AI COST OPTIMIZATION
Designed an AI-powered cost optimization tool for healthcare workforce operations, giving facility administrators predictive insights into shift pricing without leaving the platform. Led end-to-end from discovery and requirements through design, usability testing, and developer handoff.
THE CHALLENGE
Users needed a way to understand trends and forecast cost outcomes associated with shift pricing at their medical facilities without relying on manual analysis or exporting to external tools. The goal was to build an interface that complemented user expertise with machine-generated insights, enabling faster, more confident decisions.
ROLE & SCOPE
Served as the lead designer across the full product lifecycle, from research planning and requirements definition through concept development, interaction design, usability testing, and developer handoff. Worked directly with data science teams to understand model outputs and define how predictive insights should be surfaced and explained to non-technical users. Collaborated with product leadership and engineering throughout, running workshops to align on approach and contributing to roadmap decisions around how AI features were prioritized and sequenced.
RESEARCH & INSIGHTS
Research included stakeholder interviews with facility administrators and analysis of existing user workflows to understand how shift pricing decisions were currently being made. Two consistent needs emerged:
​
• Contextualization of AI predictions alongside historical data
• Control over how and when AI summaries are presented
​
Based on this, I defined design requirements that ensured AI insights felt trustworthy, transparent, and actionable.
USABILITY TESTING & DECISIONS
After building a prototype and conducting usability testing, key decisions included:
​
• Crafting visual patterns that place predictive insights near relevant performance metrics
• Designing contextual help and explanation layers for AI outputs to build understanding and trust
• Creating consistent states for forecast scenarios so users could easily compare outcomes
• Structuring the dashboard to support iterative exploration of recommended actions
​
These strategies balanced automation with user agency, a critical consideration for enterprise workflows.
OUTCOME & IMPACTS
Translated usability findings into high-fidelity designs with detailed documentation and annotated specs for developer handoff. Used Figma dev mode to produce functional front-end code alongside design deliverables, giving engineering a working starting point and keeping implementation aligned with the intended experience. Maintained close collaboration with engineering through launch to ensure design fidelity and accessibility standards held in production.
The shipped tool gives facility administrators the ability to:
Quickly interpret forecast scenarios without manual modeling or external tools
Explore AI-generated recommendations tied directly to underlying shift and pricing data
Trust predictive outputs through contextual explanation layers built into the interface
The feature reduced the time administrators spent on manual cost analysis and positioned the platform to layer in additional AI capabilities on the same foundation.
