// Journal

Field notes from the build.

Playbooks, teardowns, and points of view on shipping production AI — LLM pipelines, RAG, agents, evaluation, and the operational work that keeps them honest.

POV May 25, 2026 8 min read

Harness engineering: build the test rig before the model

Most AI builds fail because the model ships before the harness that measures it. How we engineer evals, guardrails, and a repeatable delivery rig.
Read

More posts on the way. Subscribe for updates →

Field notes from the build.

Harness engineering: build the test rig before the model