Book Image

Architecting AI Solutions on Salesforce

By : Lars Malmqvist
Book Image

Architecting AI Solutions on Salesforce

By: Lars Malmqvist

Overview of this book

Written for Salesforce architects who want quickly implementable AI solutions for their business challenges, Architecting AI Solutions on Salesforce is a shortcut to understanding Salesforce Einstein’s full capabilities – and using them. To illustrate the full technical benefits of Salesforce’s own AI solutions and components, this book will take you through a case study of a fictional company beginning to adopt AI in its Salesforce ecosystem. As you progress, you'll learn how to configure and extend the out-of-the-box features on various Salesforce clouds, their pros, cons, and limitations. You'll also discover how to extend these features using on- and off-platform choices and how to make the best architectural choices when designing custom solutions. Later, you'll advance to integrating third-party AI services such as the Google Translation API, Microsoft Cognitive Services, and Amazon SageMaker on top of your existing solutions. This isn’t a beginners’ Salesforce book, but a comprehensive overview with practical examples that will also take you through key architectural decisions and trade-offs that may impact the design choices you make. By the end of this book, you'll be able to use Salesforce to design powerful tailor-made solutions for your customers with confidence.
Table of Contents (17 chapters)
Section 1: Salesforce and AI
Section 2: Out-of-the-Box AI Features for Salesforce
Section 3: Extending and Building AI Features
Section 4: Making the Right Decision

Introducing Einstein declarative features

In this chapter, we change gears again. So far, we have primarily been looking at features that come out of the box with various Salesforce clouds. We've had to do some configuration, but nothing particularly strenuous. Mostly, things work out of the box.

While that can be a great strength, it also means that when you hit the limits, they are hard. Typically, you can't bend a feature to match requirements, even though, technically, the requirements are quite close to the core functionality.

Once you hit the limit, your next port of call should be to see if you can meet your requirements using some combination of declarative features to avoid the overhead of having to use code and train your own models. Powerful as such solutions might be, they are also more expensive, higher-maintenance, and riskier than declarative solutions.

In this chapter, we will go through three features of the Einstein platform that can help you create...