Designer. Builder. AI Enthusiast.
I didn't plan to end up at the intersection of design and AI. I just kept following the most interesting problem in the room.
I started as a graphic designer at a small edtech startup — just me, a CEO who thought in business terms, and a thousand things that needed to look good and work well. That gap between looking good and working well is what pulled me into UX.
And once I was in UX, AI pulled me further — not as a tool to outsource thinking, but as a medium to extend it. Seven years later, I design products that think alongside the people using them.
How I got here
Started as the only designer in the building. Learned that design without business context is decoration.
Built systems that made teams faster. Discovered that the best design work happens before the screen.
Worked on enterprise platforms where ambiguity was the default. Turned unclear briefs into clear problems.
First designer in the building — again. This time building AI products that reduce complexity for real users making real decisions.
What I Believe
AI is a thinking partner
Not a shortcut. The best use of AI in design is to question harder, not just move faster.
Clarity is the job
Before any screen gets designed, the problem needs to be clear. Most design failures happen upstream.
Build to learn
UXMantra exists because the best way to understand AI products is to build one.
Currently
- Working At:Finvasia — Senior Product Designer. Building sensAI and Jumpp.
- Building:UXMantra. AI-powered UX research assistant. In development.
- Interested In:AI Behaviour Design, System Prompt Design, Conversation Design, AI Red Teaming.
- Open To:Senior design roles at AI-focused companies and labs.
Beyond the work
I think seriously about how AI should behave — not just how it should look. That's pulled me toward AI behaviour design, system prompt design, and the question of what good AI interaction actually feels like.
I write about this on LinkedIn. I build experiments in my own time. And I use Claude to think harder about hard problems — which is either very meta or very practical, depending on how you look at it.