Conversational analytics metrics in Amazon Connect

The following metrics are derived from Contact Lens conversational analytics. These metrics are available only when Contact Lens is enabled for your instance and conversational analytics is enabled on the contact.

These metrics are displayed on the Real-time and Historical metrics reports. For instructions about how add these metrics to your report, see How to create a historical metrics report.

Also check out the Contact Lens conversational analytics dashboard for data visualizations about the trends of contact drivers over time.

Agent talk time percent

The talk time by an agent in a voice conversation as a percent of the total conversation duration. To calculate this metric, Amazon Connect totals all the intervals in which an agent was engaged in conversation (talk time agent), and then divides this total by the total conversation duration.

In the GetMetricDataV2 API, this metric can be retrieved by using PERCENT_TALK_TIME_AGENT.

Average agent greeting time

This metric represents the average first response time of agents on chat, indicating how quickly they engage with customers after joining the chat. It is calculated by dividing the total time it takes for an agent to initiate their first response by the number of chat contacts.

In the GetMetricDataV2 API, this metric can be retrieved by using AVG_GREETING_TIME_AGENT.

Type: String (hh:mm:ss)

Category: Conversational analytics driven metric

Average agent interruptions

This metric quantifies the average frequency of agent interruptions during customer interactions by dividing the total number of agent interruptions by the total number of contacts.

In the GetMetricDataV2 API, this metric can be retrieved by using AVG_INTERRUPTIONS_AGENT.

Type: String (hh:mm:ss)

Category: Conversational analytics driven metric

Average agent interruption time

Average of total agent interruption time while talking to a contact. Calculating the average duration of agent interruptions during contact conversations involves summing the interruption intervals within each conversation and dividing the total by the number of conversations that experienced at least one interruption.

In the GetMetricDataV2 API, this metric can be retrieved by using AVG_INTERRUPTION_TIME_AGENT.

Type: String (hh:mm:ss)

Category: Conversational analytics driven metric

Average agent talk time

Average time that was spent talking in a conversation by an agent. This is calculated by summing up the durations of all intervals during which the agent was speaking and then dividing that sum by the total number of contacts.

In the GetMetricDataV2 API, this metric can be retrieved by using AVG_TALK_TIME_AGENT.

Type: String (hh:mm:ss)

Category: Conversational analytics driven metric

Average conversation duration

The average conversation duration of voice contacts with agents is determined by calculating the total time from the start of the conversation until the last word spoken by either the agent or the customer. This value is then divided by the total number of contacts to provide an average representation of the conversation time spent on the call.

In the GetMetricDataV2 API, this metric can be retrieved by using AVG_CONVERSATION_DURATION.

Type: String (hh:mm:ss)

Category: Conversational analytics driven metric

Average customer talk time

Average time that was spent talking in a conversation by a customer. This is calculated by summing up the durations of all intervals during which the customer was speaking and then dividing that sum by the total number of contacts.

In the GetMetricDataV2 API, this metric can be retrieved by using AVG_TALK_TIME_CUSTOMER.

Type: String (hh:mm:ss)

Category: Conversational analytics driven metric

Average non-talk time

Average of total non-talk time in a voice conversation. Non-talk time refers to the combined duration of hold time and periods of silence exceeding 3 seconds, during which neither the agent nor the customer is engaged in conversation. To calculate non-talk time, we add up all the intervals in which both participants remained silent and then divide this total by the number of contacts.

In the GetMetricDataV2 API, this metric can be retrieved by using AVG_NON_TALK_TIME.

Type: String (hh:mm:ss)

Category: Conversational analytics driven metric

Average talk time

Average time that was spent talking during a voice contact across either the customer or the agent. This is calculated by summing up all the intervals in which either an agent, a customer, or both were engaged in conversation, and then dividing it by the total number of contacts.

In the GetMetricDataV2 API, this metric can be retrieved by using AVG_TALK_TIME.

Type: String (hh:mm:ss)

Category: Conversational analytics driven metric

Customer talk time percent

The talk time by a customer in a voice conversation as a percent of the total conversation duration. To calculate this metric, Amazon Connect totals all the intervals in which a customer was engaged in conversation, and then divides this total by the total conversation duration.

In the GetMetricDataV2 API, this metric can be retrieved by using PERCENT_TALK_TIME_CUSTOMER.

Non-talk time percent

The non-talk time in a voice conversation as a percent of the total conversation duration. To calculate non-talk time percent, Amazon Connect totals all the intervals in which participants remained silent (non-talk time), and then divides this total by the total conversation duration.

In the GetMetricDataV2 API, this metric can be retrieved by using PERCENT_NON_TALK_TIME.

Talk time percent

The talk time in a voice conversation as a percent of the total conversation duration. To calculate talk time percent, Amazon Connect totals all the intervals in which either an agent, a customer, or both were engaged in conversation (talk time), and then divides this total by the total conversation duration.

In the GetMetricDataV2 API, this metric can be retrieved by using PERCENT_TALK_TIME.