https://ghchinoy.github.io/mizan/https://ghchinoy.github.io/mizan/blog-series/https://ghchinoy.github.io/mizan/blog/https://ghchinoy.github.io/mizan/blog/01-why-evals/https://ghchinoy.github.io/mizan/blog/02-one-spectrum-four-users/https://ghchinoy.github.io/mizan/blog/2/https://ghchinoy.github.io/mizan/blog/03a-per-persona-playbooks-part-1/https://ghchinoy.github.io/mizan/blog/03b-per-persona-playbooks-part-2/https://ghchinoy.github.io/mizan/blog/04-5-turn-a-writing-skill-into-an-eval/https://ghchinoy.github.io/mizan/blog/04-contribute-a-template-pack/https://ghchinoy.github.io/mizan/blog/05-developing-for-mizan/https://ghchinoy.github.io/mizan/blog/authors/ghchinoy/https://ghchinoy.github.io/mizan/blog/tags/adaptive-rubrics/https://ghchinoy.github.io/mizan/blog/tags/architecture/https://ghchinoy.github.io/mizan/blog/tags/brand-alignment/https://ghchinoy.github.io/mizan/blog/tags/contributing/https://ghchinoy.github.io/mizan/blog/tags/eval-sets/https://ghchinoy.github.io/mizan/blog/tags/evals/https://ghchinoy.github.io/mizan/blog/tags/getting-started/https://ghchinoy.github.io/mizan/blog/tags/llm-as-a-judge/https://ghchinoy.github.io/mizan/blog/tags/personae/https://ghchinoy.github.io/mizan/blog/tags/rubrics/https://ghchinoy.github.io/mizan/blog/tags/templates/https://ghchinoy.github.io/mizan/guides/agent-skills/https://ghchinoy.github.io/mizan/guides/llm-as-judge-scenarios/https://ghchinoy.github.io/mizan/guides/roadmap/https://ghchinoy.github.io/mizan/guides/stax-interop/https://ghchinoy.github.io/mizan/guides/testing-guide/https://ghchinoy.github.io/mizan/guides/user-guide/https://ghchinoy.github.io/mizan/reference/0001-metric-format/https://ghchinoy.github.io/mizan/reference/architecture-final/https://ghchinoy.github.io/mizan/reference/collaboration-design/https://ghchinoy.github.io/mizan/reference/implementation-plan/https://ghchinoy.github.io/mizan/reference/research/https://ghchinoy.github.io/mizan/reference/spikes/