E B M

Loading

COVID-19 : What we’re doing

We are doing our best to play our part by adapting responsibly and responding in any way we can. Over the last few weeks, we’ve launched a quick deploy Chatbot Capability for COVID-19 Information that is being taken up by a variety of organisations. Find out more here

With more companies adopting the implementation of chatbot in various aspects of service delivery, we are a bit curious about how successful chatbot integration in multiple industries has been, and how the ‘big guys’ are achieving success. 

Chatbots are known for providing 24/7 support to customers and clients in various industries, through the uses of Artificial Intelligence (AI) and machine learning.
Particularly for chatbots, they’re primarily powered by Natural language processing.

In this article, we will be taking a take a look 40 notable chatbot examples from different industries that you can learn and take inspiration from.

Here are the best 12 chatbot examples, one from each industry, you can learn from to build an innovative bot for your business:

  • Airlines: KLM
  • Banking: HSBC
  • Beauty: Madi
  • Ecommerce: Lego
  • Education: Duolingo
  • Entertainment: Swelly
  • Financial: Cleo
  • Food & Drink: WholeFoods
  • Healthcare: Ada
  • Hospitality: Marriot
  • Insurance: Progressive
  • Legal: DoNotPay
  • Mental Health: Woebot
  • News: CNN
  • Retail: Sephora
  • Real Estate: Structurely
  • Travel: Hipmunk

Chatbot examples in Airlines

Emirates Vacations

Average CTR for display ads is at an all-time low of .35%. Considering this, Emirates Vacations created a chatbot within their display ads. The company targets different visuals and bot sequences based on the page someone’s browsing. Engagement rates rose 87% since deployment in 2018.

Key Takeaways

Be relevant to the user journey: Rather than shoot the same message to everyone, use a separate sequence for your homepage, product pages, and Facebook Business Page.

Keep users goal in mind: Emirates bot is more than just a cool ad; it’s the direct line to the desired goal. Users have a task in mind when browsing your site or Facebook Page. Your bot needs to help them complete it as quick as possible.

Flatter users with frictionless experiences: Imagine being able to book your travel right in this ad, without leaving your current page? Maybe sceptical at first. But considering that travel search is a massive headache, booking “right here, right now” is the most practical and convenient way to do so.

KLM

KLM Royal Dutch Airlines’ chatbot operates differently than the other previously mentioned. KLM makes use of Facebook Messenger’s checkbox plugin on the checkout page so that people can opt-in to receive booking confirmation, check-in notification, boarding pass, and flight status updates via Messenger. Presently, the chatbot has 13 languages, and it was built from the need to improve and simplify customer service. In a typical week, KLM has to respond to 15,000 social conversations in a dozen different languages. 

Key Takeaways

Consequently, they started exploring new ways to provide an excellent, personalized but at the same time, fast customer care, and that’s why they opted to implement a chatbot. In the first month, their volume of Facebook messages jumped 40 percent. KLM said 1.7 million messages had been sent on Messenger by over 500,000 people.

CheapFlights

If you’ve ever booked travel through a more significant aggregator site like Expedia or SkyScanner, you know the drill. Enter in your dates and shift through various options. Pretty easy, all things considered.

But chatbots can make that process even more comfortable.

Traditionally, you tell a chatbot your parameters and your price range, and it will return the best option — no need to look through results. So naturally, booking is a must in any travel bot.

But Cheapflights takes it up a notch – and were way ahead of the game.

How it helps

Cheapflights Chat was the first Facebook Messenger chatbot for flight and hotel search, and the company launched it with the goals of underlining Cheapflights’ commitment to innovation and creating products users love, and support the brand’s purpose “Smart search. Made simple.”

To do that, they put emphasis on natural, conversational language by including an “Inspire Me” feature and engaging responses to things like “I want to go to the moon,” “Are you real?” and “I love you.”

To drum up engagement, they launched the bot with a competition-led social media campaign.

Key Takeaways:

Bring your brand’s strengths to your chatbot.

If you’re known for a fun-loving, engaging brand voice, that better translate to your bot. And if convenience is your priority – as it often is in the travel industry – then run plenty of tests to make sure your bot is hassle-free.

Also, look for ways you can rise above the norm.

