Complete guide AI chatbots

AI Chatbots provide a helping hand for agents and 24/7 support for customers. Deliver better customer service with a chatbot.

A guide to the best AI chatbot

Thanks in large part to advances in artificial intelligence technology, chatbots have become a key component of any support strategy. AI chatbots enable teams to scale their efforts and provide support around the clock while freeing agents to focus on conversations that truly need a human touch.

Of course, while customers trust bots for simple interactions, they still want the ability to speak to a human agent to resolve sensitive or complex issues. And by processing natural language and responding conversationally, chatbots make that possible.

But even with AI, chatbots aren’t a set-it-and-forget-it proposition. Businesses need to understand how to leverage and combine the strengths of both bots and humans. With Zendesk, you can design chatbot conversations across your customers' favorite channels with absolutely no coding skills and ensure seamless bot-human handoffs.

Why add an AI chatbot to your website?

When businesses add an AI chatbot to their support offerings, they’re able to serve more customers, improve first response time, and increase agent efficiency. Chatbots help mitigate the high volume of rote questions that come through via email, messaging, and other channels by empowering customers to find answers on their own and guiding them to quick solutions.

When chatbots take simple, repetitive questions off a support team’s plate, they give agents time back to provide more meaningful support—nothing kills team productivity like forcing employees to do work that could be automated. Bots can also integrate into global support efforts and ease the need for international hiring and training. They’re a cost-effective way to deliver instant support that never sleeps—over the weekends, on holidays, and in every time zone.

Want to improve your support experience with a chatbot? Here’s what you need to know to get started.

What are AI chatbots?

An AI chatbot is a first-response tool that greets, engages, and serves customers in a friendly and familiar way. This technology can provide customized, immediate responses and help center article suggestions and collect customer information with in-chat forms. Using natural language processing (NLP) chatbots, like Zendesk’s Answer Bot, can recognize and react to conversation. That means AI chatbots can escalate conversations to a live agent when necessary and intelligently route tickets to the right support representative for the task with all the context they need to jump in and troubleshoot. Chatbots can also use AI to provide personalized suggestions to agents on how to deal with a given inquiry. AI bots can be deployed over various messaging apps or channels to ensure customers get instant responses 24/7.

How does a chatbot work?

Bots use predefined conversation flows or artificial intelligence (AI) to answer questions and guide customers through different scenarios, such as login issues, payment problems, or booking instructions--to name a few. 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.

How can an AI chatbot help your business?

An AI chatbot can help your business scale customer support, improve customer engagement, and provide an overall better customer experience. Here are a few things your business can accomplish with the help of a bot.

  • Help more customers in less time and boost customer satisfaction

    According to Gartner research, organizations report a reduction of up to 70 percent in call, chat and/or email inquiries after implementing a virtual customer assistant. Many companies have a small variation of questions representing a large portion of total support volume, and therefore cost. These high-frequency questions tend to be low in value and simple to solve without human intervention, making them the perfect questions for a bot.

    By taking over these basic, repetitive inquiries, chatbots enable support teams to help more customers in less time while also giving agents time back to focus on higher-stake issues. Customers benefit from reduced wait times, which increases satisfaction. In fact, an MIT technology review found that 90 percent of businesses report recording large improvements in the speed of complaint resolution after deploying a chatbot. And it’s not just support teams that benefit from chatbots; sales and marketing teams do too. In fact, according to Gartner, by 2025, “75% of B2B sales organizations will augment traditional sales playbooks with artificial intelligence (AI) guided selling solutions.”

  • Offer help as soon as customers need it and anticipate their needs

    Providing always-on support is no longer a stand-out feature; it’s something customers have come to expect. In fact, 43 percent of consumers expect 24/7 customer service, according to an e-commerce study. And as customers’ expectations continue to rise, this figure is only expected to increase.

    Customers don’t always want to take the extra step of making a phone call or keep up with the back-and-forth of an email thread. The most adaptable businesses are going where their customers are, adding new channels, so customers have convenient options to get help as soon as they need it.

