--- sourceDocument: Yokohama Enable AI sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/yokohama/intelligent-experiences Release : - yokohama ft:locale : - en-US ft:publication_title : - Yokohama Enable AI ft:clusterId : - platai bundleId : - platai workflow : - Platform --- # AI Guardian analytics # AI Guardian analytics {#ariaid-title1} Release version: Yokohama Updated February 7, 2025 ![](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 AI Guardian analytics The AI Guardian analytics dashboard in the Yokohama release enables ServiceNow administrators to monitor and evaluate the performance and effectiveness of guardrails against offensive content and prompt injection in interactions with large language models (LLMs). This dashboard provides key insights into how these guardrails impact request processing, including latency and detection rates, helping ensure secure and appropriate AI usage within your environment. Show full answer Show less ## Key Features * **Latency Monitoring:** Tracks average latency added by offensive content and prompt injection guardrails, highlighting periods of increased guardrail activity that may impact response times. * **Detection Metrics:** Displays counts and percentages of requests flagged for offensive content and prompt injection, allowing admins to measure the frequency and extent of detected issues. * **Offensive Content Breakdown:** Provides a detailed categorization of offensive content occurrences by type (e.g., toxic, defamatory), with the ability to see if content falls into multiple categories. * **Skill-Level Analysis:** Shows occurrences of offensive content and prompt injection over time, broken down by individual skills, enabling targeted investigation and remediation. * **Filter and Date Range Controls:** Allows filtering the dashboard data by skills and date ranges for focused analysis of guardrail activity. ## Practical Benefits for ServiceNow Customers * Gain visibility into how guardrails affect LLM interactions, helping balance security with performance. * Identify specific skills prone to offensive content or prompt injection, enabling focused improvements and risk mitigation. * Understand the categories of offensive content detected to tailor guardrail policies appropriately. * Use latency insights to monitor any performance impact caused by guardrail enforcement and optimize accordingly. * Leverage comprehensive analytics to ensure AI implementations comply with organizational standards and reduce vulnerabilities. Monitor the performance of guardrails enabled through AI Guardian. The AI Guardian analytics dashboard helps admins monitor and evaluate the effectiveness of offensive content and prompt injection guardrails in tracking and analyzing requests sent to large language models (LLM) and their responses. Figure 1. AI Guardian dashboard page The indicators on the AI Guardian dashboard page 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. {#now-assist-guardian-analytics__ul_ln1_nxr_bdc} Apply the filters on the dashboard to view guardrail activity for skills in a date range. See [AI Analytics dashboard indicator details](https://servicenow-prod.fluidtopics.net/10BIescpPu5ytmjzKnX~gQ "Indicator details help you understand the data and calculations behind an indicator that is presented in the form of a visualization on the dashboard.") for information on the data and calculations behind each indicator. ## Offensive content indicators {#now-assist-guardian-analytics__section_wtv_nly_k2c} 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 2. Guardrail-added latency indicator Percentage flagged as offensive : 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 3. Percentage flagged as offensive indicator 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 4. Total offensive content occurrences indicator 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://servicenow-prod.fluidtopics.net/H0bVbM_NdghPjzLAF~OnJg#now-assist-guardian "AI Guardian is built on the ServiceNow Small Language Model (SLM) and monitors generative AI interactions to detect offensive content, prompt injection attacks, and sensitive topics."). Figure 5. Categories of offensive content indicator 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 6. Offensive content occurrences by skill indicator ## Prompt injection indicators {#now-assist-guardian-analytics__section_anw_4ly_k2c} 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 7. Guardrail-added latency indicator 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 8. Percentage flagged as prompt injection indicator 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 9. Total prompt injection occurrences indicator 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 10. Prompt injection occurrences by skill indicator