Enterprise Chatbots
Technology Investigations

If you would like to learn more about PSC Labs research or have something you would like to tackle as a joint venture, please contact: info@psclistens.com.

Enterprise Ready Chatbots

For most people, the first time they interacted with a “chatbot” was likely at the prompting of a website in a commercial, consumer-facing application. Cloud vendors have started to promote the concept of bots as a new feature and a new way for users to interact with their enterprise applications. Understanding the general commercial acceptance of a bot as a user interface, the push to gain traction in the enterprise space has begun in earnest. Seeing this shift in emphasis in the vendor landscape prompted PSC Labs to create an investigation team for a short-term project. 

Rich content interactions

The common assumption is that text is the primary integration when using chat clients. This is mostly true when two humans communicate over chat, but as it relates to bots, Microsoft offers a variety of options with its abstraction.

The bot framework supports text (plain and rich), images (up to 20 Mb), video (up to 1 minute), buttons and the following rich content cards:

 

Adaptive Cards

In addition to the rich content cards, Microsoft has released a separate service which enables you to build more complex card content layouts which can be rendered from data coming from the bot framework. This also exposed more native platform specific custom rendering of cards.

The PSC Labs investigation team evaluated how commercial chatbots are used today, and how the Microsoft Bot Framework could be used to create helpful bots that operate in an enterprise environment.

We created three bots aimed to demonstrate increased productivity gains and enhanced user experiences:

  • Common Data Capture – The ability to quickly and easily view and create timesheets from a bot.
  • Predictive Analytics - Using Machine Learning techniques to return projected sales results back to users based on Product information hosted in an external database.
  • Cognitive Services – Using cognitive services and natural language processing to demonstrate free text entry in bot to create task logging on an external site.

 

Timesheet Bot

Common Data Capture
We set out to build a bot which would help fill out weekly timesheets for our consultants.

The bot features the ability to both display and create a weekly timesheet. For displaying the previous week’s timesheet, we used a carousel card which can display a collocation of cards representing the days of the week. Each card also has a set of buttons which can either link to additional actions within the bot, or external links to an existing website.

 

Product Datasheet Bot

Predictive Analytics
We created a bot demonstrating the ability to search a product database, which in turn triggered an external API call to an associated Azure machine learning service.

Users can interact with the bot via a series of question and answers, e.g. “What product are you searching for? Please select one of the following.” The results are then fed back to the bots in the form of a chart graphic. This bot demonstrates a powerful way to access a variety of on demand reports right within a chat client.

 

Natural Language Query Bot

Cognitive Services
We used the Azure LUIS service (Language Understanding Intelligent Service), which is a part of Microsoft’s cognitive services and uses machine learning to help derive intent from text.

Users can make an unstructured text request like “create a task,” 'create new task,” or “I want a new task” which the LUIS service interprets as “create a task”. Using a secure integration with an external task tracking service (Trello), the bot is then able to ask the user the necessary questions to create a task based on user inputs.

 

Conclusion

Chatbots are being used today by startups and commercial enterprises trying to break into the corporate enterprise space. Our time spent with the Microsoft Bot Framework has convinced us that bots are ready for enterprise, and there are use cases for their effective implementation today.

For more information on the Labs' findings on the readiness of chatbots for and possibilities for your enterprise applications, please contact us: info@psclistens.com

 

Featured
What's it like to work for PSC? Learn about our culture and check out our open positions.
 
PSC Group Selected as One of 2018 Tech Elite Solution Providers by CRN®
 
PSC Blog: Agile Scrum–Part 2 The Team