AI product design · Vibe coded
AI Banking Copilot
From AI concept to working prototype in 6 days.
Designing an AI-native banking experience and transforming it into a working prototype using AI-assisted development.
Instead of building another banking app, this project explores how AI understands context, recommends next-best actions and orchestrates complete workflows.

Home
Role
Product Designer
Duration
6 days
Type
AI concept + vibe-coded prototype
Stack
Figma · Claude Code · Cursor · React Native · Expo · GitHub
Repository
Public on GitHub
Why it matters
Banking has always made customers do the thinking.
The AI Copilot changes who does the thinking.
Traditional banking expects customers to search, compare, understand products and decide what to do next.
AI Banking Copilot shifts that cognitive work to the assistant — understanding intent, reasoning with customer context, and recommending the best next action.
Traditional banking
Customer does the thinking
- Goal
- Search
- Compare
- Fill forms
- Submit
AI Banking Copilot
Customer states a goal
- Goal
- AI understands
- AI reasons
- AI recommends
- Customer confirms
The customer defines the goal. The AI figures out how to achieve it.
AI workspace
Four workflows, one copilot
Each workflow starts from what the customer is actually trying to do, and ends in a completed action rather than an answer.

A charge the customer doesn't recognise is answered in a single turn — what it was, who took it, and what they can do about it.
- Answers in plain language first: the merchant and the reason for the charge, before any transaction detail.
- Backs the answer with the record — amount, merchant, date, reference — so the explanation is checkable, not just plausible.
- Ends on the three actions that actually follow: view the bill, download the receipt, or report a problem.
- Leaves the thread open, so the next question continues the conversation instead of restarting it.

The analysis is set up in conversation — which accounts, over what period — and comes back as something to act on rather than read.
- Asks two questions before answering, and no more: which accounts, and which timeframe.
- Leads with the total and its movement against the previous month, then the category split behind it.
- Names the specific things worth knowing — the category that jumped, the saving that was missed.
- Turns each insight into a recommendation with the control attached: set the budget, view the offers, enable the alerts.

Product discovery reasons over the customer's own spending, then proves the recommendation before asking them to apply for anything.
- Ranks by net annual benefit against real spending, not by product tier or marketing order.
- Justifies the match in the customer's own data — where the money goes, how often they fly, what they currently earn on it.
- Checks eligibility in place against income, tenure and credit score, without touching the credit file.
- Ends pre-qualified with the terms stated up front: documents, timing, and the odds of approval.

A reported problem is carried all the way to a raised, referenced case — inside the same conversation that surfaced it.
- Picks the dispute up from the transaction already on screen, with no separate support journey to find.
- Confirms what it understood before acting, and has the customer name the issue type rather than assuming it.
- Files the case itself and shows the summary it submitted, so nothing is raised on the customer's behalf unseen.
- Returns a ticket reference and a route back to it, so the issue outlives the session.
How I built it
From concept to prototype in 6 days
AI accelerated execution, allowing ideas to move from concept to a working prototype in days instead of weeks.
01
Explore
Benchmark AI experiences
02
Design
Create AI-first workflows
03
Vibe code
Transform into a working prototype
04
Ship
Interactive prototype + GitHub
ai-banking-copilot
Public- Update project docs for session closure4 days ago
- Fix missing horizontal padding in bottom sheets4 days ago
- Pin the app to its designed light theme and fix viewport-sized backgrounds4 days ago
- Add responsive web device frame and Vercel static hosting config4 days ago
Public GitHub
Inspect the implementation, project structure and development history.
View repositoryBuilt with
- Figma
- Claude Code
- Cursor
- React Native
- Expo
- TypeScript
- GitHub





