What is a chatbot + how does it work? The ultimate guide
Chatbots are computerized programs that can simulate human-like conversation and help boost the effectiveness of your customer service strategy.
By Maddie Hoffman, Director of Chatbot Operations
Last updated August 16, 2023
What is a chatbot + how does it work? The ultimate guide
According to the Zendesk Customer Experience Trends Report, messaging support has become a go-to for customers—tickets jumped 370 percent over WhatsApp alone last year. As messaging rates rose, so did the use of AI chatbots.
But what, exactly, is a chatbot? How do chatbots work? And will they steal customer service representative jobs? In this article, we’ll answer all your chatbot-related questions.
Table of contents
What is a chatbot?
A chatbot is a type of conversational AI that enables businesses to put a layer of automation or self-service in front of customers in a friendly and familiar way. With companies increasingly adding messaging channels to provide faster resolutions and always-on support, bots have quickly become a key component of any messaging strategy.
Chatbots can help companies improve their customer support by:
- Providing instant responses: Bots can be deployed over various channels—including messaging apps, social media platforms, and websites—and ensure customers get immediate responses when an agent is busy helping other customers (or watching Bridgerton).
- Escalating and routing tickets: If a bot can’t resolve an issue or answer a question, it can collect information from the customer and route the ticket to the right agent.
- Collecting customer feedback and data: Bots can gather insightful customer feedback and data. Zendesk’s Answer Bot, for example, asks customers if it was able to resolve their issues. This provides a way to capture end-user data to measure how well each response is performing and indicates which answers can be refined and optimized.
How do chatbots work?
Bots use predefined conversation flows, natural language processing, and/or machine learning to answer questions and guide customers through different scenarios, such as:
- Log-in issues
- Payment problems
- Booking instructions
AI bots can also learn from each interaction and adjust their actions to provide better support.
Chatbots work best with straightforward, frequently asked questions. Unless their underlying technology is especially sophisticated, bots typically can’t handle difficult, multi-part questions like a support agent can.
To better understand how chatbots work, read on to learn what Zendesk’s Answer Bot can do.
1. Surfaces help center articles and resources for customers
Chatbots like Answer Bot can recommend help center articles to customers in the chat interface. Rather than finding FAQ or support pages and then guessing which search queries will bring up the information they need, customers can ask the bot a question. The chatbot will then scan for keywords and direct them to a help center article that answers their question.
Answer Bot uses a deep-learning model to understand the context of a support ticket, associate questions with answers, and learn which help center articles it should suggest to a customer. It also learns from every customer interaction and trains itself to deliver more relevant and customized content with each resolved ticket.
This type of automation leads to faster resolutions and, ultimately, better experiences for customers and agents alike. By fielding common customer queries, a chatbot allows agents to focus on other tasks and resolve more complicated issues, increasing their productivity and engagement.
2. Collects key customer information and context
To save agents time and ensure customers are always routed to the right person for help, Answer Bot can capture customer information up front, such as name, email, account type, order number, and issue. Then, it can seamlessly hand off the customer to a live agent, along with all the conversation history and context. Answer Bot can populate this info into a ticket for the agent, too.
3. Responds to basic, repetitive questions
In addition to serving up help center articles, you can create rich, customized bot conversations with Flow Builder. This tool allows you to orchestrate the conversation between the chatbot and your customers. Once you build a conversation flow, you can publish it in multiple languages—without needing to write a single line of code.
Flow Builder is meant for the kinds of questions that your team often receives and can resolve in one touch (think FAQs). It gives customers what they want—quick answers—and agents time back for high-stakes tasks.
Benefits of chatbots
The benefits of chatbots go beyond increasing efficiency and cutting costs—those are table stakes. Bots are at their most powerful when humans can work in tandem with them to solve business challenges. Explore the many benefits of chatbots below.
Being constantly connected has increased customers’ desire for instant support. Customers today expect help as soon as they need it, on the channels of their choice. And over 40 percent of consumers think 24/7 real-time support is a top factor of good customer service, according to our CX Trends Report.
In deploying a chatbot across customers’ preferred channels, businesses ensure customers get seamless, always-on support.
Our Trends Report revealed that 42 percent of customer service leaders expect customer requests to grow, yet only 36 percent can expand headcount. This gap represents a sweet spot where a chatbot can help.
Chatbots can serve as extra support agents, handling simple questions and basic requests. As a result, support teams can scale quickly—they can help more customers without having to hire more staff.
Customer service bots can boost conversions with smarter self-service. A chatbot can enable customers to self-serve outside of a help center—like on a checkout page.
