Transforming the Financial Wellness Dashboard using AI assistance

Backbase | Amsterdam

Goal

Empower users to make smart, confident financial decisions by surfacing personalized insights without overwhelming them by reducing decision fatigue, improving clarity, and promoting healthy financial habits using AI-powered nudges.

My role

I led product discovery, design prototyping, and testing for this concept, using Gemini Deep Research and Lovable AI to inform the UI experience. I collaborated cross-functionally with Product and Design to align on vision and execution.

Impact

Research revealed strong perceived value and emotional resonance with the redesigned dashboard. Participants described it as “very helpful” for managing their finances, highlighting its clarity and depth compared to existing apps. Insights from this concept are now shaping client conversations around a broader Financial Wellness overhaul.

Before and After

Where we started

During the Retail Banking Revamp, most of our focus was on improving the app’s dashboard and overall information architecture. We streamlined navigation and reduced friction across core user flows.

At the time, the Financial Insights page was largely out of scope. It existed as a generic screen with little insights or personalization, and user engagement was low. We saw an opportunity to revisit this neglected area and reimagine how insights could feel actionable, emotionally supportive, and easy to act on.

Our first steps

  1. Revisit existing data to understand how users were interacting with the Financial Insights page.

  2. Review prior research from the Retail Banking Revamp, including insights related to navigation, dashboard usage, and content hierarchy.

Discovery

Here’s what I did:

  • Survey review: I revisited a previously run “Managing Your Money” survey with 397 participants across the US, UK, and Canada to identify what people expect from financial dashboards. Key findings shaped early decisions around clarity, forecasting, and actionable guidance.

  • Segment & persona alignment: I used Gemini Deep Research to surface behavioral segments and mapped these against existing personas to clarify needs, goals, and pain points across different user types.

  • Prompt design & ideation: I created a structured prompt combining survey themes, behavioral segments, and tone considerations, and input it into Lovable AI to generate actionable nudges.

  • Rapid concept iteration: I translated the AI nudges into a first concept prototype, integrating forecasting, debt tracking, and contextual guidance. Internal feedback and helped refine this direction.

Concept 1: Choosing course dates via a calendar, then selecting a course

Concept 2: Choosing a course, then selecting dates via a calendar

Concept 3: Month-level date selection via buttons instead of calender, then selecting a course

We moved forward with a combination of Concept 2 and Concept 3, as they best balanced user needs and business constraints:

  • Ease of Implementation (Concept 2):
    Concept 2 leveraged EF’s existing API, avoiding costly redevelopment.

  • User Preference for Course Selection (Concept 2):
    Users preferred starting with course selection. As one participant noted:
    “I want to pick my course first, then figure out the dates.”

  • Ease of Date Selection (Concept 3):
    Concept 3’s button-based date selection was clearer and easier to use compared to the more rigid and confusing calendar inputs in Concepts 1 and 2. One participant shared:
    “It’s easier to choose my options this way.”

Final design

Impact

The redesigned booking flow delivered significant improvements:

  • Users completed bookings faster with fewer drop-offs, doubling conversion rates.

  • Replacing dropdown menus with tappable buttons improved usability and minimized booking mistakes.

  • Moving the booking flow from the menu to destination pages reduced friction and simplified navigation.

  • Strong sales data convinced leadership to expand the new booking flow to a second key market.