---
sourceDocument: Australia Conversational Interfaces
sourceDocumentLink: https://www.servicenow.com/docs/r/conversational-interfaces

 Release :

    - australia

ft:locale :

    - en-US

ft:publication_title :

    - Australia Conversational Interfaces

ft:clusterId :

    - convint

bundleId :

    - convint

workflow :

    - Platform


---

# Assistant analytics dashboard indicator details

# Assistant analytics dashboard indicator details {#ariaid-title1}

Release version: Australia  
Updated December 10, 2025  
![](https://www.servicenow.com/docs/portal-asset/ico-clock) 8 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 Assistant analytics dashboard indicator details

The Assistant analytics dashboard provides detailed indicators presented as visualizations to help ServiceNow customers monitor and analyze virtual assistant interactions.
These indicators include information such as indicator type, data source, calculation method, available breakdowns, unit, and precision.
Data is collected daily but is only available for dates before the current day, requiring customers to review prior day data for the most recent insights.
Show full answer Show less  

## Key Features

* **Indicator Categories:** The dashboard organizes indicators into multiple pages focusing on different aspects such as Overview, Usage, Adoption and Engagement, Sentiment, Self-Solve Performance, and Assists.
* **Data Sources:** Data is primarily drawn from tables like Automated Gen AI Log Metadata, Automated Conversation, Automated Conversation Insights, Automated Deflection Log, and Generative AI Usage Log, ensuring comprehensive coverage of assistant interactions and AI usage.
* **Breakdowns:** Indicators support breakdowns by assistant, conversation channels, context profiles, conversation state, generative AI features, deflection types, and sentiment attributes, enabling granular analysis.
* **Calculations:** Indicators use various calculations such as counts, averages, sums, and ratios (e.g., deflection rate, assist to action ratio, inferred CSAT averages) to provide meaningful metrics.
* **Frequency and Units:** All indicators collect data daily with units typically in counts (#) or percentages (%), supporting precise monitoring over time.

## Practical Insights for ServiceNow Customers

* **Monitor Assistant Performance:** Track metrics like cumulative AI-assisted actions, total conversations, and assist usage volume to evaluate how virtual assistants are utilized.
* **Understand User Engagement:** Analyze active users, new user growth, and conversations per user to assess adoption and engagement trends.
* **Measure Sentiment and Satisfaction:** Use sentiment indicators such as overall sentiment scores, empathy rates, negative emotion percentages, and inferred CSAT scores to gauge customer satisfaction and conversational quality.
* **Evaluate Self-Solve Effectiveness:** Review deflection events, deflection rates, and live agent transfers to understand how effectively the assistant resolves issues without human intervention.
* **Optimize AI Feature Usage:** Identify top AI features and track assist consumption to optimize AI capabilities in the assistant environment.

## Expected Outcomes

By leveraging these detailed indicators, ServiceNow customers can gain actionable insights into virtual assistant operations, enabling data-driven improvements to assistant design, user engagement strategies, AI feature utilization, and overall service effectiveness. The daily granularity and breakdown flexibility support timely decision-making and targeted enhancements to improve customer satisfaction and operational efficiency.  
View the data and calculations behind an indicator that is presented in the form of a visualization on the Assistant analytics dashboard.
Assistant analytics indicators contain the following details: indicator type, data source, calculation, available breakdowns, unit, and precision.

These indicators collect data at a daily frequency. Data is only available for dates before the current date. If you want to see results from the current day, you must wait until the next day.

## Overview page indicator details {#assistant-analytics-dashboard-indicator-details__section_wkf_syw_4hc}

{#assistant-analytics-dashboard-indicator-details__table_xbb_bzw_4hc__entry__9}

| Visualization | Indicator name | Indicator type | Indicator source table | Calculation | Available breakdowns | Data collection frequency | Unit | Precision |
|-|-|-|-|-|-|-|-|-|
| Cumulative AI-assisted actions | AI-Assisted Actions in Conversations | Automated | Gen AI Log Metadata\[sys_gen_ai_log_metadata\] | Count of Gen AI log actions | By Conversation Channels, Assistant | Daily | # | 0 |
| Average Distinct Users | Daily Conversation Consumers | Automated | Conversation\[sys_cs_conversation\] | Count of unique users | By Assistant, Context Profiles, Conversation Channels, Conversation State | Daily | # | 0 |
| Assist Usage Volume | Conversation Assist Usage Volume | Automated | Gen AI Log Metadata\[sys_gen_ai_log_metadata\] | Daily count of Gen AI log assists | By Generative AI Feature, Conversation Channels, Assistant | Daily | # | 0 |
| Overall Average Conversation CSAT | Average Period Inferred CSAT (Session) | Formula | sn_na_analytics_insights table | \[\[Aggregate Daily Inferred CSAT (Session)\]\]/\[\[Conversation Insights (Processed)\]\] | By Empathy, Effort, Confusion, Frustration, Escalation, Assistant, Conversation Channels | Daily | # | 2 |
| Total Assist Usage | Conversation Assist Usage Volume | Automated | Gen AI Log Metadata\[sys_gen_ai_log_metadata\] | Count of Gen AI log assists | By Generative AI Feature, Conversation Channels, Assistant | Daily | # | 0 |
[ ]

