--- sourceDocument: Australia Conversational Interfaces sourceDocumentLink: https://www.servicenow.com/docs/r/australia/conversational-interfaces Release : - australia ft:locale : - en-US ft:publication_title : - Australia Conversational Interfaces ft:clusterId : - convint bundleId : - convint workflow : - Platform --- # Voice page # Voice page in assistant analytics {#ariaid-title1} Release version: Australia Updated August 25, 2026 ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 14 minutes to read Monitor the performance of voice assistants from the Voice page of Assistant analytics in Assistant Designer. The Voice page shows performance metrics for your voice assistants, organised across four tabs: Overview, Performance, Insights, and Assist consumption. Use these tabs to monitor conversation volume, resolution rates, tool execution, authentication performance, conversation quality signals, and AI agent assist usage. Figure 1. Voice page in Assistant analytics You can filter the data on all tabs using the following options: * Filter by voice assistant: View metrics for specific voice assistants. * Filter by language: View metrics by conversation language, such as English, German, Spanish, and so on. * Filter by communication channel type: View metrics by channel, such as phone, mobile app - iOS, mobile app - Android, or web browser. * Filter by date range: View metrics for a predefined period, such as last 7 days or last 30 days, or select a custom start and end date using the date picker. {#voice-assistant-analytics__ul_rdf_dwv_j3c} Scorecard widgets display a trend indicator below the metric value, showing the change in value compared to the equivalent previous period. The indicator includes the absolute change, the percentage change, and the comparison date range. Note: The intent and resolution metrics on this page depend on the intents and resolution criteria you define in the Asset library of AI Admin Center. To set them up, see [Create an intent in AI Admin Center (Lux UI)](https://www.servicenow.com/docs/access?context=ai-admin-center-lux-create-intent&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). Metrics marked with the AI Inferred tag are calculated through large language model (LLM) transcript analysis. Results may vary and may not be fully accurate. Review AI Inferred metrics before acting on them. ## Overview tab {#voice-assistant-analytics__section_overview_tab} The Overview tab shows high-level conversation volume, resolution performance, and AI voice agent activity for the selected date range. Total voice conversations : This area of the dashboard shows the total number of voice conversations in the selected date range. Select the chart view to see how conversation volume has changed over the selected date range. Use this metric to track growth in voice interactions and set benchmarks for assistant performance. Select Related records to view the underlying records. Figure 2. Total voice conversations Resolution rate (%) : This area of the dashboard shows the resolution rate for voice conversations. Only conversations with at least one detected intent are included. Conversations with no detected intent are not counted. A conversation is counted as resolved only when every intent in it was completed. If even one intent is not completed, the entire conversation is counted as unresolved. Intents and their resolution criteria are defined in the Asset library of AI Admin Center. See [Create an intent in AI Admin Center (Lux UI)](https://www.servicenow.com/docs/access?context=ai-admin-center-lux-create-intent&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). The dashboard shows a breakdown of resolved conversations in two categories: * Resolved by AI: conversations resolved entirely by the AI voice agent, with no human involvement. * Resolved by live agent after transfer: conversations that required a live agent to complete at least one intent. {#voice-assistant-analytics__ul_res_rate_breakdown} These two categories are mutually exclusive and together account for all resolved conversations. Select the chart view to see how the resolution rate has changed over the selected date range. Select Related records to view the underlying records. Figure 3. Resolution rate (%) Live agent transfer rate (%) : This area of the dashboard shows the percentage of conversations transferred from the voice assistant to a live agent in the selected date range. Use this metric to identify common escalation triggers and optimise assistant workflows to reduce unnecessary transfers. Select the chart view to see how the transfer rate has changed over the selected date range. Select Related records to view the underlying records. Figure 4. Live agent transfer rate (%) Additional conversation outcomes : This area of the dashboard shows conversation outcomes beyond resolution and live agent transfer. Immediate outcomes refer to events occurring within the first 30 seconds of the call.The table includes the following columns: Outcome, Conversation count, Conversation change, and Percent of