Date Published: January 11, 2021 - Last Updated 2 Years, 264 Days, 11 Hours, 55 Minutes ago
This article first appeared on HDI.
I recently learned a great deal about chatbots and the effort it takes to create a “conversation-like” interface that can successfully support customers. An adoption strategy must first identify the required customer-facing knowledge to program the bot effectively. Based on my experiences, I have developed a chatbot implementation strategy that you should consider before you jump into the world of bots.
Step 1: Develop a Deep Understanding of Your Customers
A successful bot strategy must begin with first developing a deep understanding of your customers. What services are you providing today? Which products or services generate the most volume of interactions with customers? What type of interactions require the support of the organization? Most organizations do not lack data about customers and services and often have data collected from multiple channels. The difficulty is making sense of the data and being able to understand the customer experience across multiple channels.
Support often generates data from a multi-process, cross-functional delivery organization. In most cases, the data is not cohesively structured to provide insight into a single customer interaction that may span across multiple channels. Diving into data across the delivery organization and multiple channels will help to understand what the best approach will be when designing the bot. A successful strategy will seek to introduce a bot into the environment as part of an overall channel strategy. The goal is not to replace existing channels but instead to provide a succinct way for customers to interact with your business and get quick, accurate results. Additionally, the bot will need to meet your customers in their preferred channel. Don't guess where a bot can be successful; base your strategy on a deep understanding of the customer need.
Step 2: Build an AI/KM Culture and Develop the Right Skills
The goal of implementing a bot should be customer-focused, developing outcomes that are efficiently delivered to customers. As a result, the repetitive work typically requiring staff can now be successfully moved to the bot channel, where staff can be used for value-added work and transactions that have more complex exceptions. However, the intent should not be to replace staff. A bot can eliminate repetitive work, but humans are better at providing services and dealing with exceptions. The exceptions are where customers are won or lost and having a human who can best understand the complexity of the context of the transaction who can deliver a positive experience and exceed customer’s expectations.
Staff needs to understand that a well-trained bot can help them to work on more enjoyable work that is less repetitive. Their role evolves from managing customer interactions to using the bot to assist with gathering information and funneling exceptions quickly to staff who can better handle the exceptions that do not have explicit intents. Staff will also be essential to identify new intents and responses that, when added to the bot's programming, will improve the overall customer experience. It is not enough to just filter out the repetitive work and push it through a new channel. Staff needs to be focused on improving the learning of the AI systems and have the training necessary to shift their work processes from repetition to new skills and more in-depth knowledge.
Step 3: Choose a Specific Purpose
Developing a bot is much easier when you can narrow its purpose. A bot that answers technical questions is going to be significantly more challenging than a bot that can handle simple transactions such as a question and answer or request fulfillment. The more narrow the scope, the higher the likelihood that the bot will interact with humans successfully. Over time, the bot can be trained to provide additional services and more complex outcomes as the organization understands customer adoption and behaviors.
The main goal of your initial launch of the bot should be to provide consistency in responses, an additional touchpoint for customers that is flexible, responsive, and available 24x7. A bot conversation is much more inviting to customers than using a website. When a customer uses a website, the primary tool is to search and then determine what information in the search results provides the correct answer. A bot, on the other hand, provides a specific response based upon the customer's intent. The purpose of the bot should be to identify specific intents or conversations with customers and automate these using the bot. The goal is to get customers to an outcome as quickly as possible in a well-designed conversation. A narrow scope, in the beginning, will ensure early success for customers and a desire to use the tool again.
Step 4: Capture Knowledge in Existing Channels of Support
In many cases, the knowledge you need to build quality bot conversations with customers already exists in your support organization. The best place to start is with structured data captured in the relevant customer context. Gather data across multiple channels, including transcripts of chats in assisted support, recorded phone calls, and knowledge articles specifically written for use by customers.
The greatest opportunity in technical support is the transactional knowledge captured in the request fulfillment and incident management processes as well as general questions and answers. Using knowledge-centered service, focus on capturing the customer's context, which maps closely to the intent and the technical analyst's response, which maps closely to the responses. The organization's context provides the metadata to improve the intelligence of the bot to map the intents to the correct responses. If the knowledge you have captured today is effective for customers in self-service, it is ideal to use the knowledge to train the bot. While structured data is often the most widely used, don’t forget that unstructured knowledge can also be beneficial in understanding customers’ intents.
Step 5: Define Customer Intents with Journey Maps and Use Cases
An effective bot strategy must seek to provide a successful customer experience for the common use cases that are within the defined scope. In customer experience management, the mapping of customer journeys helps an organization to understand how to engineer a better overall experience that results in higher customer satisfaction and increased loyalty. The goal is not only to create an outcome using a bot as an alternative channel, but also to create an experience that delights your customers. The goal is not only to create an outcome using a bot as an alternative channel, but also to create an experience that delights your customers.
Understanding customer intents—the identification of what a customer wants from an interaction with the support organization (requests, incidents, questions)—is crucial in developing successful conversations but also in helping to define an appropriate scope for the bot. Develop a subset of intents for the most relevant outcomes sought by your customers that make sense to deliver from a bot. Don’t try to introduce all customer intents, but instead a subset of intents that are well understood and well documented. A handful of well-defined use cases based upon customer journey maps and supporting transactional data and knowledge will be much easier to design and deliver than trying to map out all scenarios. Tackle the most common use cases first and then expand the scope of the bot as the organization learns from the experience.
Step 6: Identify Technology Platform/Architecture
You have probably heard this before, but don’t focus on the technology at the beginning. The most important thing to the successful adoption of a chatbot is understanding your customers and the type of knowledge that you need to serve them. If you do not have a good working self-service site today, the first step in your chatbot strategy likely is to address what is not working today so that you are just not adding another technology on top of the knowledge that doesn't work.
The technology platform is the least of your worries. Choose a platform that makes the most sense and one that can provide the user interface where your customers are most likely to use the bot. Most bot platforms provide integration with popular channels such as Facebook, Slack, and your website. But even more critical in the selection of your bot platform is the possible integrations you will need for the fulfillment of requests. While simple FAQs and knowledge pushed out to your customers is an obvious first step in utilizing this new platform, eventually, you may need to integrate the bot into existing ITSM or CRM tools where information about customers is automatically captured as a result of a successful outcome. At a minimum, you will want a platform that provides not just a dialog or interaction based upon pre-programmed rules. The use of artificial intelligence and natural language understanding are vital in the bot learning over time.
To read part 2 of this guide to integrating chatbots into customer service, click here.