{#assistant-analytics-dashboard-indicator-details__table_xbb_bzw_4hc}

## Usage page indicator details {#assistant-analytics-dashboard-indicator-details__section_mv5_jzw_4hc}

{#assistant-analytics-dashboard-indicator-details__table_nv5_jzw_4hc__entry__9}

| Visualization | Indicator name | Indicator type | Indicator source table | Calculation | Available breakdowns | Data collection frequency | Unit | Precision |
|-|-|-|-|-|-|-|-|-|
| Total Conversations by Assistant | Assistant Conversations | Automated | Conversation\[sys_cs_conversation\] | Count of conversations | By Context Profiles, Conversation Channels, Conversation State, Assistant | Daily | # | 0 |
| Total Conversations by Channel | Assistant Conversations | Automated | Conversation\[sys_cs_conversation\] | Count of conversations | By Context Profiles, Conversation Channels, Conversation State, Assistant | Daily | # | 0 |
| Result Types Offered | ServiceNow Otto for Virtual Agent Results returned | Automated | CI Analytics\[sys_ci_analytics\] | Count of ServiceNow Otto for Virtual Agent search results returned | By ServiceNow Otto for Virtual Agent Result Type, Assistant | Daily | # | 0 |
| Conversation State Flow | Assistant Conversations | Automated | Conversation\[sys_cs_conversation\] | Count of conversations in each of conversation states: Open, Canceled, Faulted, Completed. | By Context Profiles, Conversation Channels, Conversation State, Assistant | Daily | # | 0 |
[ ]

{#assistant-analytics-dashboard-indicator-details__table_nv5_jzw_4hc}

## Adoption and Engagement page indicator details {#assistant-analytics-dashboard-indicator-details__section_h5y_jzw_4hc}

{#assistant-analytics-dashboard-indicator-details__table_i5y_jzw_4hc__entry__9}

| Visualization | Indicator name | Indicator type | Indicator source table | Calculation | Available breakdowns | Data collection frequency | Unit | Precision |
|-|-|-|-|-|-|-|-|-|
| Average Active Users | Daily Conversation Consumers | Automated | Conversation\[sys_cs_conversation\] | Count of unique users (consumer) where Model Type = LLM and Consumer is not empty and Conversation Type = Interactive | By Assistant, Context Profiles, Conversation Channels, Conversation State | Daily | # | 0 |
| New Users | AI Engagement : New Users | Automated | Conversation\[sys_cs_conversation\] | Count of new users (consumer) where Model Type = LLM and Consumer is not empty and Conversation Type = Interactive | Conversation Channels, Assistant | Daily | # | 0 |
| Avg Conversations per User | Average Conversations per User | Formula | None | \[\[Assistant Conversations\]\]/\[\[Daily Conversation Consumers\]\] | Assistant, Conversation Channels | Daily | # | 0 |
| Active Assistants | Active Assistants | Automated | Now Assist Deployment\[sys_now_assist_deployment\] | Count of assistants | None | Daily | # | 0 |
| Conversation Volume Trend | Assistant Conversations | Automated | Conversation\[sys_cs_conversation\] | Count of conversations where Model Type = LLM and Conversation Type = Interactive | By Context Profiles, Conversation Channels, Conversation State, Assistant | Daily | # | 0 |
| Assist to Execution Trend | * Conversation Assist Usage Volume * AI-Assisted Actions in Conversations * Assist to Action Ratio {#assistant-analytics-dashboard-indicator-details__ul_vsg_4nd_b3c} | Formula | None | \[\[Conversation Assist Usage Volume\]\]/\[\[AI-Assisted Actions in Conversations\]\] | By Assistant, Conversation Channels | Daily | # | 0 |
| Conversations per Channel | Assistant Conversations | Automated | Conversation\[sys_cs_conversation\] | Count of conversations where Model Type = LLM and Conversation Type = Interactive | By Context Profiles, Conversation Channels, Conversation State, Assistant | Daily | # | 0 |
| New User Growth | AI Engagement : New Users | Automated | Conversation\[sys_cs_conversation\] | Count of new users where Model Type = LLM and Consumer is not empty and Conversation Type = Interactive | By Conversation Channels, Assistant | Daily | # | 0 |
[ ]

