TECHNOLOGIST
25+ years building web platforms, APIs, and infrastructure. From bare-metal servers to serverless edge functions, whatever the problem demands.

I build AI-native companies, production agent systems and the memory layer that lets them keep learning across sessions, providers and machines.

25+ years across the stack. Founder and CTO of Inkie. I make complicated systems feel simple, useful and solid underneath.
25+ years building web platforms, APIs, and infrastructure. From bare-metal servers to serverless edge functions, whatever the problem demands.
Stand-up comedy. Finding the absurdity in technology, parenting, and the human condition. Timing is everything, in code and on stage.
Obsessive home cook. Fermentation, Maillard reactions, and the pursuit of the perfect roast. Food is just chemistry with better reviews.
CTO of Inkie. Building tools for creators, writers, and publishers. Shipping real products, not slide decks.
The Inkie workforce answers emails, creates marketing assets, runs market research, manages files and documents, supports GTM, PA work and analytics, and ships production software.
SEE HOW I CAN HELP →

I'd been looking into which AI classifiers were better for different jobs and writing benchmarks to compare them. Useful work, but I also wanted a way to show people what these models could do....
READ ARTICLE →
I spend quite a lot of time getting AI to write code. It turns out the agents were also spending quite a lot of time waiting for TypeScript. I've been so absorbed in AI that I've neglected some of...
READ ARTICLE →
I shared the quick version of this in today’s video. This is the bit that deserves more than sixty seconds. Anthropic has finally taught Claude Code a filename the rest of the coding-agent world...
READ ARTICLE →Long-term memory for AI agents. It remembers across sessions, providers and machines. Built live and used daily by a team of agents that ship real work.
The source is available now. Read it, run it and make it useful in your own agent stack.
The repository, setup notes and current implementation are all on GitHub.
VIEW ON GITHUB ↗