    With the machine learning that powers many chatbots, AI can help you anticipate customer needs and surface personalized answers to their questions before they even have to ask. And according to Gartner, proactive customer service results in a full percentage point increase in the net promoter score, customer satisfaction score, customer effort score, and value enhancement score.

  • Improve the bottom line

    Juniper Research predicts that by 2023, chatbots will save banking, healthcare, and retail sectors up to $11 billion annually. That’s ​​the difference between a business being in the red vs. the black. In other words, a chatbot can mean the difference between turning a profit and having to explain to stakeholders why the company fell short.

    What’s more, resolving support issues via social media can be up to six times cheaper than a voice interaction. That’s because messaging and chat channels allow agents to help more customers at once, which increases their overall throughput. Also, AI chatbots can automate and resolve many of the more routine, repetitive service operations, such as answering frequently asked questions. This allows agents to focus on more complex, high-value conversations.

How do chatbots use AI?

Chatbots use two main types of AI: natural language processing and machine learning. Natural language processing enables bots to interpret customer requests, including slang, typos, and abbreviations, and machine learning allows them to improve over time. A great example is our own Answer Bot, which incorporates 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’s also learning from each customer interaction and training itself to deliver more relevant and customized content with each solved ticket. AI chatbots are most successful when they can learn from thousands of service interactions, like those already saved in enterprise CRMs.

What are the core functionalities of a chatbot platform?

There are four core functionalities to look for in a chatbot platform. Here are some questions to guide the way.

  1. Compatible with multiple channels

    Savvy businesses have known for years that customers want a choice of channels. That’s why the power of an AI chatbot depends in large part on the channels in which it can be deployed. Ideally, you’ll be able to leverage the power of chatbots across all the messaging channels your team depends on, including social media, your website, mobile app, and other messengers like Slack or Telegram. It's also important for your chatbot to work within the support, sales, and marketing tools your team depends on. That way, you can build once and deploy anywhere. In other words, you can use the best version of a rich bot experience across all your channels, even those with no native bot support. Also, by having tight integrations with the front and back end of your service channels, you can help AI-powered chatbots learn and improve themselves quickly.

  2. Able to collect key lead and customer data

    More context leads to better chatbots and more personalized conversational experiences. Look for a bot that can collect key customer information, pre-populate it into existing ticket fields, and pass through context and conversation history when an agent is needed. When a bot can capture information from your customers, it helps your agents understand the context of the problem more quickly, and removes the annoyance of customers having to repeat themselves.

    Beyond passing on relevant information to agents, be sure your bot can also pass on context to a CRM or other software. This enables things like:

    • Understanding that Rose has a necklace in her cart and sending a message to a marketing automation tool, so she receives better-targeted email offers
    • Knowing that IT buyer Bob signed up for a demo, qualifying him as a lead in a sales CRM
    • Recognizing that Kim, a customer seeking support, needs to be intelligently routed to a specialist for her inquiry to be resolved as quickly as possible.

    For these kinds of next-level use cases, our customizable messaging platform allows you to connect all your business systems to the conversation, from payment processors to third-party bots and AI.

  3. Seamless bot-to-human handoffs

    It’s always important to have a way for customers to escalate a conversation to a real person. When a customer has a valid reason to speak to a human agent, but there’s no option to do so, it’s a frustrating experience that can lead to negative CSAT, or worse, churn.

    Sometimes a bot simply can’t handle a customer’s question, or there is sensitive information that needs to be conveyed through an agent. Triggers, automations, and workflows provide support teams with a way to manage and prioritize incoming tickets that need agent help. This opens up possibilities like identifying VIP customers and routing them to a live salesperson for help—with conversation history.

    But this doesn’t all have to be manually enabled. With the right AI capabilities, chatbots can automatically recognize when an inquiry requires help from a live human.

