Intents - Use Cases and FAQs

Updated 3 weeks ago by Tamara Zaric

Using intent detection is a great way to automate a big portion of your daily workflow. This feature will help you set up rules powered by the Gorgias machine learning system in order to recognize the intents behind your customers' messages and auto-tag, close or reply to their tickets.

Before we proceed, you may want to check out this article and see the list of currently supported intents, their definition, how to use the intents feedback feature, and see the list of the supported languages as well.

Let's explore some examples of how you can use customer intents to automate your work!

Common use cases

Intents used as triggers within rules

Even if customer intents are automatically detected on all customer messages, they do not trigger automated actions by themselves. In fact, intents are just additional information embedded within rules and the best way to think about intents is to consider them automated optimized triggers in rules.

The two following screen captures show the kind of rules logic that can be simplified by intents:

  • Without using customer message intents (long, tedious, non-comprehensive)

  • Using customer message intents (easy and comprehensive)

Tagging tickets using customer intents

Here's a rule example that can be used to auto-tag tickets. This rule will tag tickets with "shipping/status", ''order/cancel' and "refund/request" intents:

  1. In Settings, go to Rules and click Create new rule
  2. Select WHEN new message in ticket and/or ticket created as a trigger
  3. Click on THEN, and select an IF statement
  4. Select message -> intents -> contains one of -> "shipping/status"
  5. Click on the following THEN, select Add tag as an action, and type "ORDER-STATUS"
  6. Click Save
  7. Don't forget to activate the rule!

Now each time you receive a message asking about an update on a delivery or an unusual delay, that ticket will be automatically tagged by the rule!

You can then filter tickets based on customer intents by creating views.

Setting up auto-replies based on customer intents

Some customer intents are suitable for automatic replies such as "shipping/status". For that, you can set up a rule that would apply a specific macro when an intent is found on a new customer message.

Since we generally don't want to auto-reply multiple times in a given ticket, we recommend adding an "auto-reply" tag when auto-replying to tickets using intents and use an additional filter to avoid auto-replying twice.

Intents Statistics

You can now check out a brand new dashboard on detected & reported message intents! This overview will help you track the most recurring inquiries, the percentage of messages with submitted feedback, a breakdown of top ten intents per day and a breakdown of individual intent occurrence.

You will find this page on the path Statistics > Intents.

FAQs and troubleshooting:

  • How does intent classification work?
    The Gorgias intent classification system is based on state-of-the-art artificial intelligence algorithms. There is nothing for you to do, it's fully automated!
  • The intent found is wrong, what should I do?
    Unfortunately, that can happen as language comprehension is hard. There are usually a lot of ways to say the same thing. You can combine message intents with simple logic for a better result.
  • Can I use message intents along with usual rules logic (IF ... THEN)?
    Of course, please do!
  • Can a single message have multiple intents?
    Yes, each message can have multiple intents. Besides, if you use intents to auto-tag tickets, tickets will be tagged with the intents of all messages it includes.
  • Do all messages have an intent?
    No, there is a predefined list of possible intents. Moreover, when the system is not confident about a prediction, it will not detect the intent.
  • Can I add an intent to the list of intents that can be detected?
    You can definitely contact us with any particular request or feedback you may have to support@gorgias.com.


What do you think? Yay or Nay?