Posts

All the articles I've posted.

• pgvector vs the Vector DB Gold Rush

  9 May, 2023

  Most teams adding semantic search this year should start in the Postgres they already run, not a new vector database. Where pgvector holds, where it doesn't, and how to tell which side of the line you are on.

• Building a RAG Pipeline Before LangChain Was Cool

  18 Apr, 2023

  A production retrieval pipeline over a few hundred thousand internal documents, hand-rolled in early 2023. The model is the easy part. Retrieval is where the quality lives or dies.

• Your Recommendation Engine Doesn't Need Deep Learning (Yet)

  21 Mar, 2023

  Collaborative filtering and plain co-occurrence carried a marketplace recommender to hundreds of millions of recs a day. The exact point where deep ranking earned its complexity, and why most teams reach for it a year early.

• FinOps Is Just Capacity Planning With a Better Hat

  14 Feb, 2023

  Owning a large cloud P&L taught me that cost is an engineering-culture problem, not a dashboard. Where the tooling earns its keep and where it is theater.