--- sourceDocument: Australia Enable AI sourceDocumentLink: https://www.servicenow.com/docs/r/australia/intelligent-experiences Release : - australia ft:locale : - en-US ft:publication_title : - Australia Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # Health tab # Health tab in AI Control Tower {#ariaid-title1} Release version: Australia Updated March 12, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 2 minutes to read Summarize ![AI sparkle icon](https://servicenow.com/docs/portal-asset/ai-sparkle-icon) Summarized using AI This content was generated using new OpenAI-powered functionality. Results are provided on an as is basis and are not guaranteed to be accurate or complete. ## Summary of Health tab in AI Control Tower The Health tab in the AI Control Tower dashboard enables ServiceNow customers to monitor the performance of guardrails implemented via AI Guardian. This tab focuses on evaluating the effectiveness of guardrails designed to mitigate offensive content and prompt injection risks across AI assets. It provides real-time insights without considering historical data, allowing customers to apply date-range filters to analyze guardrail activity for specific skills. Show full answer Show less ## Key Features * **Latency Monitoring:** Displays average latency caused by offensive content and prompt injection guardrails, which can indicate the level of guardrail activity. * **Content Flagging Metrics:** Shows both the count and percentage of offensive content and prompt injection occurrences flagged during interactions with the large language model (LLM) service. * **Skill-Based Analysis:** Breaks down occurrences by skills, highlighting which AI skills are impacted by offensive content or prompt injection attempts over time. * **Category Breakdown:** Provides detailed categorization of offensive content occurrences by type, recognizing that content can belong to multiple offensive categories simultaneously. ## Practical Use for ServiceNow Customers By leveraging the Health tab, customers can: * Assess how effectively their offensive content and prompt injection guardrails are working and where guardrail activity is highest based on latency and flagged content metrics. * Monitor trends and spikes in offensive content or prompt injection attempts within specific AI skills, enabling targeted remediation or skill tuning. * Understand the nature of offensive content through category insights, helping prioritize guardrail enhancements or content moderation strategies. * Make informed decisions by filtering data within chosen date ranges to analyze recent or ongoing guardrail performance. ## Expected Outcomes Using the Health tab, ServiceNow customers can expect improved visibility into guardrail effectiveness, enabling proactive management of AI risks related to offensive content and prompt injection. This supports maintaining AI asset integrity, reducing unwanted content exposure, and optimizing AI-driven service interactions for compliance and safety. Monitor the performance of guardrails enabled through AI 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. Figure 1. Health tab in AI Control Tower 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. {#aict-health-tab__ul_ln1_nxr_bdc} 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 {#aict-health-tab__section_ppy_ztz_ggc} 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. Figure 2. Number of content items flagged 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. Figure 3. Percentage of content items flagged of total use ## Offensive content visualizations {#aict-health-tab__section_rrj_y5z_ggc} 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. Figure 4. Guardrail-added latency for offensiveness 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. Figure 5. Percentage flagged as offensive Total offensive content occurrences : This area of the dashboard shows the total number of offensive content occurrences for the selected skills and date range. Figure 6. Total 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 [AI Guardian](https://www.servicenow.com/docs/access?context=now-assist-guardian&version=australia&pubname=australia-platform-security&ft:locale=en-US). Figure 7. 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. Figure 8. Offensive content occurrences by skill ## Prompt injection visualizations {#aict-health-tab__section_o3k_dvz_ggc} 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. Figure 9. Guardrail-added latency for prompt injection 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. Figure 10. Percentage 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. Figure 11. 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. Figure 12. Prompt injection occurrences by skill