Analyzing your Answer Bot activity

Return to top
Have more questions? Submit a request


  • Ozan Can Köseley

    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?

  • Geoff Williams

    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?

  • Daniela Catarino

    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...

  • Terry Knox

    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? 

  • Madhavan Buddha

    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 ?

  • Mirjam Happel

    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?

  • Brett Bowser
    Zendesk Community Team

    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 :)

  • Monica

    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

  • Rebecca Love

    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?



  • Jesse Marion

    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

  • Sally


    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. 

  • Brett Bowser
    Zendesk Community Team

    Hey Sally,

    I did some digging and it looks like currently the Answer-bot dataset focuses on end-user interactions. There's no way to track agent interaction with the "improve" button at this time.

    I'm going to mark this as feedback so our Product Managers are aware of your interest in this feature.


  • Ian Maison

    Hi, I was reviewing this due to needing a way to easily report on articles marked as 'Not Helpful' via Answerbot. It's not been discussed since a few messages back but Zendesk do actually allow this if you create a view on the tag "ab_marked_unhelpful".

    I'm sure Explore will allow you to create data based on the tag, but for now I just needed a View.

  • Allison S.

    Hi Ian Maison

    I just set up a view for this, and it's super easy. I used this article as a guide for setting up the view.

    But you can easily add (under conditions) Tags: Contains at least one of the following: ab_marked_unhelpful

    This will allow you to monitor when AB was marked unhelpful. 

    I hope this helps!


  • Nicole Saunders
    Zendesk Community Team

    Thanks for sharing that solution, Allison!

  • Namita Tribhuvan

    How can we pull the data for unsuccessful attempts, if we want to know which inquiries were unsuccessful?


Please sign in to leave a comment.

Powered by Zendesk