Bot is a new feature/functionality in Microsoft Teams that allows you to interact with and obtain information from a software or website in a text/search/conversational manner.
In reality bots are just automated intelligent programs. They’re providing us several things but most importantly, it’s information in a natural and comprehensive language. We’re going to use a natural language conversation. Bots are intelligent enough to both understand what we are asking but also but also provide in equally comprehensive language back to us.
Of course, we only want information that is interesting to the user based on queries or status updates that are related to the person who is requesting the information.
Finally, it needs to in an easy to find location it can’t be something that you have to look for before you can start asking those questions. These four components make up what a model block is.
Why are we using Bots?
When we look at how we all used to finding information you all going to recognize it if we look for information either if it is on the internet or on a specific website, what you going to see is that we always need to look with Search Tabs. Doesn’t matter if it’s on Bing, Google, or even more complex search like a SharePoint or even a website search. You have to know how to use search, you need to know what the operators are, you need to know really how to use that search to find information relevant to you. Search engines provides generic information in your search tabs base on your search terms.
That way of finding information has improved and now we use more natural language in finding information. It doesn’t matter if you are using Cortana, Alexa, Google, or Siri what we going to do is to ask those virtual assistance to provide us with information.
The way we find information has changed. We are looking at it more from a conversation perspective. Good bots like bots in Microsoft Teams are going to accommodate this as well.
Bots in Education
Some basic ideas in what we’ve seen bots used for in the universities. Where more conversational approach is used.
Let’s start with students because there more information there that can be provided through Bots. Also, students are more common and using technologies that is innovative. People in faculty can still rely on search engines as well.
How does it work?
What you need to get started.
So, there is a few services that you going to need. First one is what we called Qnamaker and that’s going to be our storage space for questions and answers. That is questions you think end-users will be asking, and the answers that you want to provide. You will also make use of available FAQs you already have on your websites.
Next, we need the Azure Bot Services and you going to see it’s a lot easier that you don’t need to know a lot about Azure, the information is prepopulated for you and very easy to use.
Start the qnamaker.ai and create QnA Service.
We going to create a knowledge base as seen below. This is a content of knowledge, a combination of questions and answers. We need to create QnA service and that is the service that lives on Azure.
When the button is clicked, you will automatically be taken to Azure.
Azure will be feeding all the information you need. What you need to do here is to give it a name and what subscription you want to use. Pick the data center that is local to you or makes more sense to you and that way you will know where your FAQ or QnA is being deployed.
Naming and populating the knowledge base. Here you can provide urls, pdf or docx files as many as you like, all in one Bot or Split. You can also provide your Bot with a little bit of a character if you want to give it some flavor.
- This shows a typical example of a question and an answer pair and can be updated manually.
- Add QnA manually here.
- Search the knowledge base. So, if you want to search for a question, you can do that there as well.
- Save and train your Bot with just a click.
- Finally test your Bot.
Now we need to click on the create button to create a Bot on Azure that will communicate with the Qnamaker. Pretty much the same as the previous.
Deploying the Bot
Here, there are number of channels where you can deploy the Bot. We of course want to deploy it in Teams for now but if you want to deploy it to your website you can do so.
When we click on teams, the Bot opens in teams for us, so we can go in and test it. Now that it works, we are going to make it available to all organizations.
To do that we need a special application called, App Studio.
Visit the app studio, click the Manifest Editor. Create a new application and fill in all the information you see for the app details.
On the left-hand side, under capabilities, click on bots. Choose the existing bot option. Copy and paste your application ID from Azure portal. Select what you want to you it for and click on save.
Finally, you have to Test and Distribute it. You can install and test it yourself and not the end-user. You can also download and make it available to your organization. Lastly, if you have created a remarkably successful app and think everyone should have access to it, you can submit it to be part of Teams app store.
To have the app pinned for users in the organization you will need to visit the Setup Policies under the Management Portal to do so. You can define which application should be available on your left navigation as seen below.
We have finally created and deployed a FAQ or QnA Bot without any single line of code. All we did was copy and paste information.
Jethro Seghers (Senior Program Manager Microsoft Teams) inspired this article with his video on Introduction to Microsoft Bots.
Written by Shardrack Inusah