Start tracking your progress
Trailhead Home
Trailhead Home

Turn On Einstein Case Classification

Learning Objectives

After completing this unit, you’ll be able to:

  • Implement case classification.
  • Adjust case classification field prediction settings.
  • Make case classification recommendations visible to support agents.

Set Up Case Classification

Einstein Case Classification is not available in Trailhead playgrounds, but that’s OK. Follow along to learn how an admin would set it up.

Setting up case classification is straightforward—it’s just the data preparation for building a learning model that can take some time. Since Ryan De Lyon has finished auditing closed case data, Maria is ready to set up case classification for Ursa Major Solar. Here are the main steps she follows.

Graphic showing the 8 main steps of implementing Case Classification

  1. Review the data requirements and prepare your data. Maria and Ryan have already completed this step.
  2. Turn on Einstein Case Classification in Setup.
  3. Customize your predictive model by choosing case fields to predict and deciding which closed cases Einstein learns from.
  4. Build your model to let Einstein analyze your case data.
  5. Customize field prediction settings by choosing whether to recommend, populate, or save field values above a specific confidence level.
  6. Give agents access to Einstein Case Classification by assigning permissions and updating your console layouts.
  7. Activate your model to start showing recommendations to agents.
  8. Maintain your model with the help of a prediction performance dashboard.

Enable Case Classification

  1. From Setup, enter Einstein Case Classification in the Quick Find box, and then select Einstein Case Classification .
  2. If you’re using the Try Einstein version of Einstein Case Classification, click Review Terms to review and accept the Master Service Agreement.
  3. Click the toggle to enable Einstein Case Classification. Enabling can take a few minutes.
    Einstein Case Classification Setup page with feature enabled

Customize Your Predictive Model

After case classification is enabled, decide which closed cases Einstein Case Classification should learn from, and choose fields for Einstein to predict. You can have up to five predictive models.

  1. Click Get Started or New on the Einstein Case Classification setup page.
  2. Name your model and then click Next .
  3. Einstein looks at all closed cases that were created in the past six months and include a subject or description. If that’s okay with you, select Yes, use all case data . To narrow the scope of your model to a subset, or segment, of those cases, select No, focus on a segment (advanced option) and use filters to define the segment. Then, click Next .
    Segmentation screen in the setup flowSegments let you create a predictive model for a specific part of your business. For example, you could have one model recommend field values on cases in your Enterprise division, and another cover your Consumer division’s cases. Since Einstein learns from the words customers use to reach out to you, segments can provide helpful context for recommendations. Segments also limit which cases receive recommendations: Einstein makes recommendations only on incoming cases that match your segment criteria.

    For most businesses, using all case data is the best option. If you do decide to define a segment of your case data, make sure the segment includes a healthy number of closed cases created in the past six months. The minimum segment size is 400 cases, but 10,000 is ideal. It's also good to base your segment on a record type or a similar field that indicates a case’s business category.
  4. If you want specific cases to serve as examples for Einstein, select No, learn from specific cases (advanced option) . Then, define criteria for example cases whose completed fields and field values reflect your best practices. If you’re not interested in defining an example case set, click Yes, learn from all recently closed cases. Then, click Next .
    Example case set screen in the setup flowEinstein learns only from cases that meet your criteria and are in the segment you defined (if any). Identifying example cases doesn’t affect which cases get recommendations.

    Most businesses won’t define example cases. If you do define an example case set, Einstein will identify data patterns in those cases to formulate predictions. Identifying example cases doesn’t affect which cases get recommendations.
  5.  Add the fields that you want to predict for your agents. Then, click Next . Field selection screen in the setup flow
  6. Address any warning or error messages to make sure that you have enough data.
    Review screen showing warnings about dataIf you have fewer than 400 closed cases in your segment or example case set or for a field in your model, gather more data or adjust your filters.
  7. Click Finish and move on to building your model. Your new model appears on the Einstein Case Classification setup page.
    Setup page showing list of models
Note

Note

If you create multiple models, you can drag them into priority order in the list. When a case matches multiple models’ criteria, recommendations come only from the highest priority model.


Build Your Predictive Model

After you configure the predictive model, its status changes to Ready to Build. Depending on the model’s scope, building may take a few hours or more. The process runs in the cloud, so there’s no impact on performance for your agents.

  1. On the Einstein Case Classification Setup page, click the model name in the list.
  2. Click the model’s Setup tab.
    Setup tab on the Model Details page
  3. The Fields to Predict section lists the fields whose values Einstein will predict. To remove a field from the model, click Remove from the field’s action menu. To add fields, click Edit on the model.
  4. Click Build  to build the model.

