Yoono - AI Due Diligence Assistant

The core challenge was volume and complexity.

The AI surfaced large amounts of information per individual, much of which required human validation. This resulted in dense, content-heavy screens that were difficult to navigate and cognitively overwhelming for users.

When I joined, an initial product design already existed, but the overall experience was fragmented and difficult to scale. The platform had:

• messy user flows
• long, unstructured streams of information
• growing stakeholder pressure as expectations increased
• early signs of scaling issues as new features were added

There was also a broader product challenge: the AI assistant and the platform often felt like two separate products rather than one coherent experience. At the same time, the team was still learning who the product was really for, which meant the design needed to remain adaptable as the product direction shifted.

I was initially hired as Senior Product Designer and later stepped into a Lead Product Designer role, owning the product design end to end. I worked closely with the CXO, engineers, and a researcher to translate product direction into clear UX and UI solutions, define user flows and information architecture, evolve the design system, and ensure the platform could scale as new features were introduced.

When I joined, the focus was initially on adding new features to an existing design. As the product grew, it became clear that this approach wouldn’t scale. The work shifted towards rethinking the experience as a more cohesive, dashboard-led product.

Structuring complexity

In the early phase, I focused on bringing clarity and structure to a rapidly evolving product. This meant establishing hierarchy for AI-generated content, designing modular components, mapping multi-step workflows, and working closely with engineers to understand technical constraints.

The goal was to make large volumes of information easier to review and act on without overwhelming users.

Iteration and research

As the product matured, I worked closely with the researcher to support usability testing. I created high-fidelity wireframes and prototypes specifically for testing, ensuring scenarios and flows could be properly evaluated with users.

The researcher led the sessions and gathered feedback, which we reviewed together. I then iterated on the designs based on user insights and stakeholder input, refining workflows, improving clarity, and validating assumptions as the product direction became clearer.

Evolving the product direction

As part of the shift toward a more SaaS-style dashboard approach, I explored ways to break complex information into manageable sections, surface key insights at a glance, and support workflows across multiple profiles. I also refined how AI outputs were embedded within the interface so they felt helpful rather than intrusive.

The designs shown here explore a future-facing direction for the product rather than the live implementation.

Although much of the work was internal and future-facing, the design helped reduce cognitive overload when reviewing AI-generated data, clarify complex workflows, align stakeholders around a more scalable direction, and build a stronger foundation for future development.

The dashboard-led approach created a clearer mental model for how users interact with the platform, bringing the AI assistant and web experience into a more cohesive product.

Balancing technical constraints, evolving business goals, and real user needs was central to the process. A key challenge was presenting AI-generated content in a way that felt useful rather than overwhelming, refining hierarchy, workflows, and levels of user control. It was rewarding to help shape a product still evolving, while supporting both immediate delivery and long-term growth.