11 Step Process for a Great Chatbot Design

Designing a bot is like brewing beer; it always takes the same ingredients to make it, but slight changes to the process can transform the whole outcome.

A chatbot needs a good platform, script, name and image for it to work. But it needs a purpose, personality and functionality for it to be great.

Chatbots with performance issues create stigma: According to our research, 60% of participants say that chatbots fail to resolve their issues and users rather speak to a human than a bot to answer service questions. Fair enough, but this perception can be improved.

We’ll show how you can design a chatbot that meets the expectations of your company and customers - including common pitfalls and pro tips from leading experts.

How to design a chatbot: 11 tips

  1. Determine your bot’s purpose
  2. Choose a rule-based or NLP platform
  3. Know the limitations of your platform
  4. Define personality and tone
  5. Text like a human
  6. Design the flow
  7. Integrate visuals and downloads
  8. Educate users on bot commands
  9. Find a balance between proactive and reactive
  10. Make it easy to switch from bot to human support
  11. Use an intuitive chatbot design platform

1
Determine your bot’s purpose

Chatbot design starts with a simple question: Why do you need a bot? If you cannot answer this question with conviction, then you may want to rethink if you really need one.

List of shallow reasons for wanting a chatbot

UI Designer Saumya Srivastava stresses:

The users are using your chatbot for one reason, and one reason only: to seek an answer to one of their problems.

So what is the purpose? This is what you’ll design your chatbot around.

2
Choose a rule-based or NLP platform

After the why, comes the how. But let’s get some labels straight, first. Most chatbot platforms call their bot “artificial intelligence (AI),” no matter if it actually uses smart self-learning algorithms or sticks to simple IF-THEN metrics. So the trigger words you are looking for when choosing a building platform are “rule-based,” or “NLP.” These specify how flexible and smart your bot operates within a conversation.

Rule-based bots chat according to defined decision trees. Like a flowchart, conversations are mapped out to anticipate what a customer might ask and how the chatbot should respond.


IF user's input contains 'shop' or 'buy'
THEN send message with product list

Bots with Natural Language Processing (NLP) are able to understand the context even when questions are more complex. Thanks to their ability to learn from their mistakes, they improve with every inquiry.

Take our AI Automation Hub, for example. Answers are pulled from a central knowledge base, which improves itself over time the more users interact with the AI chatbot, intelligent FAQ page or contact form.

Userlike AI chatbot chatting with users on WhatsApp, live chat and messenger
Userlike’s AI Chatbot is available to users on all their favorite channels, and learns from every conversation.

Unlike rule-based bots, the AI chatbot is immediately ready to use. There’s no coding involved and you can import your entire knowledge base in one go. This is a much simpler option for businesses that need immediate help with overwhelming inquiries or can’t afford sufficient staff to support their customer service team.

3
Know the limitations of your platform

Once you have decided on the type of platform you want, you still need to find the right one.

Some rule-based platforms solely work on a multiple choice basis without the option to create unique answers. While it’s possible to guide the conversation in specific directions, you can’t write suitable responses to questions that may be asked.

The Ultimate Guide to Chatbots in Business

Learn how chatbots work, what they can do, how to build one – and whether they will end up stealing your job.

Read more

Some (especially younger) platforms like ThinkAutomation expect you to input questions and answers in a coded format, which requires a certain affection for coding to enjoy using them.

So, it might be the better option to choose an all-in-one platform that is easy to setup and deploy but doesn’t skimp on features and functionality. You can have an intelligent bot without relying on your development team to set it up. It’s just a matter of creating and editing text fields with the click of a button.

AI chatbot text flow design overview in Userlike's AI Automation Hub
Userlike’s AI chatbot comes with prewritten texts to common questions with the option to easily edit or add your own.

If you need more help understanding the different chatbot platforms, or to get an overview of the top providers on the market, check out our post, “11 must-try chatbot providers for every budget.”

4
Define personality and tone

Your chatbot is a representative of your brand and often the first one to say "hello" to your customers. It’s important to design its language in line with your corporate identity. You might even use the birth of your digital employee as a chance to improve your brand image by giving it a likable persona.

Our recent study of consumer chatbot perceptions showed us that people prefer bots with human traits. We asked:

What would make your experience chatting with a chatbot more positive?

