Stella

Stella

Stella

Person holding iPhone with a menu displayed on the screen. Phone is silhouetted against the white background.
Person holding iPhone with a menu displayed on the screen. Phone is silhouetted against the white background.
Person holding iPhone with a menu displayed on the screen. Phone is silhouetted against the white background.

Role:

Lead Product Designer

Role:

Lead Product Designer

Role:

Lead Product Designer

Role:

Lead Product Designer

Role:

Lead Product Designer

Date:

2021

Date:

2021

Date:

2021

Date:

2021

Date:

2021

Tags:

Ai, Data Analytics

Tags:

Ai, Data Analytics

Tags:

Ai, Data Analytics

Tags:

Ai, Data Analytics

Tags:

Ai, Data Analytics

Summary

Summary

Summary

Stella is an early AI/ML-driven concept for exploring and visualizing business data. The aim was to turn raw information into actionable insights through natural interactions.

Stella is an early AI/ML-driven concept for exploring and visualizing business data. The aim was to turn raw information into actionable insights through natural interactions.

Stella is an early AI/ML-driven concept for exploring and visualizing business data. The aim was to turn raw information into actionable insights through natural interactions.

Person holding a smartphone, showing a graph on the screen to visualize data and analytics for financial tracking.
Person holding a smartphone, showing a graph on the screen to visualize data and analytics for financial tracking.
Person holding a smartphone, showing a graph on the screen to visualize data and analytics for financial tracking.
Person holding a smartphone, showing a graph on the screen to visualize data and analytics for financial tracking.
Person holding a smartphone, showing a graph on the screen to visualize data and analytics for financial tracking.

the challenge

the
challenge

Making sense before machines could

Before AI became everyday, Stella explored what it meant for design to collaborate with intelligence. The goal wasn’t to launch a product but to understand how people might one day talk to data. We set out to create an interface that could learn, respond and adapt, long before those tools existed.

the challenge

Making sense before machines could

Before AI became everyday, Stella explored what it meant for design to collaborate with intelligence. The goal wasn’t to launch a product but to understand how people might one day talk to data. We set out to create an interface that could learn, respond and adapt, long before those tools existed.

Hand holding a smartphone displaying a business application with search bar, menu, and "Favorites" options.
Hand holding a smartphone displaying a business application with search bar, menu, and "Favorites" options.
Hand holding a smartphone displaying a business application with search bar, menu, and "Favorites" options.
Hand holding a smartphone displaying a business application with search bar, menu, and "Favorites" options.
Hand holding a smartphone displaying a business application with search bar, menu, and "Favorites" options.

the constraints

the
constraints

Designing for the unknown

Machine learning was still early, training data was inconsistent and model output often unpredictable. Stella had to visualise intelligence that didn’t yet behave predictably. We built forward from assumptions, testing ways to make opaque systems feel understandable and trustworthy. Every decision balanced imagination with realism.

the constraints

Designing for the unknown

Machine learning was still early, training data was inconsistent and model output often unpredictable. Stella had to visualise intelligence that didn’t yet behave predictably. We built forward from assumptions, testing ways to make opaque systems feel understandable and trustworthy. Every decision balanced imagination with realism.

Person holding a smartphone displaying a graph of regional sales data with a line chart. Business and financial concept.
Person holding a smartphone displaying a graph of regional sales data with a line chart. Business and financial concept.
Person holding a smartphone displaying a graph of regional sales data with a line chart. Business and financial concept.
Person holding a smartphone displaying a graph of regional sales data with a line chart. Business and financial concept.
Person holding a smartphone displaying a graph of regional sales data with a line chart. Business and financial concept.

the process

the
process

Prototyping intelligence

The work began with behaviour not pixels. We mapped how users might ask questions, how the system might interpret them and how it could respond visually. Early prototypes mimicked conversation through adaptive layouts and contextual feedback. I led the design direction, framing the product principles and working closely with data scientists to turn abstract models into tangible moments of interaction. Each cycle pushed the boundary between static UI and dynamic response.

the process

Prototyping intelligence

The work began with behaviour not pixels. We mapped how users might ask questions, how the system might interpret them and how it could respond visually. Early prototypes mimicked conversation through adaptive layouts and contextual feedback. I led the design direction, framing the product principles and working closely with data scientists to turn abstract models into tangible moments of interaction. Each cycle pushed the boundary between static UI and dynamic response.

Hand holding a gold smartphone with a user interface displaying app notifications.
Hand holding a gold smartphone with a user interface displaying app notifications.
Hand holding a gold smartphone with a user interface displaying app notifications.
Hand holding a gold smartphone with a user interface displaying app notifications.
Hand holding a gold smartphone with a user interface displaying app notifications.

the principles

the
principles

Human first, machine aware

The design treated AI as a collaborator, not a feature. Information surfaced progressively, motion reflected system thinking and errors were framed as learning moments. The interface spoke a universal visual language that balanced logic with empathy, a foundation that influenced later conversational systems.

the principles

Human first, machine aware

The design treated AI as a collaborator, not a feature. Information surfaced progressively, motion reflected system thinking and errors were framed as learning moments. The interface spoke a universal visual language that balanced logic with empathy, a foundation that influenced later conversational systems.

Modern tablet with a digital assistant interface showing daily topics and a search bar for assistance.
Modern tablet with a digital assistant interface showing daily topics and a search bar for assistance.
Modern tablet with a digital assistant interface showing daily topics and a search bar for assistance.
Modern tablet with a digital assistant interface showing daily topics and a search bar for assistance.
Modern tablet with a digital assistant interface showing daily topics and a search bar for assistance.

the reflection

the
reflection

Designing before definition

Stella was never about perfection. It was about direction. The project proved that design can lead when technology is still forming, translating abstract potential into experiences people can actually imagine.

the reflection

Designing before definition

Stella was never about perfection. It was about direction. The project proved that design can lead when technology is still forming, translating abstract potential into experiences people can actually imagine.

Impact

Impact

Impact

Stella became one of the company’s first working AI concepts. It informed how later products visualised reasoning, confidence and transparency. Though experimental, it demonstrated that interface design could guide how people understand machine learning, not just how they use it.

Stella became one of the company’s first working AI concepts. It informed how later products visualised reasoning, confidence and transparency. Though experimental, it demonstrated that interface design could guide how people understand machine learning, not just how they use it.

Stella became one of the company’s first working AI concepts. It informed how later products visualised reasoning, confidence and transparency. Though experimental, it demonstrated that interface design could guide how people understand machine learning, not just how they use it.

Fineo

Travelbook

Travelbook

Travelbook