4. What is Conversational AI?
• A solution that enables a dialog between an AI
agent and a human
• Generically, conversational AI agents are
known as bots
• Bots can engage over multiple channels:
• Web chat interfaces
• Email
• Social media platforms
• Voice
5. Azure Bot Service
• Cloud-based platform for developing and managing bots
• Integration with LUIS, QnA Maker, and others
• Connectivity through multiple channels
? !
7. What new in Microsoft Graph Explorer?
New Features
• Uses Monaco Editor
• Show Access Token
• Show Adaptive Cards
• Shows Snippets
Enhanced Features
• Improved Sample Queries
• Improved History
• Modified Permission View
• Sign In
35. References
• My YouTube Channel
https://www.youtube.com/c/engsooncheah
• Sample Source Code
https://github.com/cheahengsoon/MicrosoftGraphBotShare
Point
• Extend to Microsoft Teams
https://microsoft.github.io/botframework-solutions/clients-
and-channels/tutorials/enable-teams/1-intro/
Editor's Notes
Conversational AI builds on other AI workloads, in particular natural language processing but also machine learning and potentially computer vision. In general, when people use the term "conversational AI", they're referring to bots.
People often associate the term "bot" with a chat interface on a website, but actually this is just one (very common) way to interact with a bot. Bots can be connected to multiple channels, including email, social media, telephone and so on.
Bots are used in multiple different scenarios, such as:
Customer support: for example, answering frequently asked questions or gathering information before handing off to a human customer service representative.
Reservation systems: for example, enabling users to book cinema tickets, flights, or restaurant tables.
Digital assistants: for example, an in-home or cellphone-based virtual assistant that can perform tasks based on instructions.
Online ordering: for example, ordering takeout food for delivery, or products from an online retailer.
Healthcare: for example, providing an automated diagnosis based on symptoms.
Office productivity: for example by helping users find relevant corporate resources for a particular task.
Azure Bot Service provides a platform for creating, deploying, and managing bots. With the Azure Bot Service, developers can use the Microsoft Bot Framework SDK to develop bots and easily deploy and manage them in Azure.
By using the Azure bot Service, you can easily integrate your bot with Azure cognitive services like Language Understanding (LUIS) and QnA Maker, and connect your bot to multiple channels such as webchat, email, Microsoft Teams, and others.
Microsoft Graph exposes REST APIs and client libraries to access data on the following Microsoft cloud services:
Microsoft 365 services: Delve, Excel, Microsoft Bookings, Microsoft Teams, OneDrive, OneNote, Outlook/Exchange, Planner, SharePoint, Workplace Analytics.
Enterprise Mobility and Security services: Advanced Threat Analytics, Advanced Threat Protection, Azure Active Directory, Identity Manager, and Intune.
Windows 10 services: activities, devices, notifications, Universal Print (preview).
Dynamics 365 Business Central.
Access Token is a must for Microsoft Graph API to access the data across Microsoft 365. This can be generated after the user login to the application. And we can view the long generated access token in the newly added Auth tab under Request section.
Other new additions to the Graph Explorer were Adaptive Cards and Snippets tabs, which are located under the Response section. If the endpoint generates and returns the success response and it is suitable for Adaptive Card syntax, the suitable for adaptive card was previewed in the Adaptive card tab.
The snippets tab dynamically generates the code based on the endpoint we entered and tested in the Graph Explorer. At present, the code generates for C#, JavaScript, Python and Objective-C. We can directly use copy and use the code snippets in developing applications after the inclusion of the appropriate Microsoft Graph SDK.
General Available of Graph Explorer allows us to change 3 different looks and feels
Light
Dark and
High Contrast
This is the most anticipated feature added to the GA version. The Preview version missed this one. Even though we can consent to the API request in the Modified Permission tab in the Request section, the modified Permission tab only allows consent for the required permission for the requested API. But this section allows us to apply the consent for any permissions.
In the response section, the new nice feature added is Expand Response. This allows us to expand and collapse the response section and view it on a full view.
page.
To expand this dialog, in the response section view, click the below-highlighted icon,
This is an outstanding feature and helps us to share the MS Graph API Request URL with Query information. To get this to work, click the Share Link icon button in the response section.
This will open a dialog box with the Request URL. Copy the URL and share it with others.
Once they enter the URL in the address bar, the browser navigates to the MS Graph explorer with the request and query (request body, headers) information.
Fill in the first page of the Application Manifest with the information related to your Application. Note that the App ID referenced does not related to the Application ID of your deployed Virtual Assistant.
Enter a name for your Bot and retrieve the microsoftAppId from the appSettings.json file located in your Assistant project directory and paste into the text-box under Connect to a different bot id. Then select Personal as the scope
Finally, you can now click Test and Distribute to install your Virtual Assistant for testing or Download the Manifest zip file for distribution. At this time, click Install for local testing.