When it comes to conversion opportunities, chatbots can also:
- Convert customers within the chat: Bots can nudge customers to take action by presenting them with image carousels, forms, picklists, and other messaging elements. Customers can book a hotel reservation or purchase a pair of shoes, for example, all within the chat.
- Automate cross-sell and upsell activities: With the right context, a bot can check if a consumer is eligible for a discount on a hotel room with a view or ask if they want a pair of socks to match their new Nikes.
Chatbots can aid human agents by being the first point of contact. Customers expect an instant response when reaching out on conversational channels, and bots allow companies to do that. Bots can capture customer details—like name, issue type, and contact info—before passing the customer on to an agent, which enables the agent to personalize the conversation.
Additionally, Zendesk’s Flow Builder can be used to create conversational experiences with your brand’s tone and voice, adding a bit of flavor to otherwise bland conversations.
Types of chatbots
There are different types of chatbots that businesses can use. The right one for you will depend on the products or services you offer and the type of experience you want for customers. Read on to learn the three main types of chatbots.
Help center chatbots
Chatbots that suggest help center articles can learn based on content in your knowledge base and recommend the right articles on any page of your website, inside your mobile app, over email, or via messaging channels.
Research tells us that customers want to resolve as many issues as possible with a company’s online resources. In our CX Trends Report, 70 percent of customers said they expect a company to have a self-service portal or content available to them.
Since a bot provides one-on-one support, customers don’t need to use a generic search engine, making it easier for them to find answers. Plus, when a bot works alongside your knowledge base, it uses your existing resources to deflect questions you already have answers to, resulting in faster resolutions and time to value.
Decision tree chatbots
Decision tree bots enable you to design customized conversation flows that provide customers with quick answers, suggest knowledge base articles, and include triggers for handoffs to a live agent.
Companies that are just getting started with a decision tree chatbot should look for a tool that doesn’t require coding and features a visual interface to help them create decision trees.
Task-specific chatbots are meant to help customers with a specific task and are typically highly specialized.
They are unique in that they understand many different types of questions. With access to the right customer data, they can deliver personalized responses. For instance, a recruiting company might use this kind of bot for automating the first step of the recruiting process by helping candidates submit their applications.
However, task-specific bots require comprehensive training and deeper natural language processing, so companies will need to have more resources and a bigger budget.
Zendesk makes it easy to integrate third-party task-specific chatbots into your support system for seamless bot-human handoffs and more personalized conversations.
Chatbot best practices
Ready to add a chatbot to your customer service strategy? Here are some best practices to follow.
1. Tell users they’re interacting with a bot
Our CX Trends Report found that customers are open to (and even prefer) resolving basic issues with a chatbot because it’s convenient. However, it’s important to let users know when they’re interacting with a bot because it:
- Sets expectations: Customers know they’re not speaking with a human, so they won’t expect certain things.
- Promotes acceptance and trust: Shows that you’re not hiding anything from customers.
- Provides transparency: Customers are open to communicating with bots, but they don’t want businesses to deceive them.
2. Make it easy to reach a human agent
Our Trends Report also showed that customers are most frustrated with chatbots when they:
- Can’t get an accurate answer
- Have to start all over again with a live agent
- Can’t get through to a human
Plus, 46 percent of customers get frustrated that they don’t have a choice in human vs. bot at the start of the interaction. Chatbots aren’t meant to resolve every issue, so it’s crucial to include an option to reach a live agent.
It’s also important to ensure that your bot can pass on the customer context and conversation history to agents so they have all the details they need and customers don’t have to repeat themselves. According to our report, nearly half of customers believe AI should prevent people from needing to repeat information.
3. Let chatbots handle simple issues
Chatbots work best when their task is clear and simple, so let them handle the easy stuff. Here’s where your chatbots should play a starring role, according to customers:
- Providing links and information that can help resolve problems
- Offering quick, convenient replies to straightforward inquiries
- Delivering answers and responses outside of normal business hours
However, when it comes to filing a complaint or asking for technical support, 40 percent of customers prefer to interact with a human agent. Customers prefer bots for basic issues but still want the option to speak to a human for more sensitive and complex queries.
To determine what kind of issues your chatbot should handle, start by reviewing the one-touch tickets your agents frequently see. These are usually good issues to hand over to a chatbot.
4. Incorporate bots into your self-service strategy
A chatbot can help your customers self-serve more efficiently by highlighting your FAQ pages and other resources outside of your knowledge base, such as on your checkout page and website homepage.
