Your chatbot flow is the most critical factor when it comes to creating a bot that feels natural. But how do you make one that takes into account every possible scenario?
In this article, we’re walking you through the art of building chatbot flows that feel right. Let’s get started!
What is a chatbot flow?
A chatbot flow is a structure that determines how a chatbot conversation will take place, taking into account the questions your chatbot would ask and the various replies that a user could provide. A chatbot flow is a series of paths that a user’s responses could trigger.
Each path would consist of nodes that either display, request, or process information. Some of these nodes could even be used to integrate your chatbot with third-party software.
Questions to answer before building your chatbot flows
Determine what you intend your chatbot to do. I’m not saying that your bot has to have only one goal. It can have multiple objectives, but you need to outline them clearly. This is the foundation upon which you will build all your chatbot flows.
Do you need a conversational UI to drive sales? Maybe you need it to schedule appointments. Perhaps you want to use these virtual assistants for 24/7 customer service.
Whatever your goals are, you need to define them clearly.
Identify who your chatbot Avatars primary users will be. Are these going to be prospects who are just hearing about you? Are they new customers who haven’t quite understood how to best use your offerings yet? Are your bot’s users customers who face sudden issues with your offerings and need help?
There could be many other types of users. You need to identify your primary customers, the ones you seek to serve the most through your chatbot.
Now, what are the most common issues they face? What do they already ask your sales and support teams about the most? These are the issues that you need to train your bot on the most. Your bot needs to be able to resolve as many of these queries as possible. In case some of these are too complex for the bot, you need to make it possible for your chatbot to transfer customers to a live agent.
Finding out how your users most commonly behave is also very important for building chatbot flows. Understand how they navigate across your website, which sections leave them confused, and where they would be most likely to ask your bot a query.
You don’t want to leave your customers talking to a dull bot. You need to give your bot a personality, preferably one that matches your brand. Give your bot a persona and a story.
For example, when George Hanshaw, Director of E-learning at Los Angeles Pacific University, was building a chatbot for a nursing course, the team built the bot based on a colleague’s personality.
This colleague had earned the name Agent R because she was always going on trips to distant lands before the pandemic and coming back with fascinating stories. They lent her personality to the bot and even created an avatar that wore a nurse’s outfit and sunglasses to display a cross between a nurse and an agent.
Giving your chatbot a personality makes it vibrant. It even fascinates your users. So, what’s your bot going to be like?
After you answer that, it’s time to get started with the chatbot flows.
How do you make a chatbot flow?
Sure, you could dive straight into the platform and wing it. But we’d suggest preparing in advance. Get out a pen and a paper (or a whiteboard) and design a rough flow chart for your conversations.
You don’t need to fill in the actual responses just yet. Just keep the general purpose of the message in mind.
Once you have a rough draft, you can finetune it on a tool like draw.io. You can get a little bit more specific in this step.
Once you’re done with that, you can replicate it on Engati’s no-code visual flow builder.
Fill in rough messages in the nodes for now. Don’t spend too much time here; you can always fine-tune them after your conversational flow is ready.
While you could build your entire chatbot flow in a single path, that isn’t the best idea. Creating separate paths for different scenarios will make it easier for you to understand your flow and edit it in the future. These paths can be connected using the Trigger Path node.
Once you’re done making your flow, proceed to polish the messages in the nodes. Make sure that they match your bot’s personality.
Now, it’s time for your to test your flow. You can test individual paths by pressing the play button on the top left corner of your path builder.
Building your chatbot flow is not a one-and-done task. You need to keep improving it as your customers, and your business evolve.
You can train your chatbot in two different ways on Engati.
First, you can upload FAQs either individually or in bulk.
However, you don’t need to upload these FAQs manually. With Engati’s DocuSense technology, you can automate the training process. All you need to do is upload your documents. Your chatbot will use cognitive search to parse through your documents, 12 pages every 8 seconds. It will pull answers directly from your documents and deliver them to your customers.
And the best part? You don’t even need to format your documents into questions and answers.
Now that you know how to build a chatbot flow, it’s time to address another question.
How do you end a chatbot flow?
Too many companies allow their chatbot flows to end abruptly after a user’s questions are answered. That’s far from ideal.
It feels unnatural. Worse, it looks as though you though care enough about your customers.
Make sure to conclude the conversation by thanking your users for giving you the opportunity to help them. And don’t forget to let them know that you’re always there for them, just one message away.
What nodes can you use in your chatbot flow?
These nodes can be segmented into four categories:
These nodes are used to present information to the end-user.
You can use these nodes to collect information from end-users.
These nodes help you handle & process information and make conversation flow branching decisions.
These nodes allow you to extend your marketing and support systems by integrating them with Engati.
What are the best practices for building chatbot flows?
Do not mislead users into thinking that they’re chatting with a human. Let them know that they’re conversing with an intelligent bot, and if need be, you can route them to a live agent.
You wouldn’t want to read a message that looks like a massive chunk of text. Don’t force your customers to do that either.
Don’t send too many messages in rapid succession. Give your customers a chance to read them and respond.
Ask your customers how they felt about their interaction with your bot. You can use the feedback node to collect ratings. You can even ask them for subjective feedback. This will not only help you improve your chatbot conversation flow, but it will also make your customers feel like you care about them.
Don’t assume that your customers just want to talk business and keep it to the point. Your bot should be able to respond to questions like “How are you doing?” or “Good morning.”
All you have to do is go to the Conversations section in the Configure tab and enable small talk.
There you have it. Everything you need to build chatbot flows that your customers will love. Now it’s time to give it a shot yourself. Try Engati’s visual chatbot flow builder today!