Chatbot 101

Overview

While the industry for chatbots is still evolving, best practices are emerging based on the massive number of existing products and bots that have already been developed. Here are the major considerations to address when you develop a chatbot.

Start Small

The best way to build out your chatbot is to start small and add as you go. Think of this first iteration like a Minimum Viable Product (MVP) that only contains the most necessary aspects of your chatbot. Focus on a small number of key features and fill them out as much as you can before moving on.

One of the most common mistakes bot creators make is trying to be everything for everyone. First, you should focus on your target audience and their needs. As part of your software development strategy, chatbots can and should be implemented starting with an MVP and a bare minimum number of flows and features. The product will mature and grow, addressing more and more user questions over time.

The other reason you should start small is to prove that your concept will work. Begin with something easy to handle and validate the benefits of your solution. Not only will this save time and money, but it will often lead to a better final product.

Define the Purpose

Once you have validated your chatbot, the next step is to define its personality and ultimately its purpose. This includes things like the channel where the bot is deployed, limitations on what it can and cannot do, questions it can answer and questions it turns over to a live agent. Other basics like choosing the name, preparing the greeting, and finding an image that matches your branding will be your first step. Then, meet with your team to discuss the type of bot you want to present to potential clients. Think about your brand and write down words you want to be associated with. This will be a good jumping off point.

From there, you will need to lay out how these attributes will be conveyed through the chatbot development project. For example, if you want your chatbot to be playful, spend time working on key phrases that can be peppered into the conversation to give off this image. The goal is to be memorable without being distracting.

Next, take time with your team to define the purpose of the chatbot through use cases. This will likely be something basic like “convert more users,” but it could be more nuanced like “provide a better overall experience” or “guide users through the setup process.” Clearly defining your chatbots purpose through use cases is essential in how you approach the rest of the project.

Typical Use Cases

• Customer service and support
• Automating simple transactions
• User engagement
• Brand awareness
• Streamlining social media activity
• User retention
• Organization Knowledge Management, such as people, processes, and document sources

Set Expectations

After you have defined the purpose for your chatbot, the next step is to set expectations for your users as to how they interact with the bot. This is one of the best ways to facilitate success with a chatbot: set expectations early in the conversation and then meet or exceed them throughout the interaction.

For example, you never want to mislead your users by trying to have your chatbot seem like an actual customer service representative. Let users know that they are speaking with an automated bot so that, should they not be able to find what they are looking for, they can get in touch with someone who can help them rather than waste their time.

Setting expectations is also important because you can explain the scope and limitations of the chatbot. By understanding exactly what the bot can do for them, users will be able to move through the process with confidence to find what they are looking for. The faster they can find a solution, the better their experience. 

Develop the Script

With your expectations set, your purpose defined, and your MVP built, now comes the time in the chatbot development project where we step things up a notch. At this point, you will likely have an idea of what you want your chatbot to look and sound like, but now is the time where you will develop the script for it to follow.

Start small with your opening greeting. Then, lay out a few frequently asked questions, followed by potential conversation trees that could happen from there. Since you will define the options, try your best to push users in the right direction. Finally, add a call-to-action at the end of each branch, either to complete a conversion or go back to the beginning of the conversation.

Decide on the Type of Interactions

Aside from the basic types of input, such as voice, text, or both, there are many other ways to quick replies so that users can choose from an entry rather than type it.

Strive for Consistency

According to Ben Shneiderman, noted Professor of Computer Science and the Human-Communication Laboratory at the University of Maryland, the first rule of interface design applies to conversational interfaces as well. Keeping the same voice, wording, input and output formats consistent throughout the conversation helps you create a seamless chatbot user experience and build a recognizable brand image.

Personalize

With a chatbot, you can tap the full potential of AI and machine learning to offer a personalized user experience. You can use customer data from your main database (for example, transaction history from your website) to provide custom suggestions, tailored to match the user’s preference.

Focus on Microcopy

The concept of consistency applies to content as well. For better user experience, keep your messages concise. Using a certain voice, some catchy phrases, or humor in your bot’s responses helps you create a unique character which can perfectly personify your brand. This, in turn, will have a positive impact on your brand awareness, making you stand out among your competitors.

Prepare to Handle Non-Standard Requests

Talking about possible flows of conversation, there is always a chance a user will ask a question your bot won’t be able to understand or answer. If something goes wrong, make sure your user isn’t stuck with a generic “sorry, I don’t understand that” response. You must be ready to point out what went wrong and show the way out of the dead end.

Guide your User

Interactions with chatbots can be frustrating for people of a certain age or background. Having proper onboarding and solid user flow helps you engage your users and reduce churn. Provide useful tips and examples on how to use your tool, ask questions, provide tailored suggestions to keep the user engaged and help him/her succeed with your bot.

Test for Variables

Once your initial script is developed, test the chatbot for variables in the conversation and potential hang-ups. This is vital to presenting the chatbot as conversational and accurate. If you skip this testing, it will become obviously very quickly that your chatbot has not been fully thought out and developed for practical use. 

The best approach is to recruit a sample volunteer audience who can attempt to run through each of the chatbots scripts to achieve the designated goal.

Always Have a Backup Strategy

If your chatbot will need to handle complex tasks, have human agents always ready to step in. This is especially important for customer support, complex transactions, or non-standard inquiries, which require additional consideration.

Final Word

According to a study conducted by Oracle, 80 percent of the respondents are planning to use chatbots for customer interactions by 2020. At the same time, 36 percent of them have already implemented a chatbot service. Considering that the mass use of chatbots has just begun, this expected growth is quite impressive.

While apps will definitely continue to hold the field, due to the growing adoption of the mobile-first business strategy, more companies will invest in AI and bots to automate their business processes and reduce costs. A recent study by Juniper Research finds that chatbots could save businesses over $8 billion every year by 2022. According to this research, the current cost savings due to the use of chatbots equals $20 million globally. The chatbot market is ready to take off!