The Chatbot Cheatsheet: 7 Tips for Building a Chatbot Program

Chatbot Cheatsheet: 7 Tips for Building a Chatbot Program TW

So, you think you’re ready to invest in conversational automation, but you want to avoid the hype and nonsense? Great, then we are here to help! Keep these seven points top-of-mind as you build out your chatbot program, and you’re sure to see value in no time.

1. Understand Your Metrics

“Containment rate” (the percentage of total conversations fully handled by the bot), or its alternative name, “deflection rate”, is a key metric to track when trying to figure out how well your bot is performing. Customer satisfaction is also important. Keep in mind how the introduction of a digital assistant could alter existing performance indicators. For example, will average handle time increase now that agents are only handling more complex inquiries? Ultimately, a well-defined bot program will be able to communicate increased agent efficiency and customer satisfaction, which equals a reduction in the cost of care.

2. Start With Hello

Your first bot does not need to be elaborate. In fact, we recommend against it. When you are first getting started, pick one or two simple, but useful, use cases to automate. Then, you can learn and iterate as you discover how your customers prefer to interact with a chatbot. No one gets it totally right out of the gate, so avoid wasting time by trying to build something “perfect”.

3. Leverage the Agent

We have seen countless chatbot programs fail to engage the existing front-line customer service team when designing an automated conversational experience. It’s great to learn from data and prevailing user experience research, but your agents are the ones who know how your customers are interacting with the bot. Treat the bot like another agent: when you need performance feedback, use its peers.

4. Templates, Rules, and Machine Learning

Not all chatbots are “conversational AI”, because not all use cases require machine learning. Very effective bots can leverage rules and simple conditional logic, it all depends on the use case. Similarly, natural language processing is great when you have a bot with many different skills and a large corpus of knowledge — why make your customers trudge through structured flows when all they should do is ask the question directly? In both cases, we recommend leveraging buttons, quick replies, and other conversational templates that help the user move through the conversation quickly and efficiently.

5. Know When to Handover

A chatbot is not a replacement for a human agent. Often you need to give the user a way to bail out of tough conversations and difficult questions, and that’s alright. Chatbots are excellent at fully resolving low level queries. However, just because an issue is complicated does not mean a chatbot cannot be helpful. Consider how you can use the bot for information gathering and light triage before routing to the right agent. In these cases, the chatbot helps reduce handle time and expedites the customer’s support request.

6. Automation Happens Elsewhere, Too

Chatbots get a lot of attention when it comes to automation. Often it’s the mental model in our heads for intelligent customer service. Consider other ways you can streamline the customer support experience with a bot, and leverage additional intelligent services: automatic tagging, routing, and prioritization for the agent, just to name a few.

7. Be Customer-Centric

At the end of the day, the success of your chatbot comes down to how well it fits into the support journey and cadence strategy you have outlined for your customers. Consider different segments of customers that might prefer automation to that “direct human” connection. Perhaps automation can be more helpful at the end of an interaction than at the beginning. Take a good look at your customers, and we’ll help you find out the right size that fits.

Want to learn how to get started with intelligent chatbots? Find out more here.
 

The Undeniable Power of Chatbots

The Undeniable Power of Chatbots TW

Since the dawn of the computer age, engineers and designers have had to consider how humans can, and should, interact with new technology. They designed and implemented interfaces that altered our mental models for exchanging information; we had to learn novel symbols, workflows, and behaviors in order to interact with these new platforms. Basically, we conformed to the computer, not the other way around. Yet over the last few years, a new service has emerged that represents a departure from this norm: the chatbot, a digital experience that replicates and automates the medium of human conversation.

Three Benefits of Automated Conversation

Conversation is the new interface. We now spend more time messaging and chatting than on social networking applications. Smart businesses have capitalized on this behavioral shift by supporting chat, messaging, and text channels for marketing, sales, and customer service. However, it’s difficult to scale a one-to-one communication operation. This is where chatbots come into the picture.

As automated chat interactions, chatbots can essentially exist wherever human-to-human dialogue is the best way to exchange information and accomplish an assignment. The best way to experience the benefits of this kind of automation is to focus on the conversations that are already in play with your customers. Oftentimes, this starts with customer service. Here is where you’ll see an immediate impact:

  1. Faster Response Times: Chat and messaging work best when someone can immediately respond, not when customers are waiting in a queue because agents are tied up. With a chatbot, each message is seen and responded to, and your most common questions are quickly addressed. Further, by allowing chatbots to handle initial information gathering, agents are able to join and resolve conversations faster if escalation is needed.
  2. Better Agent Utilization: No one wants to answer the same question over and over again. Chatbots remove basic, low-level questions from the workload. By reducing the number of messages your agents receive, you will increase the efficiency of your support operations and be able to focus on the more complicated questions and tasks.
  3. Data on What Customers Need: Chatbots automatically collect and analyze your customers’ questions and issues. Instead of manually reviewing conversations or asking agents for anecdotal insights, you can review organized and aggregated intent data.

Getting Started With Chatbots

If you think you’re ready to automate and streamline the interactions you’re already having with customers, I recommend starting with these skills to experience the core benefits:

  1. Five to Ten One-Touch FAQ Answers: Focus on supporting your most common questions that can be addressed with one response. You can direct customers to an FAQ article, or deliver a conversational answer directly.
    One Common Workflow: Similar to the above, there are certainly interactions that require authentication or simple lookups from another data source; these aren’t hard to tackle, just usually require manual attention. Verify, authenticate, and pull in data to automate simple workflows. If you’re an e-commerce business, “Where is My Order” or “Return Status” are great, universal examples.

  2. Easy Agent Takeover with Routing: Once a chatbot cannot answer a question or resolve an issue, make the handover process to human support quick and painless. Better yet, ask a few questions just prior to the handover to give agents context for the conversation and route to specialized teams.
  3. Natural Language Processing: Natural language processing and machine learning — the “AI” of conversational AI — make it possible for your bot to understand and respond to customer intent, not specific keywords. This allows the bot to keep up with the way each customer thinks, communicates, and switches topics, ultimately leading to higher understanding and better resolution rates across all conversations.

Want to learn more about how chatbots can transform your customer experience? Check out how Kustomer powers intelligent self-service here.
 

Deliver effortless, personalized customer service.

Request Live DemoStart Interactive Demo