Product leader building at the intersection of human behavior and machine learning. Currently exploring AI product judgment, UX intuition, and strategic thinking.
Three high-level teardowns evaluating where AI tools create genuine user magic vs. friction, with concrete product recommendations.
Prompt → running full-stack app (frontend + backend + DB) in a WebContainer. No local setup. WebContainer tech runs Node.js in the browser — real npm, real Vite, real Supabase/Postgres. You get a URL that works. S...
AI-first code editor that replaces your workflow, not just your autocomplete. Tab-to-accept multi-line edits across files; Composer mode spins up entire features from a prompt; @-mentioning files/do...
Prompt → production React code. The shortest path from 'I need a dashboard' to 'it's deployed.' Shadcn/UI + Tailwind defaults mean every output looks production-ready instantly. Iteration loop: 'make the sidebar coll...
Evidence-backed roles, scope, and outcomes. Focus on taste, product intuition, and AI collaboration over pure execution.
Led 8-person team owning the core AI platform (models, tooling, evals) for 50M+ MAU product. $2M annual model budget. Shipped 3 major model upgrades, 40% latency reduction, 25% cost reduction. Outcome: Launched in-house eval framework adopted org-wide; reduced hallucination rate from 12% → 3% on critical paths; built PM-facing dashboard for model quality tracking.
Owned developer experience for 500k+ developers. 12-person team across CLI, SDKs, docs, and API platform. $1.5M budget. Shipped v2 API, new CLI, interactive tutorials. Outcome: API v2 adoption 80% in 6 months; CLI downloads 3x; 'Time to First Hello World' from 45 min → 3 min; NPS +34.
Experimental electronic artist — calculated late-night tension. Tech house grit meets deep electronic atmospheres. Direct support for NIIKO X SWAE, TWINSICK.
ENTER CONTROL_ROOMProduct leader with a focus on human-AI interaction, product judgment, and building tools that amplify human agency. This portfolio demonstrates analytical teardowns of AI products rather than showcasing design or coding execution — the goal is to show how a product thinker evaluates where machine learning creates genuine user value versus where it introduces friction.
Previously: [background]. Based in ATX.