You have decided to deploy a chatbot in your contact centre! Great! Not only can you eliminate your agents doing administrative tasks - often repetitive and mundane, but also you can also greatly enhance your customer experience.
Making the decision is, however, only the influential factor in the process, more importantly, is initially determining what the role of your chatbot should be and what goal should it accomplish.
To get to the answer, you have to be very specific.
Bill Gay, director of Self Service, Agent and Desktop Experience at Ocular Technologies' partner company, Aspect, highlights the following factors that should be determined in your first step to chatbot creation:
- Identify the top five to 10 items that customers want to know about. Limiting the topics allows for finer tuning of the bot to understand the subject better which in turn allows answers with higher confidence.
- Construct frequently asked questions responses: These are normally 10 to 25 topics and answers with short text responses along with follow up links as needed that contains additional details and information. However, note that the chat medium demands a more conversational approach, so make sure responses are less regurgitation of long explanations, and more chat.
- Match the chatbot to your existing voice self-service platform capabilities: Recreating well-defined and understood topics creates consistency across all modalities for your customers.
- Identify the transactional use cases beyond merely informational ones. This would be for creating a more fully functional bot that manages all types of the business tasks your staff handles today, such as providing detailed order status or handling appointment reminders.
- No matter which direction is decided upon to get you started, it is important that the bot-customer transcript be provided to the agent so they have context to help the customer and provide a higher touch experience.
Only once this step has been completed, is it wise to continue with building your chatbot, which, according to Aspect's '10 Steps to Chatbot Creation' blog, includes evaluating and picking a channel; creating the conversational architecture; designing dialogue flows and storyboards; designing the integrations; picking a platform and a development approach; implementing the dialogue flow and engineer the NLU; internal testing and revision of your use case detection; and finally, early deployment and revisions.
As with all buildings, laying the strongest foundation determines the solidness of your end result.
Share