How to design and build an SMS chatbot
Everything you need to know about text chatbots, including what makes them successful and how to build one without having to write a line of code.
What is an SMS chatbot?
An SMS chatbot is a software program that can automatically send or reply to text messages, and by being trained to understand intent can even have ‘conversations’ with people over SMS.
Text chatbots are commonly used by businesses as a way of automatically providing information and answering questions from customers. They can be deployed to help in a number of areas.
SMS chatbot use cases
- Operational messages: Text chatbots are ideal for sending important information that needs to be seen and responded to immediately. This can be triggered by a customer action, for example making a booking, or an event like a credit limit being reached, or a policy expiring. This is different to SMS alerts and notifications which are a one-way broadcast. SMS chatbots can receive replies back from the customer and perform actions based on that information – for example ‘You have reached your spending limit. Would you like to extend it by $50? Answer YES or NO.’
- Customer support: SMS chatbots can be used to provide support and answer basic customer queries that don’t need a detailed reply that would exceed the 160-character limit of SMS. Rule-based chatbots can provide answers via a set of pre-configured options covering FAQs like ‘What are your store opening hours’ or ‘What is your returns policy?’ See the ‘How to build an SMS chatbot‘ section below for step-by-step instructions on how to build one of these useful bots.
- Marketing: While some channels that support images, video and other dynamic content are more commonly associated with marketing use cases, the simplicity, reach, and high open rate of SMS messages make text message chatbots a great tool for sending high value promotional messages that include an action. For example, “You now have enough loyalty points to qualify for a 40% discount on a Platinum subscription. Would you like to upgrade now? Y/N”
Why use an SMS chatbot?
While chatbots can be effectively deployed on all sorts of digital channels, there are a number of reasons to include text messages in the mix.
- Reach: Text messages can be received by any of the 6 billion + people globally that own a mobile phone. No data or internet connection is required as messages are delivered by the regular cellular network, and SMS can be received by people who use an older style phone without ‘smart’ capability. Â
- High open rate: SMS has one of the highest open rates of any messaging channel at over 98%
- Simplicity: The majority of business use cases for automated messaging are incredibly simple – usually a short piece of information is sent, and then a short reply or binary YES or NO is received back. SMS is ideal for these scenarios. For example – when a policy renewal date is approaching you might send “Your policy expires on the 15th January 2024. Would you like us to automatically renew. Reply YES or NO.”
- No app required: All mobile phones can receive text messages by default with no requirement to download a separate app.
- Control: With an SMS chatbot a business has full control of their messaging strategy and don’t have to abide by the rules set for WhatsApp and Messenger for example. However, when sending SMS messages businesses do need to make sure that they abide by the SMS regulations in all the regions that they send to.
- Trust: SMS is the most commonly used channel for sending PIN codes and passwords as part of a 2FA verification process. With authorized senders, people are used to receiving automated SMS messages from brands that they trust. Â
- Originality: Compared to web bots and chatbots deployed on digital channels like WhatsApp, Messenger, and Viber, not many businesses incorporate text chatbots into their messaging strategy. We see this as an oversight as it offers all the advantages that we have listed above. Adopting an SMS chatbot will enable businesses to provide their customers with an easier and more dependable messaging service than competitors. Â Â Â Â
Types of text chatbot
There are two main types of SMS chatbot, but they are not distinct as elements of both can be incorporated into the same text chatbot.
Rule-based SMS chatbots
These chatbots are designed to enable the exchange of information using YES/NO answers or a pre-configured menu of options for users to select from. They are the quickest and easiest to set up but can be incredibly useful for use cases where a quick and simple answer is required, for example answering day-to-day queries that customers would previously have called a contact center to answer. Anything from store opening hours, product availability, and account balances can be provided via a simple set of options.
Intent-based or conversational SMS chatbots
These are more sophisticated chatbots that can be designed to provide a more conversational experience for people interacting with them. They take longer to build as they use natural language processing (NLP) and need to be ‘trained’ to understand multiple words, phrases and user intents. While these conversational chatbots can be deployed on the SMS channel, the relative cost and speed of typing text on a mobile device make them better suited for web and chat app channels.
Text chatbots vs messaging app chatbots comparison
SMS chatbots | Messaging app chatbots | |
Available in all countries? | Yes | No (e.g no WhatsApp in China) |
Mobile number required? | Yes | No |
Requires internet or data? | No | Yes |
Requires mobile signal? | Yes | No |
Supported on android and iOS? | Yes | Yes |
App download required? | No | Yes |
Character limit? | Yes – 160 | Very high (20,000 +) |
Read receipts available? | No | Yes |
Emojis supported? | Partly (can reduce char limit) | Yes |
Are messages encrypted? | No | Yes (in most cases) |
Supports links? | Yes | Yes |
Supports images? | No | Yes |
Supports videos? | No | Yes |
Customer pays for messages sent? | Yes | No |
Consent required? | Yes (in most regions) | Yes |
How to build an SMS chatbot
Our worked example uses the free trial version of our chatbot building tool Answers.
