Blog
Thoughts on frontend engineering, AI, design systems, and building things.
RAG, End to End: Building Reliable AI with Your Own Data
Large language models are trained on public data up to a cutoff date. They have no knowledge of your internal documentation, your product database, or last wee…
Agent Harnesses: The Infrastructure Your AI Needs to Actually Work
An LLM by itself is a text transformer. You give it tokens; it gives you tokens back. To make it do things — browse the web, write code, call APIs, update a da…
MCP: The Protocol Standardizing How AI Talks to the World
Every AI product eventually needs to talk to the outside world: read a file, query a database, call an API, search the web. Until recently, every team built th…
PRIME
Testing this for the content text