total conversations. Outcomes tracked include: * Immediate live transfers: conversations where the caller requested transfer to a live agent within the first 30 seconds. * Immediate disconnects: conversations that disconnected within the first 30 seconds. * Session expiration: conversations that ended due to session timeout. * Ticket created: conversations that resulted in a ticket created for follow-up. Only incidents and service requests are included. {#voice-assistant-analytics__ul_conv_outcomes} Figure 5. Additional conversation outcomes The Conversation mechanics widgets show how voice conversations unfold during the selected date range. Average handle duration (with voice assistant) : This area of the dashboard shows the average duration of the AI-handled portion of voice conversations, excluding time spent with a live agent after transfer. Duration is measured using a single call duration event per call. Use this metric to identify opportunities to streamline conversations and reduce resolution time. Figure 6. Average handle duration (with voice assistant) Average turns : This area of the dashboard shows the average number of turns taken by the voice assistant per voice conversation in the selected date range. A turn is counted each time the voice assistant speaks. Use this metric to assess how efficiently the assistant resolves user requests. Figure 7. Average turns Average CSAT score : This area of the dashboard shows the average customer satisfaction (CSAT) score for voice conversations in the selected date range. CSAT scores are captured through your own post-conversation survey solution. Conversations with no score are excluded from the average. Select Related records to view the underlying records. Figure 8. Average CSAT score AI voice agent performance : This area of the dashboard shows a breakdown of conversation count, resolution rate, and AI resolution rate by invoked AI agents. Use this table to identify high-performing agents and improve underperforming ones.The table includes the following columns: * Voice AI agent: name of the AI voice agent. * Conversations: total number of conversations the agent took part in. * Conversation change: change in conversation count compared to the previous period. * Resolution rate (%): percentage of the agent's conversations where all detected intents were completed. * Resolved by AI (%): percentage of the agent's conversations that were fully resolved with no human involvement. {#voice-assistant-analytics__ul_aivap_cols} Note: Resolution rate in this table uses the same intent-based calculation as the Resolution rate scorecard. Only conversations with at least one detected intent are included. If a call involved more than one AI agent, it appears in each agent's row. Figure 9. AI voice agent performance ## Performance tab {#voice-assistant-analytics__section_performance_tab} The Performance tab shows response time, authentication performance, and tool execution metrics for the selected date range. Figure 10. Performance tab Response Time Time from when a user finishes speaking to when the voice assistant responds. Figure 11. Response time scorecards Response time (50th percentile) : Response time within which 50% of voice assistant responses were completed. This is measured from when the user finishes speaking to when the voice assistant responds. Only 50% of responses took longer than this time. Select Related records to view the underlying records. Response time (90th percentile) : This area of the dashboard shows the response time within which 90% of voice assistant responses were completed. Only 10% of responses took longer than this time. Select Related records to view the underlying records. Response time (99th percentile) : This area of the dashboard shows the response time within which 99% of voice assistant responses were completed. Only 1% of responses took longer than this time. Select Related records to view the underlying records. Guest authentication Number of interactions with successful and failed guest authentication. Successful means the caller was authenticated at any point in the interaction. Failed means every authentication attempt was unsuccessful. Guest authentication : This area of the dashboard shows guest authentication outcomes as a donut chart. A daily bar chart shows how successful and failed authentication attempts trended over the selected date range. Select Related records to view the underlying records. Figure 12. Guest authentication Guest authentication time Time from the first voice AI identification question until the authentication API call response. Use the outcome selector to filter results by all attempts, successful, or failed. Figure 13. Guest authentication time scorecards Guest authentication time (50th percentile) : This area of the dashboard shows the time within which 50% of guest authentication sequences were completed. Use the outcome selector to filter results by Successful, Failed, or all authentication attempts. Select Related records to view the underlying records. Guest authentication