From restaurants to late nights teaching myself to code. From entry-level developer to VP of Product at JPMorgan. From automating tedious tasks with Python to shrinking my work with LLMs. Now building AI-native applications for real problems. Not fully product, not fully engineering; an ambitious balance of both.
A permission-aware context layer that turns an organization’s communications into structured, persistent memory — served to both the people and the agents doing the work.
A custom TypeScript MCP orchestrator that runs a self-closing build loop — agents hand off through a shared file with no human in the routing seat.
The accountable exit — what 3.5 years and four iterations actually taught me.
Found out my batch fit after the deadline passed. Applied anyway.
Why the right abstraction for a solo builder is removing yourself from the handoff.
I’m moving into an AI-native product role this year. If that’s the kind of person you’re hiring — or building with — reach out.
Get in touch