Building a Multimodal AI Agent
That Tripled Conversion.
Led 0→1 design through engineering handoff
As the only designer in T-Mobile's AI Innovation Lab, I designed its first agentic AI assistant from concept to engineering handoff. It is now rolling out on web, iOS, and Android. I owned the conversational UX, the design system, and the framework we used to grade the AI's answers.
Switching carriers is overwhelming
65% of customers called switching to T-Mobile a hassle. Even with digital support, 80% still finished the switch in a store. People didn't need more information. They needed guidance.
There's too much to figure out on my own.
Research participant · switching study
I just want someone to tell me what's right for me.
What we set out to do
Goals for the redesignAn assistant that guides, not a search box that responds
Voice-led multi-modality
As the conversation moves, the interface follows. Visuals, options, and structure surface only when they help. People talk to it. They don't manage it.
It already knows what you're looking at
The assistant sees the same screen you do, so you never have to re-explain. Say "compare these two" or "is this one on sale for me?" and it picks up the context, surfaces the right options, and starts the upgrade for you.
Clarify by tapping, not typing
Typing out an answer to every follow-up question gets tedious fast. So the assistant asks them as a quick quiz instead: tap to answer. It learns the same things with a fraction of the effort.
What the MVP test changed
I shipped an MVP, watched how people used it, then redesigned what the data exposed. Each pair reads left to right: the problem, then the fix.
I owned how good the AI actually was
A great chat UI means nothing if the answer is wrong. I built the evaluation and red-teaming that made the answers trustworthy.
Measure it before we ship it
I built a red-team set of 300+ real customer questions and scored every answer against real plan data. It caught wrong prices, missing discounts, and invented benefits before a customer ever saw them.
Rules that keep answers honest
Every failure became a principle the model and the UI both follow, so the assistant stays accurate, admits what it doesn't know, and stays easy to read.
Real failures the evaluation caught, and how the fixed response reads.
One assistant, three platforms, one system
A calmer path to a confident decision
Won executive approval to ship. The work scaled org-wide
and led T-Mobile to stand up a dedicated AI design team.
Soojin bridged our AI and Product organizations and set the standard for how design leads at the intersection of the two.