You can also incorporate a chatbot into your knowledge base to personalize the experience. A bot can help customers find the right articles for their unique issues and questions.
5. Use chatbots to collect customer context
Chatbots can collect key customer information up front, like their:
- Order number
- Email address
This helps ensure that agents have all the details they need to personalize conversations and resolve issues more efficiently.
Chatbots can also use this information to route customers to the right agent for the inquiry based on things like language, skill, or account type. This makes chatbots a helpful lead generation tool, as they can capture prospect contact information and connect the prospect to the appropriate salesperson.
6. Use data to improve your bot
Getting your bot up and running isn’t the end of your chatbot strategy. You also need to track metrics to improve and get the most value out of the tool. Here are a few data points to watch:
Use rate is the percentage of customers who choose to engage with a bot when prompted or given the option. It will help you see if customers like using bots, if they respond to nudges to use bots, and what channels they look to bots for answers.
Volume refers to the number of questions answered by your bot. This will allow you to understand how cost-efficient and time-efficient your bots are.
Bot response failure rate
This is the percentage of questions your chatbots can’t respond to because they don’t understand them. It will give you an idea of what people are looking for when using self-service options and identify where you can improve your bot flows.
Most answered questions
Tracking these questions can highlight common areas of frustration as well as opportunities for improving the customer experience.
Referral data is a metric that indicates how often a bot transfers an interaction to an agent. It can help you:
- Determine how bots integrate with agents’ workflows.
- Give you insight into how customers approach complex support questions.
Customer-reported bot success metrics
After a customer ends an interaction with a bot, send a survey that asks them to rate their experience. Their responses will reveal whether or not your bot provides good service.
Chatbot use cases
Many businesses are using chatbots to improve their customer service and foster brand loyalty. In our CX Trends Report, 26 percent of companies said they currently offer AI and chatbot-guided self-service, while 25 percent plan to add this capability soon.
Here are some ways that companies are leveraging the technology:
- Automating website support: Businesses have been taking advantage of the automation abilities that chatbots have for website support, like 24/7 customer service. Chatbots can provide further information about products and services and answer basic questions anytime, anywhere.
- Site navigation: Businesses can also use chatbots to help customers navigate their website and provide instructions when it comes to things like signing up for a service or free trial.
- Personalized recommendations: Chatbots can give customers personalized recommendations by analyzing their behavior on the website.
- Tracking orders and inventory: Bots can even tell customers whether a certain product is in stock or how long shipping will take.
- Boosting sales: Chatbots like Answer Bot can connect visitors to help center articles and answer questions about a product or service—before customers abandon their cart.
Are chatbots bad?
With the rise of chatbots, there have been mix-ups with the interpretation of the term. But the word chatbot should not be associated with the type of bots that hack accounts and carry out cyberattacks.
There are also a few limitations of chatbots that are important to consider, including:
- They’re not built to take over customer support: Chatbots were designed to serve as intermediaries. They keep customer support accessible when agents are off the clock and enable agents to focus on tricker requests.
- They can’t solve every issue: Chatbots are most successful when they’re paired with human agents. For example, bots can help customers troubleshoot basic issues successfully. But when there are more complex technical problems, a well-trained agent should step in.
- They don’t work well alone: Chatbots can help your brand scale 1:1 communication, but agents bring empathy to the table. Some inquiries require a human touch that only live agents can provide—meaning chatbots work best when they’re used in tandem with humans.
What chatbot platform is right for you?
Today, there are many different types of chatbots that you can deploy across a variety of messaging channels. However, chatbots are relatively new to customer service, and companies are still figuring out how they fit within their support strategy.
This can make it tough to know how to find the right chatbot for your business. Answering the following questions will help you choose a solution that best fits your support team’s needs.
1. What problem are you looking to solve, and what resources do you need to solve it?
For starters, you need to figure out what use cases to automate. Base your decision on the problem you need to solve and the resources you need to solve it.
Some companies may need a bot to surface help center articles across an array of channels and capture basic customer context. Other companies may need bots for personalized requests, like telling a customer how much data her iPhone used this month or recommending a new plan based on usage.
Offering personalized service with a chatbot requires more resources and a bigger budget. You’ll need a chatbot solution that integrates with customer service software and other relevant systems.
2. Can the chatbot work across different channels?
Customers expect to get support over their favorite channels—whether they’re interacting with a human or a bot—so your chatbot needs to work across various channels. According to our CX Trends Report, 40 percent of companies are already using AI to engage with customers via their preferred contact methods, and 65 percent want to add tools to allow this.
