1. Introduction to Chat Bots
In recent years, chat bots and artificial intelligence (AI) have become a hot topic in the tech sector and the public imagination. Chat bots, computer programs that can communicate using natural language, are doing everything from ordering pizza to buying clothes to saving money on parking tickets Initially, developing a chat bot was tantamount to developing an integration with a messaging platform. There was no easy way to represent a conversation flow in code. When Microsoft created the Bot Framework and the Bot Builder SDK, this changed. Microsoft created a rich environment in which the developer was liberated from the concerns of integrating with individual channels and could focus on writing code that performed the conversational tasks a chat bot needs to accomplish. The Bot Builder SDK provided a generic approach to the development of conversational experiences. Microsofts Bot Connectors implemented the logic to translate from the generic format to channel-specific messages.
The result is that chat bot development has become significantly more accessible to millions of developers. Engineers no longer have to learn the ins and outs of integrating with something like Facebooks Messenger APIs or Slacks Web API. Instead, developers focus on core bot logic and the conversational experience. Microsoft worries about the rest.
The Bot Builder SDK is available for .NET and Node.js and is run as an open source MIT-licensed project on GitHub. The team is active in both development and responding to the various issues that development teams run into. And the team is friendly to boot!
In December 2017, Microsoft made both the Bot Framework and the Language Understanding Intelligence Service (LUIS) generally available. LUIS is Microsofts natural language service that will aid us in adding conversational intelligence to our bots. The Bot Framework is now also called the Azure Bot Service ; the two refer to the same thing. As implied by the name, the Azure Bot Service is now a full-fledged part of Microsofts Azure cloud offering. Microsoft has also provided free tiers of the service so we can play with the framework to our hearts content. All of the samples and techniques in the book can be experimented with at no cost!
Over the last years, all the big tech companies like Microsoft, Facebook, and Google, as well as many smaller ones, have been taking a stab at creating the best and easiest-to-use chat bot development frameworks. The field is very dynamic. Frameworks come and go. Things seem to change daily. Despite the spaces dynamic nature, Microsofts Bot Framework remains the best platform for developing powerful, fast, and flexible chat bots. I am thrilled to take you on a journey through chat bot development using this tool.
The Expectations Game
For more than two years now, a substantial chunk of my conversations with customers has been spent on discussing chat bot capabilities, what they are, and, more importantly, what they are not. Our culture largely confounds chat bot abilities with artificial intelligence, and it is easy to see why. Some chat bots employ rich natural language capabilities, leading us to imagine there is more to them. Likewise, voice-based digital assistants such as Cortana, Alexa, and Google Assistant live in our homes and may be spoken to like real humans. Why wouldnt chat bots display more intelligence?
The culture is additionally permeated with references to the likes of IBMs Watson on Jeopardy,
These and many other stories highlight the investment and interest in these techniques, foreshadowing the kind of AI-driven interactions with our devices that we are heading toward. Developments in the field of AI have changed the way we interact with, as well as what we expect from, our technology. Assigning human attributes and abilities to our devices is becoming more prevalent. Thinkers in the cognition and science-fiction spaces have long grappled with this possibility as popularized by Asimovs Three Laws of Robotics , a set of rules that robots obey to ensure the robots dont go after humans. And now that there are some clear and concrete AI examples in the real world, that kind of reality seems so much closer.
Yet, reality does not match the expectations set forth by AIs successes in some very specific problem areas. Although we have made tremendous leaps and bounds in terms of natural language processing, computer vision, emotion detection, and so forth, composing all of these pieces into a human-like intelligence, usually referred to as Artificial General Intelligence AGI , is not yet within our grasp and is not a realistic target for chat bots. For every article that celebrates the tremendous achievements in the AI space, theres a matching article downplaying the hype around the same technology and showing examples of why this type of AI is still far from perfect (think of the articles showing all the images that computer vision algorithms still cant correctly classify). As with any technology that has been hyped up in the media, we must be reasonable with the expectations we set on it.
Are our bots going to be agents with human-level intelligence having conversations with our users? No. Given the technology and the tasks we want our bots to accomplish, can we make our bots perform those tasks very well? Absolutely. This book aims to equip the reader with the necessary skill to build compelling, engaging, and useful chat bots. It is up to the engineer how much of the latest AI techniques you want to incorporate during this journey. Certainly, these techniques are not required for a great chat bot.
What Is a Chat Bot?
At the most basic level, a chat bot , also referred to simply as a bot throughout this book , is a computer program that can take user input in natural language and return text or rich media to the user. The user communicates with the chat bot via a messaging app , such as Facebook Messenger, Skype, Slack, and others, or via a voice-activated device such as the Amazon Echo, Google Home, or Harmon Kardons Invoke powered by Microsofts Cortana.
Figure illustrates our first bot built using Microsoft Bot Framework. This bot simply returns the same message to the user prefixed by the string echo: . The logic that runs this experience on the Bot Framework is brain-dead simple.
var bot = new builder.UniversalBot(connector, [
function (session) {
// for every message, send back the text prepended by echo:
session.send('echo: ' + session.message.text);
}
]);
Figure 1-1
A simple echo bot
This is a chat bot. Basic and not terribly useful, right? We can just as easily create a YouTube bot that, given user text input, searches for videos on that topic and sends the user links to those videos (Figures ).
This is another basic bot that does just one thing, and it kind of does it well. It integrates with the YouTube API, uses your input as a search parameter, and returns what are referred to in the Bot Framework as cards , something we will explore later in the book. The images make for a richer and more engaging experiencea bit more interesting but still rather basic.
