Zendesk Reporting Analytics

AI in customer support is based on continuous training, evaluation, and improvement. However, your ability to do so means that access to essential reporting information and analytics is fundamental. Zendesk has limited analytic capabilities for its AI, making it difficult to judge what is working and what is not.

We will cover the types of analytics available on Zendesk, as well as how to use them and the common problems encountered by users.

Keep in mind that some of these analytics apply to Zendesk’s Advanced AI features, which is a paid add-on, rather than to basic Zendesk AI or Generative AI. You can find more information on the differences here, as well as pricing for each option here.

What types of analytics are available?

Some analytics are quite simple and straightforward. Others are more complex, particularly analytics related to the Advanced AI add-on. There are additional filtering features in some tools, but it is up to the user to be able to use these data sets appropriately and to recognize any confounding variables that may influence the results.

1. Generative AI agent tools dataset and prebuilt dashboard: This is Zendesk’s first dataset linked to AI, offering comprehensive insights on the use of generative AI agent tools, including summarization, expansion, and tone change features. It comes with a prebuilt dashboard for easy visualization and analysis.

2. Intelligent triage predictions and confidence reports: These reports focus on the predictions made by the intelligent triage feature, including analysis of intent, language, and sentiment, as well as their respective confidence levels.

3. Agent engagement analytics: These analytics specifically track how agents use the AI tools, providing detailed information on the frequency and usage patterns within the support team.

4. Ticket metrics linked to AI tool usage: These metrics allow you to compare tickets where AI tools were used and those where they were not, helping quantify the impact of AI assistance on key performance indicators.

What information do they provide?

Generative AI agent tools dataset and prebuilt dashboard:

Metrics:

• Number of tickets with AI tool usage: This metric quantifies the number of tickets processed using any of the AI tools, giving a clear picture of AI tool adoption.

Time spent for first response: This is the median time between ticket submission and the first response, allowing teams to assess whether AI tools are speeding up initial replies.

Full resolution time: This measures the median time between the creation of the ticket and its complete resolution, making it possible to assess whether AI tools are reducing the overall ticket handling time.

AI tool usage over time: This tracks the frequency of AI tool usage over different time periods, enabling trend analysis.

Attributes:

• Agent name: Identifies which agents use the AI tools.

• Ticket ID: Allows you to dive into specific tickets for detailed analysis.

• Interaction ID: Enables tracking of individual interactions where AI tools were used.

Insights provided:

• A detailed view of how agents use AI tools in support operations.

• Evaluation of the impact of AI tools on critical metrics such as resolution time, CSAT, and requester wait time.

• Ability to compare performance between AI-assisted and non-AI-assisted tickets.

Intelligent triage predictions and confidence reports

Shows:

• Intent predictions: What the system thinks is the main purpose or objective of the customer request.

• Language predictions: The detected language of the customer’s message.

• Sentiment predictions: The perceived emotional tone of the customer’s message.

• Confidence levels: How certain the system is about each of these predictions.

This enables support teams to:

• Evaluate the accuracy and effectiveness of the intelligent triage feature.

• Identify areas where the triage system may need improvements or further training.

• Understand how well the system interprets customer communications.

Agent engagement analytics

Provides data on:

• Frequency of AI tool usage per agent: How often each agent uses AI assistance.

• Total number of times AI tools have been used by each agent: Quantifies overall adoption of AI tools by individual agents.

• Distribution of AI tool usage within the agent team: Helps identify the main adopters and those who may need additional training or encouragement.

This information helps managers:

• Identify which agents use AI tools most effectively.

• Spot agents who may need extra support or training in using AI tools.

• Understand the overall adoption of AI technologies by the team.

Ticket metrics

Compares metrics for tickets with and without AI tool usage:

• First response time: Assesses whether AI tools help agents respond faster to initial requests.

• Full resolution time: Assesses whether AI tools contribute to faster ticket resolution.

This comparison enables support teams to:

• Quantify the impact of AI tools on ticket management efficiency.

• Identify which types of tickets benefit the most from AI assistance.

• Make data-driven decisions regarding the expansion or refinement of AI tool usage.

Where to find the reports and how to use them?

Generative AI agent tools dashboard

• In Explorer, click the Dashboards icon (represented by a visual icon in the interface).

• Go to the Dashboards library page.

• Select Zendesk AI > Generative AI Agent Tools.

• Click on the desired tab (for example, Agent Engagement or Ticket Metrics).

Custom intelligent triage predictions report

• In Explorer, click the reports icon and select “New report.”

• Choose Support > Tickets dataset as the data source.

• Add relevant metrics such as ticket ID, intent confidence, language, and sentiment.

• Apply necessary filters, such as excluding NULL values for intent and setting an appropriate date range (e.g., This week).

• Save the report for future access and analysis.

Optional filter for intelligent triage:

• Open any report using the same dataset.

• Create a standard calculated attribute via the Calculations menu.

• Name the filter appropriately and enter the required formula (specific formula not provided in the given information).

• Use this newly created attribute to filter reports, showing only tickets that have been enriched by intelligent triage predictions.

What to do with the information?

Having lots of fancy charts and numbers is not very useful on its own. But it’s important to regularly check and compile this information for several reasons. The most important is making sure your use of AI is both helpful and cost-effective, since it can become very expensive if left unchecked.

Measure AI tool adoption

• Use agent engagement analytics to identify heavy and light adopters of AI tools.

• Set benchmarks for AI tool usage and track progress over time.

• Recognize and reward agents who effectively integrate AI tools into their workflow.

Assess AI tool impact

• Compare resolution times and CSAT scores for tickets with and without AI tool usage.

• Quantify time savings and customer satisfaction improvements attributable to AI assistance.

• Use this data to justify further investment in AI technologies or to refine existing tools.

Optimize workflows

• Identify which AI tools (e.g., summarize, expand, tone change) are most effective in reducing resolution times or improving CSAT.

• Develop best practices based on usage patterns of the top-performing agents. Observe and ask how they are making the best use of AI in their workflow and help other agents do the same.

• Encourage the use of high-impact AI tools across the entire agent team. Some may be hesitant to start using AI if they’re not familiar with it.

Evaluate intelligent triage accuracy

• Analyze confidence levels for intent, language, and sentiment predictions.

• Identify patterns in low-confidence predictions to improve the triage system.

• Use this information to refine the intelligent triage system or provide additional training data as needed.

Track performance over time

• Monitor trends in AI tool usage and their impact on key metrics over several weeks or months.

• Identify patterns or seasonal trends in AI tool effectiveness.

• Use this longitudinal data to make informed decisions about expanding or modifying AI tool implementation.

Justify AI investment

• Compile data showing improvements in efficiency and customer satisfaction due to AI tool usage—or dissatisfaction.

• Calculate whether AI has yielded cost savings or productivity improvements.

Enhance training programs or look for alternatives

• Use insights from top AI tool users to develop training materials for other agents.

• Identify common scenarios where AI tools are most effective and integrate them into agent onboarding and ongoing education.

• Decide if the indicators and analytics are sufficient for your team’s needs, and consider alternatives.

By carefully analyzing these reports and acting on the insights gained, support teams can make data-driven decisions to improve their use of AI tools, boost agent performance, and ultimately deliver better, more efficient customer service.

At eesel AI, we want you to have full control over evaluating and adjusting how AI works for your business. We know it is essential to be able to accurately assess how AI impacts your customer satisfaction, employee productivity, and bottom line. We offer more value, more customization, and more reporting features, at a fraction of the price.

We believe it’s worthwhile to make informed decisions, so we hope our free trial and our discussion of Zendesk’s features help you implement AI in the way that works best for you.