Continuing from the original post available HERE, and titled “The rise of the Bots”, let’s have a look specifically at Microsoft’s offering in the Bots space.
As we have seen from the previous article, there is quite some competition in this space, with offerings from all the big players in the industry, including Google, IBM, Amazon, ServiceNow and others. Furthermore, there are offering from small specialized players with solutions for various industries and various degrees of complexity (or simplicity if you want).
Around 2016, Microsoft recognized the value of a Bot offering, and presented the Microsoft bot Framework. This was a very developer focused offering, with the ability to build complex Bots using either C# or Node.js as the core languages supported.
This framework was presented in conjunction with Microsoft Cognitive Services, as well as the expansion of Cortana and chatbots into Skype.
The main components of the Microsoft bot Framework included:
- Bot Framework Service (BFS)
- Bot Framework SDK
- Bot Framework Tools for development
- Bot deployment and channel configuration
This service also leverages:
- Azure Cognitive Services
- Azure Storage
Value is provided through:
- LUIS – natural language processing
- QnA Maker – answering questions in a natural way
- Dispatch tool – allows for selecting the right tool for each scenario
- Cards – complex presentational elements that can include elements like graphics and menus to augment standard text
The most common channels supported include:
and many others.
Important to note, the Bot Framework SDK is in fact an Open Source SDK.
Improvements and new features are continuously added. To note for example for this year, a new implementation of Azure Blob storage for better performance, as well as better integration to Azure Queues. Bots talking to to other bots is possible.
Fast forward to the end of 2019, and Microsoft introduces for the first time the public preview of Power Virtual Agents. Wrapped under the Power Platform, it now provides users the ability to create chatbots in a no-code/low-code manner. Leveraging Azure AI and a specific toolset for building bots, the aim is to allow “citizen developers” to create and deploy chatbots with minimal effort.
The new offering relies heavily on AI functionality to understand intention from existing conversations without the need to define all possible key phrases. It also relies on other features like Power Automate to triggers specific actions on other platforms.
A key aspect of the new offering is the ability to generate and capture advanced analytics. You can easily track where the bot fails to provide the right answers, and easily make adjustments to improve the communication. A robust analytics dashboard provides deep insights into things like engagement over time, outcomes over time, resolution, escalation and abandon rates, as well as, when configured as such, customer satisfaction.
A lot of the analytics we were looking for in a regular customer service agent interaction are now bubbled-up and presented to the user for the bot interactions. And this being a scripted process, you can easily go in and adjust or tweak the process as needed for better results.
Have you seen the Power Virtual Agents offering yet?
We will delve deeper into this in the near future, so stay tuned.
For feedback, comments, or help on this topic please reach out to me.
If there’s a particular topic you want me to delve deeper in, send me a note.