Strategic case studies that show how I think through product risk, delivery constraints, stakeholder alignment, and measurable outcomes.
Solo-built AI assistant giving people affected by diabetes clear, source-backed answers drawn from curated medical literature. Uses a RAG pipeline with real-time streaming, a two-mode adaptive response system (Learning vs. Newly Diagnosed), and a four-layer safety architecture. Built as a deliberate product exercise in a domain where safety and trust requirements are substantially higher than a typical AI product.
Read case studySolo-built AI fitness coaching app for users from African, South Asian, East Asian, and Hispanic backgrounds. Designed, built, and shipped the full MVP to validate the hypothesis: if a fitness app personalises around cultural food heritage rather than Western defaults, it achieves meaningfully better activation. Live at fitforall.up.railway.app.
Read case studyLed 0→1 product strategy for an AI security platform helping enterprise teams detect prompt injection and unsafe model outputs before they hit customer-facing systems.
Read case studyOwned end-to-end lifecycle delivery across healthcare and payment products, balancing patient workflow constraints with financial transaction reliability.
Read case studySupported design and rollout of invoicing and recurring billing capabilities to reduce payment friction for growing SME merchants.
Read case study