The AutoQA dashboard tracks your teams’ performance across all AutoQA categories for 100% of your ticket volume. It’s the best place to track trends over time and identify the training needs of your teams and individual agents.
Automated reviews are tracked using the Auto Quality Score (AQS), while manually submitted grades contribute to the agents’ Internal Quality Score (IQS).
It monitors your teams’ quality performance, agent quality scores over time, and performance breakdowns by agent and category.
This article contains the following topics:
- Accessing the AutoQA dashboard
- Filtering the AutoQa dashboard
- Understanding the AutoQA dashboard cards
- Drilling down into AutoQA dashboard data
Related articles:
Accessing the AutoQA dashboard
The AutoQA dashboard tracks your teams’ performance across all AutoQA categories.
- In Zendesk QA, click the Dashboard icon (
) in the left sidebar. - From the list of dashboards, select AutoQA.
Filtering the AutoQA dashboard
After accessing the AutoQA dashboard, you can filter the data to analyze specific datasets and gain insights into auto-review performance.
To filter the AutoQA dashboard
- From the AutoQA dashboard, use the Conversation created cate drop-down
list to select a time period.
By default, the dashboard returns data for the last month.
- Choose your workspaces from the Workspace drop-down list.
This filter displays results based on selected workspaces with AutoQA review results.
- From the Root cause drop-down list, select one or multiple root causes.
Options are displayed based on available root causes, categorized by grammar, spelling, and style.
- Use the Reviewee filter to display results based on selected reviewees.
- Additional filters include:
- Language: Displays results based on selected conversation languages.
- Rating category: Displays results based on selected auto categories.
- Group: Displays results based on user groups.
- Sentiment: Displays results based on customer sentiment. It helps you assess your agents' empathy skills and tone of voice when handling difficult customers.
- Conversation channel: Displays results based on set channels.
- Connections: Displays results based on set connections.
- Outliers: Displays results based on your selection of Yes or No for outliers.
- Rating score: Displays results based on selected values.
- Click the Update icon (
) to refresh the dashboard data based on your
filters. - To clear your filters, click the Dashboard actions menu (
) and select Reset filters.
Understanding the AutoQA dashboard cards
The following quality indicators represent the main metrics displayed on the AutoQA dashboard cards:
- Auto-reviewed conversations: Number of conversations that had at least one category automatically scored without human intervention.
- Manually reviewed conversations: Number of conversations manually reviewed by humans.
- Efficiency gain: Ratio of how many times AutoQA can cover tickets compared to manual reviewing: auto-reviewed conversations / manually reviewed conversations.
- Auto-reviewed per reviewee: Average number of reviews done for each reviewee by AutoQA, illustrating how AutoQA aids in providing feedback.
- Manually reviewed per reviewee: Average number of reviews manually given to each reviewee.
- Acceptance rate: Percentage of AutoQA scores accepted by users as accurate. A high acceptance rate indicates strong alignment between AutoQA scores and user assessments.
- Modified AutoQA conversations: Number of conversations where a human has changed the AutoQA score in at least one category.
-
AQS: Average auto quality score of all conversations evaluated by
AutoQA.
- AQS over time: Difference in auto quality score over a selected period. Helps to quickly identify drops in performance, allowing you to address issues sooner.
-
Breakdown for top languages: Ratio and count of conversation languages. This
can help you identify where to invest your support efforts. For example, if you
experience an increase in volume for a specific language, it may be beneficial to
include that language in your knowledge base.
- Category insights: Breakdown of AutoQA scores per category.
- Custom category insights : Breakdown of AutoQA scores per custom AutoQA category.
- Category scores over time: Line graph showing changes in category scores over a selected period.
-
AutoQA conversations by category: Number of conversations that received an
AutoQA rating. These are conversations that were closed with at least one public reply by the agent and the customer.
- Category scores per reviewee: Information on reviewees and their automatically calculated average score for specific auto categories over a selected time period. Helps to quickly identify which agents are underperforming in that area, allowing you to see who needs training the most, giving. It also provides a reference for relevant conversations to review for each agent.
- Root causes of spelling and grammar mistakes per reviewee: Information about reviewees and the AutoQA-assessed root causes identified by AutoQA's Spelling and Grammar categories.
- Root causes of tone mistakes per reviewee: Information about reviewees and the AutoQA-assessed root causes identified by AutoQA's tone category.
- Repeated spelling and grammar mistakes per reviewee: Lists repeated errors, broken down by reviewee and frequency.
- Last data update time (UTC): Date and timestamp of the last dashboard update. The AutoQA dashboard updates every hour automatically.
Drilling down into AutoQA dashboard data
You can also drill into additional data points.
To drill into the data
- From the AutoQA dashboard, click on the metric you want to drill down into.
- From the dropdown, choose Drill into conversations.
- Click any Conversation link to open it.
- You can also download the data.
You can drill into the following data points
- Auto-reviewed conversations
- Manually reviewed conversations
- Acceptance rate
- Modified AutoQA conversation cards
- Category insights
- Category scores per reviewee
- Root causes of spelling and grammar.