The Definitive Guide to Conversational AI with Dialogflow and Google Cloud

Build enterprise chatbots for web, social media, voice assistants, IoT, and telephony contact centers with Google's Dialogflow conversational AI technology. This book will explain how to get started with conversational AI using Google and how enterprise users can use Dialogflow as part of Google Cloud. It will cover the core concepts such as Dialogflow essentials, deploying chatbots on web and social media channels, and building voice agents including advanced tips and tricks such as intents, entities, and working with context.

The Definitive Guide to Conversational AI with Dialogflow and Google Cloud also explains how to build multilingual chatbots, orchestrate sub chatbots into a bigger conversational platform, use virtual agent analytics with popular tools, such as BigQuery or Chatbase, and build voice bots. It concludes with coverage of more advanced use cases, such as building fulfillment functionality, building your own integrations, securing your chatbots, and building your own voice platform with the Dialogflow SDK and other Google Cloud machine learning APIs.

After reading this book, you will understand how to build cross-channel enterprise bots with popular Google tools such as Dialogflow, Google Cloud AI, Cloud Run, Cloud Functions, and Chatbase.

WHAT YOU WILL LEARN

* Discover Dialogflow, Dialogflow Essentials, Dialogflow CX, and how machine learning is used
* Create Dialogflow projects for individuals and enterprise usage
* Work with Dialogflow essential concepts such as intents, entities, custom entities, system entities, composites, and how to track context
* Build bots quickly using prebuilt agents, small talk modules, and FAQ knowledge bases
* Use Dialogflow for an out-of-the-box agent review
* Deploy text conversational UIs for web and social media channels
* Build voice agents for voice assistants, phone gateways, and contact centers
* Create multilingual chatbots
* Orchestrate many sub-chatbots to build a bigger conversational platform
* Use chatbot analytics and test the quality of your Dialogflow agent
* See the new Dialogflow CX concepts, how Dialogflow CX fits in, and what’s different in Dialogflow CX

WHO THIS BOOK IS FOR

Everyone interested in building chatbots for web, social media, voice assistants, or contact centers using Google’s conversational AI/cloud technology.

Lee Boonstra is a senior developer advocate at Google working with conversational AI. In this role she focuses on Dialogflow, Contact Center AI and speech technology. Lee is based in Amsterdam, the Netherlands, where she has been working with different technologies over the past 15 years, ranging from web/mobile, Ext JS, Sencha Touch, and Node.js, to conversational AI, Dialogflow, Actions on Google and Contact Centers.

Over the years she has helped many brands and enterprises to build and deploy conversational AI solutions (chatbots and voice assistants) at enterprise scale. She’s worn different hats from engineer to technical trainer to sales engineer to developer advocate. Prior to Google, Lee worked at Sencha Inc.

You can find Lee on online via the Twitter handle: @ladysign.

CHAPTER 1: INTRODUCTION TO CONVERSATIONAL AI

Why do some chatbots fail?

Machine learning simply explained

Chatbots and machine learning

Machine learning and Google

About Dialogflow

Dialogflow essentials & Dialogflow CX

About Google Cloud

About Contact Center AI

Other Google conversational AI products

Actions on Google / Action Builder

AdLingo

Chatbase

Duplex

Meena

Summary

Reference

CHAPTER 2: GETTING STARTED WITH DIALOGFLOW ESSENTIALS

Creating a Dialogflow agent

Creating Dialogflow agents for enterprises

Configuring your Dialogflow project

Summary

Reference

CHAPTER 3: DIALOGFLOW ESSENTIALS CONCEPTS

Setting up intents

Creating custom entities

Creating intents with entities in training phrases

Keeping context

Testing in the simulator

Summary

Reference

CHAPTER 4: BUILDING CHATBOTS WITH TEMPLATES

Creating prebuilt agents

Enabling small talk modules

Creating a FAQ knowledge base

Summary

Reference

CHAPTER 5: REVIEWING YOUR AGENT

Validating your Dialogflow agent

Summary

Reference

CHAPTER 6: DEPLOYING YOUR CHATBOT TO WEB & SOCIAL MEDIA CHANNELS

Integrating your agent with Google Chat

Integrating your agent with a web demo

Integrating your agent with a Dialogflow Messenger

Summary

Reference

CHAPTER 7: BUILDING VOICE AGENTS

Building a voice AI for a virtual assistant like the Google Assistant

Building a callbot with a phone gateway

Building bots for contact centers with Contact Center AI

Improving speech quality

Fine tuning voice bots with SSML

Summary

Reference

CHAPTER 8: CREATING A MULTILINGUAL CHATBOT

Building multilingual chatbots

Summary

Reference

CHAPTER 9: ORCHESTRATE MULTIPLE SUB CHATBOTS FROM ONE CHAT INTERFACE

Creating a mega agent

Summary

Reference

CHAPTER 10: CREATING FULFILLMENT WEBHOOKS

Building a fulfillment with the built-in editor

Building webhook fulfillments

Building multilingual webhook fulfillments

Using local webhooks

Securing webhooks

Summary

Reference

CHAPTER 11: CREATING A CUSTOM INTEGRATION WITH THE DIALOGFLOW SDK

Implementing a custom chatbot in your website front-end

Creating rich responses in your chatbot integration

Using markdown syntax & conditional templates in in your Dialogflow responses

Summary

Reference

CHAPTER 12: IMPLEMENTING A DIALOGFLOW VOICE AGENT IN YOUR WEBSITE OR APP USING THE SDK

Building a client-side web application which streams audio from a browser microphone to a server

Building a web server which receives a browser microphone stream to detect intents

Retrieving audio results from Dialogflow and play it in your browser

Summary

Reference

CHAPTER 13: COLLECTING & MONITORING ADVANCED AGENT INSIGHTS

Capturing conversation related metrics to store in BigQuery

Session Id

Date / time stamp

Sentiment score

Language & keyword

Platform

Intent detection

Building a platform for capturing conversation related metrics and redact sensitive information

Detecting user sentiment

Monitoring chat session & funnel metrics with Dialogflow , Chatbase or Actions on Google

Total Usage

The number of requests the intent was matched to and the percentage of all users that matched the intent.

Completion Rate & Drop off Rate / Drop off Place

User retention

Endpoint health

Discovery

Dialogflow Built-in Analytics

Monitoring metrics with Chatbase

Analytics on Actions on Google

Capturing chatbot model health metrics for testing the underlying NLU model quality

True positive - A correctly matched intent

False positive - A misunderstood request

True negative - An unsupported request

False negative - A missed request

Accuracy

Precision

Recall & fallout

F1 score

Confusion matrix

ROC curve

Improve the Dialogflow NLU model with built-in training

Summary

Reference