All travel brands will offer easy booking, so think about ways you can enhance the experience like Cheapflights does with its “Inspire me” feature.

Average CTR for display ads is at an all-time low of .35%. Considering this, Emirates Vacations created a chatbot within their display ads. The company targets different visuals and bot sequences based on the page someone’s browsing. Engagement rates rose 87% since deployment in 2018.

Chatbot examples in Banking

Bank of America

Meet Erica, your new financial assistant from Bank of America. She can do anything from providing bank balance information, make budgeting suggestions, pay bills, and help with simple transactions. The banking chatbot example has already surpassed over 7 million users and completed over 50 million transactions to date. 

Key Takeaways

Become an advisor to customers: Erica went from just scheduling payments to offering advice on how to pay down debt. And her capabilities continue to evolve with her banking customers’ needs. Whether you’re selling meal plans or online coaching services, guidance helps build better relationships between you and your customers. 

Provide helpful content for users: One of the key elements of a successful chatbot is solving customers problems. For example, if you ask Erica about credit scores, she’ll give you a video from Better Money Habits and other content around spending and budgeting. 

Easy-to-use transaction-search functions are becoming increasingly valuable for chatbots. Give your users the ability to search and discover the products and services your company offers. 

Chatbot examples in healthcare

From our search and analysis of chatbots in healthcare, we found these use cases as the most common and beneficial for business:

  1. Scheduling & reminder for appointments
  2. Early triaging and diagnosis
  3. Q&A, FAQs and Information retrieval automation

BabyCentre UK

The BabyCentre UK is a trusted pregnancy and childcare resource website in the United Kingdom owned by the Johnson & Johnson family of companies. 

How it helps

BabyCentre focuses on contents geared toward all stages of motherhood, from due date calculators to articles on self-care for moms to user communities. With the addition of the chatbot to the websites, service delivery is a whole lot easier.

BabyCenter website’s bot leverages the power of Facebook Messenger to provide expectant mothers with a seamless, and well-planned service. 

The mother is asked various questions about the child or a challenge the parent is facing, the bot then provides personalized and targeted advice suitable for such situations.

For instance, when a parent says their child is weaning, BabyCentre offers suggestions regarding when the child would be ready for solid food and also engages the parents by asking if they want to know other signs to look out for.

BabyCentre’s email marketing is equally personalized and targeted, much like its Facebook Messenger Bot. For instance, when users sign up to BabyCenter’s email list, they’re required to input their baby’s due date so they will receive content based on the age of the baby.

Results

When BabyCentre, however, tested its chatbot and email marketing website traffic drive, the results showed that on average, the bot had an 84% “read” rate and a 53% CTR – 1,428% higher engagement rate than the email funnel.

Though its email content and bot content were both super-personalized, BabyCentre’s bot avoided the spam filters and “inbox fatigue” that is currently the main argument for looking into Messenger bots vs email.

Key Takeaways

  • Ensure you create personalized channels depending on your user answers to produce better results. 
  • Be proactive with answers and information: people like reassurance and convenience. 
  • You can get more out of your chatbots by using it together with other marketing mediums. 

Ada

Ada uses NLP to let a user start typing a symptom and then outputs possible options to specify the source of discomfort for you to pick from, e.g., headache location – eye area, temples, back of the head and more. 

This hinting helps the bot grasp the concern right away, increasing the chance of valuable output.

Ada is compatible with Alexa speaker, enabling the users to communicate with the bot orally.

How it works

  • Differential diagnosis. While asking questions, Ada separates the main symptom from additional issues. This ranging creates a differential diagnosis, meaning that the bot will later offer a few possible conditions with different probability chances. It is an incredibly complex algorithm, currently used in clinical decision support systems.
  • Explains-it-all. The bot offers explanations for each question to avoid random answers, sometimes supporting the query with a picture, e.g., for discomfort localization.
  • Step-by-step guidance. After the user has completed the questionnaire, Ada offers next steps (emergency care, appointment, painkillers, etc.) and shows a clear and concise report describing possible conditions with details on lab tests and treatment. Besides, it lists reported symptoms and calculates the condition’s likelihood. This list can be then shown to a physician during an appointment.
  • Follow-ups. Ada also offers follow-ups, but in a more detailed way than Babylon. The bot asks whether the user visited a doctor and if yes, asks if the primary condition guess was confirmed. If not, the algorithm analyzes the right answer to learn more and improve itself.