  4. Easy to integrate with your customer service platform

    Bots are only as powerful as the systems backing them up. And AI chatbots are enhanced when the AI can collect, process, and learn from data in other systems. Be sure to thoroughly consider the customer service software you utilize underneath your chatbot. Remember, chatbots are only one part of your larger customer communication strategy, so your support platform is often even more important to consider before choosing your bot. Understanding who is reaching out and why, as well as how often they need help, along with ensuring their issue gets resolved when a bot can’t help them, requires a robust back-end customer support platform.

    A chatbot that connects to your support systems means it can pass on information to automate ticket creation and equip agents with conversation history when their expertise is needed. Even better, using artificial intelligence, your chatbot may even be able to deliver recommended answers, knowledge base articles, and more to your agent. So when an agent picks up a complex help request from a bot conversation, they will already be in your support platform, where they can respond to tickets with context at their fingertips. This connected experience also gives you a single view to track how your bot is impacting agent performance and your support metrics.

    Zendesk provides agents with a real-time, conversation-focused interface to seamlessly track and manage conversations between agents and bots.

What are the benefits of AI chatbots?

The benefits of AI 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 key business challenges.

  1. Provide convenient 1:1 service, 24/7

    Being constantly connected has increased customers’ desire for instant support. Customers today expect help as soon as they need it on channels convenient for them. In deploying an AI chatbot across customers’ preferred channels, businesses ensure customers get seamless, always-on support—no need for customers to sit in a queue or wait for an agent to come online.

  2. Serve more customers

    In our Trends Report, we found that many customer service leaders expect customer requests to grow, yet not everyone can expand headcount. This gap represents a sweet spot where a chatbot can help. Rather than hiring more talent on the roster, bots can help teams become more productive. Chatbots can act as extra support reps, triaging simple questions and basic requests.

  3. Increase your team’s impact and output

    Boost agent productivity by taking mundane inquiries off their plates and freeing them up for complex questions. Chatbot software also lets you gather information from customers upfront and immediately connect them to the right agent for their issue.

    The time that automation gives back to agents is invaluable. It was key for razor blade subscription service Dollar Shave Club, which automated 12 percent of its support tickets with Answer Bot. “We wanted to deflect these kinds of tickets and have more meaningful, consultative conversations with our members and Answer Bot has been the answer,” said Trent Hoerman, Senior Program Manager at Dollar Shave Club.

  4. Watch customer satisfaction soar by supporting customers where they are

    AI Chatbots can help you serve customers where they are, and where they are is on messaging channels. In fact, messaging apps have the highest customer satisfaction score of any support channel, with a CSAT of 98 percent. Customers want to interact with brands on the same digital channels they’re already using in their personal lives. Business messaging apps, like Facebook Messenger for Business, WhatsApp Business, Twitter for Business, LINE, and Apple Business Chat (which integrates with iMessage), lend themselves to more convenient and rich conversational experiences—and can be up to six times cheaper than a voice interaction.

  5. Unlock more opportunities for conversion

    Online chatbots can boost conversions with smarter self-service. A chatbot can enable customers to self-serve outside of a help center, like on a checkout or product page, with knowledge tailored to their context. A bot can also provide information customers weren’t aware they needed, including new products, special discount codes for followers, and company initiatives. Especially in a world where the highest volume of e-commerce sales happens after standard working hours—between 8 and 9 p.m.,—having bots available to answer questions can help ensure customers don’t abandon their carts due to lingering questions while reducing the need for agents to work unusual hours. This personal touch can drive customers from just taking a look to taking action.

    Chatbots can also automate cross-sell and upsell activities, in addition to providing support assistance. For instance, businesses using the WhatsApp API can build a bot over the platform to send customers proactive messages. From sharing coupons and new product information to customers who want to receive promotional content to sending personalized messages based on customers’ preferences and shopping history for a white-glove experience, automating proactive communications can help maintain loyalty and drive revenue.

