Skip to content
Courses/AI Router and content system/Quality scoring without hype

Quality scoring without hype

A router improves when you record which output was good, bad, or uncertain. Without scoring, you only have intuition.

Minimum score

TerminalCode
score:
  factuality: 1-5
  usefulness: 1-5
  format: 1-5
  safety: pass|fail
  needs_human: true|false
  reason: "invented citation in the second paragraph"

Who scores

  • Deterministic rules: valid JSON, complete fields, citations present.
  • Automatic evals: compare against expected cases.
  • LLM-as-judge: useful for triage, not as absolute truth.
  • Human: required for editorial, legal, financial, or reputational content.

Official source

Langfuse documents traces, evaluation, datasets, and scores for self-hostable LLM applications: https://langfuse.com/docs/observability/overview