How to train a conversational chatbot

From Inside Intercom:

Our conversational chatbot, Answer Bot, is designed to do more than chat. Its purpose is to let you scale your business faster and more efficiently. How? By automatically and instantly resolving your customers’ most common questions, so your team can focus on the conversations only humans can resolve.

If you are using Intercom or live chat on your website already, you’ve probably received a number of conversations where customers just say “Hello” or “Hi”, and then it’s up to your team to figure out what they need help with before routing it to the correct person.

“Training Answer Bot is much more straightforward and intuitive than you might imagine.”

Answer Bot can reply to these vague conversations and find out what your customer needs help with. If it’s a very common query that Answer Bot recognizes, it will go ahead and provide an instant answer. If not, the query will be routed to your team to solve.

Some people worry that bots might disrupt or interrupt conversations or relationships with your customers, but that’s not the case here. Answer Bot is fully trainable so you can decide the types of queries you want it to handle versus the types of queries you would prefer to have your team look at.

How do you train a bot?

“Training a bot” might sound complex, but in fact training Answer Bot is much more straightforward and intuitive than you might imagine.

Quite simply, you choose a common question, train Answer Bot to recognize it, then create the answer. Once you set the answer live, Answer Bot will reply to every customer who asks a matching question. The more answers you create, the more hours you save your team every week.

We recently wrote about how we trained Answer Bot for our own website. Essentially, there are three steps to take for maximum effectiveness:

1. Train Answer Bot to recognize the question

Answer Bot can automatically identify and surface common questions from your conversation history, but you want to make sure it recognizes all the potential variations of those questions as well. So gather your team and have everyone collate the various ways that the same question can be or has been asked before.

The aim of the game isn’t to have Answer Bot take over from your team in answering customer queries. It should minimize the time your team spend answering common queries and allow them to focus on resolving more complex questions that require hands-on assistance.   

2. Create answers for a broad range of topics

As well as individual questions, you should focus on covering the various topics that customers are focusing on in their queries. You should create answers for each of the most common topics, so Answer Bot can cover more questions and provide instant resolutions more often.

Some common examples might include “subscription,” “password,” “delivery” or “billing”.

Intercom Answer Bot – question clusters

An example of how our analytics team clustered our most commonly referenced topics in order to inform the questions we we now use Answer Bot to resolve.

3. Cover many questions on the same topic

Within each individual topic, customers ask different questions. You should also create answers for each common question you receive within a single topic. For example, if your topic is “invoices”, your list of common questions might be:

  • Where can I view my invoices?
  • How do I change my invoice address?
  • How often will I receive invoices?

As you can see, each of these questions are closely related to one topic, but require different answers. By creating many answers within a single topic, you’ll help Answer Bot understand the nuances between questions within a single topic, so it can deliver accurate answers more often.

Is Answer Bot the right solution for your business?

If your team is getting the same queries over and over again, and having to come up with new ways to answer the same questions then Answer Bot is likely to be a good solution. It can analyze your conversation history, identify common questions and surface them for you to create answers.

Remember, training a bot isn’t a one-off task. You should choose a member of your team to regularly create and review answers, to ensure you maximize its effectiveness. By constantly expanding Answer Bot’s coverage, you’ll provide more instant resolutions, create a more efficient team, and make your customers (and teammates) happier.

PS: Answer Bot is one of our three automation products powered by our Operator automation technology. We have also built Custom Bots to help sales teams generate more leads, and Task Bots to help you automate simple actions.




The post How to train a conversational chatbot appeared first on Inside Intercom.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.