Field notes
Blog
Written by the engineers doing the work. Opinionated, occasionally wrong, always specific.
Data & AI
You cannot ship an LLM feature without an eval suite
Manual spot-checking does not scale past the demo. Offline evals are the difference between a prototype and a product.
11 min read
Data & AI
Retrieval quality beats model choice
Teams spend weeks comparing models and days on their retrieval pipeline. The ratio should be reversed.
9 min read
Data & AI
Why your data team spends its week firefighting
Untested transformations and undefined ownership produce a permanent incident queue.
6 min read
Ready when you are
Let's scope your next platform
Tell us what you are building. A principal engineer joins the first call — not a sales rep.