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

Configure 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.

    Get Started page for Einstein Case Classification
  2. Name your model and then click Next.
  3. Decide which type of cases your model will focus on. If you want, define criteria that narrow the scope of your model to a subset, or segment, of cases. Your segment limits which closed cases Einstein learns from and which new cases get predictions. Then, click Next.

    Segmentation screen in the setup flow
    You can use segments to focus a model on a particular business unit. For example, use record type-based segments to have one model predict 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 predictions.

  4. If you want specific cases to serve as examples, define criteria to identify example cases. Einstein will learn only from cases that meet your criteria. If you defined a segment, your example cases come from your segment. Then, click Next.

    Example case set screen in the setup flow
    Example cases help you point Einstein to cases whose completed fields and field values reflect your best practices. For help understanding when to use segments and example cases, check out Einstein Case Classification Key Concepts in the Salesforce Help.

  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 data
    If 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


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 under Configure Data.
  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.

Configure Field Prediction Settings

After your model is built, it’s time to decide how much prediction automation you’re comfortable with. At a minimum, Einstein recommends the top three field values for each field in your model. You can also have Einstein select or automatically save the best field value, and set a percentage-based prediction confidence threshold for each option.

Update a field’s prediction settings at any time, whether or not the model is active. 

  1. On the model’s Setup tab, click Edit under Configure Predictions and select a field.

    Review button on the Model Details page
  2. To let Einstein show the field with the best value already selected, turn on Select Best Value. Agents see a BEST label next to the value and must confirm and save the value. Then drag the slider to choose a prediction confidence threshold, which is your minimum required confidence level for selecting the best value. A prediction’s confidence level represents the likelihood that the best recommendation for the field value is correct.

    Select Best Value setting with prediction confidence graph
  3. To let Einstein update and save the field without agent review, turn on Automate Value. Then drag the slider to choose a prediction confidence threshold for auto-updating the field. Because updating a case is an automated action, this confidence threshold must be higher than the Select Best Value threshold.

    Automate Value setting with prediction confidence graph
  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 let Einstein start making predictions, activate your predictive model. On the model’s Setup tab, click Activate. Einstein makes recommendations on a case right after the case is created. You may need to refresh the page to see them.

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

  • At a minimum, 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 your threshold, Einstein shows the field with the best value already selected next to the word BEST.
  • If you enabled Automate Value for a field and the prediction confidence is above your threshold, Einstein saves the best 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. 



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-hand chart indicates how often one of the top three recommended values matches the final field value at the time the case is closed. The right-hand chart shows how often the top-recommended value matches the final field value when the case is closed. When a case with field predictions is closed, the dashboard refreshes.

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.

Keep learning for
Sign up for an account to continue.
What’s in it for you?
  • Get personalized recommendations for your career goals
  • Practice your skills with hands-on challenges and quizzes
  • Track and share your progress with employers
  • Connect to mentorship and career opportunities