Results

Though Ada tracks health status, it focuses on mental health, e.g., sleep issues, social anxiety, depressed mood, and avoidance behaviour. If the user reports any of mental health issues, the app starts asking about these symptoms daily to build a pattern. This is useful, but how about temperature, blood pressure, or sugar levels at least?

You can download Ada from the app store here.

Key Takeaways

Ada is a strong example of an advanced healthcare chatbot, conducting differential diagnosis, supporting voice control via a smart speaker, and navigating towards needed medical assistance comprehensively. To make Ada even better at helping its users, developers should improve health tracking options.

Your.MD 

How it helps

  • All at once. The bot offers to pick a few symptoms simultaneously, streamlining the conversation. Fewer questions, faster analysis.
  • Good consultation report. Upon completing the assessment, the user gets a report with entered symptoms, possible conditions, and next steps. There’s also a remarkable tip on when to worry and seek emergency care.
  • Quizzes and self-assessments. There’s so much you can do with the bot, starting from passing mental health and sleep assessments to finding a well-fitting birth control method for women. Engaging and interactive content is Your.MD’s forte for sure.
  • Various ways to help. If you ask Your.MD about an organ instead of a symptom, the bot will output a few articles on the query.

Results

Health tracking? Nope. The app doesn’t allow for it. The user can only enter mood, weight, sleep, or steps. The bot lacks real health status metrics to understand patterns in symptoms and physical changes.

No alternative conditions. Sadly, Your.MD supports only one diagnosis suggestion at a time.

Key Takeaways

Your.MD’s AI is rather complicated and quick to come up with a possible diagnosis, but it offers no decent health tracking functionality. On the positive side, the bot is stuffed with engagement techniques and even introduces therapeutic education.

Chatbot examples by Insurance

Progressive

Progressive offers a chatbot called Flo, which the company claims can help their customers file claims, view and change payment dates, and get quotes for their auto insurance. The chatbot uses natural language processing and a cloud-based API that pulls data from social media responses and training data.

How it helps

The AI behind the Flo bot is trained on hundreds of thousands of customer support tickets and their responses from customer service agents involving filing claims, billing, and deductible rates. This text data would have been labelled as claims-related, billing-related, deductible-related, or related to other categories Progressive chose. The labelled text data would then be run through the software’s machine learning algorithm. This would have trained the algorithm to discern the chains of text that a human might interpret as a claims-, billing-, or deductible-related question as displayed in a text message.

A customer could then message the chatbot, and the algorithm behind the software would then be able to categorize the ticket as claims, billing, or deductible-related. The chatbot likely then comes up with a confidence interval on how likely it correctly classified the ticket. It would also be programmed to take two actions depending on that confidence interval. Above a certain percentage, the chatbot would send an appropriate response to the user. Under a certain percentage, the chatbot would route the ticket to a human agent for review.

Chatbot examples in Sales

LeadPages

In this example, LeadPages, an industry leader in drag-and-drop landing page creation, started using Drift messaging and chatbots to convert site visitors from casual browser to middle of funnel product comparison page.

How it helps

The experiment started small, with the bot popping up with a welcome message.

And this minor change worked.

Before the welcome message, LeadPages had 310 conversations in a month. The next month, they implemented the welcome message and had 1168 conversations with site visitors.

LeadPages then used Drift to set up an automated campaign that targeted users based on the page they were currently visiting. The automated messages directed visitors, dependent on their needs to a product comparison page, often the last step before purchase.

Targeted messages from LeadPages’ proactive chatbots had an open rate of 30% and a 21% click-through rate to the product comparison page. Compared to email’s 21.5% open rate and a 2% click-through rate, the LeadPages chatbot won out over of the traditional medium.

Key Takeaways

LeadPages provided an immediate and targeted response which navigated visitors — gently — from browsing to content that could help them evaluate LeadPages as a potential solution.

You can read the full rundown here

Chatbot examples in Travel

Amtrack

One reason the travel industry has been the fastest to adopt chatbots is speed and convenience. In this example, Amtrak helps site visitors plan a vacation, book reservations, navigate Amtrak.com, get route information, and more. It’s become a company powerhouse, generating 30% more revenue per booking, 8X ROI, and answers over 5 million questions a year.

