I design the architecture of AI conversation — state machines, evaluation rubrics, prompt frameworks, and behavioral guardrails that make models coherent, safe, and genuinely useful to people. Trained in psychology. Grounded in a decade of operational leadership. Certified in AI product management to sharpen the strategic edge.
Designed a 12-phase conversational state machine with anti-loop and anti-dependency guardrails for a sensitive emotional wellness context. Authored evaluation rubrics scoring model behavior across safety, tone, and pacing dimensions.
Translated user and stakeholder requirements into conversation flows and AI task structures for a career guidance platform. Developed onboarding quality criteria, memory accuracy benchmarks, and interaction consistency standards.
Defined agent roles, interaction flows, and evaluation criteria for a coordinated multi-agent system serving entrepreneurs. Identified UX and logic gaps across agent outputs. Validated system behavior in a live keynote demo.
State machines, branching logic, anti-loop rules, and multi-turn flow design for complex, high-stakes AI interactions.
Structured rubrics, failure mode mapping, behavioral benchmarking, and reproducible feedback cycles grounded in UX research.
Authoring prompt frameworks that precisely control model tone, pacing, accuracy, and boundary adherence at scale.
Safety guardrails, dependency prevention, and quality thresholds for AI in emotionally sensitive and high-stakes domains.
The words an AI produces matter. So do the rules that shape when it speaks, how it paces itself, what it refuses, and why. I work on that layer. My background in psychology and UX design informs how I think about human behavior, and my experience in operations informs how I build things that actually scale. An AI product management certification rounds out how I think about the full lifecycle from research to deployment.
Before moving into AI and UX, I spent four years directing business operations at a global cybersecurity firm. The company grew 250% during that period, across multiple countries and U.S. states, and my job was to make sure the organization didn't break under that weight. I worked closely with executive leadership on budgets, resource allocation, and compliance, led SOC II audits, built workforce analytics dashboards, and cut hiring time-to-fill by 30% through process redesign.
That experience gave me a ground-level understanding of how enterprise teams operate, where processes fail, and what it takes to build systems that hold up beyond a slide deck. It is the lens I bring to every AI project.
