Book Image

Voicebot and Chatbot Design

By : Rachel Batish
Book Image

Voicebot and Chatbot Design

By: Rachel Batish

Overview of this book

We are entering the age of conversational interfaces, where we will interact with AI bots using chat and voice. But how do we create a good conversation? How do we design and build voicebots and chatbots that can carry successful conversations in in the real world? In this book, Rachel Batish introduces us to the world of conversational applications, bots and AI. You’ll discover how - with little technical knowledge - you can build successful and meaningful conversational UIs. You’ll find detailed guidance on how to build and deploy bots on the leading conversational platforms, including Amazon Alexa, Google Home, and Facebook Messenger. You’ll then learn key design aspects for building conversational UIs that will really succeed and shine in front of humans. You’ll discover how your AI bots can become part of a meaningful conversation with humans, using techniques such as persona shaping, and tone analysis. For successful bots in the real world, you’ll explore important use-cases and examples where humans interact with bots. With examples across finance, travel, and e-commerce, you’ll see how you can create successful conversational UIs in any sector. Expand your horizons further as Rachel shares with you her insights into cutting-edge voicebot and chatbot technologies, and how the future might unfold. Join in right now and start building successful, high impact bots!
Table of Contents (16 chapters)
Voicebot and Chatbot Design
Contributors
Preface
Other Book You May Enjoy
Index

Challenges and consequences of the FB Messenger bot


The Wit.ai platform offers a tool to build an initial bot, where businesses can communicate with clients and offer services automatically. Like other solutions that we've discussed, when complexity is involved in interactions, those tools are very limited and heavier programming is required.

The integration and connectivity between the various stacks are also not easy to use and require a deeper development background. In addition, while being able to learn from a user's request using the inbox panel is of great value, the problem is usually when you have thousands or tens of thousands of requests running through the system, and a manual detection and re-mapping is nearly impossible.

In fact, FB itself shared that 70% of its automated bot interactions fail. A failed conversation means that the end user didn't get what they were asking for. While improving the NLU capabilities is a rather large task, FB decided to deal with this situation...