Make Smarter Chatbot Conversations by Handling Interruptions in Teneo

When you build a flow that prompts the user for information you need to decide what should happen if the user does not respond to the question as expected. Here you'll learn how to slightly change the coffee order flow so that it may be interrupted and then resumed if the user does not immediately respond to which coffee she wants.

You may also like:  A Beginner’s Guide to Creating an Interactive Chatbot Flow in Teneo

Let's look at an example:

User: I'd like to order a coffee.
Bot: Ok, what coffee would you like?

User: Which coffees do you have? (the coffee order flow is interrupted)
Bot: We offer a variety of handcrafted coffee drinks, from espressos to macchiatos to flat whites and more.
Bot: Let's continue with your order. Which coffee would you like? (the coffee order flow is resumed)

User: A large flat white, please.
Bot: Ok, a large flat white will be ready for pick up in 5 minutes.

In the conversation above there are two flows at play. First the coffee order flow, and then, in the middle of that flow, the flow about available coffee types. These flows are designed independently of each other, and there is nothing in the flows that link them to each other. In fact, once we've adjusted the coffee order flow to survive interruptions, it may be interrupted by any other flow and still be resumed at the point it was interrupted.

To cater to the conversation above you only need to do two things:

• Allow the output node in the coffee order flow to survive interruptions (set it to re-visitable).
• Add a resume prompt (optional).

Set the Output Node to Revisitable

To allow the output node to survive interruptions you need to make it re-visitable. This is how you do that:

1. Open the 'User wants to order a coffee' flow in edit mode
2. Select the output node 'Ask for coffee type'
3. Open the 'Answers' panel
4. Use the toggle at the bottom that initially says 'Not re-visitable'. Change it to 'Limiting revisits to' and leave the limit to the default value 2. This limits how many interruptions in a row the output node should survive. Note that the border around the node in the graph disappears! This signals that the node is now re-visitable.
5. Hit 'Save'

Interrupt Your Bot in Try Out!

Now, go ahead and try the adjusted flow in tryout! When the bot asks which coffee you want, test what happens if you say: 'Which coffees do you have?'.

User: I'd like to order a coffee.
Bot: Ok, what coffee would you like?
User: Which coffees do you have?

Add a Resume Prompt

If you want your bot to say something slightly different when the output is resumed, you can add a resume prompt. This is how you go about it:

1. Select the output node 'Ask for coffee type'.
2. Open the 'Resume prompts' panel.
3. Click 'Add' and enter an answer text. For example Let's continue with your order. Which coffee would you like?
4. Hit 'Save'!

Interrupt Your Bot Again!

Have another play in tryout. What happens now if you say 'What coffees do you have' instead of replying to the prompt for type of coffee?

User: I'd like to order a coffee.
Bot: Ok, what coffee would you like?
User: Which coffees do you have?

There are no clear-cut rules which flows (or outputs) you should make re-visitable. Rather it's an act of balance. On the one hand, you don't want your bot to be annoyingly stubborn. On the other hand, if the interruption happens in the middle of a complex flow, you don't want to drop that flow and force the user to start all-over once the interruption is dealt with. Regardless of your design skills, re-visitability is something that you are likely to fine-tune once you've gathered some log data with real interactions.

Extra Challenge for the Brave!

We have shown you how to make the "Ask for coffee type" node re-visitable. However, the user may just as well interrupt the current conversation after being prompted for the coffee size. Can you make the "Ask for size" node re-visitable to enable a conversation like the following:

User: I'd like to order a coffee.
Bot: Ok, what coffee would you like?
User: A flat white, please.
Bot: What size would you like?

User: Is your store in London? (the coffee order flow is interrupted)
Bot: We have recently opened a brand new store in London! We're looking forward to seeing you there!

Bot: Let's continue with your order. What size would you like for your flat white? (the coffee order flow is resumed)
User: A large one, please.
Bot: Ok, a large flat white will be ready for pick up in 5 minutes.

Further Reading

How to Develop a Chatbot From Scratch

Why Chatbots Cannot Learn Directly From Human Conversations