How can we build AI products that solve real problems, not just showcase capabilities?

I'm an AI product builder focused on turning messy workflows into practical systems people can use. My journey from sales to a Product Solutions Architect at Google was driven by a single question: "How can this be better?" Today, I work between product judgement, workflow design, and hands-on implementation.

At Google, I ideated and built an AI compliance pilot that achieved a 78% automatic reapproval rate and won the 2024 'Risk Taker' Award, not just for the technical solution, but for navigating the delicate balance between commercial enablement and platform safety. (See the full case study)

The Strategy: Useful AI products need active refinement, source quality, and clear failure handling. I use RAG Ops to benchmark LLMs across performance, latency, and cost. I use AI agents to move from concept to image-ready mockups where they speed up product thinking. I also build tools to clean and structure messy web data so RAG systems are fed higher-quality information.

How I Build: I work in a fast loop using custom agents for PRDs and technical plans, Cursor for building, and Vercel for deployment. I design RAG Operations around the trade-offs between model precision and response speed. I focus on specific high-friction challenges, then simplify the workflow once the useful path is clear.

Beyond enterprise work, I'm growing The Tenant's Voice, my own 0-to-1 AI social good project that helps users navigate complex legal systems. With 50+ daily active users and up to 90% success rates in deposit disputes, it's proof that production-grade AI can serve both business and social impact. (Explore my AI Product Lab)

I'm not a software engineer by trade; I'm a product builder who understands enough of the how to prototype, test, and simplify real systems. What happens when AI systems fail silently? How do we design for explainability from day one? These are the questions that drive my work.