Accelerated Development

Using the Microsoft Bot Framework, you can build, connect, deploy, and manage intelligent chatbots that interact with users through web sites, mobile apps, Cortana, Microsoft Teams, Skype, Slack, Facebook Messenger, and more.

Azure Bot Service provides developers with an integrated environment for chatbot development using Microsoft Bot Framework connectors and bot-builder SDKs. With such functionality, developers can use out-of-the-box templates, such as forms, in business scenarios; and language, questions, and answers can be used for user engagement.

Creation of Intelligent Bots with Cognitive Services

You can build a bot that recognizes users in photos, moderates user content, provides smart recommendations, translates languages, and more. Cognitive Services facilitates your bot in seeing, hearing, understanding, and interpreting in a human way.

User Engagement

Chapter 2 described the integration of chatbots with business applications. Our objective behind the integration of chatbots with other applications is to demonstrate the convenience of an Azure chatbot. A high level of coding is not necessary. Using the standard services available in Azure Portal, integration is easy to achieve.

Commerce Chatbots

Information Chatbots

Informational chatbots are designed to answer questions defined in the form of a knowledge set or FAQ using Azure Cognitive Services. QnA Maker attempts to answer more open-ended questions using Azure Search. A typical workflow is shown in Figure 3-3.

1. 1.

   A user accesses their device.

    
2. 2.

   The Azure Active Directory authenticates the user.

    
3. 3.

   The user posts a query inside the chatbot.

    
4. 4.

   Cognitive Services returns a FAQ created using QnA Maker .

    
5. 5.

   A user defines a valid search string if the FAQ is irrelevant.

    
6. 6.

   The chatbot processes the query and submits the query to Azure Search, which returns information based on available data.

    
7. 7.

   Application Insights captures the user personas.

    

Enterprise Chatbots

Using LUIS and Azure Bot Service, enterprises can build powerful productivity chatbots to streamline common activities by integrating with external systems such as Office 365 Calendar, customer cases stored in Microsoft Dynamics CRM, and much more. A typical workflow is shown in Figure 3-4.

1. 1.

   A user accesses the enterprise’s productivity chatbot.

    
2. 2.

   Azure Active Directory authenticates the user’s identity.

    
3. 3.

   The chatbot queries Office 365 Calendar using Azure Graph.

    
4. 4.

   Using data collected from the calendar, the chatbot accesses information in another system (for example, Microsoft Dynamics CRM ).

    
5. 5.

   Information is returned to the user.

    
6. 6.

   Application Insights tracks user personas in the organization.

    

Cortana Chatbot

Using a Cortana chatbot, anybody can schedule a mobile auto maintenance appointment using a cognitive voice service. Cortana chatbots act as a personal assistant. In this example, it helps the user speak with a representative of any auto shop to schedule an appointment. The chatbot can provide users with a list of maintenance services, availability, and time required to implement the service. Before scheduling an appointment, Cortana checks for meeting conflicts and, based on a free slot, an appointment is scheduled. A typical workflow is shown in Figure 3-5.

1. 1.

   A user access a Cortana chatbot from their device.

    
2. 2.

   Using text or voice request, Cortana processes the request.

    
3. 3.

   Because of the integration of Cortana with a calendar, conflicts are checked before scheduling an appointment.

    
4. 4.

   The chatbot sends a query to the auto service representative regarding available appointment times.

    
5. 5.

   The user chooses the appointment time and sends a confirmation.

    
6. 6.

   Application Insights analyzes future developments for the Cortana chatbot.

    

IoT Chatbots

IoT chatbots make it easy to control devices around the home, such as lighting, using voice or interactive chat commands. A typical workflow is shown in Figure 3-6.

1. 1.

   A user logs in to Skype and accesses the IoT chatbot.

    
2. 2.

   Using voice or text commands, the user requests the IoT chatbot to turn on the lights in their home.

    
3. 3.

   The request is transmitted to a third-party service that has access to the IoT device.

    
4. 4.

   The request is shared with the user.

    
5. 5.

   Application Insights identifies user patterns and generates new ideas for developing IoT chatbots.

    

IoT chatbots are so simple that users can use channels such as Skype or Slack as chatbots to interact with home devices, as just described.

Some Factors Do Not Guarantee Bot Success

The First Impression of a Chatbot Really Matters

When we develop a mobile app, the first user interface we think of showing to users is a menu as soon as they open a mobile app. From there, they navigate to different places in the app. Intuitively, looking at the user interface, users understand different areas, such as the About Us page, team details, downloading, privacy policy, and others. When we develop a chatbot, we need to think similarly. Let’s look at a couple chatbot user interfaces.

In Figure 3-7, the first user interface starts with an open-ended question: How can I help you? If users do not know what the chatbot can do, there is strong possibility they may get confused and ask a number of queries to resolve issues. If the chatbot doesn’t explain what it can do, how will users know its capabilities?

If you look at design 2 in Figure 3-8, it looks very precise. In this user interface, the chatbot definitely informs users of what it can do. If you provide menu options, as in the case of mobile apps, users are likely to find information with a minimal number of steps. In addition, having menus in place saves users time by not requiring them to enter text or too many character the chatbot may not understand. With menu options, users can access information with one click.