A respondent answered:

If they reacted in a bit more human fashion. If their responses were more true to life or they were more responsive to language cues.

But how do you create a humanlike personality for a chatbot? Try using screenwriting principles. First, define the role your bot plays (its purpose), then create a short background story: What’s your bot’s motivation, what’s its specialty, what are its striking character traits? And not to forget, what name fits this persona?

For now, let’s take a look at a great example of bot design: Siri. Apple has done an excellent job of giving their voice assistant a lively, engaging personality. Siri is truly a sweet and funny character.

Siri gives a witty response to user about Santa Claus

Wittiness works great for a trendy company like Apple, but it really isn’t for every brand, as an article published by The Manifest points out: “Don’t feel pressured to program humor or street-smarts for audiences that don’t crave those traits. A simple, helpful, and polite robot is the best choice for many brands.”

Need inspiration for your chatbot UX design? Here’s some articles you may find useful:

5
Text like a human

Defining a character is one thing, bringing it to life using engaging dialogue is a different story.

Since we learned that users want the interaction to feel human, it’s important to invoke positive emotions during the conversation.

Vaibhav Verma, UI designer for chatbots, suggests the following: “Taking up the user’s name frequently, greeting him, congratulating him etc. are some practices, which make conversations more personalized.”

Another easy way to invoke human emotions is through the element of surprise. Design a chatbot that is surprisingly smart, witty, empathetic or all of the above.

Chatbot congratulates user with funny image

6
Design the flow

While chatting, your bot should use prompts to keep visitors engaged to quickly and efficiently resolve their request. The biggest challenge is identifying all the possible conversation scenarios, and defining how it’ll handle off-topic questions and unclear commands.

“It is actually a good idea to spend a lot of time on this step to get close to defining the experience for your users,” Saumya Srivastava recommends.

Define the key terms that your bot is able to “understand,” how it responds and which options you give your visitor to move forward. Chatbot expert Vaibhav Verma explains “If the user does not know what to say, the chatbot must come up with suggested tasks that he can perform for the user.”

7
Keep it flowing

Chatbots, like real service agents, sometimes need to ask users to wait while it retrieves information. Instead of radio silence, fill the waiting gap with fun facts or news and updates about your service or products.

This’ll make the wait for confirmations or search results — such as a hunt for popular cafes in a new city — a lot more bearable.

Chatbot shares a coffee fact while it retrieves information for user

7
Integrate visuals and downloads

Besides the text, visuals are the second most important and useful element of your chatbot design. According to research conducted by 3M, the company behind those famous yellow Post-its, visuals are processed 60,000 times faster than text. This means using images to illustrate your chatbot’s messages are likely to hook your user’s interest.

Your chatbot can show your customer a map of the closest stores based on their location, or the sofa they’re interested in a room display for size reference.

In addition to being helpful, visuals are a great way to put a smile on your visitor’s face. Use them in a clever way to add some humor to conversations.

Chatbot using humor and a gif in conversation

Use images, brand logos, icons, and other visual graphics in a carousel to highlight important pages on your website. For example, your products, services and FAQ pages. Users will have the combination of a quick visual overview of what you offer and can easily click on and explore what’s most interesting to them with a chatbot on screen to answer their questions.

Userlike chatbot carousel feature

Some chatbot providers, such as Userlike, even let you send downloads directly in the chat. Whether it be a shipping label, prescription or registration confirmation, a chatbot can send important documents without the help of an agent.

8
Educate users on bot commands

A bot conversation can be draining if the user speaks in short sentences. Before the chat, give users guidance on how to quickly solve their request.

User orders a taxi with a chatbot

The simplest way to educate is to let users know at the start which command elements are required for a quick search, or to simply ask “What can you do?”

If the user goes silent for a few seconds during the conversation, the bot can remind them of cheat commands or show button options for common requests.

Some real life examples:

Both companies used a different approach, but were able to convey the scope of their bot’s ability in as few words as possible. This helps avoid overwhelming your customer with options.

9
Find a balance between proactive and reactive

Chatbots can be smart promoters — if you don’t push it.

They can invite visitors to start a conversation with deals and promotions, like after they’ve lingered on a page for 30 seconds: “Hey, just letting you know - if you order within 24 hours, shipping is free. Want a promo code?”

