Health tab in AI Control Tower

  • リリースバージョン: Australia
  • 更新日 2026年03月12日
  • 所要時間:6分
  • Monitor the performance of guardrails enabled through Now Assist Guardian.

    The Health tab in the AI Control Tower dashboard helps you monitor and evaluate the effectiveness of offensive content and prompt injection guardrails active on your ServiceNow AI assets.

    図 : 1. Health tab in AI Control Tower
    Health tab showing the metrics for offensive content and prompt injection guardrails.
    The visualizations on the Health tab provide the following insights.
    • Average latency as a result of active offensive content and prompt injection guardrails. High latency could mean increased guardrail activity in the period.
    • Count and percentage of offensive content and prompt injection occurrences.
    • Skills where offensive content and prompt injection occurrences were detected.

    The dashboard does not consider historical data for Health metrics.

    Apply the filters on the dashboard to view guardrail activity for skills in a date range.

    Content guardrail effectiveness

    Number of content items flagged
    This area of the dashboard shows the number of offensive content and prompt injection occurrences in the selected date range.
    図 : 2. Number of content items flagged
    Visualization showing the total number of content items flagged for offensiveness and prompt injection.
    Percentage of content items flagged of total use
    This area of the dashboard shows the percentage of requests and responses to and from the large language model (LLM) service that are flagged for offensiveness and prompt injection.
    図 : 3. Percentage of content items flagged of total use
    Visualization showing the percent of content items flagged for offensiveness and prompt injection.

    Offensive content visualizations

    Guardrail-added latency
    This area of the dashboard shows the average latency as a result of the active offensive content guardrail for the selected skills and date range.
    図 : 4. Guardrail-added latency for offensiveness
    Guardrail latency for offensiveness guardrail.
    Percentage flagged as offensive
    This area of the dashboard shows the percentage of requests and responses to and from the large language model (LLM) service that are flagged for offensive content.
    図 : 5. Percentage flagged as offensive
    Percentage of offensive content occurrences.
    Total offensive content occurrences
    This area of the dashboard shows the total number of offensive content occurrences for the selected skills and date range.
    図 : 6. Total offensive content occurrences
    Total number of offensive content occurrences.
    Categories of offensive content
    This area of the dashboard shows a breakdown of offensive content occurrences by the categories. If content is deemed to be offensive under more than one category, for example, toxic and defamatory, the occurrence is counted individually toward both the categories. For more information on offensive content categories, see .
    図 : 7. Categories of offensive content
    Visualization showing the categories of offensive content.
    Offensive content occurrences by skill
    This area of the dashboard shows the number of offensive content occurrences over time by the skills in which the content is detected.
    図 : 8. Offensive content occurrences by skill
    Offensive content occurrences by skill.

    Prompt injection visualizations

    Guardrail-added latency
    This area of the dashboard shows the average latency as a result of the active prompt injection guardrail for the selected skills and date range.
    図 : 9. Guardrail-added latency for prompt injection
    Visualization showing the guardrail-added latency
    Percentage flagged as prompt injection
    This area of the dashboard shows the percentage of requests and responses to and from the LLM service that are flagged for offensive content.
    図 : 10. Percentage flagged as prompt injection
    Visualization showing the percentage of requests and responses flagged as prompt injection.
    Total prompt injection occurrences
    This area of the dashboard shows the total number of offensive content occurrences for the selected skills and date range.
    図 : 11. Total prompt injection occurrences
    Total prompt injection occurrences.
    Prompt injection occurrences by skill
    This area of the dashboard shows the number of prompt injection occurrences over time by the skills where prompt injection attempts were detected.
    図 : 12. Prompt injection occurrences by skill
    Visualization showing the number of prompt injection occurrences by skill.