We explore what's possible with AI
and turn experiments into products.
Real tools solving real problems. Each project starts as an experiment and evolves into something useful.
Stop LLM regressions before they merge
The Problem
AI model regressions slip into production because there's no good way to test LLM outputs in CI.
The Solution
GitHub PR checks that validate your AI features before they merge. Deterministic tests, LLM-as-judge evals, zero infrastructure.
A mobile-friendly web interface for Claude Code CLI
The Problem
Claude Code runs in a terminal, which is great for focused work. But sometimes you need to step away—and Claude keeps working, needing permission or asking questions while you're not there.
The Solution
A real-time web interface to your Claude Code session. Watch Claude work, approve commands, answer questions, and send messages—all from your phone while you're away from your desk.
One person can now build what used to require entire teams.
We're proving that thesis—shipping real products, learning what works, and sharing what we discover. Every project is an experiment in what's possible when AI handles the heavy lifting and humans focus on vision, taste, and judgment.
I've spent two decades building products and engineering teams at startups. As VP of Engineering at BlueOwl, I scaled the team and launched a regulated insurance carrier in 18 months. Before that, I built systems at Humin (acquired by Tinder) and led infrastructure at Sparkart handling traffic for major entertainment brands.
Now I'm focused on what happens when AI meets software development. AOTP Ventures is where I explore that question—building real tools, shipping fast, and sharing what I learn along the way.
Interested in collaborating, investing, or just want to chat about AI?