Here are some final tips to keep in mind when creating your Chatbot.
1. Manage customer expectations.
Especially if your Chatbot has limited functionality, it’s important to let users know upfront what the Chatbot can help them with.
2. Use related questions to inform customers.
Related questions are another great way to keep customers engaged. They can proactively teach them the answers to other questions that they may have been wondering. And if your Chatbot’s answer wasn’t satisfactory, they give customers a range of other questions that might be.
3. Deal proactively with ambiguities and misunderstandings.
If your bot detects various key words, have it clarified with the customer. As digital products designer Jesús Martín says, “Chatbots need to be designed for any possible misunderstanding in every step. That means that a specific error message needs to be set just in case the misunderstanding happens. That would help us to get the user back to the scope without restarting the whole process.”
4. Use teamwork to anticipate all the ways customers could ask a question.
Everyone says things differently, which is why factoring all the ways a customer could ask a question into your decision tree is best done as a team effort. Consider grouping agents off into teams of four or five and seeing which team can come up with the most ways to ask the same question. Whomever who can come up with the most synonyms in 5 minutes gets a prize!
5. Give your customers an out.
Do you like being stuck on the telephone with a useless bot? Probably not. The same goes for your customers and Chatbots. Make sure that your customers can get from your Chatbot to an agent easily. If your Chatbot takes over after hours, be sure to let customers know what times they will be able to speak to a representative. If you are using Chatbots on social messaging channels like Facebook Messenger, give your customers give your customers the option (and easy instructions on how) to start over or return to the main menu.
6. Build the Chatbot into your current system.
Often when building a Chatbot, companies try to recreate functionality from scratch. As Fabricio Teixeira, design director at Work & Co explains, “Let’s say you are creating a bot to book appointments in a spa. If your Chatbot does not communicate with the spa’s existing appointment management system, that means extra work for the business owner to handle requests coming through this new channel – and ultimately lack of consistency for the user. Chatbots are part of a larger ecosystem, formed by multiple touch points between customers and brands. Creating a Chatbot in a silo can be pretty harmful for both businesses and customers.” By building the bot into your current system, you can expect less work for agents and a better customer experience.
A Chatbot is only as good as the planning that goes into it. Effective mapping can make any Chatbot – regardless of its level – a useful customer engagement tool and self-service resource.
We hope that this chapter has had a hand in showing you how best to work with and optimize your Chatbot. Keep these steps and tips in mind when it comes time to map your own Chatbot, and buckle up for Chatbot success.