Viewing Virtual Agent analytics for Zoom Virtual Agent

Requirements for accessing Virtual Agent analytics for Zoom Virtual Agent

• Account owner or admin privileges; or relevant role with Virtual Agent permission
• Voice/Chat SKU purchased for Zoom Virtual Agent

How to access Virtual Agent analytics

1. Sign in to the Zoom web portal.
2. In the navigation menu, under Personal, click Analytics & Reports.
3. Click the Virtual Agents tab.

Reporting capabilities

Overview tab

Total engagements/Total interaction duration

• Historical duration/engagement count trends

Containment rate

Topic analytics

• Popular topics: Frequently asked topics in customer inquiries.
• Solved topics: Topics that are contained effectively by AI agents.
• Escalated topics: Topics that are frequently escalated to human agents. They can help identify gaps and guide the development of new skills, tools, or flows to handle them more effectively.

Cost savings analysis

• Total engagements for chat/total duration for voice calls handled by AI.
• Average cost of human-handled interactions.
• Projected savings based on successful containment.

Virtual agent performance tab

Tools 

• Unique tools invoked: Total tools invoked to understand the breadth of usage of additional support set up in addition to conversational experience.
• Total tools invocation: Unique tools invoked to understand the depth of usage of setup tools.
• Tools usage leaderboard: Leaderboard of top tools used across all agents.

Latency analytics

• P50 latency (Median): Reflects the typical response time experienced by users.
• P90 latency: Highlights latency after removing extreme outliers.
• Historical trends: Track latency over time to identify patterns or performance issues.

Individual agent containment rates

• Agents with the highest containment rates
• Agents with the lowest latency offering good customer service
• gents with the highest engagement volume contributing to the greatest cost savings

Using agent performance report for optimization

• Identify top-performing agents and analyze their interaction patterns
• Use latency data to optimize response workflows
• Target skills build for underutilized but high-value tools
• Create performance benchmarks based on successful agent configurations

Knowledge performance tab

Aggregated knowledge base metrics

• Knowledge-assisted engagements: The total number of engagements that contained at least one knowledge retrieval.
• Knowledge-assisted engagements rate: The number of engagements that contained at least one knowledge retrieval divided by total number of engagements.
• Article referenced leaderboard: The number of times an article was referenced during engagements.
• Average knowledge referenced per engagement: The average number of knowledge bases accessed during each engagement.
• Average article referenced per engagement: The average number of articles referenced during each engagement.
• Article feedback trend: A visual breakdown of user feedback on knowledge base articles, categorized as Helpful, Not helpful, or No response. 

Topic analytics

• Article matched topics: Common topics in customer queries that successfully matched relevant knowledge base articles.
• Article escalated topics: Topics frequently escalated due to lack of a suitable knowledge base match, highlighting potential knowledge gaps.

Using the knowledge base report for optimization

• Identify your highest-performing knowledge base articles and knowledge base sources.
• Address content gaps revealed through topic analytics.
• Understand how AI combines several articles in an engagement to improve conversational experience.
• Use knowledge base article feedback to assess article quality and relevance over time.

Query insight tab

This tab provides a detailed view of consumer queries handled by agents and virtual agents, helping you understand query volume, efficiency, and trending topics.

Query metrics

This section shows summarized statistics for the selected date range and filters, including:

• Total queries: The total number of customer queries submitted during the selected time period. A comparison indicator shows the percentage increase or decrease versus the previous equivalent period.
• Average queries per engagement: The average number of queries submitted within a single engagement. This metric helps indicate interaction complexity, higher values typically suggest multi-turn or more detailed conversations.

Topic performance metrics

These leaderboards highlight how queries are distributed and handled across different topics.

• Popular topics leaderboard: Displays the most frequently asked topics, ranked by share of total queries. This helps identify common customer needs and high-demand knowledge areas.
• Solved topics leaderboard: Shows topics where queries were successfully resolved without escalation. This metric is useful for evaluating knowledge base coverage and virtual agent effectiveness.
• Escalated topics leaderboard: Lists topics that most frequently required escalation to a human agent. A higher percentage may indicate gaps in automation, missing knowledge articles, or complex customer issues.

Query match trend
A time-based view of how queries were classified each day, broken down into the following categories:

• Matched article: Queries that were successfully matched to a knowledge base article.
• Matched intent: Queries that were matched to a predefined intent.
• No match: Queries where no suitable article or intent was found.
• No match attempt: Queries where the system did not attempt a match, typically due to configuration or routing rules.

This view helps identify gaps in knowledge content or intent coverage over time.

Feedback

These metrics reflect customer feedback on query responses and are displayed as a pie chart to show the distribution of feedback types.

• Helpful: The portion of queries where users indicated the response was helpful.
• Not helpful: The portion of queries where users indicated the response did not meet their needs.
• No response: The portion of queries where users did not provide feedback.

Conversation details tab

Aggregated engagement metrics

• Total engagements: Overall number of engagements, along with historical trends.
• Multi-turn engagements: Analysis of multi-turn interactions to understand how many high-value or complex queries your virtual agent successfully handled.
• Non-engaged drop-offs: The total number of engagements that ended without having an interaction from user during selected time period.
• Containment rate: The percentage of engagements handled by AI agent without being escalated during selected time period.
• Average interaction duration: The average duration of interactions between the consumer and the agent during engagements.
• Total Interaction duration: The cumulative time users spent interacting with your virtual agents, useful for measuring engagement depth and agent workload.
• Tool failure: The total number of tool call failures that occurred during the time period.

Escalation and interaction metrics

These metrics help you understand when and why queries are escalated, as well as the overall time spent interacting with customers.

• Escalation rate trend: A time-based line chart showing the percentage of queries that were escalated to a human agent over the selected period. This metric helps identify spikes or patterns in escalations, which may indicate complex topics, insufficient automation, or gaps in knowledge coverage.
• Total interaction duration: A time-based view of the cumulative duration of all interactions within the selected period. This represents the total amount of time customers spent interacting with agents or virtual agents.

Conversation log

The Conversation log provides a detailed, engagement-level view of individual customer interactions. It allows admins and supervisors to review specific conversations for troubleshooting, quality analysis, and optimization.

Engagement recordings and transcripts

1. From the list of engagements, go to the last column and click Play Recording for voice engagements or View Transcript for chat engagements.
2. Click Download and select either Recording or Transcript:
   • Selecting Transcript will download a .vtt file.
   • Selecting Recording will download an .mp4 file.

Using engagement performance report for optimization

• Identify patterns among engagements to understand how duration and turns may result in better outcomes.
• Listen / view transcripts of individual engagements to further optimize your flows for escalated engagements.
• Understand how tools might have resulted in better containment.

Consumer engagement surveys tab

This tab displays key metrics including survey launches, response rates, and completion rates across different agent types. Admins can filter surveys by agent name or survey name, drill down into individual survey responses, and view detailed question-answer pairs. Analyzing survey performance and user feedback helps teams optimize their virtual agent interactions and improve customer satisfaction measurements.

How to customize the AI Agent Analytics reports

• Adjust the date range using the selector to view data for your desired timeframe.
• Filter the report by channel, agent, or other available criteria based on the report’s context.
• Click the settings icon to customize visible columns within any table view.
• In the upper-right corner, click the Export button to export the data in CSV format.

How to download AI Agent Analytics reports

1. Access the AI Agent analytics report.
2. From any tabular data view in the dashboard, click the Export button in the upper-right corner.