Explore recipe: Analyzing the last 100 suggested article tickets

Available on Suite Professional plans and above Available on Explore Professional plans and above

Zendesk has renamed our bot capabilities. Answer Bot is now Zendesk bots. Flow Builder is bot builder, and Article Recommendations are autoreplies. The Explore dashboard described in this article uses legacy names and will be updated in the future.

This functionality is part of AI agents.

In this Explore recipe, you'll learn how to create a dashboard that shows detailed information about what customers are asking Answer Bot and which articles are being recommended.

This article contains the following sections:

What you'll need
Creating the report
Creating the dashboard
Further reading

What you'll need

Skill level: Intermediate

Time required: 25 minutes

Editor or Admin permissions (see Adding users to Explore)
Zendesk Guide Professional or Enterprise with the Answer Bot add-on

Creating the report

In this section, you'll build a table showing detailed information about the last 100 Answer Bot tickets. In addition, you'll make the article names clickable so that viewers can go straight from your report to the relevant article.

To create the report

In Explore, click the reports ( ) icon.
In the Reports library, click New report.
On the Select a dataset page, click Answer Bot > Answer Bot - Article Recommendations, then click Start report. The report builder opens.
In the Metrics panel, click Add.
From the list of metrics, choose Answer Bot answers > Attempts, then click Apply.
Next, create the attribute that will display the article title as a link to the article itself. In the Calculations menu (), click Standard calculated attribute.
On the Standard calculated attribute page, name the attribute Article and enter the following formula:
```
LINK([Article translation URL],[Article translation title])
```
The formula window will look like the following example:

Tip: If you're working in a language other than English, read this article to help you enter Explore formulas in your language.
When you are finished, click Save.
In the Rows panel, click Add.
From the list of attributes, choose the following:
- Ticket > Ticket ID
- Time - Ticket created > Ticket created - Date
- Ticket > Ticket status (the status of the Support ticket that was created)
- Answer Bot answer > Answer status (The status of the suggestion provided by Answer Bot, for example, Unoffered, Offered, Clicked, or Resolved)
- Calculated attributes > Article (the standard calculated attribute you created previously)
- Answer Bot answer > Answer enquiry
  To see all of the available metrics and attributes for Answer Bot, see the article: Metrics and attributes for Zendesk Answer Bot.
When you are finished, click Apply. Explore displays the table. The next step is to perform some extra work to make the article titles link to the relevant article in your Help Center. From the chart configuration menu (), choose Chart.

Tip: If you have a large Zendesk instance, you might have a very high number of Answer Bot attempts which Explore cannot load. If this is the case, consider using a date filter to restrict the amount of results that are returned.
On the Chart page, from the Text interpretation drop-down list, choose HTML.
Ensure that the Clickable URL box is checked. Now, whenever you click an article name in the table, your web browser will open that article in a new tab.
Now, add a top/bottom filter to show only the last 100 Answer Bot attempts. From the result manipulation menu (), click Top/bottom.
On the Top/bottom page, enable Top and configure the top value to be 100. Click Apply.
From the result manipulation menu (), click Sort.
On the Sort page, click Z-A, then click Apply.
Finally, give your report a name like Last 100 Answer Bot tickets, then click Save.

Your finished report will look similar to the following example:

Creating the dashboard

Now your report is complete, you'll add it to a dashboard along with three filters that enable the dashboard viewer to filter the results by answer status, answer channel, and ticket status. Once the dashboard is complete, you can share it with others in your organization.

To create the dashboard

In Explore, click the dashboards library icon ().
In the Dashboards library, click Create dashboard.
On the Start a dashboard page, select Blank dashboard, then click Select.
A new, blank dashboard opens.
From the Add menu, choose Report.
From the list of reports, choose the report you created previously, Last 100 tickets. The report is added to the dashboard. You can drag and resize the report to make it look how you want.
Now, you'll add three dashboard filters to let viewers filter the results by answer status, answer channel, and ticket status. From the Add menu, choose Data filter.
On the Choose data filter columns page, enable the Answer status attribute and configure the following values:
- Display: In a drop down
- Enable Multiselection
- Enable Select valuesThe Answer status attribute indicates the status of an answer provided by Answer Bot. Possible values include Unoffered, Offered, Clicked or Resolved.
When you are finished, click Apply.
Add a second data filter. This time, enable the Answer channel attribute and configure the same settings as you did for the first filter.
The Answer channel attribute is the channel on which Answer Bot interacted with the end user. Possible values include Email,Web Widget (Classic),Web form,API,SDK, and Slack.
Add a third and final data filter. This time, enable the Ticket status attribute and, once again, configure the same settings as you did for the first filter.
The Ticket status attribute is the current status of the ticket itself, for example, Closed, Open, etc.
Click the title of the dashboard and name it Answer Bot last 100 tickets.
You'll now have a dashboard showing your report and the three filters you added. Drag and drop the items on your dashboard until they resemble the example below:

The dashboard is now complete. You can add more reports to it, add company branding, or share it with others. For more help with all things dashboard-related, see Creating dashboards.

What you'll need

Creating the report

Creating the dashboard

Further reading