What are some use cases for AI chatbots?

Here are some simple yet effective use cases for chatbots.

  1. Chatbots to answer FAQs

    As previously mentioned, one of the most successful use cases for a bot is to automate basic, repetitive questions. These are the kinds of questions that your team can predict and agents can resolve in one-touch. Not only do customers prefer to use chatbots for simple issues, but this also gives agents’ time back for high-stakes tasks and to offer more meaningful support.

    Chatbots enhanced with artificial intelligence take this a step further. Not only can they answer common questions, but they can also intelligently route tickets when canned answers won’t suffice. Also, by fielding customer inquiries 24/7, AI chatbots start to learn and can help your team find the most common FAQs.

    More sensitive or complex issues such as technical questions or billing or payment questions usually don’t make sense for a bot. But if a bank sees hundreds of calls about its routing number or an e-commerce company gets bogged down with questions about its return policy, those would be great inquiries to deflect to a bot. That way, agents don’t have to waste time responding to the same questions over and over.

    If your team already has FAQs inside its help center, these can be a great starting point for building your FAQ bot.

  2. Chatbots to bolster self-service

    We already know that most customers check online resources first if they run into trouble and want to take care of their own problems. With the help of artificial intelligence, chatbots can highlight your self-service options by recommending help pages to customers in the chat interface. Rather than finding your FAQ or support pages and then guessing which search queries will bring up the information they need, customers can ask questions that bots will then scan for keywords to lead them to the right page. And if customers end up on the wrong chatbot, AI on the backend can switch those users over to the properly equipped chatbot without disrupting the customer experience.

    This convenience means each customer’s path to resolution is easier. You can deploy AI-powered self-service bots inside your knowledge base to help customers find the right article faster or outside of it so customers don’t have to leave their experience to self-serve.

    Self-service bots are also simple and cost-effective to build, making them a good option for teams without large developer budgets and who are looking to get their chatbot up and running quickly.

  3. Chatbots to help provide global support

    One of the advantages of AI chatbots is that they can provide customers with answers in every time zone and language. A chatbot can ask your customers what language they prefer at the start of a conversation or determine what language a customer speaks by their input phrases.

    This is especially beneficial for global brands. Suppose you're an enterprise company that operates internationally or is considering expanding. Bots can ease the transition to becoming a fully distributed global support team and keep customers across the world happy.

  4. Chatbots to help with ticket spikes and fluctuations

    Since chatbots never sleep, they can support your customers when your agents are off the clock—over the weekend, late-night, or on the holidays. And as customers’ e-commerce habits fluctuate heavily due to seasonal trends, chatbots can mitigate the need for companies to constantly turnover seasonal workers to deal with high-volume times.

    For instance, a chatbot can help serve customers on Black Friday or other high-traffic holidays. It could also take pressure off your support team after product updates or launches and during events. Consider Spartan Race, an extreme wellness platform that deployed a Zendesk chatbot to help its small team of agents tackle spikes in customer requests during races. Spartan Race has seen a 9.5 percent decrease in chat volume, extending its team’s live chat availability by three hours every day.

  5. On top of all that, AI-enhanced chatbots actually get smarter over time, improving the service they provide. For example, AI can recognize customer ratings based on its responses and then adjust accordingly if the rating is not favorable. Over time, as your chatbot has more and more interactions and receives more and more feedback, it becomes better and better at serving your customers. As a result, your live agents have more time to deal with complex customer queries, even during peak times.

  6. Chatbots for sales

    Beyond customer service use cases, chatbots can be used for prospecting, making them a helpful hand for your sales team. A chatbot can help with lead generation by capturing leads across multiple channels. It can also pass a prospective customer to the next step in the sales process, whether that’s a human sales agent or an email and phone number capture.

    For example, a bot can welcome website visitors and ask them if they want to get in touch with sales. Prospects can leave their contact information and a note about what they’re interested in, and the bot can pass on the details to the right team. Taking it a step further, a chatbot can ask qualifying questions such as 'how large is your company?’ or ‘what is your job title?’

