Online vehicle trade-ins often involve long, multi-step forms that can be tedious and error-prone. It is hypothesized that a conversational digital avatar could streamline the process by collecting trade-in data in a more natural and engaging way than a multi-step form. It is also hypothesized that this...
Experiences should adapt to the user’s device of choice. Before this experiment got away from me, I made a point to regularly pause and check that the foundational UI I was vibing in Cursor would scale gracefully across iOS phones and tablets—both in landscape and portrait orientations.
I’ve been exploring a problem space in the automotive industry for a few years now—long before AI entered the spotlight. What started as a client-led Design Thinking project that ultimately stalled became a personal pursuit. After the client engagement ended, I continued the investigation on my own, initially applying classical product design methods to draft a PRD. Recently, I’ve returned to the project, now leveraging AI to push the work further.
Rushing to high-fidelity models in today's AI-driven world is a smart thing to do. When potential risk to user adoption demands taking a more deliberate and methodical approach to the work at hand, AI can still be exploited to investigate content strategy and user interface pattern opportunities.
I've been following the vibe coding threads online, but until now, I've only been dabbling here and there. This was my first serious experiment at vibe coding. It's a multipart experiment with this first part focusing on using ChatGPT to assist in the the setup of Windsurf (and XCode).
After exhaustive research and experimentation, I have yet to come across an AI agent or SaaS platform that can arrest and visualize complex, conditionally-saturated funnels with any reliable detail or consistency while adhering to established best practices.
Modeling human decision-making in task-heavy experiences is often a daunting and intimidating task for most designers. Early in my career, I learned best practices for arresting and visualizing complex branching logic and I still rely on those best practices today. I have yet to experience an AI agent or tool that can accurately mirror complex branching logic with any level of reliable detail. In fact, the AI tools I experimented with consistently achieved mild mediocrity and never consistency.
Nothing will ever beat talking to human beings. Not even AI. But, lately I’ve been exploring new ways to bring user voices into the room—especially when the room is full of stakeholders. And not just quotes on a slide. I mean really bringing users to life.