Key Takeaways

Leverage post-sales support as a revenue channel. Returning customers spend 67%more on average, and more often if they are satisfied with your service. Quick and convenient customer support (in any industry) leads to happier customers, and for Amtrak, it’s proved to be insanely profitable.

Have Live Chat ready for back-up. Chatbots can’t answer everything. Instead of aggravating people, design your bot to get browsers in touch with live support for queries that need a little human love.

Build your bot around customer problems. For example, more travellers are booking tickets online compared to other methods. Amtrak wanted to make it easy for their 375,000 daily visitors to self-service. Julie was the answer.

Hipmunk

Few niches are more competitive and saturated than travel, but Hipmunk was able to cut through the noise with their location-based approach to booking flights, hotels, cars, and more. Considering the average person visits over 38 sites before booking, Hipmunk is an engaging and convenient way to book travel.

How it helps

The sequence is perfectly tailored to the intricacies of how users search:

Send deals or promotions based on user preferences: It’s a simple, yet powerful feature that helps users pull information from multiple sites, all in one place — Messenger. Anyone who’s used to the “million tab search method” can finally feel some relief during their search.

Use conversational language to personalize experiences: Mastering conversation builds trust between bot and user. Each interaction mimics a live agent, making it easy for users to connect with and understand. Imagine talking to a friend or live agent.

Create content that is rich and useful. In most situations, users wait a bit to get results from different sites. But with ‘HipTips,’ their wait time turns into a way to find new deals and ways to use the app.

Key Takeaways

Hipmunk brings two powerful elements to the table here: proactive outreach and simplifying an exhaustive process for users. You can quickly get where you want to go without visiting travel sites and finding deals yourself.

Chatbot examples in real estate

Real estate agents deal with a ton of customer inquiries – everything from available listings, pricing information, location, neighborhood standards, etc.

And while a bot won’t replace an agent’s role, it can help streamline the initial process.

At its simplest, Chatbots can be used to collect contact information, provide available listings, and book viewings.

As you get more advanced, bots can be used to show off property videos, answer questions, and find suitable properties based on a user’s specific needs based on questions like their price range, desired location, number of beds and baths, etc.

Structurely Real Estate Chatbot Example

Structurely’s chatbot, Holmes, helps uses AI to answer customer’s questions in real-time and serves as an excellent chatbot conversation example.

How it helps

Holmes personalizes the experience by asking a series of quick questions to determine a user’s ideal property.

Users can ask it to send them home updates when the ideal buying times are in certain areas, and even identify ideal listings based on features from other homes.

In this chatbot conversation example, Holmes returns a related property based on the kitchen from another property.

Key takeaways: 

While your business doesn’t have to go as far as Holmes, loading your bot with a series of personalized questions will help you return more relevant results and collect valuable information about your leads.

x.ai

x.ai is an intelligent personal assistant that automatically schedules and keep tracks of meetings and appointments. By delegating such tasks to Amy and Andrew, the platforms AI personal assistants, users, especially leaders, can focus more of their efforts in meeting their business challenges.

How it helps

With x.ai, teams can reach an agreement when it comes to meetings. That is because the platform searches for the best time for a team meet-up without showing a user’s available times.

Moreover, x.ai personal assistants make sure that no email is left unanswered. All correspondences coming from clients and contacts are processed, and meetings are set-up with them at a time that is convenient for the user.

Key Takeaways

Intelligent Personal Assistants

x.ai gives users access to Amy and Andrew, the platform’s AIs. By utilizing either one of them, users make their calendars full but not cluttered and contribute to making the AIs smarter. All they must do is send an email to either Amy and Andrew to set-up a meeting or CC them in email threads and have them automatically work their scheduling magic.

Opportunity Tracker

With x.ai, users no longer have to worry about missing an opportunity. Amy and Andrew keep users in touch with their clients, contacts, and leads and sends them automated responses. Aside from that, the AIs can instantly set-up meetings with correspondents at a most opportune time.

