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.
Frame the operating decision
What must be correct, sourced, complete, and current? What evidence should the system cite or expose to the reviewer? Use the combined view to name the business outcome, source of truth, and owner who will decide whether to proceed.
Set the control boundary
Did the system call the correct deterministic tool with valid inputs? When should the system stop and route to a person? State the risk to avoid, review or escalation route, and record needed to keep the workflow controlled.
Commit to the first move
Does the output match the workflow, audience, and risk level? What score or defect pattern allows output to proceed? Record the smallest safe scope, baseline, owner, evidence, decision date, and next action.
Decision summary
What score or defect pattern allows output to proceed? Which failures require stopping the workflow? Summarize the proposed move, operating benefit, and the evidence that supports it.
Evidence and control
Which cases should be tested every release? State the source, review boundary, accountable owner, and condition that would require revision or pause. Keep the decision receipt with the workflow record.
Next review
Record the decision owner, evidence source, review date, and the explicit condition to scale, revise, defer, or stop. Confirm how the resulting decision will be communicated, implemented, and retained in the operating record.
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.