Hi, I’m Ross.
I lead UX research for flagship agentic AI products at Microsoft Azure and have been researching human–AI interaction since 2016. My work defines how startup and enterprise cloud professionals adopt and trust AI tools at scale.
Research that defines product strategy
I've been studying how people interact with AI systems since my PhD, when I designed and built a conversational agent for post-surgical patient education, years before Claude and ChatGPT went mainstream. That work led to a paper I co-authored that was published at CHI and extended Nielsen's heuristics for conversational agents.
Today I lead mixed methods UX research for the Azure Deployment Agent, a 0→1 agentic AI product, with a focus on trust, control, and human oversight in agentic systems. These topics were uncharted territory two years ago. I defined the research questions that shaped trust, control, and oversight patterns for the product, presented the answers to executive leadership, and transformed an idea into a product shipped in 2025
AI has been the focus of my research for a decade. Recently, I’ve also transformed how I do the research itself by building new tools to streamline my processes. I use AI across analysis, synthesis, and reporting workflows. Simultaneously I'm defining the evaluation frameworks Azure uses for agentic systems with cross-functional stakeholders on my team. The result: higher-quality work, shipped faster, tailored to specific audiences.
Projects
Azure Deployment Agent
Leading research on a 0→1 agentic AI product, currently in preview. My research is shaping UX patterns for Azure's agent portfolio, in territory where no playbook existed for trust, control, and human oversight. This work defined the trust, control, and oversight patterns now being adopted across Azure's agent portfolio.
Details coming soon
Virtual Machine Networking
Uncovering unmet user needs and challenges for one of the highest traffic and mission critical pages in the Azure portal. This research reframed a stalled redesign by showing that features generating "junk drawer" complaints were the same features generating a competitive advantage. This reframe unlocked the redesign and drove a material increase in load balancer deployments.
Details coming soon
Hernia Coach
Designed, built, and evaluated a conversational AI agent, Hernia Coach, focused on post-surgical patient education for my dissertation on patient-facing conversational AI in healthcare. This work directly produced a paper, published at CHI, that I co-authored with academic and industry researchers, extending Nielsen's heuristics for conversational agents.
Details coming soon
Get in touch
If you're working on agentic systems, human–AI interaction, or enterprise UX, please reach out.