{#assistant-analytics-dashboard-indicator-details__table_i5y_jzw_4hc}

## Sentiment page indicator details {#assistant-analytics-dashboard-indicator-details__section_ehb_kzw_4hc}

{#assistant-analytics-dashboard-indicator-details__table_fhb_kzw_4hc__entry__9}

| Visualization | Indicator name | Indicator type | Indicator source table | Calculation | Available breakdowns | Data collection frequency | Unit | Precision |
|-|-|-|-|-|-|-|-|-|
| Overall Sentiment | Average Daily Inferred CSAT (Session) | Automated | Conversation Insights\[sn_aci_insights\] | Average CSAT where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM | By Confusion, Effort, Empathy, Escalation, Frustration, Assistant, Conversation Channels | Daily | # | 2 |
| Conversations Analyzed | Conversation Insights (Processed) | Automated | Conversation Insights\[sn_aci_insights\] | Count of conversations where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM | By Confusion, Effort, Empathy, Escalation, Frustration, Assistant, Conversation Channels, Next Steps, Resolution State | Daily | # | 0 |
| High Empathy Rate | High Empathy Rate - Conversation Insights | Formula | None | (\[\[Conversation Insights (Processed) \> Empathy = High\]\]/\[\[Conversation Insights (Processed)\]\]) \* 100 | By Conversation Channels, Confusion, Effort, Empathy, Escalation, Frustration, Assistant | Daily | % | 0 |
| Conversations with Negative Emotions | Percentage of Conversations with Negative Emotions | Formula | None | (\[\[Conversation Insights (Negative Emotions)\]\]/\[\[Conversation Insights (Processed)\]\])\*100 | Conversation Channels, Assistant | Daily | % | 2 |
| Average Inferred CSAT Over Time | Average Daily Inferred CSAT (Session) | Automated | Conversation Insights\[sn_aci_insights\] | Average CSAT where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM and Session CSAT is not empty | By Confusion, Effort, Conversation Channels, Empathy, Escalation, Frustration, Assistant | Daily | # | 2 |
| Transfers and Escalations Over Time | Conversation Insights (Processed) | Automated | Conversation Insights\[sn_aci_insights\] | Count of conversations where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM | By Confusion, Effort, Empathy, Escalation, Frustration, Assistant, Conversation Channels, Next Steps, Resolution State | Daily | # | 0 |
| Average Inferred CSAT (Virtual Agent) | Average Daily Inferred CSAT (Virtual Agent) | Automated | Conversation Insights\[sn_aci_insights\] | Average CSAT (Virtual agent) where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM and AI agent CSAT is not empty | By Confusion, Effort, Empathy, Conversation Channels, Escalation, Frustration, Assistant | Daily | # | 2 |
| Average Inferred CSAT (Live Agent) | Average Daily Inferred CSAT (Live Agent) | Automated | Conversation Insights\[sn_aci_insights\] | Average CSAT (live agent) where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM and Human agent CSAT is not empty | By Confusion, Effort, Empathy, Conversation Channels, Escalation, Frustration, Assistant | Daily | # | 2 |
| Average Inferred CSAT (Session) | Average Daily Inferred CSAT (Session) | Automated | Conversation Insights\[sn_aci_insights\] | Average CSAT where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM and Session CSAT is not empty | By Confusion, Effort, Conversation Channels, Empathy, Escalation, Frustration, Assistant | Daily | # | 2 |
| Assistant Recommended Next Steps | Conversation Insights (Processed) | Automated | Conversation Insights\[sn_aci_insights\] | Count of conversations where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM | By Confusion, Effort, Empathy, Escalation, Frustration, Assistant, Conversation Channels, Next Steps, Resolution State | Daily | # | 0 |
| Conversation Insight Inferred Resolution State | Conversation Insights (Processed) | Automated | Conversation Insights\[sn_aci_insights\] | Count of conversations where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM | By Confusion, Effort, Empathy, Escalation, Frustration, Assistant, Conversation Channels, Next Steps, Resolution State | Daily | # | 0 |
| Empathy Levels Distribution Over Time | Conversation Insights (Processed) | Automated | Conversation Insights\[sn_aci_insights\] | Count of conversations where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM | By Confusion, Effort, Empathy, Escalation, Frustration, Assistant, Conversation Channels, Next Steps, Resolution State | Daily | # | 0 |
| Negative Emotion Feedback Over Time | Conversation Insights (Processed) | Automated | Conversation Insights\[sn_aci_insights\] | Frustration: Count of conversations where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM and Frustrations is Yes Confusion: Count of conversations where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM and Confusion is Yes | By Confusion, Effort, Empathy, Escalation, Frustration, Assistant, Conversation Channels, Next Steps, Resolution State | Daily | # | 0 |
[ ]

