No customer service rep wants to answer the same question a hundred times a day. No sales rep wants to talk to people who aren’t going to buy. And if you’re leading an organization, you can’t afford to let either of those scenarios be the norm.
Chatbots (more affectionately known as virtual assistants) provide a solution to both of these problems. Their infinite capacity helps free up your employees and scale your organization’s efforts. Whether you use chatbots for customer service, sales, or something else, their artificial intelligence ensures that your human resources are only used when they’re needed, and that your organization communicates with the most people possible.
But the fear many organizations have is that chatbots are heavy on the artificial and light on the intelligence. Few things are more infuriating when you need help than having to repeatedly rephrase your question or jump through hoops to talk to a real person. Most of us prefer talking to humans, and that’s OK. That’s why chatbots are most-suited for highly specialized tasks.
The best chatbots interact with more people faster than humans will ever be able to. The trick is knowing when and how to use them. In many cases, you’ll find that chatbots are basically a more informal way for people to navigate your website.
To help you see if there are opportunities for your organization to use chatbots, we found 10 case studies of companies that used them successfully. We’ll show you what they did, how they did it, and where you can go to see the full case study.
Some of these organizations started with live chat systems before switching to chatbots. Some used chatbots conservatively, and others used them for everything.
Check out these 5 case studies on chatbots.
Amtrak: 5 million questions answered by chatbots annually
Chatbot system: Next IT
Industry: Public transportation
- 800% return on investment.
- Increased bookings by 25%.
- Saved $1,000,000 in customer service expenses in a single year.
- Over 5,000,000 questions answered every year.
- Bookings through chatbots generate 30% more revenue.
- Chatbots with advanced AI provide site visitors with a “self-service” option.
Where the study came from: Next IT shared this chatbot case study on their website about Amtrak’s experience with “Julie”, which began in 2012.
Amtrak is the largest organization you’ll find in our list of case studies. They have 20,000 employees and serve 30 million passengers per year. At the time Next IT published this case study, Amtrak.com was getting 375,000 visitors every day.
Here’s what Next IT says she’s capable of:
“Travelers can book rail travel by simply stating where and when they’d like to travel. Julie assists them by pre-filling forms on Amtrak’s scheduling tool and providing guidance through the rest of the booking process. And, of course, she’s easily capable of providing information on what items can be carried on trains or helping make hotel and rental-car reservations.”
Instead of making a phone call or waiting for customer service to email them back, more and more visitors are turning to Julie. In fact, Next IT reported a 50% growth in Julie’s usage year over year.
Julie “was designed to function like Amtrak’s best customer service representative,” and with 5 million answered questions per year, it’s hard to argue that she isn’t their best customer service rep.
Not to mention, when Julie answers questions, she tacks on subtle upsells like these:
So in addition to answering more questions and increasing the number of bookings, Julie actually increased the value of bookings. Bookings made through Julie resulted in an average of 30% more revenue than bookings made through other means.
Clearly, the self-serve model is working for Amtrak. What’s interesting about Julie is that despite the smiling face, you know you’re talking to a robot. It doesn’t feel like AI that they’re trying to pass off as a real person. It’s almost like she’s a more advanced search feature of the website. When visitors ask questions, she pulls in only the relevant information, and it’s all contextualized to fit their specific question.
Maybe it’s just me, but that could be the difference between a helpful tool and a frustrating conversation.
Anymail finder: 90% of “big customers” chat before buying
Chatbot system: Intercom
Industry: Email verification software (SAAS)
- 1 in 3 buyers used the chat system before making a purchase.
- 9 out of 10 “big buyers” used the chat system before making a purchase.
- Estimated 60% of revenue comes from chatbots.
- Average response time was three minutes in their first 30 days of using Intercom.
- Chatbots allowed a two-person team to stay on top of support and sales.
- Popular customer questions provided content ideas, and eventually prewritten responses.
Where the study came from: Pardeep Kullar published this case study on the Upscope blog in 2017.
As a two-person marketing startup, Anymail finder was stretched thin between sales, marketing, and support. They were answering the same few questions over and over via email.
Intercom’s operator bot helped this two-person team look and feel like they had a full-fledged support department.
Pardeep Kullar of Anymail finder says that the same handful of questions kept popping up in the chat window. They were usually questions like “how are you different from your competitor?” or “how do I upload this file?”