Einstein Case Classification starts analyzing your closed cases and building the predictive model for the fields you selected. To add more fields later, edit the model, add the fields, and then rebuild. After the model finishes building, you can customize each field’s prediction settings and then activate the model to start showing recommendations in the Service Console.

Customize Field Prediction Settings

For each field, decide when and whether Einstein should recommend the field value, populate the field for the agent to review and save, or automatically save the field value. You can update a field’s prediction settings at any time, whether or not the model is active. 

Select a required confidence level for each prediction option so that the action Einstein takes depends on the prediction confidence. Confidence levels range from 50 to 100, and represent the likelihood that the best recommendation for the field value is correct. 

  1. On the model’s Setup tab, click Review and select a field.
    Review button on the Model Details page
  2. Turn on Select Best Value to let Einstein populate, but not save, the field. Then drag the confidence slider to select the minimum prediction confidence that Einstein needs to select the best value. Guidance to the right of the confidence graph helps you choose a level.
    Select Best Value setting with prediction confidence graph
  3. Turn on Automate Value to let Einstein populate and save the field. Then drag the confidence slider to select the minimum required confidence. Since saving a value is a more substantial change than selecting it, this confidence level must be higher than the Select Best Value level.
    Automate Value setting with prediction confidence graphIf you keep Select Best Value and Automate Value  turned off, agents can see recommendations for the field, but must manually select the field value.
  4. Save your changes. They take effect immediately, and the prediction settings appear in the field list.
    Model Details page showing prediction settings for each field

Give Agents Access to Einstein Case Classification

To let agents view and act on Einstein Case Classification field predictions, assign the Einstein Case Classification User permission set to them.

  1. From Setup, enter Permission Sets in the Quick Find box, and then select Permission Sets .
  2. Select Einstein Case Classification User . This standard permission set is already created for you.
  3. Click Manage Assignments and assign users to the permission set.

Add Case Classification to the Service Console

To show Einstein Case Classification recommendations to agents, add the Einstein Field Recommendations component to the Lightning Service Console.

  1. In the Lightning App Builder, open the case record page or a custom page where you want to show case classification recommendations.
  2. Drag the Einstein Field Recommendations component onto the page.
  3. Select Case Classification  as the type. Optionally, update the remaining settings. The Update Action’s layout determines which fields appear in the component.
  4. Save your changes.
    Adding the component in the Lightning App Builder

Activate Einstein Case Classification

When you’re ready to show recommendations to your agents, or apply and save field values, activate your model. On the model’s Setup tab, click Activate .
Activate button on Model Details page

Einstein makes recommendations on a case when the case is created and whenever an agent clicks Einstein Recommendations Available in the console. 

Understand What Agents See

When your model is active, agents can click Einstein Recommendations Available on a case to see recommendations. A green dot appears next to fields with recommendations, and the text at the top of the component changes to Einstein Recommendations Applied .

Component with Einstein recommendations applied

  • Einstein recommends the top three values for picklist and lookup fields on new cases, and the top value for checkboxes (enabled or disabled). Agents can click into a picklist or lookup field to see which values Einstein recommends.
  • If you enabled Select Best Value for a field and the prediction confidence is above the minimum level, Einstein populates the field and labels the selection Best .
  • If you enabled Automate Value for a field and the prediction confidence is above the minimum level, Einstein applies and saves the field value and triggers any case routing or assignment rules that you've put in place.

After the agent reviews the recommendations, they click Save to save the changes. 

Note

Note

If fields are auto-updated by Einstein Case Classification, those updates appear separately in the case feed.

See How Einstein Case Classification Is Helping Your Agents

The Performance dashboard shows Maria how well Einstein Case Classification predictions are working, and helps her decide when to automate field values.

From the model’s Overview tab, select a field and choose a date range to display performance information for closed cases.

Overview tab showing performance graphs

The left chart indicates how often one of the top three recommendations is selected as the final field value at the time the case is closed. The right-hand chart shows how often the top recommendation is selected as the final field value at the time the case is closed. The dashboard refreshes when a case that received Einstein recommendations on that field is closed.

Now that Ursa Major Solar has implemented Einstein Case Classification, support agents have more time to deliver exceptional customer experiences. Case data quality is sure to improve because of less human error determining field values, and Sita and her team are excited to see where machine learning and AI can take her company next.