The Problem: A Fragmented Research Approach

The challenge was to conduct discovery interviews that focused on user problems and desired solutions, rather than getting distracted by premature feedback on a full interface. We needed a way to visually conceptualize a complex product’s capabilities without stifling conversation or receiving feedback on a low-fidelity prototype.

The Solution: A Modular Prototype for Discovery

I designed and created a modular, low-fidelity prototype to be presented in segments during discovery interviews. This strategy allowed us to:

Guide future development: The feedback and insights gathered from these interviews informed our project’s core requirements, serving as a blueprint for the technical team and validating our design vision.

Focus the conversation: By breaking the prototype into separate modules, we could guide the discussion to specific user problems and needs.

Validate core concepts: We confirmed our understanding of user pain points and their desired solutions without the distraction of premature design feedback.

With the current capability of AI model in mind we developed potential processes to demo for our users, these ideation sketches allowed us to coordinate which model features to further improve visually.

We conducted a comprehensive user research study to understand and validate key user needs. Our methodology was structured in two phases:

Contextual Inquiries: We began by observing users’ current workflows for uploading and exploring datasets. This helped us uncover foundational pain points and understand their existing challenges.

User Stories & Ideation: Based on the requirements of our project, we developed user flows to ideate on the delivery of our AI data models. This allowed us to collaborate with our engineering team early on to validate our approach and ensure the design was technically feasible

Project Delivery: A Framework for Success

This project’s final output was a structured framework of six core requirements for an advanced data analytics platform. This framework served a crucial dual purpose:

• Guiding User Validation: It provided a clear guide for conducting targeted user interviews, ensuring our concepts were validated by genuine user needs.
• Driving Technical Implementation: It acted as a clear blueprint for the technical team, directly informing the implementation and integration of interactive user data models within the SaferData system.

This approach ensured a seamless transition from research to development, aligning our design vision with technical feasibility and user expectations.

This process included:

Semi-Structured Interviews: We presented users with scenarios for data enrichment, augmentation, and synthesis. This allowed us to gauge the business value and relevance of these advanced capabilities.

Low-Fidelity Prototype Testing: We introduced a prototype of a conversational interface, asking users to pose their own business questions and react to probabilistic answers. This helped us assess their comprehension, trust, and readiness for a novel method of data interaction.