A Simple Chatbot May Be All You Need to Teach the Basics

I normally think of a chatbot as something that can handle a moderately complex conversation. This means they need strong natural language processing capabilities and a sophisticated knowledge base. However, there is another application of chatbots that doesn’t use AI at all, yet, to my eyes, provides a surprisingly effective learning experience.

The essence of these chatbot learning tools is a decision-tree driven “conversation” that looks something like this:

Chatbot: Would you like to learn about the new product? (yes/maybe later)
Store clerk: Yes

Chatbot: Great, the most important feature is that the memory can be upgraded. (Got it / Tell me more)
Store clerk: Tell me more

Chatbot: [Shares key facts about the memory upgrades] (Is that clear? Yes / No)
Store clerk:“Yes

Chatbot: Fantastic! Give yourself a hand. (Applause)
Store clerk: Applause

Chatbot: Do you want to learn about more features? (absolutely/maybe later)
Store clerk: Maybe later

Article Continues Below

Chatbot: Okay, I’ll text you tomorrow to continue. Goodbye. (Bye)
Store clerk: Bye

The simplicity comes from the fact that the user can only choose from a few options, however, it still has the feel of an instant messaging conversation. In terms of conveying content, it’s not doing much that couldn’t be done in a document, so why not use a document? Well, if people are engaging effectively with written documents then that’s a good solution. If they are not then this kind of microlearning, gently pushed out to users, maybe just a minute at a time, may be the solution. There is something remarkably engaging about a simulated conversation that you are involved in; it works better than you would imagine.

You can see what these tools are like by downloading some of the free mobile apps. A search for chatbots in the Android or Apple App Store will reveal many choices. I was impressed with “Woebot” which deploys cognitive behavioral therapy in a chatbot conversation. A much more sophisticated tool is Babylon Health for diagnosing illness. You can try building your own with a tool like ManyChat.

What’s interesting

  • Text messaging has become an extremely popular means of communication. We can mimic that medium for training and communications. When we think about it this way it seems obvious that we should be providing training and communication via text messaging.
  • Very simple applications of technology can be highly effective, maybe more effective than something more sophisticated.

What’s really important

A text messaging style of chatbot could be the solution to one of your learning issues. If you have issues of engaging people with learning, and the content can be shared in small pieces, then this could be the best approach.

David Creelman is CEO of Creelman Research. Based mainly in Toronto and partly in Kuala Lumpur, he’s best known for his research on the latest issues in human resources.

He works with think tanks such as Talent Tech Labs (New York), Works Institute (Tokyo), Workforce Institute (Boston) and CRF (London). He’s collaborated with leading academics such as Henry Mintzberg (leadership development), Ed Lawler (“Built to Change”) and John Boudreau (future of work).

His books include The CMO of People: Manage employees like customers with an immersive predictable experience that drives productivity and performance with GrandRound’s CHRO Peter Navin; and Lead the Work: Navigating a world beyond employment with John Boudreau (USC) and Ravin Jesuthasan (Willis Towers Watson).

You can connect to Mr. Creelman on LinkedIn