time (90th percentile) : This area of the dashboard shows the time within which 90% of guest authentication sequences were completed. Only 10% took longer than this time. Use the outcome selector to filter results by Successful, Failed, or all authentication attempts. Select Related records to view the underlying records. Guest authentication time (99th percentile) : This area of the dashboard shows the time within which 99% of guest authentication sequences were completed. Only 1% took longer than this time. Use the outcome selector to filter results by Successful, Failed, or all authentication attempts. Select Related records to view the underlying records. Tool executions How many times each type of tool was used. Execution count by tool type : This area of the dashboard shows the total number of tool executions across voice conversations, broken down by tool type. Select the chart view to see how execution counts have changed over the selected date range. Use this metric to understand which tools are most frequently invoked during voice conversations. See [Add tools and information to an AI agent](https://www.servicenow.com/docs/access?context=add-tool-aia&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US) for information on tool types. Figure 14. Execution count by tool type Tool time Time required for the voice assistant to complete actions using tools. Figure 15. Tool time scorecards Tool execution time (50th percentile) : This area of the dashboard shows the tool execution time within which 50% of tool executions were completed. Select Related records to view the underlying records. Tool execution time (90th percentile) : This area of the dashboard shows the tool execution time within which 90% of tool executions were completed. Only 10% of executions took longer than this time. Select Related records to view the underlying records. Tool execution time (99th percentile) : This area of the dashboard shows the tool execution time within which 99% of tool executions were completed. Only 1% of executions took longer than this time. Select Related records to view the underlying records. Tool Performance : This area of the dashboard shows performance broken down by individual tool. Success % reflects the share of executions that completed without error. P50, P90, and P99 represent execution time percentiles in seconds.The table includes the following columns: * Type: the tool type. Supported types are Flow actions, Scripts, Subflows, and RAG-based search. * Tool: the name of the specific tool invoked. * Success rate: the percentage of executions that completed without error. * P50 Time (s): median execution time in seconds. * P90 Time (s): 90th percentile execution time in seconds. * P99 Time (s): 99th percentile execution time in seconds. {#voice-assistant-analytics__ul_tool_perf_cols} Figure 16. Tool Performance ## Insights tab {#voice-assistant-analytics__section_insights_tab} The Insights tab shows intent tracking data and conversation quality signals. Intent tracking data is based on the intents you define in the Asset library of AI Admin Center. The conversation quality signals are measured through large language model (LLM) transcript analysis. Intents What customers are calling about and how each intent performs. Displayed metrics are tracked per intent, not per conversation. A single conversation can include several intents. Note: The intents in this section, and their resolution criteria, are the ones you define in the Asset library of AI Admin Center. To set them up, see [Create an intent in AI Admin Center (Lux UI)](https://www.servicenow.com/docs/access?context=ai-admin-center-lux-create-intent&version=australia&pubname=australia-intelligent-experiences&ft:locale=en-US). Intent breakdown : This area of the dashboard shows how often each intent was detected and how well it was resolved in the selected date range. Use this table to identify intents with low resolution rates or high live agent transfer counts and focus assistant improvement efforts on those areas. The table includes the following columns: * Intent name: the intent detected during the conversation. Select View source records to view the underlying records for a specific intent. * Detected count: the number of times this intent was detected. * Intent resolution rate: the percentage of detections where this intent was resolved. * % Resolved by AI: the percentage of detections resolved by the AI agent with no human involvement. This percentage uses total detections as the denominator, not resolved detections. It is always less than or equal to the intent resolution rate for the same intent. * Live Agent Transfer: the percentage of detections that resulted in a transfer to a live agent. {#voice-assistant-analytics__ul_intent_breakdown_cols} You can search the table by intent name and sort by any column. Detections with no matching intent reference are grouped into a single row labelled No intent detected. Note: Resolution rate in this table is measured at the intent level. A session with two intents where only one was