Case studies
Slashed tech debt
Several product teams were building complex, interrelated data models to power both the product UI and a new generation of AI agents at a Fortune 500 company. The agents depended on that data model content — names and descriptions for hundreds of fields — to understand customer data and act on it. But the existing workflow gave data model content only a brief review window. That wasn’t enough time for the iterative, cross-functional work that clear, AI-ready content requires. I redesigned the review workflow so we could vet the content without putting the release date at risk. The result was a 15% ongoing cut in technical debt and rework, freeing the team to pull more from the backlog.
Boosted agent performance
A team at a Fortune 500 company was developing a series of interrelated data models. These data models would drive the product UI, including an AI agent that was key to product adoption and retention. But the data model content — API names and descriptions — didn’t meet standards that would provide good context for the LLM that powered the agent. I made a major improvement in LLM context for the agent by rewriting the content to clearly represent the model’s inherent structure and relationships.
Lifted productivity and usability with a UX reference
A department of writers at a Fortune 500 company had no shared reference for routine UX writing questions. UI labels often didn’t align with the brand or industry standards. These problems made for a muddy UI, hampering product adoption and leading to unnecessary customer cases and backlog work. Applying proven methodology, I designed a standards system that captured years of tribal knowledge in an easy-to-use reference. The standards eliminated bottlenecks; improved products by aligning them with the company’s brand, design system, industry conventions, and cognitive psychology principles; and freed time for teams to focus on work that boosted growth and adoption. Results included a 20% productivity boost and usability improvement of up to 15%.
Saved time and cut debt with UI text tracking
UX writers at a Fortune 500 company didn’t have reliable visibility into what UI text was required and when. Communication and manual recordkeeping took up too much time, and last-minute requests and end-of-release scrambles were routine. I designed and rolled out a simple tracking feature inside the existing project-tracking tool that gave teams a shared, reportable view of UI text status. Teams could use the feature to collaboratively define UI text requirements and track implementation during product development. The feature eliminated late-release bottlenecks, cut label-related tech debt, and gave writers space to do better work.