May 20, 2026
Why we use TypeScript for every AI integration we build
Untyped LLM responses are a liability. Here is how we handle the contract boundary.
Blog
Writing on AI systems, product, and engineering.
May 8, 2026
Building reliable LLM pipelines: eleven systems, one lesson
Across eleven production AI systems, one pattern shows up every time a pipeline fails.
April 26, 2026
The case for server-rendered AI dashboards
Most AI dashboards are built as SPAs. Most of them load too slowly and rank nowhere.