01Noul
inspect: candidateOutput, reference
01 INPUT
What should be evaluated?
Provide the input, candidate response, and reference evidence as JSON.
Leave blank to use the deployed workspace key. A pasted key stays in this browser tab and is never exported.
02 Questions
Atomic evaluators
02Choice
inspect: candidateOutput, reference
03Score
inspect: candidateOutput, reference
04LLM judge
inspect: candidateOutput, reference
03 Results
Normalized evidence
Run the suite to compare calibrated decisions and structured critique.