llm-as-a-judge

3 posts with the tag “llm-as-a-judge”

Beyond fuzzy text: turning LLM-as-a-judge into strongly-typed code with boul, choice, and score

Oct 7, 2026

Traditional LLM evals yield unstructured prose or require sprawling JSON schemas. Mizan introduces three strongly-typed decision primitives — boul, choice, and score — turning opaque eval SDKs into predictable developer code.

One spectrum, four users: from brand alignment to technical metrics

Sep 15, 2026

ghchinoy

Mizan maintainer

Four Mizan users sit on one spectrum, from "is this on-brand?" to "is this grounded and accurate?" The same machinery answers both. Only the criteria change.

Why evals, and what is an LLM-as-a-judge, really?

Sep 15, 2026

ghchinoy

Mizan maintainer

You already judge generative output by eye. An eval turns that private judgment into something explicit, repeatable, and shareable.