AI Evaluation Rubric Builder
Define evaluation criteria for outputs, tool calls, retrieval quality, escalation behavior, and reviewer confidence.
Fill this onlineTemplate preview
The exact sections inside the download.
Accuracy
What must be correct, sourced, complete, and current?
Grounding
What evidence should the system cite or expose to the reviewer?
Tool behavior
Did the system call the correct deterministic tool with valid inputs?
Escalation
When should the system stop and route to a person?
Tone and fit
Does the output match the workflow, audience, and risk level?
Pass threshold
What score or defect pattern allows output to proceed?
01 / 03
Frame the decision
Name the real operating need before designing a solution.
Draft, summary, recommendation, classification, tool call, or answer.
Name who can judge quality and risk.
Describe what happens if weak output passes review.
How to use it
Start with one real decision.
Complete the canvas with the workflow owner, then use the blank areas to expose missing context and controls.