Verified AI summary ◀▼
Spotlight insights enhance your QA process by automatically highlighting key interactions for review, using predefined insights like outliers, churn risk, and exceptional service. This tool helps you identify improvement opportunities by analyzing conversations and tagging them with performance indicators. Access insights through the Feedback section to quickly assess and address customer interactions, improving your team's response and service quality.
In addition to automatically scoring specific categories within scorecards, you can use spotlight insights to further streamline your Quality assurance (QA) process.
This article contains the following topics:
- About spotlight insights
- About the standard spotlight insights
- About the spotlight insight tag types
Related articles
About spotlight insights
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.
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.
| 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 is available in the 100+ languages supported by OpenAI. |
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’s available in the 100+ languages supported by OpenAI. |
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’s available in the 100+ languages supported by OpenAI. |
Yes |
| Exceptional service | Identifies instances where a support representative provided
exceptional service and the customer expressed gratitude. It’s available in the 100+ languages supported by OpenAI. |
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. It's currently available in English, Spanish, French, German, Polish, Italian, Dutch, Portuguese, Turkish, Japanese, and Swedish. |
No |
| SLA | Detects whether the service level agreement (SLA), which specifies and measures the response and resolution times that your support team provides to customers, has been breached. | 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 |
About the spotlight insight tag types
Spotlight insights are available by accessing the “Feedback” section of a conversation, regardless of whether you access that conversation via a dashboard, the Conversations view, the Assignments view, or the Reviews view.
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.