IBM Developer
  1. Introduction
  2. Private, Hybrid, and Public Clouds
  3. IBM Cloud Pak for Data
  4. Workshop Prep
  5. Setup Watson Discovery
  6. Apache OpenWhisk Setup
  7. Setup Watson Assistant
  8. Putting it Together
  9. What's next?

Introduction

Enhancing customer help desks with Watson Discovery, Assistant, and Cloud Functions on IBM Cloud Pak for Data


What you will build

In this workshop, we walk you through a working example of a web application that utilizes multiple Watson services on IBM Cloud Pak for Data to create a better customer care experience. Here, we use the typical customer care chatbot experience but instead of relying on predefined responses, our dialog will provide a hook that can call out to other IBM Watson services for additional sources of information. In our case, it will be an owners manual that has been uploaded into Watson Discovery.

Using Watson Discovery, document queries will be focused to search the most relevant information found in a typical owner’s manual.

Using Watson Assistant, we will use a standard customer care dialog to handle a typical conversation between a custmomer and a company representitive. When a customer question involves operation of a product, the Assistant dialog will communicate with the Discovery service using a webhook.

The webhook will be created by defining a web action using IBM Cloud Functions (Apache OpenWhisk).

In addition to exploring Watson Discovery, Assistant, and Cloud Functions, we’ll also examine IBM Cloud Pak for Data and discuss the differences between public, private, and hybrid clouds.

The typical customer care chatbot can answer simple questions, such as store locations and hours, directions, and maybe even making appointments. When a question falls outside of the scope of the pre-determined question set, the option is typically to tell the customer the question isn’t valid or offer to speak to a real person.

In this workshop, we’ll provide another option. If the customer’s question is about the operation of a device, we’ll use the webhook feature of Watson Assistant to pass the question onto our Watson Discovery Service, which has been pre-loaded with the device’s owners manual. So now, instead of “Would you like to speak to a customer representative?” we can return relevant sections of the owners manual to help solve our customers’ problems.

What is Watson Discovery?

Watson Discovery is an award-winning cloud search and AI search technology that breaks open data silos and retrieves specific answers to your questions while analyzing trends and relationships buried in enterprise data. Watson Discovery applies the latest breakthroughs in machine learning, including natural language processing capabilities, and is easily trained on the language of your domain. Unlike competitors, a Watson Discovery search app can be deployed on any cloud or on-premises environment.

What is Watson Assistant?

Watson Assistant is IBM’s AI product that lets you build, train, and deploy conversational interactions into any application, device, or channel.

Most chatbots try to mimic human interactions, which can frustrate users when a misunderstanding arises. Watson Assistant is more. It knows when to search for an answer from a knowledge base, when to ask for clarity and when to direct users to a human. Watson Assistant can be deployed in any cloud or on-premises environment – meaning smarter AI is finally available wherever you need it.

What are webhooks and Apache OpenWhisk (and IBM Cloud Functions)?

Based on Apache OpenWhisk, IBM Cloud Functions is a polyglot functions-as-a-service (FaaS) programming platform for developing lightweight code that scalably executes on demand.

A webhook is a mechanism that allows you to call out to an external program based on something happening in your program. When used in a Watson Assistant dialog skill, a webhook is triggered when the Assistant processes a node that has a webhook enabled. The webhook collects data that you specify or that you collect from the user during the conversation and save in context variables, and sends the data to the Webhook request URL as an HTTP POST request. The URL that receives the webhook is the listener. It performs a predefined action using the information that is provided by the webhook as specified in the webhook definition, and can optionally return a response.

In our workshop, the webhook will communicate with an IBM Cloud Functions web action, which is connected to the Watson Discovery service.

Goals

After completing this workshop, you’ll understand how to:

Estimated length of workshop

Prerequisites

Agenda

Let’s get started!

Back
Next