Get started with a free account
To follow the steps, just sign up for your own free account using this link. You get full access to Answers with the ability to build SMS chatbots as well as bots for WhatsApp, Messenger, Viber, and web.
Note that to actually deploy your SMS chatbot will require adding credits to your account.
To get started building your first SMS chatbot, log into your account and select the Answers icon from the panel on the left.
Then click the Try for Free button.
Under Basic setup, click Your first chatbot and then from under Start from template or create new select CREATE CHATBOT.
This page displays a number of pre-built templates that you can use to form the basis of your chatbot, or you can select Start from scratch to create your own.
The final setup step is to give your chatbot a name and select SMS as the deployment channel. There is no need to specify a Sender at this point, although this will need to be configured before the chatbot is made live.
Introduction to the interface
Answers’ interface provides a drag and drop canvas where you can build up your chatbot flow by dragging elements from the panel on the right-hand side. Simply drag on the element that you want and then configure it using the settings on the right.
In our example we will only be using a few of Answer’s basic features, but you are free to experiment as much as you like with more advanced options. These are fully documented in our online help, which includes a number of useful tutorials:
Step 1 – Configure a welcome message
Due to the cost of sending SMS messages, chatbots deployed by SMS should be designed to achieve a specific purpose with as few messages backwards and forwards as possible.
It is also important that the value of the interaction is clear to the customer up front so that they are willing to invest their time and money in the process.
With this in mind, the first message in the interaction is important as it needs to catch the person’s attention and make the purpose of the message crystal clear.
Drag on a Text element from the Chatbot sends menu and configure a welcome message.
When sending multiple messages in a sequence, it is best practice to include a Delay between each one to give the user time to read and absorb the previous message to avoid overwhelming them with information.
Simply drag on a Delay element from the Chatbot actions menu and set a suitable delay according to the length of the previous message. You can always fine-tune delays during the testing phase.
Step 2 – Provide options for users to select from
In our welcome message we have made it clear what the intent of the chatbot is. We are asking the person if they would like to book tickets and there are only two answers – YES or NO.
We therefore use a User Input element to capture their response so that we can create the appropriate flows depending on their choice.
The next step is to add a Go to dialog element for each reply, so that we can deal with each intent separately. At this point you could add as many options as you like, but this would require a separate flow for each option, so it is best to keep it simple.
In our example we are just creating flows for the answers YES and NO, but we could have added additional options like ‘Remind me later’.
Step 3 – Link responses to next action
This is the point where the chatbot delivers on its promise and is configured to perform an action that delivers value to the user.
If the user selects NO then we simply sign off with a friendly goodbye, but if they select YES then that would trigger the action – in this case to reserve tickets.
The next step would require an integration with a third-party booking system, which is no problem to do via the API. In our example we can send the person a payment link by SMS, although any supported payment system could be used.
Step 4 – Draw the interaction to a close
When building an SMS chatbot you should always confirm with the person that the intent has been achieved. If the person has not achieved their goal, you should provide them with an alternate path, so they are not left in limbo and don’t waste any further SMS messages.
You can then sign off the chat or loop them back to the beginning.
To close and reset the chatbot interaction add a final Close session attribute. This can also optionally delete any saved data – or it can be copied to your customer database to enrich future interactions with the person.
Step 5 – Test using the Simulation option
Answers provides a Simulation option that can be used to test your chatbot flow and make final adjustments to ensure a good user experience. If you have missed any steps, or have misconfigured any dialogues, then these will be flagged before the simulation can be used.
This is simple example of a rule-based SMS chatbot that allows the exchange of information between the business and customer using a combination of simple YES and NO options and direct multiple-choice questions.
Using Answers, you can go on to create highly sophisticated text chatbots that use natural language processing to understand customer intent and to facilitate conversational interactions via text. Take a look at the following video which provides a good introduction to building chatbots with Answers.
Talk to an expert about building effective text chatbots
Get in touchLearn more about building chatbots
How to build a Facebook Messenger chatbot
Everything you need to know about creating a chatbot for Facebook Messenger, including the unique Messenger benefits you can tap into, and step-by-step instructions on how to build your own chatbot with no coding knowledge required.
How to build a web chatbot – best practice and step-by-step instructions
Everything you need to know to build a chatbot for your website, including design best practice and step-by-step instructions using Answers no-code chatbot builder.
Conversational AI in marketing
Explore the benefits of conversational AI for marketing agencies, from boosting customer satisfaction to optimizing workflows.