Time & Team Management

x.ai also offers insights into how much time users have saved by letting Amy and Andrew handle their meeting schedules. This lets individuals and teams appreciate the assistance the AIs offer them. On top of that, the platform enables team leaders to control their team members’ access to the AIs, such as their settings. This allows them to make certain that the AIs are secure and untampered.

Enterprise-Level Security

With x.ai, entrepreneurs and businesses can rest easy knowing that their AIs and their information are protected by enterprise-grade security protocols. Their meetings, their contacts list, and everything that has passed through Amy or Andrew are safe and unlikely to be illegally accessed.

Chatbot examples in eCommerce

eBay

The eBay chatbot is the most advanced e-commerce chatbot out there. And is also the most used! It is built for the Google Assistant, which means that you can use it with your Google Home or on your phone. You can ask him to buy anything in the world, at a very low price. It’s impressive, especially if you consider the scale of eBay. Heck, we like this so much that we interviewed Elaine Lee, the designer behind it.

Key Takeaways

The eBay interface is designed beautifully and allows you to navigate across a very high number of product categories. Try it. You can try this chatbot out by saying, “Ok Google, let me talk with eBay.”

Lego

Everyone knows that kids love Lego. Chances are you did as well when you were one. But the problem is that it’s not always easy to decide which exact set you should give to a kid. Maybe a ninja castle, a pirate island, a police station? Or something else entirely?

It can be difficult, especially when you don’t know the kid that well, but still want to surprise them with a nice present.

And that’s where Ralph, Lego’s bot on Facebook messenger, comes in.

How it helps

It asks you a few questions about your price range, child’s age, their interests, etc. Then it comes up with a personalized gift suggestion. If you like what you see, you can buy the set immediately.

Ralph is a very simple rule-based bot that doesn’t need Natural Language Processing and AI, yet it has been a great success. According to Sumo, Lego has seen a 6x increase in return on ad spend in the markets where they introduced the chatbot (they used Facebook’s click-to-Messenger ads), and it also helped to reduce their cost per conversion by 31% when compared to other ads. That’s customer service at its best.

Chatbot examples in Beauty

Madi 

Madison Reed’s genius hair colour bot who’s “obsessed with finding your most flattering shade.” This chatbot example is mostly text-based, but what sets it apart from the list of chatbots is the selfie submission. Users can submit a selfie, and Madi will point them towards the best colour product recommendations. Cool, right? 

How it helps

Madi teaches us a few important lessons on how to build the best chatbot conversations.

• Speak your audience’s language: Informal tone is one thing, but speaking the style of your audience is another. Madi uses “x’s and o’s” as well as flattering comments to build a connection with their audience.

• Solve an actual problem: Similar to most lead generation tactics; your chatbot should help alleviate a struggle your buyers have. For example, waiting for a colourist appointment can take months. Madi is like having a personal colourist available 24-7.

• Ask relevant questions: Madi asks questions such as “What colour is your natural hair (not including grey)?” and “Is it chemically treated?” to garner responses from users. She’s witty, funny, and feels like your talking to a friend on Facebook.

Key Takeaways

Charming always wins. Madi has boosted engagement by 400% with a 21% click-through rate to the company’s website.

MMF Beauty

MMF Beauty App is a cloud-based business management platform designed specifically for the beauty industry. Ideal for hair salons, spas, parlors, and other similar establishments, MMF Beauty App, helps businesses graduate from paper-based processes and turn all their management workflows, and operations fast, seamless, and streamlined.

How it helps

Its features include a calendar functionality that simplifies schedule and booking management, sales and inventory tools for easy and reliable monitoring of finances, sales, and stocks, and staff management capabilities to help users manage their employees, schedules, commission plans, and contact details.

MMF Beauty App comes with customer management tools designed to help users build and maintain strong relationships with their clients and attract a new one. Reports and analytics provide insights that enable businesses to see how they are performing and what they can do to grow their customer base as well as their revenue further.

Key Takeaways

MMF Beauty App provides you with a cloud-based application that simplifies and streamlines all processes and workflows of your beauty services business. It is built with the needs of the beauty industry in mind, from attracting and maintaining customers, creating viable schedules for your staff, to monitoring customer trends, and more.

Being a cloud-based tool, you don’t have to install MMF Beauty App into your system, saving you money as well as precious resources that you can use to address other priorities. It is basically a plug and play system that works immediately and creates wonders for your business right off the bat.

