Analyzing intelligent triage results and taking action

Return to top

9 Comments

  • CJ Johnson

    Can you clarify what is different about detecting the language in this feature, vs people not using this? How is this different from the email-based language detection that Zendesk uses for all accounts currently? 

    0
  • Riah Lao

    Hi Jake Bantz, will this work for live chat tickets?

     
    0
  • Jake Bantz
    Zendesk Product Manager

    CJ Johnson - Intelligent triage will detect the language for all new tickets for any channels enabled for intelligent triage. The alternate methods of language detection are focused particularly on the user creation event. For example, intelligent triage can be used for detecting the language for tickets which belong to users who had the wrong language assigned (via one of the methods/exceptions in the above article) or are multilingual and may contact support in their most comfortable language. This allows for the proper language considerations to be made on every ticket - given that it was created via a supported and intelligent triage enabled channel.

    Riah Lao - Intelligent triage does not work for live chat or messaging. It is only available for asynchronous channels such as email, web form, and API. You can read more about the configuration here.

    0
  • Ian Marston

    Jake Bantz

    Is there a way in which i can set the triggers and automations to exclude the triage based on presence of a tag added on a previous trigger/automation?

    0
  • Jake Bantz
    Zendesk Product Manager

    Ian Marston do you mean you want intelligent triage to ignore specific tickets altogether based on certain conditions?

    If that's the case - at this time the only way to include/exclude tickets from being enriched is based on ticket channel and the option to exclude agent created tickets (in the admin settings for intelligent triage).

    If that's too broad of a change, my recommendation would be leaning on business rule order and using the presence of tags to override what actions may be implemented with conditions based on the intelligent triage conditions in later triggers/automations.

    With that in mind, what sort of exclusion conditions would you like to see? Could this be something that doesn't have to reference a trigger applied action, but instead some other parameter(s)? If so, what sorts of parameters?

    The intelligent triage enrichment is kicked off at virtually the same time as the ticket is created, and at that point only the subject and message body are consumed for the predictions. If additional checks are added for tags or other values added after creation, that would mean added delay in adding the enrichment.

    0
  • Jen C

    Jake Bantz Does this work on Messaging now? I saw your comment here, but then I'm seeing that the Zendesk AI feature mentions it works for Messaging. Maybe that is new, but I wanted to make sure I'm understanding all the features available with the Advanced AI Add-on. Thanks!

    https://support.zendesk.com/hc/en-us/articles/4550640560538-Automatically-triaging-tickets-based-on-intent-language-and-sentiment

    0
  • Jake Bantz
    Zendesk Product Manager

    Hi Jen C,

    Yes! There are a couple of ways intelligent triage can influence Messaging. Pre-trained intents can be used with Advanced bots to provide specialized answers in the Messaging conversation, but if a Messaging conversation has to be routed to an agent (becomes a ticket), the end-user's messages will be assessed for an overarching intent which is then passed to the ticket as the intent which can be leveraged in routing, business rules, etc.

    0
  • Tatiana Christensen

    Hello Jake,

    Our trial is starting soon, and we are preparing to go live. 

    I appreciate your idea about making an internal macro for agents to report AI feedback in practice (or any Support related cases, really). We'll implement it right away!

    How would you advise that we track cases where our agents do not agree with the intent set by the AI, no matter if it's set with a low or high confidence level. Is there a setting within the AI set up to indicate that the AI is wrong or should we set up some work arounds, like a check box for the agent to indicate that the intent is not suitable? Or a dropdown with suitable/not-suitable intent... What are your thoughts about this?

    Thanks for the informative and practical guides here and in form of videos as well, which makes this big topic easier to comprehend and implement.  

    0
  • Jake Bantz
    Zendesk Product Manager

    Hi Tatiana Christensen,

    I'm glad you're finding use out of the resources we've put together! There are a couple of approaches you could take when the agents see the intents as incorrect. You could encourage the agent to pick an intent which better fits the ticket and report on those values as outlined in this article, or you could implement a workflow change like you suggested, so that you can see the original value of the intent and decide yourself which intent was best suited to the ticket.

    As you called out, when you look at these tickets, you can look at the confidence level and determine if a workaround or workflow update is only needed for something with a low confidence, but higher confidence matters seem ok. You determine the flexibility of the process.

    Hope that helps!

    0

Please sign in to leave a comment.

Powered by Zendesk