Einstein Recommendation Builder Blog

  • Share this:

Einstein Recommendation Builder is a tool that predicts what a user may or may not like among a list of given items. Admin can use a point and click interface to build AI-driven recommendations for custom and standard matching problems.


Einstein Recommendation is used to fulfill the customer expectations by collecting relevant data for all customers and predict their preference of the individual customer, Like Best solution for resolving the cases, Top product to purchase, and more.


It helps majorly in 3 things:

  • Improve Business Outcomes: Deploy real-time, personalized recommendations to boost revenue, customer satisfaction, and more.

  • Build Faster With Clicks: Create Recommendations in a few clicks. No Code

  • Accelerate Decision Making: It provides you with the ability to service actionable(being automated) to your users by combining machine learning and business rules. For this, you can use tools like Einstein's Next Best Action.

Einstein Recommendation is used for many roles like Marketing, HR, Sales, Service, etc. 

  • For a sales team to boost revenue, they can use Upsell or Cross-Sell Recommendations. 

  • For a Service team, they can use the Next Best offer. 

  • For the marketing team, they can use Campaign Recommendations. 

  • For the HR team, they can use Candidate Recommendations.


The term recommendation is common in our day-to-day lives. We may have seen while searching anything in Google, YouTube, Flipcharts, Amazon, Netflix, or any other website. Below the search bar, while clicking on a tab, it suggests recommendations based on our history, rating on a particular product, or based on our preferences. 

So Einstein Recommendation Builder provides this feature in the Salesforce platform, which helps Admin to solve business problems faster and efficiently with AI-powered recommendations. Also, leverage the power of low code tools like Einstein's Next Best Action, Salesforce Flow, to automate those processes(recommendations) or make them actionable.

  • Einstein Next Best Action

It uses predictions to automate the process of choosing the right action to take any Salesforce object.

For example, you see a recommendation on the Contact page for customers who are always late with their payments. This recommendation is to send a reminder email to the faulty customer. Then some customers are punctual, and the Contact page displays a recommendation to offer membership in a rewards program. 

So you find no reason to worry with Salesforce on concerns like customer payments, rewards, etc. It provides you with a built-in strategy for customers.

  • Salesforce Flow

It automates business processes without writing code.

For Example - A customer accepts the Payment recommendation from their Contact page, then a reminder email is sent to the customer's email. At this point, flow is triggered in the background. So with the use of flow, you do not need to send an email manually to every customer.


There are the following steps to build and Deploy a Recommendation:

  • Configure Recommendation  - Gather all relevant data of the customer.

  • Build Recommendation - Analysis of data and create the best solution for the customer.

  • Review Recommendation Quality - Recommendations provide reports and metrics for clarity about how the recommendation builds and help you to evaluate quality before you deploy recommendations.

  • Deploy Recommendation - Last but not least, deploy recommendations for your customer.

Follow the below steps to perform recommendations in your org.

  • Step 1: Go to setup in salesforce org, enter Einstein Recommendation Builder in the Quick Find box, and click it.

  • Step 2: Select the object if you want a recommendation for that object. In this case, For the Recommendation Object item section, select the "Product" object. Then select the Recipient object as "Work Order" that receives the recommendation. And the interaction object is set as "Product Consumed", which stores past interaction between objects(product and Work Order Object) and Click Next Button.

  • Step 3: Enter the name of your recommendation and the API name auto-populated in the API section. Also, describe the recommendation in the description section, then save it.

  • Step 4: Build your recommendation by clicking the build button in the pop-up. It may take some time, depending on your data.

  • Step 5: After completion of the build, you can see the scorecard. If you are satisfied with your scores, then you may deploy your recommendation. If you are not, then you also review it and make changes.

  • Step 6: Deploy your recommendation; it uses Einstein's Next Best Action. In Einstein Next Best Action Section, click Add Strategy button, and through this, it creates strategy by Strategy Builder.

  • Step 7: In Strategy Builder, choose the object you will use to display your recommendations, add a new recommendation to your strategy, and run it.

  • Step 8: Go back to the Work Order page. Then, edit the page in App Builder.

  • Step 9: Drag the Einstein Next Best Action component to the page, add your new Action Strategy, and click the Save button.

  • Step10: Then we can see the product on the work part page. If users accept the recommendation, then the mail is sent to the user's email address with the help of salesforce flow.


  • Recommend Parts on Field Service Work Orders with a Recommendation Template 

For boosting productivity and saving a lot of time by suggesting parts. 

Instead of using predefined rule-based logic, we can use a preconfigured Parts to Work Order template to build an Einstein recommendation builder. You may also create a custom recommendation.


This change applies to Lightning Experience in Enterprise, Performance, Unlimited, and Developer editions.


This feature is available with the Service Cloud Einstein and Lightning Platform Plus licenses.


  • Step 1: Enable your field service features in the salesforce org.

  • Step 2: Go to setup and Enter Field Service Settings in Quick Find Box, Enable and save it.

  • Step 3: You can build custom or template-based recommendations. For the Field Service Template in the New, Recommendation Page, click the Part to Work Order template and click the next button.

  • Step 4: Based on the template, Einstein uses objects that are relevant for a Field Service Recommendation.

  • Step 5: Enter your Recommendation name and then build it.


After completing the build, you can see your scorecard if you want to iterate it or make some changes. For this, clone the recommendation and adjust the settings.


  • Use segments - Segment your Recipient or Recommended Items objects to focus only on relevant records.

  • Exclude irrelevant fields - By default, Einstein considers all the fields Recommended Items objects. So exclude those that are not relevant.

  • Define positive and negative interactions - Always define positive interactions, which helps to improve performance. For example - contact purchases a product. Negative interaction is not necessary, but it helps in recommendations like predictive signals. For example - a prospect explicitly rejects a promotion.

Vibhuti Rai

Vibhuti Rai

My name is Vibhuti Rai. I am Cloud Apps Engineer at mindZcloud Technologies. I am happy to share new things that I learn. Hope this Blog helps you to enhance your knowledge.