The Complete Guide to Chatbots


We realise the idea of chatbots might seem a little intimidating. After all, while some robots warm our hearts others-well, they kind of freak us out.

But the truth is, robots aren’t here to take over the world (at least not yet), they’re here to make life easier.

In this guide, we’ll show you how to leverage chatbots for the incredible tool that they are: Taking on the burden of time-consuming tasks, and allowing you to better serve your customers in  the ways that matter most.


What are chat bots?

Chatbots are programs built to automatically engage with received messages. Chatbots can be programmed to respond the same way each time, to respond differently to messages containing certain keywords and even to use machine learning to adapt their responses to fit the situation.

Chatbots leverage chat mediums like SMS text, website chat windows and social messaging services across platforms like Facebook and Twitter to receive and respond to messages.

Chatbots come in all forms. There are some fun and goofy chatbots like Cleverbot, a chatbot that chats with real people and learns as it goes.

And there are also business bots for satisfying customers. Facebook recently released a host of data proving the value of bots for business:

  • 2 billion messages are sent between people and businesses monthly

  • 56% of people would rather message than call customer service

  • 53% of people are more likely to shop with businesses they can message

While they aren’t a new business tool, the utilisation of chatbots has certainly gained momentum in the last few years. Data from Google Trends shows over the last five years, search volume around “chatbots” grew 19x as individuals and businesses began to realise their value.

Screenshot 2018-11-21 at 14.12.18.png

But the questions then become: What types of business bots exist? How do bots save time and create a better experience? What do end users want to achieve when using these bots? And how do they work?

How do chat bots work?

There are essentially two different kinds of chatbots: rule-based functionality and machine learning chatbots. 

Rule-based chatbots can only respond to specific commands. In other words, the chatbot will answer questions based on keywords. The most common type of rule-based chatbot uses a document retrieval system and is limited in its capabilities. In many cases, rule-based chatbots cannot understand conversations, as the computer only recognises certain keywords. This can lead to contextual mistakes regarding the question. For example, think of the times you have interacted with Siri or Alexa. Sure, they can pick up on certain conversations, however, they occasionally default to Google. This can cause frustration when looking for customer support. Generally, organisations prefer rule-based bots due to how easily they can be created.

When conducting business in a highly competitive industry, any small thing such as having an intelligent and responsive chatbot can greatly set you apart from the competition. More and more businesses are gravitating towards the use of chatbots, specifically rule-based bots.


Machine learning bots on the other hand utilise artificial intelligence in order to continuously learn and evolve from their conversations with people. In machine learning cases, chatbots are able to understand language instead of just scouting for keywords.

This is due to machine learning chatbots utilising a program known as natural language processing (NLP). The NLP program evolves by means of supervised and unsupervised learning. Supervised learning allows chatbots to translate input data into desired output data. What this means is that, essentially, the chatbot takes conversations and adds them to a function so that future conversations can be interpreted to produce similar outputs. Therefore, supervised learning creates a learned interpretation of the conversation.

Unsupervised learning looks at patterns in the data without previous inputs. As the program analyses data, it will assign a function to an input and extrapolate the output. NLP also uses algorithms to make decisions and learn patterns. Many NLPs are a combination of support vectors, statistical regressions, and decision trees. All of this creates a machine learning chatbot.


Chatbot Types:

Chatbots are able to accomplish many functions. We are going to list some of them but with a little imagination, you can adapt their characteristics to more tasks than you will see here.

  • Branded or service chatbots – these helpers are the solution for improving the services provided by companies. They can perform different actions that enhance the performances of each business. There are many domains that encounter the need for service chatbots:

  • Customer service to offer answers for clients

  • Data analysing for optimising marketing strategies

  • Gathering feedback for finding client’s opinions about specific products

  • Messenger app for maintaining the presence for your customers

a) Virtual Assistants:
Businesses use chatbots for a variety of cases, such as customer service. Simply put, an artificial intelligence service can be used to answer simple questions, help users book services, get more information about a specific topic, buy a product, etc. Having a chatbot help expedite this types of tasks, allows for human agents to focus on more relevant problems. At the same time a chatbot allows the company to have a 24/7 service to attend to their customers needs.

b) Idea Generation:
Data is the commodity that powers the digital economy these days. However, it is necessary to have the necessary resources to transform them into something of value. Ideally companies will have cognitive solutions in place that learn automatically from all the data they collect. What makes artificial intelligence systems so powerful is precisely the fact that they can learn. That allows them to adapt when market behaviour changes, as well as continuously improve performance as more data comes in.

c) Automation of manual processes:
Artificial intelligence is rapidly automating routine and mechanical cognitive processes. Leaving more time for innovation. The use of intelligent algorithms, for example, can now automate the process of collecting data from various reports and perform an analysis to determine the profitability of a particular business path.

d) Analysis of unstructured data:
It is estimated that 80% of the digital data is not structured. Organizing and tracking these data has the potential of leading to a better understanding of the users and making predictions based on tendencies.


A luxury fashion brand, Burberry may have a presence that dates back to over 160 years, but it successfully embraces new technologies like chatbot to connect with the luxury seekers of today. Its bot for Messenger helps the users to pre-order pieces, view live streaming of their runway shows, browse the latest collections and do a lot more.