And so on. Posing specific questions takes users to destinations and produces a better user experience. Another important aspect: If your chatbot collects personal data, the chatbot user interface should have a privacy policy and inform users for what purpose and in what manner their data will be used.

Conversation Flow

In general, web sites or mobile apps have multiple user interfaces that are nothing but multiple screens. These user interfaces are connected with each other and, based on input provided in the user interface, redirection to another user interface takes place. Mostly, web sites or mobile apps have one main screen where all navigation links to other user interfaces are present, or users are asked to enter some other input before being redirected to an alternate screen. User interfaces consist of visually appealing designs and colors. To conclude, web sites and mobile apps contain user interfaces that need to be designed meticulously so that users do not get confused while navigating to different links. In addition, they should be able to reach the home page from any other user interface.

Similarly, chatbots also have multiple user interfaces, with one being the main user interface, similar to web sites and mobile apps. But user interfaces in chatbots contain dialog so the user can interact with the chatbot. Dialog can instruct users to take action before they get their results. The chatbot user interface could be plain text, with dialog to links or images, or it could be an input form where users are forced to enter information to get output.

Dialogs help developers to separate various scenarios and build user interfaces for each corresponding scenario. For example, developers can create a different dialog for users to choose their type of pizza crust and another dialog for users to make a payment after order confirmation.

Figure 3-9 shows the flow of a traditional application compared to the dialog flow of a bot.

In Figure 3-9, we see the traditional app’s main screen invokes a New Order user interface, which remains in control until it is either closed or invokes another user interface. When the New Order user interface is closed, the user is redirected to the main screen. The user has to navigate multiple user interfaces.

With a chatbot, everything begins with the root dialog. The root dialog invokes the New Order dialog. The New Order dialog is in control until it invokes other dialog or closes it. If the New Order dialog closes, then control of the conversation is returned to the root dialog. The user interface stays the same even if the flow of information is the same as in the web app.

Dialogs, Stacks, and Humans

During the actual working of a chatbot, users navigate across dialogs, create a dialog stack, and return to where they started. Referring back to Figure 3-9, the user starts with the root dialog, invokes the New Order dialog, and, finally, the Product Search dialog. At the final stage, the user selects a product, confirms it in the Product Search dialog, and completes the order. The user exits the New Order dialog after the order is confirmed, then arrives back at the root dialog. In an ideal situation, users follow a linear path, but this doesn’t happen often because people frequently change their mind. Let’s consider the example in Figure 3-10.

Although the bot may have constructed a logical stack of dialogs, users may decide to do something entirely different or ask a question unrelated to the current topic. In Figure 3-10, the user asks a question instead of providing the yes-or-no response expected. How should the chatbot dialog respond?

• Force the user to answer the first question.

• Attempt to solve the user’s question and then move back to yes/no question.

• Disregard all previous dialog, reset the entire dialog stack, and start from the beginning.

There is no right answer to this question. The best solution to this kind of situation is related to the scenario and the way the user expects the chatbot to respond. As conversation becomes complex, managing dialog stacks becomes complex. For complex branching situations, it is easy to create a logical flow to keep track of user conversations.

Design Bot Navigation

The Stubborn Chatbot

The stubborn bot insists on maintaining the current course of the conversation, even though the user might steer into a different context. Consider the scenario in Figure 3-11.

To handle this type of situation, know that users can move out of context at any time. If chatbots ask the same question repeatedly when users move out of context, the chatbot is not called a “smart” bot. There is a good chance the user’s frustration level will increase and lead to a bad user experience.

The Clueless Chatbot

Clueless chatbots respond in a nonsensical manner when they do not understand user requests. A user may use common words such as help or cancel, with the expectation that the chatbot will understand and deliver the proper answer. Consider the scenario in Figure 3-12.

Ideally, we want to design chatbots to cover all possibilities, but this is close to impossible because we cannot predetermine user behavior. In the scenario presented in Figure 3-12, we can make use of middleware functionality, which logs every message and query in external data sources. By defining the logic in the middleware, we make information accessible to every exchange with the user.

The Mysterious Chatbot

The mysterious chatbot fails to acknowledge the user’s input immediately. Consider the scenario in Figure 3-13.

The chatbot could be in an outage state or could be compiling the user request. Both situations produce a poor user experience. Therefore, it is important to indicate to the user that the chatbot is processing input. This can be sent in the form of an acknowledgment message or a graphic that indicates user input is being compiled.

The Captain Obvious Chabot

The Captain Obvious chatbot provides unsolicited information that is completely obvious and therefore useless to the user. Consider the scenario in Figure 3-14.

Design your chatbot to provide useful information so that users engage and receive a better user experience.

The Unforgetting Chatbot

The unforgetting chatbot integrates information inappropriately from past conversations into the current conversation. Consider the scenario in Figure 3-15.

It is important to maintain the flow of the current conversation to reduce user confusion and frustration, and to increase the chance of users engaging in conversation with the chatbot.