resolved counts as unresolved on the Resolution rate scorecard on the Overview tab, but contributes to the resolution rate for the completed intent in this table. Figure 17. Intent breakdown Percent of conversations with multiple intents (%) : This area of the dashboard shows the percentage of voice conversations in which more than one intent was detected. Use this metric to understand how often callers raise multiple issues in a single call and whether your assistant handles multi-intent conversations effectively. Select Source records to view the underlying records. Figure 18. Percent of conversations with multiple intents (%) Percent of conversations with no intents detected (%) : This area of the dashboard shows the percentage of voice conversations in which no intent was detected. These sessions are excluded from resolution rate calculations. Use this metric to identify whether callers are reaching the assistant without a recognised intent, which may indicate gaps in intent coverage or issues with intent detection. Select Source records to view the underlying records. Figure 19. Percent of conversations with no intents detected (%) Conversation insights Key sentiment signals from voice conversations, measured through large language model (LLM) transcript analysis. Metrics in this section are marked with the AI Inferred tag. Select the chart view on any widget to see how each signal has changed over the selected date range. User effort required with AI agents : This area of the dashboard tracks how much effort a user had to put in during a conversation, based on signals like transfers, wait times, and escalations. Scored as Low, Medium, or High. This is measured through large language model (LLM) transcript analysis. Select Related records to view the underlying records. Figure 20. User effort required with AI agents AI agent empathy : This area of the dashboard measures how politely and attentively the agent acknowledged the user's needs and concerns throughout the conversation. Scored as Low, Medium, or High. This is measured through large language model (LLM) transcript analysis. Select Related records to view the underlying records. Figure 21. AI agent empathy User / AI agent confusion : This area of the dashboard indicates whether the agent misunderstood or failed to interpret the user's intent at any point in the conversation. Scored as Yes or No. This is measured through large language model (LLM) transcript analysis. Select Related records to view the underlying records. Figure 22. User / AI agent confusion User frustration with AI agents : This area of the dashboard indicates whether the user expressed frustration, through complaints, sarcasm, or dissatisfaction, during the conversation. Scored as Yes or No. This is measured through large language model (LLM) transcript analysis. Select Related records to view the underlying records. Figure 23. User frustration with AI agents ## Assist consumption tab {#voice-assistant-analytics__section_assist_consumption_tab} Note: The data on this tab is for informational purposes only and should not be relied upon as a definitive statement of your AI usage for billing purposes. The Assist consumption tab shows AI agent assist usage metrics for the selected date range. An assist is recorded each time an AI voice agent completes an action during a conversation. Assists are categorised into three tiers based on the number of actions taken by the voice agent: Small, Medium, and Large. Total assists consumed : This area of the dashboard shows the total number of assists consumed by AI voice agents in the selected date range. A daily chart alongside the scorecard shows how assist consumption has changed over time. Select Related records to view the underlying records. Figure 24. Total assists consumed Total assists consumed over time : This area of the dashboard shows how the total number of assists consumed by AI voice agents has changed over the selected date range. Hover over a date to view the number of assists consumed for that date. Figure 25. Total assists consumed over time Total assists consumed by tier : This area of the dashboard shows the total assists consumed, broken down by tier: Small, Medium, and Large. Assists consumed outside these three tiers are included in the total but do not appear as a separate tier in the chart. Figure 26. Total assists consumed by tier Assist consumption by agent : This area of the dashboard shows the average actions per call and total assists consumed, broken down by AI voice agent. Assist tier is based on the number of actions the voice agent took per call. Actions counted per call include tool executions and one additional action for each call that included an authentication event.The table includes the following columns: * AI voice agent: name of the AI voice agent. * Average actions per call: average number of actions the agent took per conversation. * Assists Consumed: total number of assists consumed by the agent. {#voice-assistant-analytics__ul_assist_agent_cols} Figure 27. Assist consumption by agent