Zendesk Explore features a pre-built dashboard to help you monitor your Answer Bot activity and article effectiveness. The dashboard can help you identify if Answer Bot is solving your support requests, how quickly users are opening suggested articles, and how your individual articles are performing.
You can edit and customize the Answer Bot dashboard by cloning it (see Duplicating pre-built dashboards).
- Explore Lite: Each day at midnight in the timezone of the account.
- Explore Professional: Once every hour. The update time is randomized within the hour.
In the following topics, you'll learn how to access the Answer Bot dashboard and see the available reports:
Accessing the Answer Bot dashboard
Use the following procedure to access the Answer Bot dashboard.
To access the Answer Bot dashboard
- In the Zendesk product tray, click the Explore icon (
). - From the list of dashboards, select the Zendesk Guide dashboard.
- In the Guide dashboard, click the Answer Bot tab.
Tip: Knowledge Capture and Answer Bot are the Guide components that Explore currently reports. If they are not configured then the Guide dashboard won't be displayed.
Understanding the Answer Bot dashboard reports
The Answer Bot dashboard shows information about Answer Bot activities, ticket resolutions, and activity by articles. You can filter the reports on the dashboard by Time, Answer channel, Answer brand, Article language, Ticket group, and Ticket form.
Answer Bot dashboard headline metrics
The dashboard displays the following headline metrics (KPIs):
- Suggestion rate: Displays the percentage of customer enquiries where Answer Bot offered a suggestion. The KPI also displays the number of answers, unsuccessful attempts, and attempts that Answer Bot made. Click the Improve link to get tips about how to improve the suggestion rate.
- Click-through rate: Displays the percentage of responses clicked by end users from the total responses offered by Answer Bot. The KPI also displays the number of clicks, clicked articles, and the median click time. Click the Improve link to get tips about how to improve the click-through rate.
- Resolution rate: Displays the percentage of enquiries that are resolved with no agent involvement. The KPI also displays the number of resolutions, indirect resolution answers, and the median resolution time. Click the Improve link to get tips about how to improve the resolution rate.
- Rejection rate: Displays the percentage of suggested article marked as unhelpful by end users from the total number of suggestion offered by Answer Bot. The KPI also displays the number of articles marked unhelpful. Click the Decrease link to get tips about how to improve the rejection rate.
Answer Bot dashboard reports
The dashboard displays the following reports:
- Answer Bot activity volumes by date: Shows the number of offered, clicked, and resolved bot answers and resolutions over the chosen time period.
- Answer Bot activity rates by date: The percentage of Answer Bot answers clicked, rejected, or resolved over the selected time period.
- Resolutions by month (12 month): The number of resolutions and the percentage resolution rate over a 12 month period.
- The following reports can be filtered by Suggested article language, Answer brand, or Answer channel:
- Answers by selected attribute (top 10): Displays the top ten offered answers by language, brand, or channel.
- Answers by selected attribute (top 10): Displays the top ten offered answers by language, brand, or channel.
- Clicks and resolutions by selected attribute (top 10): Displays the top ten clicks and resolutions by language, brand, or channel.
- Resolutions by selected attribute (12 months): Displays the resolutions over the last 12 months sorted by language, brand, or channel.
- Answer Bot activity by article: A detailed report about Answer Bot activity for all of your Guide articles. You can restrict the range of results shown by using the Top and Bottom filters. The table contains the following information for each article that Answer Bot interacted with:
- Article author: The author of each article
- Suggested articles: The number of times each article was suggested
- Clicked articles: The number of times each article suggested by Answer Bot was clicked
- Resolution articles: The number of tickets for each article that were solved by an Answer Bot suggestion
- Rejected articles: The number of times an Answer Bot suggestion for each article was rejected by an end user
- Resolutions/Clicks: The percentage of resolutions from clicked answers for each article. It is possible for this number to be over 100% as you can resolve an answer from the initial suggestion without clicking into it.
11 Comments
If user clicks on Answer Bot offered article but doesn't select whether the article helped or not. In this case, how do you consider that? Is it still resolved case? What is the rule here?
I'm curious about historical records. Can Gooddata be used to generate custom reports that target specifically tickets that have received an answer bot response, or have been solved using answer bot month over month. Or is reporting on answer bot specifically limited to insights?
I'm trying to estimate how many times the tickets that were solved by the Answer Bot were reopened, is there a specific report for that, or do I simply build a report on Gooddata using the attributes "# Answer Bot resolutions" and "# Tickets Reopened" ?
We're starting to realise that often when the customer clicks to say that the article was helpful, he doesn't understand that he's be solving his own ticket by doing that. As a result, we've been receiving some Bad CSATs saying that we never answered to their question...
We're in the same boat as Daniela - is there any planned reporting/functionality to deal with reopens, or do we just need to account for these situations in our own processes and reporting?
We are able to capture tickets only when Answerbot answers correctly i.e. only when the end user clicks "Yes, the article was helpful". But, we don't get any tickets if the user clicks "No, the article did not help" or simply doesn't select any response (even if responses may have been correct). So, we don't know how many times Answerbot answered incorrectly/provided unsatisfactory responses nor how many times end users did not select any feedback response. The dialogue/transcript between Answerbot and end user is not available in the database. Could you fix this or suggest where we can get this insight ?
I would like to be able to filter on Answer Bot answers given by email, chat or on the webform. To be able to measure the effectiveness (and counter-effectiveness) of Answer Bot on the different channels.
At this point that is not possible. Would it be possible to submit this feature request?
Hi Mirjam,
I think this would make a great feedback post regarding answer-bot! I would recommend cross posting this in our Guide Product Feedback forum to provide visibility to our Product Managers as well as other users in need of a similar functionality.
Thanks again for taking the time to share this with us :)
To add to Madhavan's points, we'd like a way to track when agents and users indicate an article is not helpful. This adds more information to the perspective of answers. It can help distinguish between whether the title is not landing well (click-through rate) and whether the user is not understanding the content.
I see that there are these attributes in the data, but am uncertain of how to structure a custom metric to highlight instances a customer or agent marked it as unhelpful: Hour User Marked Unhelpful and Hour Agent Marked Unhelpful
Can you please confirm what 'Average Number of Results' means? For example; A client searches our bot system and the average number of results is 2.5. How can you have half a result?
Thanks
Hi everyone,
Is there any plans to have a filter ability for outside of business hours - we would be curious to see the success and metrics with Answer bot outside of business hours when support is not in.
Thank you
Hi,
Is there going to be any functionality which allows us to report on agents' usage of the 'improve' button in support tickets?
We'd like to know which specialists are proactively improving suggested articles the most.
Please sign in to leave a comment.