The Chatbot Analytics module provides a dedicated area for tracking chatbot metrics.
With it, you can access predefined metrics without manually creating them from scratch. This allows you to monitor and analyze your bot's performance, including customer engagement and satisfaction.
For instance, you can view data such as the number of people who accessed the chatbot and how many were transferred to a human agent.
How to access Chatbot Analytics
The Analytics module is located in the left-hand menu of Zenvia Customer Cloud. Click on it and then select Chatbots.
Below the screen description, you’ll see three navigation tabs, each corresponding to a specific dashboard:
Interactions Dashboard: Displays metrics related to interactions handled by the chatbot.
Customers Dashboard: Displays metrics related to the volume of customers who accessed the chatbot.
Quality Monitor: Shows satisfaction indicators and interaction metrics.
All three dashboards share the same usage tutorial, differing only in the metrics displayed. Later in this article, you’ll find all the specific metrics for each dashboard. For now, here’s how to navigate them:
Setting dashboard parameters
In the chatbot dashboards, you can define parameters to filter data and track metrics related to interactions, customers, and chatbot quality.
The main benefit of these dashboards is their customizable nature, providing actionable insights and ensuring a consistent and seamless user experience.
To get started, set the filters based on your needs. The process is the same for any dashboard you are viewing:
Chatbot: Select the chatbot you wish to analyze.
Channels: Choose the channel. By default, "All Channels" will be selected.
Period: Define the time frame. By default, "Today" will be selected.
After defining the filters, click the Apply Filters button next to the Period filter, and the corresponding metrics will be displayed.
Exporting chatbot dashboards
The process for exporting a dashboard is the same across all tabs: Interactions Dashboard, Customers Dashboard, or Quality Monitor.
There are two export options:
Individual metrics export: Hover over any metric, such as Interactions by Channel, and click the download icon to export that specific metric.
Full dashboard export: Click the Export Dashboard button at the top of the screen, next to Apply Filters, to export all metrics after applying the filters.
Both options generate files based on the filters and displayed values. If the selected format is CSV, you can choose specific metrics to export. The Download File button initiates the download via your browser.
💡Tip:Configure automatic metric updates to keep your dashboard up-to-date. Click Set Auto-Update on the right-hand side of the screen, below Export Dashboard, and define an interval between 5 and 10 minutes.
Metrics in the interactions dashboard
Use the Interactions Dashboard after launching your chatbot to monitor the performance of your new digital channel. The available metrics include:
Interactions: The total number of interactions created with the chatbot during the selected period.
Interactions by channel: A graphical distribution of interactions by channel or the total sum across all channels.
Retention rate: Percentage of customers who interacted with the chatbot more than once, calculated as:
(Total Conversations - Total Abandonments - Total Conversations Transferred) / Total Conversations.Abandonment rate: Percentage of customers who didn’t complete their interaction, calculated as:
(Total Conversations - Conversations where users stopped responding before end_chat - Total Transferred Conversations) / Total Conversations.Transfer rate: Percentage of interactions transferred to a human agent, reflecting conversations where a transfer action was triggered.
Peak hours: The average volume of interactions per hour, based on the days within the analyzed period.
Metrics in the customers dashboard
After reviewing the Interactions Dashboard, use the Customers Dashboard to supplement your analysis with insights such as active and recurring customers or the total customer volume within a specific period. Available metrics include:
Active customers: Number of customers with at least one interaction, counting each individual only once, even if they generated multiple interactions.
Recurring customers: Number of customers with more than one interaction during the selected period.
Recurrence rate: Percentage of active customers who interacted with the chatbot multiple times, calculated as:
(Recurring Contacts / Total Created Contacts) in percentage.Customer volume over time: The total number of customers during the selected period.
Metrics in the quality monitor
The Quality Monitor provides insights into customer opinions about your company. This feature is especially useful for analyzing satisfaction and engagement, enabling improvements to your product or service. Metrics available include:
CSAT: Customer Satisfaction Score, measuring customer satisfaction with your product or service on a scale from 1 (low) to 5 (high). Results show the percentage of satisfied customers (scores 4 and 5).
NPS: Net Promoter Score, gauging customer loyalty and likelihood of recommending your brand. It is calculated as the difference between promoters and detractors, ranging from -100 (critical) to 100 (excellent).
Average interactions: The average number of messages exchanged between the chatbot and customers.
Explore the Flow Map in the Chatbot module to understand and optimize customer journeys during chatbot interactions.