Or let them know about special deals on products they’ve viewed:

“Did you know that we have Nike shoes on sale? Click here to browse :)”

If you decide to use a proactive approach, it’s best to have the chat window pop up in an unobtrusive spot. According to the Gutenberg Diagram, the bottom right corner works best. This will help keep visitors from closing the window before the chatbot can do its thing.

Gutenberg diagram illustration
The human brain scans a web page from top left to bottom right.

This is also a good opportunity to offer products and services after your customer has accepted your chatbot’s help.

Seems salesy? You're right.

That’s why it’s all about the balance between responding to the customer’s needs and offering a comprehensive service experience.

For example, if the bot helps me find a new computer monitor, but then starts recommending expensive gaming keyboards and graphics cards, I would be annoyed. These products are potentially relevant, but it’s purely making assumptions about what I need. On the other hand, if a chatbot recommended a warranty plan or HDMI cables, I might be interested. This is useful to me in the moment, and within a more reasonable price range.

Finding this balance and creating targeted campaigns and promotions takes some thoughtful planning.

For some more tips, check out our post on how to use proactive chat effectively.

10
Make it easy to switch from bot to human support

Your bot cannot help with every possible inquiry, especially if it comes to complaints or exceptional cases. That’s when your customer needs to talk to a human.

When you design your chatbot, allow for an easy shift from bot to agent. Here’s what the conversation flow could look like:

Chatbot agent fallback flow
Source: Botcore

We recommend either integrating your chatbot solution into your live chat, or using a customer messaging platform that provides a built-in chatbot. That way you can monitor your bot’s performance from one platform and provide an easy fallback to your agents.

Prototyping

Before your bot comes to life, you might need to present the design to a team lead, investor or contractor. A prototype is useful for finding clarity and direction during the chatbot design process. Plus any issues with your flow, commands and more will rise to the surface.

Luckily, you have many options for creating professional bot prototypes to showcase your design. Here is a list of bot prototyping tools you may find useful.

If you want to skip prototyping and build a bot you can preview before making it live, consider tools like the AI Automation Hub or IBM Watson, which let you preview your chatbot within the software before it’s available to your users. That way you can actually chat with your bot in a live demo instead of just showing a chat concept.

Testing & Data Analysis

Let me stress once again that chatbots are like perfectly brewed beer. The creation takes time to perfect. Your bot design is not going to be great overnight, which is why you need to test it within a closed group (e.g. employees, existing customers, testers) and analyze test data to improve the performance.

You will not get around involving real humans in the test process, but you can partly automate testing by using tools designed for this purpose. Botium, one of the first companies offering automated chatbot testing, claims that you can run the same 200,000 tests that a team of 30 people run within six weeks in two hours.

These are some useful chatbot testing tools:

11
Use an intuitive chatbot design platform

Chatbot design requires pre-planning humanlike, engaging and educational conversation flows. But information is constantly changing and people are unpredictable — it’s difficult to fully write, design and program a chatbot that covers all bases.

At Userlike, we wanted to make intelligent automation attainable for every business. That’s why we created the AI Automation Hub as part of our live chat and customer messaging solution. It eliminates the need to use a third party software, and is easy for anyone to use, from your support agents to your marketing team. Anyone can design an engaging chatbot.

Userlike's AI chatbot uses button options and catalogs in conversation
Userlike gives you a chatbot that can talk to your customers on all their favorite channels from one inbox.

Instead of planning scenarios, the AI Chatbot is connected to a central knowledge base loaded with your business data. It uses this information to talk to your customers and deliver the best answer. It’s self-learning, which means its conversations improve over time, and not just through chatbot conversations.

The hub also has a Smart FAQ and Contact Form Suggestions module, which automatically try to predict what the user is looking for as they type. With every inquiry, the knowledge base grows smarter and improves its accuracy across all three modules.

Userlike's smart contact form auto predicts an answer to the user's question as they type

If you’re getting started with chatbot architecture design and development, our AI Automation Hub will make your life easier. Test it out for free for two weeks by signing up for a free Userlike trial. Don’t worry, we don’t need a credit card for you to test.

If you’re having an easy time using our product, get in touch with our support team on our website or send us an email at support@userlike.com to discuss your chatbot and automation plans further. We look forward to getting you set up with intelligent automation for your business!