So Pardeep and his colleague wrote detailed articles that answered these popular questions and any related ones, then incorporated the articles in readymade responses and automated messages. Website visitors encountered one of 10 automated chat messages, depending on the page they arrived at.
It’s like putting multiple fishing lines in the water at once, waiting for potential customers or users to bite. When a visitor replied to an automated message, employees got a push notification so they could promptly respond to every inquiry. Anymail finder’s prewritten responses to popular questions let them reply to some inquiries within seconds.
Intercom’s messaging metrics let Anymail finder gauge which automated messages were producing the best results:
One of the primary benefits of chatbot services is that they can answer most questions customers have and qualify your leads without eating up valuable time from your customer service or sales staff.
But Intercom is pretty anti-AI, and their chatbots serve a more limited role. For Anymail finder, real people were waiting behind every automated message, but chatbots still helped them provide superior customer service with a limited team.
MongoDB: increased new leads by 70% in three months
Chatbot system: Drift
Industry: database/development platform
- Increased net new leads by 70%
- Increased total messaging response by 100%
- Chatbots are more scalable than live chat services.
- Chatbots can help your customer service and sales teams by scheduling meetings and screening inquiries
Where the study came from: Drift published this case study on their website.
MongoDB was having a lot of success with live chat, but like all humans, their salespeople were limited by things like “time” and “space.” They couldn’t significantly increase the number of conversations they were having without significantly increasing the size of their team.
As their director of demand generation puts it:
“We needed a messaging tool that could scale with our business and increase the volume of our conversations, leading to the increase of our pipeline and Sales Accepted Leads (SALs)—the metrics my Demand Generation team are measured on.”
Like RapidMiner, MongoDB let Drift’s Leadbot ensure that their sales reps only talked to the people who were most likely to buy. And with Drift’s meeting scheduler, people didn’t have to play phone tag to make an appointment:
For MongoDB, automating lead-qualifying conversations allowed them to have more conversations, and automating the scheduling process let them turn more of those conversations into leads.
Charter Communications: 500% ROI in six months
Chatbot system: Next IT
Industry: Cable/Internet provider
- 500% ROI within six months.
- Reduced live chat volume by 83%.
- Decreased time it took customers to reset passwords by 50%.
- Common customer service questions are now handled completely through the chatbot.
- Chatbots can resolve issues faster by reducing handoffs.
Where the study came from: Charter Communications implemented Next IT’s chatbot in 2012. Next IT published this case study on their website.
Charter Communications is the second largest cable provider and the fifth largest phone providers in the U.S. They have 16,000 employees and 25 million customers.
Before switching to a chatbot service, Charter Communications had 200,000 live chats per month. 38% of these live chat conversations were for forgotten usernames and passwords. That’s 76,000 ridiculously simple requests that had to be handled by a real person every month.
Obviously, all of those conversations take up a lot of customer service time. Since so many people were accustomed to resolving issues through chat, Charter didn’t wanted to pull the plug on the entire chat system, but they needed a self-serve option to save their customer service reps for more complex problems.
When they switched to a chatbot, it didn’t just take over those basic password and username questions. 83% of all of chat communications were handled by the bot. That’s 166,000 chat requests per month that Charter no longer had to worry about.
But Charter’s chatbot wasn’t just bumbling its way through these conversations, either. Part of their goal was to increase first-contact resolution rates, so customers wouldn’t need to be relayed through several people to get what they needed. The chatbot could also handle those tedious password and username requests 50% faster than a real person.
Ultimately, chatbots delivered a solid win for Charter and for their customers.
Facebook Messenger bot case studies
Since Facebook opened up its Messenger app for developers to create their own bots, a lot of brands have seized the opportunity to interact with their audience this way. The case studies you’ll see below are a little lighter than the ones we’ve looked at so far, but they showcase a few ways organizations are successfully using Facebook Messenger bots. Some ecommerce sites have had a lot of success with Messenger bots, but the three examples we’re going to look at are all primarily content-focused brands.
Something to think about: while the other chatbots we’ve looked at live on your website, this one lives in an app people are already using, and they can find your bot there. Facebook shares Messenger bots in the discover tab, and if you open Messenger right now and search, you’ll find “bots” right below “people.” In other words, a Facebook Messenger bot could grow your audience.
BabyCenter: 53% click through rate from Facebook Messenger
Chatbot system: Facebook messenger
Industry: baby products
- 84% read rate on automated messages.
