Case Study
Overview
Hilbert AI aimed to help researchers, investors, and analysts find and evaluate companies more effectively.
As an early stage startup, the goal was to create an AI-powered research tool that could surface relevant companies, organise complex information clearly, and help users discover patterns and opportunities.
My role
As the founding designer, I worked directly with the founder to shape the product from its earliest concept. With no existing product structure in place, I defined the information architecture, designed search and research interactions, and explored multiple approaches to presenting AI-generated data. I prototyped rapidly, tested ideas in short cycles, and iterated based on feedback.
The core hypothesis
This belief guided everything we built. We set out to create an AI workspace where the barrier between asking a question and getting a structured data answer would disappear.
To prove this hypothesis, we had to solve fundamental questions about how people interact with AI tools.
Main question and focus
This was the central question before a single screen was designed.
So we didn't start with the answer. We explored a bunch of concepts and our process was a series of experiments to find the right balance between immediate clarity and long term scalability.
Option 1
Quick access sidebar and project switching in top navigation
Option 2
Hover triggered sidebar revealing created projects and documents
Option 3
Persistent project sidebar with expandable file navigation
A glimpse of the broader iteration process
Where we landed
The final layout was a strategic bet on scalability and driven by future proofing
Anticipating and planning new features, I prioritised a flexible architecture over a fixed layout.
It was less about choosing the 'best' navigation pattern and more about building in flexibility from the start. I designed a foundation that could hold future features without needing a complete overhaul.
Continuing to scale the workflow
How to offer the right balance of freedom and guidance from the very start?
Speed for efficiency. The project template library
To eliminate blank canvas anxiety and accelerate time to value, I provided a curated library of pre built project templates. Users could instantly start with a proven structure, making the tool useful from their very first session without any setup.
Creating your own project template. Visualising progress
At each stage, users could generate a live preview to validate their input. This step by step confirmation first for documents, then for lists transformed setup into a series of confident decisions, ensuring the final template matched their expectations before creation.
Our initial setup used structured forms users filled fields for company names, industries, criteria. Functional, but constraining. Users adapted to our structure rather than expressing their intent naturally.
This broke a core principle
Users should lead their creation, not follow our forms
I redesigned the setup flow to be conversational. Instead of
filling forms, users describe research goals in natural language.
Conversation creation
The new flow feels like working with an assistant rather than filling out paperwork. Users type their research goal naturally, and the AI responds intelligently suggesting relevant filters, asking for clarification only when genuinely needed.
This shift moved control from system to user. The AI became a helpful collaborator rather than a structured questionnaire. Users could express complex research needs in one sentence instead of navigating through multiple form fields.
Outcomes & Impact
Through 120+ rapid iterations over 8 weeks, I translated a vision into a tangible product that achieved both technical and strategic validation to securing funding.
While the product didn't find its market fit, the design work secured funding validating the approach even as the product direction changed.
