05 — Writing

Lab notes

Notes from the workbench — what I'm building, what broke, and what the numbers said.

July 20261 min read

Sample post

The moment I started drawing my agent workflows as state machines instead of 'loops with vibes', the bugs got boring — in the best way.

#agents#langgraph#architecture

May 20261 min read

Sample post

I assumed retrieval quality was about embeddings. Three rebuilds later: it's mostly about what you feed them.

#rag#retrieval#embeddings

March 20261 min read

Sample post

LLM-as-judge is cheap and useful — as long as you keep checking the judge. A few practices that kept my evals honest.

#evals#llm#testing

05 — Writing

Notes from the workbench — what I'm building, what broke, and what the numbers said.

July 20261 min read

Sample post

The moment I started drawing my agent workflows as state machines instead of 'loops with vibes', the bugs got boring — in the best way.

#agents#langgraph#architecture

May 20261 min read

Sample post

I assumed retrieval quality was about embeddings. Three rebuilds later: it's mostly about what you feed them.

#rag#retrieval#embeddings

March 20261 min read

Sample post

LLM-as-judge is cheap and useful — as long as you keep checking the judge. A few practices that kept my evals honest.

#evals#llm#testing