Research and framing

How I defined who Northstar is for and what it has to do, before designing any screen. For the short version, see the main Northstar page.

Framing tools

I framed the project with an AI Experience Canvas (Human Centered AI Institute), a project definition, and conversation design for three types of learner. Together they set who the tool is for, what jobs it has to do, and where AI actually helps.

Persona: Nora

<aside> 👤

Nora, design student focused on responsible innovation. In her ethics course she debates algorithmic fairness, but it stays theoretical. Learns by doing, visual thinker, not technical.

</aside>

Goal: "I want to understand how design choices and data diversity change AI outcomes, not just be told they do."
Pain point: "I know bias exists, but I can't picture what it looks like in practice." Resources are theoretical or built for engineers, and it's hard to see how a small data change shifts outcomes.
Behaviour: "I learn best by doing. I want to experiment, not just read about ethics."

Jobs to be done

Job	Led to
When I'm learning about AI bias, I want to interact with simple visual simulations of how dataset diversity changes system behaviour, so I can see the link between data, bias and outcomes.	Experiment mode
When I'm exploring cases of biased AI in hiring, lending or healthcare, I want to adjust the variables and observe outcomes, so I can understand the human impact of data decisions.	16 domains
When I finish a simulation, I want an AI guide to help me reflect on what I saw and why it matters, so I can apply it in my practice.	Narrator and voice guide
When I share what I learned with peers or teachers, I want to export visual summaries and notes, so I can show my reasoning.	Study material

Three learners, three conversations

I mapped the AI's behaviour for three intents before designing any screen:

Explorer: "What happens if…?"
Goal-driven: "Explain this."
Frustrated: "This seems wrong." The AI validates, restates the numbers, explains, and offers one next step.

Insight

Existing fairness tools are built for people who already understand machine learning. Learners needed to cause bias themselves, with plain controls and immediate feedback, and get an explanation grounded in the numbers they just produced.