AI DASHBOARD
Predictive rate adjustments
THE ASK
My team was tasked with creating a tool that harnesses machine learning to help healthcare facilities predict and set shift rates that make the most of their staffing budgets. Previously, this process was entirely manual. Facilities would email updated rate tables to their account managers, who then had to enter each change into the backend by hand. The goal was to replace that error-prone workflow with a self-service platform that not only lets users manage their own rates, but also provides intelligent recommendations to optimize their spending.
WORKSHOP
To make sense of the complex rate update process, I facilitated a working session with several backend engineers and mapped how different rate layers interacted across the system. This exercise exposed inefficiencies and dependencies that weren’t visible in documentation, giving the team a shared understanding of where the biggest pain points existed.
USER INTERVIEWS
Given the technical and operational complexity of this project, I wanted to ground the design direction in real user experiences. I recruited and interviewed three users who work directly with rate adjustments, capturing their challenges, mental models, and expectations. These conversations shaped the foundation for how the new experience would need to function.
CURRENT STATE USER FLOWS
To visualize what I’d learned, I created a detailed user flow that outlined every step of the current process. This helped validate assumptions, highlight redundancies, and ensure that both users and engineers had a clear view of how rate changes moved through the system. The resulting diagram became a valuable artifact for aligning the team before design began.
NEW USER FLOWS
Using those insights, I developed updated user flows that introduced simplified paths and defined key entry points for interacting with the new tool. I collaborated closely with engineering to validate technical feasibility and ensure the proposed structure could scale as the system evolved. This alignment early on helped prevent rework later in the process.
USABILITY TESTING
After I felt I had a good solution, I wireframed and prototyped my idea. I initially sent my usability test out to internal teammates to gather their feedback before it went out to users. I gathered feedback from different teams including client facing teams and engineering teams and was able to implement the insights before it went out to users via our user testing platform. The results provided valuable insight into areas that needed more work.
HANDOFF
After synthesizing usability findings, I translated the improved flows into high-fidelity designs supported by thorough documentation for developer handoff. I partnered closely with engineering throughout implementation, ensuring design fidelity and accessibility standards were maintained. This continuous collaboration allowed the product to move efficiently from prototype to production.
RESULTS
The new tool saved significant time for internal teams by automating what was previously a manual, error-prone workflow. More importantly, users responded enthusiastically to the transparency and control it introduced—finally being able to see how rates were calculated and how small adjustments could optimize their spending. The result was a smarter, more empowering experience for both sides of the process.