How the virtual service agent’s data set is trained

The virtual service agent develops and trains a machine learning model that's tailored to your organization, based on a training data set.

The training data set includes:

• intents and training phrases created by your project admin

• intents and training phrases generated using your project’s historical data that your project admin uses to create an intent

• intents and training phrases suggested by us that your project admin uses to create an intent

• intents and training phrases created using any of the above methods that have been edited or modified by your project admin

This tailored machine learning model is used to understand questions from your customers in the context of your organization. Based on the configurations set by your organization admin and/or project admin, the virtual service agent responds to your customers using conversation flows or Atlassian Intelligence answers. Read more about Atlassian Intelligence answers in the virtual service agent.

The trained machine learning model developed for your organization won’t be shared with other Atlassian customers. Analysis of Jira Service Management issues and chat transcripts in the connected Jira Service Management project submitted by your customers is used to serve your experience only.

If you decide you no longer want to use the virtual service agent, your organization admin can turn it off. Find out more about turning off the virtual service agent.