Human-in-the-loop
evaluation interface
Project overview
As H-E-B increasingly relies on predictive and generative AI systems to inform the output of customer search, merchandising teams needed visibility into that output. Those outputs required human analysis to validate the results or adjust based on business objectives or additional context, especially during the initial adjustment to an AI-informed approach.
I was tasked with building a Human-in-the-Loop tool to streamline workflows, enhance scalability of search output overrides, and ensure that we're building trust in AI systems and continuing to improve outputs.
What I did
Role: Lead (and sole) product designer and content designer
Mapped current merchant workflows
Evaluated user needs for auditing search results outputs to ensure effective and transparent override methods
Leveraged the H-E-B design system to build this UI from scratch, while also reusing existing and familiar pieces of merchant experience to maintain connection to existing tooling
Partnered closely with front end engineering to constantly iterate and respond to changing user needs
Prepared final files for handoff and led visual QA