Our research also tells us that customers want to interact with brands on channels they use with friends and family. Messaging channels—such as Facebook Messenger, WhatsApp, Twitter Direct Message, LINE, Apple Business Chat, and SMS—lend themselves to more convenient conversational experiences.
3. What level of context will the chatbot need?
More customer context leads to personalized conversations and better service experiences. 44 percent of customers say it is most frustrating when they have to explain themselves over again to a human agent after interacting with a bot.
To provide context for your chatbot, do the following:
- Incorporate CTAs: Ensure the chatbot displays proactive CTAs tailored to what a user is trying to accomplish.
- Use contextual metadata: This includes a user’s name for a personalized greeting.
- Take advantage of sentiment analysis: This is the ability of a chatbot to gauge the sentiment behind the words used in the conversation. A virtual agent can understand when a customer is frustrated and react accordingly.
4. How will you manage conversations between chatbots and agents?
You also need to decide how you’ll manage the conversations that occur between your agents and chatbots. This helps ensure agents can understand the intent behind every conversation and streamline handoffs between agents and chatbots.
With the help of triggers, automation, and workflows, support teams can centrally define engagement rules and track, manage, and prioritize chatbot interactions at scale. In fact, 39 percent of companies already use AI to prioritize customers based on their status or account type. This opens up possibilities, like automatically assigning:
- A high priority to VIP customers, so a bot can route them to a live salesperson for help—along with the conversation history.
- A repeat dissatisfied customer to a specialized customer support team by looking at the context, sentiment, and intent.
To effectively control bot interactions, a business will need to integrate its chatbot solution with its customer service software. The Agent Workspace in Zendesk provides agents with a real-time, conversation-focused interface to seamlessly manage conversations between agents and bots.
How have chatbots evolved, and what’s next?
Chatbots have come a long way, partly due to advances in AI and machine learning. Most recently, the rise of messaging has made bots an essential part of any customer service and engagement strategy. Today, nearly all the top messaging platforms offer APIs so businesses can offer seamless messaging experiences with a bot.
Chatbots are a continuously evolving technology. Below are some current trends in the chatbot space.
The rise of messaging
There are already 300,000 active Facebook Messenger chatbots, and messaging will only become a more critical customer engagement channel. Businesses need to add the channels that matter most to their customers.
With support that’s fast, personal, convenient, and secure, it’s no surprise that messaging has seen an upswell of adoption by both customers and businesses.
Chatbots will see an adoption boost
AI isn’t new technology anymore; however, many companies are still learning how it fits into their overall business strategies. As AI continues to improve and chatbots become more sophisticated, more businesses will adopt them.
In fact, the chatbots market was worth $1274.428 million in 2018 and is projected to reach $7591.82 million by 2024, registering a CAGR of 34.75 percent over 2019 to 2024, according to Research And Markets.
Human agents will remain important
Even as chatbot technology gets smarter, bots shouldn’t replace human agents—they’ll just help them work more efficiently. Businesses get the greatest value from AI when using augmented intelligence: human intelligence and machine intelligence combined.
According to our CX Trends Report, customers want interactions to feel authentic and personalized. They want past interactions to inform future conversations, too—this is why human agents will remain important. Currently, 32 percent of businesses use both bots and human agents for chat.
The best bot experiences are built with Zendesk
Zendesk makes it easy to enhance your customer support experience with automation. There are multiple options available.
Deploy in minutes: Answer Bot leverages your existing help center resources to guide customers to a resolution via self-service and collect customer context. Additionally, use Flow Builder to build conversations without writing a single line of code and create multiple unique bots for different brands, languages, locales, and departments.
Choose from a variety of third-party solutions: You are also able to integrate third-party chatbots with Zendesk for your chatbot needs with Zendesk’s developer platform.
Build your own: Zendesk’s developer platform enables brands to build their own custom bots for sophisticated use cases.
Most importantly, our award-winning support platform provides teams with a real-time, conversation-focused interface to seamlessly track and manage conversations between agents and bots.
While the public is only just now beginning to grapple with the rise of artificial intelligence,…
ChatGPT and Google Bard provide similar services but work in different ways. Read on to learn the potential benefits and limitations of each tool.
In the fifth episode of Conversations with Zendesk, AWS's Deepam Mishra talks about the promise of AI and how to maintain the human touch as the technology grows in use.
Zendesk's adaptable Agent Workspace is the modern solution to handling classic customer service issues like high ticket volume and complex queries. This guide explores new features that make agents' jobs easier.