01
Recently we had some issues with flakey e2e tests, which turned out to be caused by the Puppeteer page.type method…
After many years of commuting to a city office in a 5 speed manual I came across the opportunity to…
Recently I was presented with the challenge of writing some file upload components for a single page app. There are…
02
Right now I’m deep in the weeds of agent reliability engineering – building systems that can recover gracefully when tool calls fail, context windows overflow, and models hallucinate mid-plan. The intersection of software engineering rigor and probabilistic AI is where the interesting problems live.
Agent Frameworks
Designing composable agent architectures that are debuggable, testable, and don’t collapse under real-world edge cases.
Model Evaluation
Building custom evaluation harnesses that measure what actually matters for specific engineering applications.
Infrastructure
The glue between models and production: caching, rate limiting, observability, and cost management at scale.
03
I’m an AI engineer based in New Zealand, working at the intersection of foundation models, agent systems, and production software. This blog is where I document what I learn – the techniques that work, the ones that don’t, and the thinking that goes into building AI systems that are actually reliable.
Previously I’ve worked across the full stack of web and software engineering. These days I’m focused on making the tooling around large language models better for the engineers building with them.