{#assistant-analytics-dashboard-indicator-details__table_fhb_kzw_4hc}

## Self-Solve Performance page indicator details {#assistant-analytics-dashboard-indicator-details__section_zvn_15t_xhc}

Note:  
The records in the Deflection Log \[sys_cs_deflection_log\] table are retained for a period of 60 days.
{#assistant-analytics-dashboard-indicator-details__table_blt_c5t_xhc__entry__9}

| Visualization | Indicator name | Indicator type | Indicator source table | Calculation | Available breakdowns | Data collection frequency | Unit | Precision |
|-|-|-|-|-|-|-|-|-|
| Total Deflection Events | Deflection Logs | Automated | Deflection Log\[sys_cs_deflection_log\] | Count of events where Conversation is not empty and Conversation Conversation Type = Interactive and Conversation Model Type = LLM | Assistant, Conversation Channels, Deflection Types, Deflection State | Daily | # | 0 |
| Total Deflections | Deflection Logs : Resolved | Automated | Deflection Log\[sys_cs_deflection_log\] | Count of events where State = Resolved and Conversation is not empty and Conversation Conversation Type = Interactive and Conversation Model Type = LLM and Conversation Live Agent Transfer Time is empty | Assistant, Conversation Channels | Daily | # | 0 |
| Total Live Agent Transfers | Total Live Agent Transfers | Automated | Conversation\[sys_cs_conversation\] | Count of conversations where Model Type = LLM and Conversation Type = Interactive and Live Agent Transfer Time is not empty | Assistant, Conversation Channels | Daily | # | 0 |
| Deflection Rate | Deflection Rate | Formula | Deflection Log \[sys_cs_deflection_log\] | (\[Number of deflection records Resolved\]/\[Number of deflection records\])\*100 | Assistant, Conversation Channels | Daily | % | 2 |
| Deflection Rate Over Time | Deflection Rate | Formula | Deflection Log \[sys_cs_deflection_log\] | (\[Number of deflection records Resolved\]/\[Number of deflection records\])\*100 | Assistant, Conversation Channels | Daily | % | 2 |
| Deflection Outcome Distribution | Deflection Logs | Automated | Deflection Log \[sys_cs_deflection_log\] | Count of events where Conversation is not empty and Conversation Conversation Type = Interactive and Conversation Model Type = LLM | Assistant, Conversation Channels, Deflection Types, Deflection State | Daily | # | 0 |
| Deflection Types Offered | Deflection Logs | Automated | Deflection Log \[sys_cs_deflection_log\] | Count of events where Conversation is not empty and Conversation Conversation Type = Interactive and Conversation Model Type = LLM | Assistant, Conversation Channels, Deflection Types, Deflection State | Daily | # | 0 |
| Effort Score | Effort Score | Automated | Conversation Insights\[sn_aci_insights\] | Count of conversations where CSAT processed = true and Conversation Conversation Type = Interactive and Conversation Model Type = LLM and Effort Score in (High, Medium, Low) | Assistant, Conversation Channels, Effort | Daily | # | 0 |
[ ]

{#assistant-analytics-dashboard-indicator-details__table_blt_c5t_xhc}

## Assists page indicator details {#assistant-analytics-dashboard-indicator-details__section_irc_kzw_4hc}

{#assistant-analytics-dashboard-indicator-details__table_jrc_kzw_4hc__entry__9}

| Visualization | Indicator name | Indicator type | Indicator source table | Calculation | Available breakdowns | Data collection frequency | Unit | Precision |
|-|-|-|-|-|-|-|-|-|
| Sum of all Conversational Assists | Conversation Assist Usage Volume | Automated | Gen AI Log Metadata\[sys_gen_ai_log_metadata\] | Count of Gen AI log assists | By Generative AI Feature, Conversation Channels, Assistant | Daily | # | 0 |
| Assist Consumption | Conversation Assist Usage Volume | Automated | Gen AI Log Metadata\[sys_gen_ai_log_metadata\] | Count of Gen AI log assists by assistant | By Generative AI Feature, Conversation Channels, Assistant | Daily | # | 0 |
| Executions per Assistant | AI-Assisted Actions in Conversations | Automated | Gen AI Log Metadata\[sys_gen_ai_log_metadata\] | Count of Gen AI log actions by assistant | By Conversation Channels, Assistant | Daily | # | 0 |
| Trending sum of all Assists | Conversation Assist Usage Volume | Automated | Gen AI Log Metadata\[sys_gen_ai_log_metadata\] | Sum of Gen AI log assists | By By Generative AI Feature, Conversation Channels, Assistant | Daily | # | 0 |
| Top 10 Most Used AI Features | Generative AI Usage Log | Pivot Table | Generative AI Usage Log \[sys_gen_ai_usage_log\] | None | None | Daily | # | 0 |
[ ]

{#assistant-analytics-dashboard-indicator-details__table_jrc_kzw_4hc}