    A bot can be integrated into your sales CRM like it’s integrated into your customer service software. This similarly ensures seamless handoffs between bots and sales representatives, equipping sales teams with context and conversation history. Chatbots can also automatically schedule meetings when integrated with your calendar and conferencing apps.

  7. Chatbots for marketing

    A chatbot can also be a lead generation tool for your marketing team. Similar to sales chatbots, chatbots for marketing can scale your customer acquisition efforts by collecting key information and insights from potential customers. They can also be strategically placed on website pages to increase conversion rates.

    Beyond conversions and lead capture, marketing teams can use chatbots as a tool for customer engagement. For example, we incorporated a chatbot in our State of Messaging report so customers can learn more about the stories behind the report.

    Or, the mattress brand, Casper, created a chatbot for people who have trouble sleeping and want a late-night friend to talk to. Casper’s bot’s single purpose is to bring people closer to its brand. And since AI-powered chatbots can learn your brand voice, they can use a tone, personality, and language that’s familiar to the rest of your brand properties.

  8. Abandoned cart/discount chatbot

    Shopping cart abandonment happens when online shoppers add items to their carts but leave purchasing. The worldwide shopping cart abandonment rate is nearly 70 percent, and this number has only been increasing over the years. Reasons that customers abandon their carts include unexpected shipping costs, a complicated checkout process, and lack of trust.

    Chatbots can help mitigate these concerns. They can be a great way to answer any questions a customer might have to give them the confidence to purchase or upgrade their account. In fact, customers are three times more likely to make a purchase when you reach out with a chat. And even if that customer isn’t ready to connect yet, providing a quick and convenient option to get in touch builds trust.

    An abandoned cart chatbot can also offer customers with a loaded shopping cart a discount to provide an incentive to purchase. The chatbot would need access to key customer context that tells it when a customer has an item in its cart, triggering it to offer that customer a discount. But AI takes the abandoned cart workflow a step further with intelligent, personalized recommendations. So instead of just trying to save a sale, AI can also help increase the total value of your customers’ carts.

  9. Chatbots for internal support

    Businesses can use chatbots to support employees, too. A chatbot is a handy addition to any internal support strategy, especially when paired with self-service.

    Many IT and HR teams use a knowledge base to help mitigate repetitive questions they get and empower employees to self-serve. A chatbot can help scale your internal self-service efforts by serving employees help center articles, which can be particularly helpful during employee onboarding or company-wide changes. An IT or HR team might also use a bot to answer FAQs over convenient channels such as Slack or email. Similar to chatbots for external support, internal support chatbots ensure employees get fast help around the clock, making them useful for global companies and remote teams with employees in different time zones.

What chatbot software is right for you?

The right chatbot software for your business depends on your current support needs and available resources.

If you have a knowledge base, a great place to start is with a bot that suggests articles from your existing help center content and captures basic customer context for the fastest time to value. If you want a little more control, look for a bot builder with a visual interface. This enables you to design customized bot conversations without having to write any code.

If you need a bot that’s more specialized to your business niche, make sure your customer service solution can seamlessly incorporate outside bots, whether you build it yourself or buy it from a third-party, for seamless bot-to-human handoffs. Also, keep your eye out for chatbots that are enhanced with artificial intelligence. AI enables chatbots to learn and improve over time as well as intelligently redirect users to agents or self-service content which lightens the load on your service team.

Answering these questions can help you find a chatbot solution that best fits your support team’s needs.

  • What problem are you looking to solve—and what resources do you need to solve it?

    If you’re thinking of using a bot, make sure to first identify your company’s problem area and what resources you have to solve it. Are you inundated with requests and inquiries? Could your agents be spending their time more efficiently? It’s equally as important to understand the scope of the bot you might be implementing. Does it help with repetitive tasks? Or is it an expert on a certain product?