MMF Beauty App eliminates the needs for paper-based files and records. You got a digital calendar where you can schedule your appointments as well as the workload for your staff. You can modify, edit, and even cancel appointments in just a few clicks. Managing your schedule has never been easier.

Keeping an eye on your stocks is crucial for your business. With MMF Beauty App, you no longer have to physically count your items to see if you’re running low and need to make new orders. Whenever you issue an invoice or make retail sales, MMF Beauty App automatically updates your stock levels and instantly notifies you when an item is low in stock.

An online booking page for your customers allows your clients to book your services without them having to come or call. This feature offers great benefits to you and your clients. This increases the number of appointments while bringing down instances of no-shows.

Knowing your customers allow you to provide a more personalized service that they will appreciate. With MMF Beauty App, you can easily keep a record of all your customers’ information, check their history, and track their services, among others. You can send reminders to your customers regarding their booking. This feature increases your sales as it significantly reduces the number of no-shows.

Chatbot examples in Retail

Sephora

Next on our list of chatbot examples is Sephora’s bot. This brand offers bots on two different platforms, and each of them provides a separate set of services.

How it helps

Offers makeup tutorials, how-to videos, and product reviews

Provides a quiz that gathers information and makes suggestions (e.g., age, makeup brand preferences)

Uses Buttons & Emoji (rule-based)

Redirects users to the mobile site or Sephora app for purchase

Facebook Messenger:

Offers the Virtual Artists feature that lets you try on different makeup looks using the same technology as the popular Snapchat filters.

Lets you book an appointment for a makeover in one of Sephora stores. (Uses Natural Language processing).

Connects you with a customer service representative in real-time

Key Takeaways

Sephora aims to encourage more people to visit their physical stores. And indeed, thanks to the reservation assistant, the brand has seen an 11% increase in their booking rates. The in-store sales also grew as they’ve seen an average spent of $50 per client who booked their appointment on Facebook.

ASOS

ASOS’s chatbot is a fashion lover’s dream. It turns any photo or screenshot into shopping and style inspiration. Users send Enki the chatbot a picture and set a budget, and Enki will provide recommended outfits that they can shop.

Key Takeaways

The ASOS app has offered a visual search option for some time, but with Enki, the experience is far more interactive. Enki feels more like a personal shopping assistant by actively searching for items on customers’ behalf and sending weekly suggestions. 

With 70 percent of ASOS’s U.K. sales coming from a mobile device, Enki is a smart move for the retailer. And as of October 2018, Enki is also available via Google Assistant, giving shoppers a hands-free way to explore ASOS’s 85,000 products. 

Chatbot examples in Financial

Cleo

Cleo is an AI program that helps you keep track of your money by analyzing transaction data on your bank account.

How it helps

It’s creators strongly believe in the power of new technologies to help us manage finances better. Since its launch in 2016, Cleo has grown exponentially, currently helping 400,000+ US users have a clearer and more positive relationship with their budgeting.

How does Cleo work?

By providing Cleo with your online banking login, it’s able to analyze your transaction data securely. It uses the information to chat with you on Facebook Messenger or in the app, where you can ask it to:

Set and keep track of daily, weekly, or monthly budgets.

Check your direct debits.

View your balance.

Check latest transactions

View your spending habits split up into categories.

Is Cleo safe?

Cleo gains read-only access to your account, meaning it can only view encrypted transactions — it can’t move money into or out of your account.

Your credentials will never be stored on Cleo’s servers, and the company uses bank-level bank-level encryption to keep your data safe.

Cleo is so confident in your safety that they pledge to cover you up to $250,000 for any security breaches.

Key Takeaways

Sign up in less than two minutes.

Easy to use — contact Cleo from the Messenger app at any time.

Intelligent insights into your budget and spending.

Great for those who aren’t particularly engaged with their money.

Cleo may not be useful for people who are already in the habit of saving.

Requires you to give access to your bank logins to a third party.

Plum

What is Plum?

Plum is a smart savings software designed to save you money in the easiest possible way automatically. It was founded in 2016 with the idea of making saving easy and stress-free, but also effective for those of us who struggle to put that bit extra aside.

