Chapter 1, AI Solutions on the Salesforce Einstein Platform, starts by clarifying why it is a good idea to build AI solutions on Salesforce and what business and technical benefits this approach can have. It will then present a bird's-eye view of the various components that will be discussed throughout the book, present a basic architectural view of Salesforce Einstein, and then continue with a discussion of how architecting AI solutions is different from architecting traditional solutions. The chapter ends by previewing the structure of the parts and chapters to come and giving a preview of the Pickled Plastics Ltd. scenario that will be expanded throughout.
Chapter 2, Salesforce AI for Sales, covers the core Sales-related AI options in Salesforce. It will go through Einstein Lead and Opportunity Scoring, Einstein Forecasting, Einstein Activity Capture, and Einstein Conversational Insights, and covers the main features and configuration options. For each topic, there will also be a discussion of the pros and cons and what options an architect has if the limits of the feature are reached. As part of each feature discussion, it will reference the scenario that is used throughout the book to give a real-world grounding.
Chapter 3, Salesforce AI for Service, covers the core Service-related AI options in Salesforce. It will go through Einstein Bots, Case Classification and Routing, Einstein Article Recommendations, and Einstein Reply Recommendations, and covers the main features and configuration options. For each topic, there will also be a discussion of the pros and cons and what options an architect has if the limits of the feature are reached.
Chapter 4, Salesforce AI for Marketing and Commerce, starts by going through the integration architecture between core Salesforce, Marketing, and Commerce clouds to show how one needs to think differently about architecting across multiple clouds. It will then focus on the features of first Marketing Cloud Einstein and then Commerce Cloud Einstein. These will be covered in slightly less depth than the Sales and Service features due to the large number of features to cover, but will still be covered in sufficient depth to make an architectural assessment of their potential inclusion in a solution.
Chapter 5, Salesforce AI for Industry Clouds, covers how Einstein has been brought into Salesforce's various industry clouds, including the Health, Financial Services, Manufacturing, Consumer Goods, Education, and Non-profit clouds. As most of these features have been created using other elements rather than being unique, this is more a showcase for how Einstein features can be used than a discussion of new technical material.
Chapter 6, Declarative Customization Options, shows how you can use generic Einstein declarative features to create your own solutions, as well as discussing when that can be the right approach. It will first show some of the many ways you can embed and configure Einstein Next Best Action, then walk the user through making a good prediction with Prediction Builder, and finish with creating a story using Einstein Discovery.
Chapter 7, Building AI Features with Einstein Platform Services, will take you through three examples of using the Einstein Platform Services APIs to create custom AI solutions for the platform. Along the way, it will also discuss the architectural choices and trade-offs involved. The examples will move from an image classifier to a form text recognizer to a sentiment analysis application, all integrated into a normal Salesforce Sales or Service workflow.
Chapter 8, Integrating Third-Party AI Services, takes you through three examples of custom development, in this case using external third-party services as part of normal Sales/Service workflows on Salesforce. For each example, the architectural setup and the relevant choices in relation thereto will be discussed. The first example will show automated translations with the Google Translation API, the second will extract information from documents attached to a Case, and the third will train a custom prediction model using Amazon SageMaker.
Chapter 9, A Salesforce AI Decision Guide, presents a summary of all the key architectural decisions and trade-offs that are relevant to the technologies discussed in the book. It will start by introducing the guide and how to use it, then move on to a discussion of common use cases for AI technologies. For each use case, it will make architectural suggestions based on the key dimensions of the particular use case. It will then do a similar thing, but focusing instead on common technical requirements and constraints that may impact the architectural choice to be made.
Chapter 10, Conclusion, summarizes the main points of the preceding section. First, it will remake the case for using out-of-the-box declarative features when this is possible and summarize the substantial architectural benefits of doing so. Then it will revisit the key considerations for going above and beyond these features and the ways this can be done. It will end by giving some hints for other resources that can be consulted should the reader wish to go further in various directions.
