Configure an evaluation metric template

  • Release version: Zurich
  • Updated April 3, 2026
  • 1 minute to read
  • Adjust the scoring formula for a metric template to change which metrics contribute to quality or safety scores, or to change how much weight each metric carries.

    Before you begin

    Role required: sn_ai_governance.ai_steward

    About this task

    You can adjust a metric's influence on the score, add metrics previously tracked for visibility only, or remove metrics that aren't required by editing a metric template. Changes apply to new evaluation sessions only. Existing sessions keep the scores they were originally calculated with.

    For the full list of quality and safety metrics, see Evaluation metrics.

    Procedure

    1. Navigate to All > AI Control Tower > Home > Settings > Rules and templates > Evaluation.
    2. Select the Metric templates sub-tab.
    3. Select the metric template that you want to edit.
    4. Update the metric template as needed.

      For example:

      • Select the primary metric, which is required for every measure.
      • Adjust a metric's weight to increase or decrease its influence on the score.
      • Add a metric by selecting + Add metrics and assigning a weight.
      • Remove a metric from the formula.

      After any change, verify that all weights still sum to 100%.

      Note:
      Only metrics that are enabled for scoring on the AI evaluations page are available to add. See Activate evaluation scoring for ServiceNow AI systems and Activate evaluation scoring for external AI systems.
    5. Verify the updated formula by expanding the How is this score calculated? section.

    Result

    The updated formula is applied to new evaluation sessions. Scores on the monitoring overview reflect the updated formula as new data is collected.