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)
1
Section 1: Salesforce and AI
3
Section 2: Out-of-the-Box AI Features for Salesforce
8
Section 3: Extending and Building AI Features
12
Section 4: Making the Right Decision

Speeding up chat with Einstein Reply Recommendations

Einstein Reply Recommendations gives AI-powered suggested replies to agents using Salesforce Chat. In the following sections, you will learn how this works and what you need to adopt it successfully.

Einstein Reply Recommendations basics

Einstein Reply Recommendations is a way for you to leverage your old chat transcripts to generate suggested replies to common customer queries using a machine learning model. It works similarly to standard Quick Text, which you would write manually in so far as the agent is concerned, but the actual text is generated from historical conversations. Before you start getting concerned about inappropriate suggestions surfacing from some quirk of the AI compromising your customer conversations, it is worth noting that only suggestions that you have reviewed and approved will be suggested.

When you turn on this feature, Salesforce will build a model for leveraging your historical chat transcripts...