| Add-on | Quality Assurance (QA) or Workforce Engagement Management (WEM) |
In addition to automatically scoring specific categories within scorecards, you can use spotlight insights to further streamline your QA process.
Spotlight is a discovery tool in Zendesk QA that enhances and accelerates your evaluation process by highlighting valuable opportunities for improvement and learning. It analyzes all team interactions, automatically surfacing newly synced closed conversations by identifying and labeling specific keywords or phrases. Spotlight also offers various out-of-the-box insights to help you identify specific events or signals for further analysis.
This article contains the following topics:
- Overview of spotlight (video)
- About the standard spotlight insights
- Understanding the spotlight insight types
- Viewing spotlight insights in conversations
- Creating custom filters using spotlight insights
Related articles
Overview of spotlight (video)
In addition to the details in this article, this video provides a helpful visual overview of spotlight.
About the standard spotlight insights
Spotlight offers predefined insights to help you identify specific events or signals for further analysis. Some require LLM-based AutoQA to be enabled for functioning.
The following predefined spotlight insights automatically surface newly synced closed conversations in Zendesk QA:
| Spotlight insight name | Description | LLM-based AutoQA required? |
| Outliers |
Offers the highest learning potential by allowing you to find critical conversations for review with a single click. It automatically identifies must-review interactions that are atypical or unusual for the team. It’s available in over 100 languages. Flags conversations where:
|
No |
| Churn risk | Highlights conversations where customers express a potential risk of attrition. It identifies instances where customers explicitly mention canceling their subscription or switching to a competitor. The Churn risk insight uses AI and is available in all languages. | Yes |
| Escalation | Flags conversations where the customer requests to speak with a higher-level representative, such as a manager. It does not detect internal escalation processes that occur outside the conversation. It uses AI and is available in all languages. | Yes |
| Follow up | Flags instances where a support representative has promised to take a future course of action. It does not assess the validity of the action, only whether it was completed. It uses AI and is available in all languages. | Yes |
| Exceptional service | Identifies instances where a support representative provided exceptional service and the customer expressed gratitude. It uses AI and is available in all languages. | Yes |
| Sentiment | Detects both negative and positive sentiments in conversations, enabling you to identify dissatisfaction or delight and address critical issues. Understanding how customers feel when interacting with your support team through sentiment analysis helps you assess your agents' empathy skills and tone when handling difficult situations. | No |
| Bot communication efficiency | Compares your bot’s conversation handling to that of average agents. It returns an efficiency percentage that indicates whether interacting with the bot resolved the issue faster and with fewer questions than speaking with a human. Efficiency percentages under 20% are not returned. | No |
| Bot repetition | Reports when the bot is stuck in a loop and repeating the same message to the customer. Filter values include ‘detected’ and ‘not detected’. | No |
| Dead air (voice) | Highlights calls where the gap between consecutive messages exceeds the set threshold. The default industry threshold is 30 seconds, but it can be adjusted to any duration. | No |
| Recording disclosure missing (voice) | Detects whether the speaker discloses that the conversation is being recorded. It can be customized to specify which conversations it applies to. | Yes |
Understanding the spotlight insight types
Spotlight insights are available in both the Conversation view and in Assignments.
The following icons serve as visual indicators of performance for each spotlight:
- A yellow exclamation mark icon (
) indicates negative feedback. - A gray eye icon (
) indicates neutral feedback. - A green happy face icon (
) indicates positive feedback.
Viewing spotlight insights in conversations
You can view the spotlight insights labels for each conversation in the feedback section of the Conversations view.
To access spotlight in conversations
- In Quality Assurance, click
Conversations in the sidebar. - Select a conversation.Create custom filters to quickly find conversations by spotlight insight for reviewing.
- In the sidebar on the right, click the Feedback
icon (
). - View the spotlight insights feedback for this conversation.
Creating custom filters using spotlight insights
You can use custom filters to quickly find conversations by spotlight insight for reviewing.
To create a filter using a spotlight insight
- In Quality Assurance, click
Conversations in the sidebar.
- Click the Sidebar toggle icon (
) to display the side menu. - Next to Public filters click the plus icon (
) to create a new filter. - Enter a Filter name, for example “Escalation”.
- Choose whether the filter visibility should be set to Public or Private.
- Select a Date. This indicates when the conversation was initially created. For example, "Last 30 days."
- Turn on Show all conditions.
- Under Conversation, search for and apply the spotlight filter you want to create. For example, “Escalation”.
- Under Spotlight, click the Escalation filter.
- Click Apply filter.
- Click Create filter.Use additional filter conditions to locate only the conversations you want to review. See Finding conversations to review using custom filters.
0 comments