Automate your work using Customer Intents

Updated 3 months ago by Victor Suo

If you're not familiar with the basics of Rules in Gorgias, please check out the following article before you get started: Getting started with rules

Customer intents

If you want to automate repetitive tasks, such as tagging tickets or responding to common questions, but do not want to spend a lot of time setting up rules, Gorgias offers a much more convenient way to simplify rules by using customer intent detection.

Each time a new customer message arrives, our system will try to figure out the customer's intent. Intents include:

  • shipping/status
  • refund/request
  • exchange/request
  • order/damaged
  • order/cancel
  • and many others

Intents can be used to automate your ticket processing workflow.

Please note that, if your rule triggers on the 'ticket updated' event, then this rule won't be able to register the intents in the ticket messages as it can not read the message body. In other words, you won't be able to use 'message body' or 'message intent' conditions in a rule.

List of supported customer intents

Name

Description

discount/request

Asks for a discount or needs help applying one

exchange/request

Requests to exchange a received product or get a replacement

exchange/status

Requests a status update on an ongoing exchange

feedback

Customer provides feedback on a product, brand or customer service.

Can be combined with `positive` or `negative` sentiments for more fine-grain classification.

order/cancel

Requests to cancel an order before it ships

order/change

Requests to edit an order before it ships

order/damaged

Received order contains damaged item or customer needs troubleshooting

order/wrong

Received order contains wrong/missing item

other/no_reply

A message that does not need a reply. The ticket can probably be closed*

other/question

General question on product, brand, policies ...

other/thanks

The customer expresses gratitude. The ticket can probably be closed**

product/question

Question about a specific product (usage, properties...)

product/recommendation

Requests help choosing a product (size, color, model...)

refund/request

Requests to proceed a refund

refund/status

Requests a status update on an ongoing refund. Can overlap with return/status

return/request

Requests to return a received product

return/status

Requests a status update on a received product

shipping/change

Requests to change shipping information (address, name)

shipping/delivery-issue

Notifies of an error with a package (lost, not in the mailbox...)

shipping/policy

Asks information on shipping (countries, usual delays)

shipping/status

Asks a status update on an expected order

stock/request

Asks about the availability of a product

subscription/cancel

Requests to cancel a subscription (auto-shipment, monthly order)

subscription/change

Requests to edit a subscription (frequency, content...)

*other/thanks intent: This intent is often found on messages where the customer is concluding a ticket with a kind word or a thank you message to the agent. Examples of messages that correspond to this intent are "Great - thanks so much! Appreciate the quick response and follow up!", "Thanks so much! Will do!", "Oh ok cool. I think we'll all end up ordering one! Have a great night!" , "". Finding an 'other/thanks' intent on a message often means the ticket can be closed.

**other/no_reply: This intent is often found on messages that do not need to be replied to. Messages that correspond to this intent are for example "Your Amazon order has just been delivered" or "Call ended. Duration: 57s" or "A customer just ordered a ...". Finding an 'other/no_reply' intent on a message often means the ticket can be closed. Social media tags also fall into this category.

Intent feedback

In order to constantly improve on our intent detection system, we have developed a brand new feature that allows you to submit feedback for every single customer message! You can now let the system know what the intent is behind your customers' messages by using the drop-down menu that will appear in the tickets as shown on the screenshot below:

Here's a quick video tutorial on how to use this feature:

So the next time that your intent-based rule is supposed to fire on a ticket, for example, the prediction will be more precise!

You can then get a clear overview of the most recurring inquiries and similar statistics on the brand new Intents statistics page!

Supported languages

Intent detection works in a number of most commonly spoken languages which is a huge advantage! The feature supports 16 most commonly spoken languages, so even if the customer is writing over to you in another language, we can detect the keywords and trigger the rule.

The currently supported languages are:

  1. Arabic (ar)
  2. Chinese (PRC) (zh)
  3. Chinese (Taiwan) (zh-tw)
  4. Dutch (nl)
  5. English (en)
  6. German (de)
  7. French (fr)
  8. Italian (it)
  9. Portuguese (pt)
  10. Spanish (es)
  11. Japanese (ja)
  12. Korean (ko)
  13. Russian (ru)
  14. Polish (pl)
  15. Thai (th)
  16. Turkish (tr)


What do you think? Yay or Nay?