Save Service Reps Time with Einstein Article Recommendations

To create a model, you select fields from cases and knowledge articles that are most relevant to your business. Based on these associations, Einstein builds a model that leverages your case history data from the last two years. The model:

• Proactively examines new cases as they come in
• Identifies the language and key words, phrases, and text field values within the case
• Suggests articles that are most likely to solve the problem

Recommendations appear right where your service reps work, in the Knowledge component in the Lightning Service Console. There’s no need to manually search for or sift through long lists of articles. Reps can simply select the most relevant articles from a short list to attach to cases and send to customers.

Note

Einstein Article Recommendations is being turned on for Lightning Knowledge starting Summer ’21. It uses a prebuilt model that’s based on generic data, and it has default field and language settings. Service reps can then see Einstein's recommendations in the Knowledge component right away. If your business uses specific case and knowledge fields, customize the model so that Einstein analyzes cases closed or cases within a certain time period in your org and provides more accurate recommendations.Tell Me More.

If you don't want Einstein Article Recommendations in your org, you can turn it off in Setup.

To get Einstein Article Recommendations up and running, follow the setup steps.

• Prepare for Einstein Article Recommendations
  To get the best results from Einstein Article Recommendations, review its data requirements and get tips for testing the feature.
• How Does Einstein Article Recommendations Work?
  Einstein Article Recommendations helps support service reps resolve customer cases efficiently by recommending knowledge articles that were attached to similar cases in the past. Reps don’t have to waste time searching or scrolling through lists of articles, and can quickly attach recommended articles or dismiss them as not helpful.
• Set Up Einstein Article Recommendations
  Set up Einstein Article Recommendations so you can build, activate, and benefit from your custom predictive model. Einstein Article Recommendations analyzes the data in case and knowledge article fields that you select to determine which articles are most likely to solve a customer inquiry. Service reps see recommendations in the Knowledge component of the Lightning Service Console.
• Set Up Agentforce Article Recommendations for Conversations
  Help your service reps address customer voice conversations and messaging by suggesting relevant knowledge articles based on the conversation’s messages or utterances.
• Migrate to Agentforce Article Recommendations from a Previous Version
  If your organization currently uses a previous version of Article Recommendations, follow these steps to switch to the new version.
• Enable Article Recommendations
  To get started, turn on Einstein Article Recommendations.
• Select Languages and Fields for Your Article Recommendation Model
  Select which supported languages to include in your model. Then select fields on cases and knowledge articles that Einstein Article Recommendations can analyze to identify relevant articles.
• Build and Activate Your Article Recommendation Model
  After you select data-rich fields from cases and knowledge articles, build and activate your article recommendation model.
• Give Service Reps Access to Einstein Article Recommendations
  By default, all Lightning Knowledge users see Einstein Article Recommendations in the Knowledge component. A Lightning Knowledge user is a standard user with the Knowledge User permission and read access to Knowledge articles in Lightning Knowledge. If you prefer, you can limit access to users of your choice.
• Add the Knowledge Component to the Lightning Service Console
  If it’s not there already, add the Knowledge component to the Lightning Service Console so your service reps can receive article recommendations.