Brands I worked with
About
Fourteen years turning creative ideas into production systems.
I started out hand-coding interactive ad experiences for Fortune 500 brands and spent more than a decade across ad tech and fintech. Today I build AI-native content pipelines and the tooling creative teams actually use.
More about me
Experience
AI Platform Engineer & Founder
Building an AI-native media company and the tooling behind it: multi-agent content pipelines, an MCP connector platform, and a publishing stack engineered for AI search.
2024 - Present
Sr. UI/UX Developer & Project Manager
Built front-end components and handled creative compliance for the marketing team, then led the revamp of the firm's internal sales CRM.
2023 - 2024
Sr. Front End Developer
Built responsive React interfaces for blockchain and digital-asset platforms with integrated internal APIs, and managed the HubSpot CMS for marketing landing pages.
2023
Sr. Front End Developer
Built dynamic creative frameworks tied to campaign KPIs that lifted conversion 30%, and shipped an A/B testing framework that cut prototyping time 50%.
2020 - 2023
Sr. Creative Developer / Client Solutions
Built interactive brand campaigns for Fortune 500 advertisers including HBO, Audi, Marvel, Delta, and Porsche, shipping high-impact creative across premium publishers.
2014 - 2020
Creative Development Manager
Media Operations Manager
Junior Engineer
Rebuilt the company's responsive template system and trained a global creative production team, driving a 65% increase in mobile conversions.
2013 - 2014
2012 - 2013
2012
Builders Log
Building a Commit Guard for AI Agents That an Adversary Can't Slip Past
I gave a coding agent a guard that checks every commit lands in the repo and branch I intend. My 417 tests were all green. Then I hired a second agent to break it, and it walked through two holes the green suite never thought to check.
Graph Engineering Makes Agent Failure Legible, Not Agents Reliable
A video making the rounds argues graph engineering supersedes the loop-based agent pattern. After building multi-agent systems, I think the loop-versus-graph framing asks the wrong question. Topology decides whether you can SEE a failure, not whether one happens. Reliability lives in the deterministic checks at the edges, not in how you wire the agents.
Claude Desktop vs Cowork vs Code: A Beginner's Roadmap to Which One to Use
Claude Desktop, Cowork, and Code look interchangeable. The real difference is what survives when the session ends, and that decides which one to build in.
Let's build something.
Advisory and hands-on builds for teams putting AI into production.