// tag
#prompt-engineering
2 posts
-
Evals, Scores, and Prompt Receipts
Phases 37-38 of kodr: a scored eval command so model regressions surface as a number instead of a squint, and prompt versioning so every run can be traced back to the exact prompt that produced it.
#ai#kodr#local-models#agents#verification#prompt-engineering -
Context Is Just an Input
Phase 06 of kodr: build the workspace context for a prompt deterministically, then let yourself look at it before it ever hits the model.
#ai#local-models#agents#context#prompt-engineering#kodr