I design chatbots that don’t make people want to throw their phone.
In ten+ years of actual, hands-on experience designing for AI (starting with IBM's Watson in 2015), I've seen the hype cycles and the technology evolve — and somehow, incredibly, most conversational assistants still suck.
Why? Companies have rushed to ship chatbots with very little thought about what people actually experience when they use them. The tech might be there and the metrics might actually look good, but people still hate using it—and that frustration bleeds into how they feel about your entire organization. Is that fair? Probably not. But it’s real.
This is where I come in. I understand the nuts and bolts of conversational tools, but I also have a deep background in user-centered design, systems thinking, and branding. Because whether or not you realize it, your chatbot is a representation of your brand—and the foundation for your team’s future AI work.
What I’ve worked on
Education: Personalized tutoring assistant
Designed conversational guidance that helped college students ask better questions, stay engaged with material, and build confidence in their own reasoning instead of relying on answers alone.
Enterprise: Visa, IBM, & ADP internal chatbots
Defined conversation patterns, tone, and error-handling for internal assistants that support complex workflows, reduce repetitive questions to support teams, and respect employees’ expertise and autonomy.
Healthcare: Patient appointment scheduling
Shaped conversational flows for sensitive, high-stakes interactions where clarity, accessibility, and graceful recovery from errors were as important as speed.
Customer service: Real-time agent assist
Designed conversational behaviors and guidance that help live agents interpret AI suggestions in the moment, improving response quality without undermining (or replacing) human judgment.
Voice to digital: IVR self-service playbooks
Created playbooks and conversation patterns that determine when voice interaction is helpful, when to hand off to human agents, and when a traditional UI is the better choice.
Document intelligence: DocAI
UX audit, user research, and strategy for a chatbot that interprets internal policy documents for financial underwriters, uncovering the gap between model accuracy and human confidence and designing ways to surface evidence so people can verify results.
LLM evaluation & emotional intelligence research
Developed evaluation approaches and guidelines for enterprise chatbots that look beyond accuracy to tone, frustration handling, and long-term trust and adoption.
How I work
Research-driven
I talk to actual users, watch them interact with systems, and learn what they’re really trying to accomplish—not what we think they should be doing. I pay close attention to where trust breaks down in real conversations, instead of simply whether tasks technically complete.
Cross-functional collaboration
I can talk to engineers about token limits, context windows, hallucination patterns, and evaluation signals, translate for product teams about user needs and adoption risks, and help design teams adapt their existing skills for conversational systems.
Systems thinking
I’ve adapted foundational UX principles (like Nielsen’s heuristics) for conversational AI—accounting for probabilistic behavior, turn-taking dynamics, and trust calibration that don’t exist in traditional interfaces.
Practice-building
I don’t just design—I help teams build their own conversational design capability through frameworks, workshops, and knowledge transfer. The goal is for you to keep improving your conversational tools long after I’m gone.
Experience
Senior AI Design Consultant – Slalom / Capital One
Conversational and AI UX for an enterprise document intelligence platform, including heuristics, flows, and patterns to close the gap between model accuracy and user trust.
Conversational Architect – Amelia.ai (now SoundHound AI)
Designed text and voice agents in healthcare and service contexts, focusing on multi‑turn flows, error recovery, and safe escalation paths.
Product Designer – IBM (Watson & Cloud Garage)
Led design for early Watson AI products and later ran AI-focused design engagements with enterprise clients, defining conversational patterns, tone, and evaluation frameworks for chatbots and assistants.