  • Is your chatbot flexible enough to work across different channels?

    Customers expect to receive support over their preferred touchpoints—whether they’re interacting with a human or a bot. They also expect options. As such, it’s important for your chatbot to work across a range of messaging channels.

  • What level of context will your chatbot need?

    A key component of any artificial intelligence solution is data because the more data you have, the faster your AI chatbot can learn and improve its service. In short, more context leads to better chatbots—and more personalized conversations.

  • How will you manage conversations between chatbots and agents?

    Businesses need tools to both deploy chatbot conversations on the front end and manage them on the back end. This ensures agents can understand the intent behind every conversation and streamlines hand-offs between agents and chatbots.


Frequently asked questions on chatbots

What technology is used in an AI chatbot?

Two of the core technologies underlying AI chatbots are natural language processing (NLP) and machine learning (ML). NLP is a subfield of artificial intelligence, the goal of which is to understand the contents of a message, as well as its context so that the technology can extract insights and information. Based on the information extracted, actions can be performed.

For example, Answer Bot uses NLP to interpret customer (or employee) requests and route them to the proper service agent.

Like NLP, machine learning is also a subfield of AI. ML algorithms take sample data and build models which they use to predict or take action based on statistical analysis. As mentioned, AI chatbots get better over time and this is because they use machine learning on chat data to make decisions and predictions that get increasingly accurate as they get more “practice”.

For instance, Answer Bot uses machine learning to learn from each customer interaction to get smarter and provide better answers over time.

Can you add a chatbot to a website?

Yes you can just about any chatbot on the market to your website. In fact, before mobile apps and social media, the only place companies used chatbots was on their website. And still today, your company website is an ideal place to deploy an AI chatbot.

How are AI chatbots and automation used in business?

AI chatbots and automation work together to do a lot of heavy lifting for businesses. Some of the most common uses cases of these technologies include:

  • Automatically helping customers find answers to FAQs.
  • Collecting lead submissions to help with lead generation.
  • Routing complex customer requests to live agents.
  • Providing personalized recommendations based on previous history.
  • Create pre-populated customer service tickets.

How do you install an AI chatbot?

How you install an AI chatbot will depend in large part on the chatbot software you’re using and your level of technical proficiency. For non-technical users, many solutions offer visual chatbot builders, which you can configure with different rules, triggers, and automations. If you’re installing the chatbot on your website, once you’ve configured the conversation flow for your purpose, you’ll need to embed the code for your chatbot wherever you’d like it to appear. Of course, that’s just a basic AI chatbot install. You can also integrate your chatbot with existing help center resources so the bot can automatically answer frequently asked questions and provide resources.

How do you integrate a chatbot into your website?

Typically, after you’ve built your chatbot on your platform of choice, you’ll be provided with an embed code which you can copy and paste into the page(s) that you want the chatbot to appear on. Or, if you already have live chat software set up, that software may allow you to integrate chatbots into your website from within the existing live chat software.

More advanced users can also integrate a chatbot into their website by connecting to a specialized AI solution, such as IBM Watson.

What is the easiest way to implement an AI chatbot on your website?

The easiest way to implement an AI chatbot on your website is by using your existing live chat software’s chatbots (if they’re available) or using an out-of-the-box chatbot. With an out-of-the-box chatbot, like Zendesk’s Answer Bot or HubSpot’s chatbots, you simply configure that chatbot using a visual interface and then embed its code into your website pages.

Try our AI chatbot service for free

Zendesk makes it easy to enhance your customer support experience with a chatbot. Answer Bot can leverage your existing help center resources to guide customers to a resolution via self-service and collect customer context. And if you want a little more control, our click-to-build flow creator enables you to create rich, customized bot conversations without writing code. Most importantly, our customer service software is directly tied into our award-winning support platform that provides teams with a real-time, conversation-focused interface to seamlessly track and manage conversations between agents and bots. It also integrates with all the systems your team depends on, including third-party bots.