe, a checkout sheet reading £45 = 2 gig tickets, and a home screen with Maya's top three priorities.

Short version

VibeCheck by Visa shows a Gen Z cardholder what a non-essential purchase costs in the things they care about, just before they pay. We took it from an open brief to a written spec and a clickable prototype in five days.

Problem

Visa’s brief was open. What’s a valuable problem to solve for Gen Z in the financial space? It asked us to consider the AI experience and the current ecosystem of partners.

By the third day we had narrowed it to one target.

Show Gen Z what an impulse buy costs them in terms of what they really care about, right before they pay.

Constraints

Most of the design came from five facts about what the system can and can’t know.

  • Card data shows where you spent, not what you bought.
  • Card authorisation happens after the decision to buy is already made.
  • Inferring someone’s interests from their spending counts as profiling under UK GDPR.
  • Nudges that feel judgemental get ignored.
  • Visa is a network, not a bank. The issuer owns the customer and holds the money.

Approach

VibeCheck compares what you’re about to buy with the priorities you’ve set and your wishlist. The checkout check is the core of it, and in the prototype it runs like this.

  1. Before payment, VibeCheck compares the basket with the user’s priorities and wishlist.
  2. It shows the trade-off in their own terms, like “this £45 = 2 nights in Lisbon” or “this is on your wishlist and £10 cheaper than last week”.
  3. Two optional views add context. Forecast shows how the purchase is likely to feel later, and Worth It? shows the user’s own ratings of similar past purchases.
  4. The user picks buy, save to wishlist, or wait 24 hours. Buying is always one tap away.
Two phone screens. Left: a mock TrendShop bag with cargo trousers, a crop top and socks, £45 in total, and a Pay with Visa button. Right: the VibeCheck sheet over the same bag, reading '£45 = 2 gig tickets. Live music is your #1.', with VibeCheck's take, Forecast and Worth it? toggles, and Buy, Save to wishlist and Wait 24 hours buttons.
Mock data
Two phone screens. Left: the Worth it? view, 'You rated 3 of your last 4 clothing hauls 2/5 or lower', listing a denim jacket, a going-out top, a bucket hat and a hoodie with their ratings. Right: a StrideCo checkout where the sheet reads 'On your wishlist, and £10 cheaper' for running shoes that dropped from £70 to £60.
Mock data

We built the checkout sheet first, because every other screen exists to feed it. The prototype was built in Kiro, an agentic coding tool, from a written spec instead of ad-hoc prompts. The spec covered screens, copy, states and seed data.

Two phone screens. Left: the TrendShop bag with a toast reading 'Parked until tomorrow at 20:14. It's in your wishlist as Waiting.' and an Undo link. Right: a VibeCheck notification, 'Still want the cargo trousers? Yesterday you chose to wait.', above a sheet with Buy now and Remove buttons.
Mock data

Decisions

Check before payment, from the basket

Ruled out
Insights on the statement afterwards
Went with
A check inside checkout, from basket data

Card data has no line items, and by the time a payment is authorised the decision is already made. A statement insight would only need data the issuer already has, but it arrives too late to change anything. So the check runs inside checkout and reads the basket the shop shares, in an app, at online checkout or inside an AI agent. The cost is that it only works where a shop shares its basket.

AI suggests, the user confirms

Ruled out
Infer the profile from spending
Went with
AI suggests priorities, the user confirms each one

Inferring interests from spending is profiling under UK GDPR. So consent is a required step in setup, and the AI only suggests priorities. The user confirms, edits or deletes each one. Setup gets longer, and that’s the price.

Two phone screens. Left: 'Want suggestions from your spending?', with what VibeCheck looks at (shop names, amounts and dates from the last 12 months), what it doesn't see (what you bought, unless a shop shares your basket), and an opt-in toggle. Right: 'Here's what we spotted. You decide.', listing Live music, Fitness, Eating out and Travel, each with That's me and Not me buttons.
Mock data
Two phone screens. Left: Priorities, 'Drag to reorder. Your #1 sets the trade-off.', with Live music and Fitness marked Suggested, Eating out marked Added by you, and a preview reading £45 = 2 gig tickets. Right: Wishlist, '2 of 4 items back a priority', with a festival ticket, running shoes, a film camera and a waiting TrendShop basket.
Mock data

Never block a purchase

Ruled out
Hard spending limits
Went with
Never block, always offer a choice

Nudges that feel judgemental get ignored, and a blocked payment is as judgemental as it gets. The check always offers buy, save to wishlist or wait 24 hours, and buying stays one tap away. That means the check can only persuade. It never stops anyone.

A desktop TrendShop checkout with the VibeCheck panel open on the right: 'Basket shared by TrendShop · 3 items', '£45 = 2 gig tickets', VibeCheck's take, Forecast and Worth it? sections, and Buy, Save to wishlist and Wait 24 hours buttons.
Mock data

Issuer owns, Visa supplies

Ruled out
A standalone Visa app
Went with
A feature issuers add to their own apps

Visa is a network, not a bank. The issuer owns the customer and holds the money. So Visa supplies the feature ready-made and banks add it without building it, and “by Visa” keeps Visa’s name in front of the cardholder. Visa gives up owning the relationship with the user.