--- sourceDocument: Zurich Conversational Interfaces sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/conversational-interfaces Release : - zurich ft:locale : - en-US ft:publication_title : - Zurich Conversational Interfaces ft:clusterId : - convint bundleId : - convint workflow : - Platform --- # Self-Solve Performance page # Self-Solve Performance page in Assistant analytics {#ariaid-title1} Release version: Zurich Updated January 6, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 3 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 Self-Solve Performance page in Assistant analytics The Self-Solve Performance dashboard in Assistant analytics allows ServiceNow customers to analyze self-solve and deflection metrics, measuring the effectiveness of assistants in resolving user issues without live agent intervention. This dashboard aggregates key metrics such as self-solved events, deflection rates, and live agent transfers, enabling customers to monitor assistance effectiveness and identify areas for improvement. Show full answer Show less ## Key Features * **Total Deflection Events:** Displays the total user queries where deflection was attempted, providing insight into query volume. * **Total Deflections:** Indicates the number of queries successfully resolved by the assistant, highlighting successful interactions. * **Total Live Agent Transfers:** Shows how many conversations were escalated to live agents, allowing for tracking of trends over time. * **Deflection Rate:** Represents the percentage of interactions successfully deflected from live agents, calculated to benchmark assistant performance. * **Deflection Rate Over Time:** Tracks trends in deflection rates, helping to correlate performance changes with updates or external factors. * **Deflection Outcome Distribution:** Displays the breakdown of deflection attempts into categories (Resolved, Response Provided, No Response Provided, Not Resolved), aiding in understanding success rates. * **Deflection Types Offered:** Illustrates the distribution of different AI assets used for deflection, such as catalog items and knowledge articles. * **Effort Score:** Measures user effort levels across conversations, categorized as High, Medium, or Low, to assess the user experience during self-service interactions. ## Key Outcomes Utilizing the Self-Solve Performance dashboard allows ServiceNow customers to: * Monitor self-solve deflection rates effectively. * Identify trends in user interactions and assistant performance over time. * Recognize areas needing improvement to enhance user experience and reduce reliance on live agents. * Make data-driven decisions to optimize assistant behavior based on user feedback and performance metrics. Analyze self-solve and deflection metrics to measure how effectively assistants help users resolve issues without live agent intervention. The Self-Solve Performance dashboard page aggregates metrics related to self-solved events (instances where assistants resolved user queries), deflection rates, live agent transfers, and user effort. These metrics enable you to monitor resolution success, track deflection trends over time, and analyze the distribution of deflection outcomes. The insights from these metrics support targeted improvements to assistant behavior and help reduce the need for live agent support. Figure 1. Self-Solve Performance dashboard page in Assistant analytics The visualizations on the Self-Solve Performance page help you with the following. * Monitor self-solve deflection rates to identify how often users resolve issues without live agent assistance. * Track deflection trends over time to evaluate the impact of assistant updates and optimizations. * Analyze user effort scores and deflection outcome distributions to guide improvements in user experience. {#self-solve-performance-page-in-assistant-analytics__ul_dvn_hvk_whc} Total Deflection Events : This area of the dashboard shows the total number of user queries in the selected date range that have the potential of being deflected. Use this metric to understand the overall volume of queries where deflection was attempted.Figure 2. Total Deflection Events Total Deflections : This area of the dashboard shows the number of user queries successfully deflected by the assistant. This count indicates the number of interactions where deflection outcome was Resolved. The deflection can be attributed to AI agent, skill, topic execution or a positive feedback provided by the user.Figure 3. Total Deflections Total Live Agent Transfers : This area of the dashboard shows the number of conversations transferred to a live agent during the selected period. The percentage change from the previous period helps you track whether transfers are increasing or decreasing over time. Use this metric to identify opportunities to improve assistant capabilities and reduce the need for human intervention.Figure 4. Total Live Agent Transfers Deflection Rate : This area of the dashboard shows the overall percentage of interactions where users were successfully deflected from contacting a live agent. This is calculated using: ((Total number of self-solved events)/(Total number of events)) x 100.A higher deflection rate indicates that the assistant is effectively helping users find solutions independently. Use this metric to benchmark assistant performance and track improvements over time. Figure 5. Deflection Rate Deflection Rate Over Time : This area of the dashboard tracks the deflection rate as a trend line across the selected date range. Hover over the trend line to view the deflection rate on a given day. This chart helps you identify periods of improvement or decline in deflection performance and correlate changes with assistant updates or external factors.Figure 6. Deflection Rate Over Time Deflection Outcome Distribution : This area of the dashboard shows the distribution of outcomes for deflection attempts. The chart displays breakdown of Resolved, Response Provided, No Response Provided events, helping you understand how often deflection attempts lead to successful resolution. * Resolved: conversations where at least one AI asset, for example, AI agent, skill, topic was executed or a positive feedback was provided by the user * Response Provided: conversations involving small talk or where the assistant provided a synthesized response with no further action from the user * No Response Provided: conversations where no response was provided by the assistant * Not Resolved: conversations where negative feedback was provided by the user or the query was escalated to a live agent {#self-solve-performance-page-in-assistant-analytics__ul_mjs_gls_whc} Figure 7. Deflection Outcome Distribution Select a segment in the pie chart to drill down to the Deflection Details page and view conversations associated with that outcome. See [Deflection details page in Assistant analytics](https://www.servicenow.com/docs/qXZglrgl6WSnTtiMkj9s3A "View detailed insights into how your assistants resolve user queries, including deflection outcomes and the types of deflection methods used.") for more information. Deflection Types Offered : This area of the dashboard shows the distribution of AI assets offered as deflection methods to users. For example, catalog item, synthesized response, knowledge article, and so on. Use this chart to understand which deflection methods are being employed and evaluate their relative usage.Figure 8. Deflection Types Offered Select a segment in the pie chart to drill down to the Deflection Details page and view conversations associated with that deflection type. See [Deflection details page in Assistant analytics](https://www.servicenow.com/docs/qXZglrgl6WSnTtiMkj9s3A "View detailed insights into how your assistants resolve user queries, including deflection outcomes and the types of deflection methods used.") for more information. Effort Score : This area of the dashboard tracks user effort levels across conversations in the selected date range. Effort is categorized as High, Medium, or Low, indicating how much time and energy users needed to invest during the conversation to resolve their issues. Lower effort scores suggest a smoother self-service experience. Use this chart to help identify trends in user effort over time and prioritize improvements that reduce friction in the self-solve process. Effort score is based on the inferred Effort CSAT (customer satisfaction) factor. See [Conversation Insights](https://www.servicenow.com/docs/access?context=conversation-insights&version=zurich&pubname=zurich-intelligent-experiences&ft:locale=en-US) for more information.Figure 9. Effort Score