Nordstrom’s chatbot talks with customers about what they’d like to purchase from the store. [Source]

Chatbots for ecommerce companies are typically designed to:

  • Complete buyers’ purchases

  • Offer buyers product recommendations

  • Provide customer support

Even with this list of functions, it might be difficult to imagine how online sellers use chatbots since the technology is relatively new. Here are a few examples of how ecommerce chatbots can help businesses connect with their customers:


The office supply store uses Facebook Messenger to offer customers product suggestions based on their requests and past orders. Staples’ Facebook chatbot can also enable customers to complete their purchase from the chat.


Sephora’s chatbot on the bot platform Kik offers users makeup tips and makes product suggestions based on their personal quiz answers about their makeup usage. It also redirects users to the Sephora app or site to complete purchases.

Chatbot (1).jpg

What’s the value of having a chatbot?

One way to stay competitive in modern business is to automate as many of your processes as possible. Evidence of this is seen in the rise of self-checkout at grocery stores and ordering kiosks at restaurants.

In fact, Amazon just opened a store without any cashiers or self-checkouts, limiting human interactions to those only absolutely necessary.


The value in chatbots comes from their ability to automate conversations throughout your organization. Below are five key benefits businesses realize when using chatbots.

1. Save Time & Money

By automating conversations that would otherwise require an employee to answer, organizations save time and money that can then be allocated to other efforts.

Instead of having your reps spending all of their time answering inbound questions, those individuals reallocate time to proactively finding relevant conversations to join with social listening tools.

The amount of time you save increases as your inbound message quantity increases. And since Sprout Social research shows the number of social messages requiring a response from a brand increased by 18% from 2015 to 2016, you save countless hours by automating responses with a chatbot.

2. Generate Leads & Revenue

Chatbots use direct messages to gather information necessary to provide effective support. For example, asking users why they’re visiting your page is one question that is likely asked in every engagement.

Automating this initial interaction allows users to share the information needed for the agent to better serve them without requiring a human to ask for it. For example, Drift’s website chatbot qualifies prospects and gathers their email addresses so a sales rep can follow up.


This chatbot automatically delivers qualified leads to the sales organization while also fighting the fatigue caused by answering the same questions over and over. You’ll find the team is happier with more quality leads and time to spend on more meaningful work.

3. Guide Users to Better Outcomes

Customers don’t always know where to go to find the information they’re interested in. In fact, your customers may not even know what it is they’re interested in. Maybe they just heard your brand name in passing and decided to explore. By asking a series of qualifying questions, you route users to the best place for them to find the information they want.

Think through some of the questions to ask that will route your visitor to the best possible solution. These questions vary by business type, but some common ones are:

  • What problem are you trying to solve?

  • What are your goals?

  • Where are you located?

  • What department are you in?

  • What industry are you in?

  • Would you like personal support?

Imagine a global organization such as an airline. Between departing locations, arrival locations, potential upgrades and a myriad of places to purchase tickets, there are an almost infinite number combinations for purchase.

By personalizing the questions a chatbot asks, those airlines direct customers to the best way to buy and create a better user experience.

This seamless user experience makes the painstaking process of planning a trip much easier for both the user and the business.

4. Provide ‘After Hours’ Support

As we saw from the Drift data, the most popular use of chatbots is to provide quick answers in an emergency. However, organizations that don’t offer 24-hour support won’t provide answers when the office is closed.

By using a robust chatbot when your business is closed, customers still gain access to the information they need.

This is especially important as consumers expect a quicker response than brands can guarantee. According to Sprout Social’s Q2 2016 Index, customers expect a response between 0-4 hours. However, brands typically take 10 hours to respond.


Chatbots help you significantly decrease the average time to respond, bringing you closer to your customers’ expectations.

5. Engage Users in a Unique Way

Traditionally, customer questions were routed to businesses via email or the telephone, which made user experiences fairly standard and non-customized. But chatbots offer a new, fun and interactive way to engage with brands.

One great example is Domino’s Pizza’s Twitter. Domino’s allows customers to order pizza by simply sharing an emoji. The Domino’s bots then route those orders and ask additional questions if necessary.


Another great chatbot example comes from Fandango. Unlike the days when you had to spend time sorting through Moviefone’s options via its 1-800 number, you now go to Fandango’s social profiles and leverage its chatbots to find movie times and theaters near you.


These seamless and memorable user experiences ensure that your users will think of your bots the next time they’re looking for dinner and a movie.

Are you curious to learn more about social media chatbots? Fill in a bit of info below and someone from Sprout Social will reach out to discuss how to build Twitter and Facebook chatbots!

Talking to a robot sounds foreign, cold, and impersonal. And yet, chatbots have made many brands more human and approachable to buyers. These bots are personal in remembering customers’ preferences and are convenient as a 24/7 service. As long as companies are upfront about bots being technology and not actual people, this technology is a surprisingly intimate and useful way to communicate with buyers.

In a fast moving world, it is important to provide immediate solutions for your customers. This is the core reason chatbots were created.

If you’d like to discuss how a potential build and implementation of a chatbot could benefit your business, get in touch with a member of the UNBXD team today.

Thanks for reading.

article signiture template.png