- 53% click through rate from Facebook Messenger to BabyCenter.com.
- Used a Messenger bot to drive traffic to the website.
- Facebook messages were opened more than emails.
Where the study came from: BabyCenter asked ubisend to design a Facebook Messenger bot in 2016. Ubisend published this case study on their website.
BabyCenter is one of the most trusted pregnancy websites out there (seriously, I’ve seen my wife’s OBGYN check this site during appointments). One of their biggest draws is a sequential email campaign that follows you every step of the way through pregnancy, and their revenue model is based on advertisements and a strong affiliate sales program.
Through ubisend, BabyCenter created a bot on Facebook Messenger to do two things:
- Drive traffic to their website.
- Provide an alternative content delivery system.
As you can see in the GIF below, the bot also provided a more interactive way for people to consume BabyCenter’s content.
The new bot accomplished both objectives, with some impressive results. On average, 84% of people read the message, and 53% of those who opened also clicked through to the website. Ubisend compares that to MailChimp’s open and click-through rates, and with some unstated math determined that the Messenger bot had a 1,428% higher engagement rate. I can’t speak to the validity of that claim, but here are a couple of reasons why the bot may have had better open and click-through rates than email:
- The floating messenger icon and that little red number is a lot harder to ignore than an email.
- People are used to glancing at a subject line without opening the email.
- Far fewer brands are on Messenger, so a notification is more likely to be from someone you know. (And unless you’re avoiding someone, you’re probably going to open it.)
- The load time for a Facebook message is almost instant. Email? Not so much.
- It only takes two taps to open a message and click through. Email takes a little more navigation.
Whatever the reason, a Messenger bot was clearly a viable content delivery system for BabyCenter. If enough people adopt it, the Messenger bot may even rival their well-established sequential email campaign.
Good Spa Guide: 29% increase in website traffic
Chatbot system: Facebook Messenger
Industry: Spa reviews
- 47% click through rate on automated messages.
- 29% increase in website traffic in six weeks.
- 13% increase in spa bookings.
- Messenger bots can help consumers navigate the website before they even get there.
Where the study came from: Good Spa Guide solicited ubisend’s services in 2016. Ubisend published this case study on their website.
As the name implies, Good Spa Guide reviews spas. They make money when people use the site to book a spa, so not surprisingly, they really value website traffic.
Like BabyCenter, Good Spa Guide was looking for an alternative to their email list. They used ubisend to design a Messenger bot that functions a lot like Amtrak’s “Ask Julie” bot. It basically provides a more conversational way to navigate the website—but without actually being on the website.
Check it out:
After a short conversation with the bot, people can go to the exact spa review page they need, and continue their hunt on the website.
With a 29% increase in traffic and a 13% increase in spa bookings, it looks like a Facebook Messenger bot helped Good Spa Guide either tap into a new audience, or engage their existing audience in a better way.
What do these chatbots all have in common?
In most cases, chatbots aren’t going to fool anyone. The chatbots we’ve looked at here are obviously not real people. The brands that use them and the companies that make them might be excited about how human they seem, but that’s not the point.
In the right situations, chatbots can provide customers and users with a better experience because they process your request instantly, and it doesn’t matter how many other conversations they’re having. And if you’re waiting around for basic help (like, say, password reset), you’re really not going to care if the person who’s helping you is a Bob or a bot.
Unless you’re looking for something gimmicky (like a chatbot monkey that tells dad jokes), most chatbots simply provide a more conversational way for your audience to consume the information on your website. It’s certainly not for everyone—some people (myself included) would rather navigate websites the old fashioned way and read blog posts on a blog—but for many people, chatbots provide a helpful shortcut to the information they’re looking for. And that’s something you should probably care about.
One clear takeaway: if you’re using a live chat service right now, a chatbot can either outright replace it or vastly improve it. Ask your customer service reps what questions they get the most and how often they get them. Go ahead, ask them.
But even if you’re not already using some sort of chat service, chatbots can:
- Automate the lead generation process.
- Deliver your content in new ways (maybe even to new people).
- Drive traffic to key pages of your website.
- Save your customer service and sales reps a boatload of time.
Still, chatbots are just one tool you can use to grow your organization. We hope these case studies have helped you envision how they might work for you, but there might be better ways to reach your goals. (We’d love to help you find out.)