Rather than a separate account that requires a lengthy set-up, Plum utilizes many partners (such as Amazon servers, the Facebook Messenger app, and others) to make its savings scheme secure, accessible and user-friendly.

How does Plum work?

Bank account access: Plum users give it access to their bank accounts in a read-only view.

Spending and saving analysis: This allows Plum’s smart software to understand patterns in the user’s income and spending habits and to recognize the most effective way for savings to be made.

Automatic saving: Once Plum calculates a suitable amount to be saved each week, this amount is automatically transferred through direct debit into your Plum account to be held until you withdraw it.

Messenger: Plum communicates with you through Facebook messenger. It’ll tell you how much you’ve saved each week, for instance. You can send commands to Plum too. If you want to take £10 out, simply message Plum ‘withdraw 10’. If you want to save more next week, just write ‘save more.’

Flexibility and accessibility: You can withdraw, deposit more savings, keep a record of your saved amount, and even invest your savings directly through messenger.

Key Takeaways

Pros

  • Save money easily and automatically.
  • Free to register and use.
  • Contact Plum easily through the Facebook messenger app.
  • Withdraw money any time and receive it within 24 hours.
  • Personalized savings rate just for you

Cons

  • If you choose the investment option, your capital is at risk.
  • Access to money isn’t instantaneous; it can take 24 hours.
  • As Plum doesn’t use its own app, it relies heavily on the usability and security of others.

Chatbot examples in Entertainment

Swelly

Swelly is probably the most famous Facebook Messenger chatbot. It allows users to pick and choose one of two options and vote together with the general public. Users can also create their ‘Swell’ and see what the people around the world will vote.

Swelly has been used by a staggering number of people from around the world – more than 1 million. I think it is because it has a very strong virality component to it

Why I like it, I like how the Swelly experience is designed. It feels extremely easy to use and natural. It’s actually very well crafted, as it’s difficult to reach this level of simplicity.

Yes sire

Yes Sire is an Alexa game. It is extremely funny: You will play as the lord of your feud. You need to take tough decisions – Yes or No questions. The results are often hilarious and unpredictable. You will need to balance your attributes – wealth, influence, and more.

Yes Sire is the best-reviewed game on the Alexa Skill store. So if you need to pick a game between these chatbot examples, pick this one!

Why I like it, the basic game mechanism is really intuitive, as it’s based on yes-no questions. Beating the game is actually challenging, as it’s not easy to keep your attributes balances the more you progress.

Try it out. Just say ‘Alexa, let’s play. Yes Sire.’

National Geographic

Ever wonder what it would be like to talk to Albert Einstein? Well, now you can — kinda. 

How it helps

To help promote their new show Genius, National Geographic created a conversational chatbot who spoke like Einstein would. While most companies’ blast promos into your chat window, they used Einstein bot to follow users conversation and reply with information about the show and other interesting bits.

The result? 6-8 minute average conversations, 11 turns per conversation, 50% user re-engagement, and an involved community of followers. These metrics come from a carefully chosen, user-friendly chatbot strategy.

Key Takeaways

• Use chatbots to create intimate experiences: People felt they were “talking to Einstein” in real-time, in a human and friendly way. Einstein was able to answer professional and personal questions, making users feel a one-to-one connection to the bot, and in turn, the show.

• Make people laugh to engage with them: Laughter is not only good for the soul, but it’s something we don’t expect to do. Especially when you interact with a brand. Build your bot to be informational and conversational, with a little sass here and there.

• Rethink older concepts in a novel way: Chatbots are now used by many different companies across the board. Instead of reusing the same old sequences, try something new that people haven’t seen before.

Chatbot examples in Food & Drink

Dominos

Dominos changed the way we order food with Dom, the Interactive Pizza Bot. The Domino’s chatbot can re-order previous orders, offer a full menu, and track deliveries all in Messenger. It’s become one of the best chatbots for customer service — and now I want a pizza.

Key Takeaways

Make it accessible across platforms: Chatbots that span cross-platform perform better than one channel. For example, you can order through the Domino’s Pizza Bot by Slack, Messenger, Apple Watch, Mobile App, Twitter (by Pizza Emoji), Smart Home Assistants, and more. 

Don’t be afraid to be fun: More often than not, companies are afraid to be too simple or fun. This will not diminish your brand. Executing a key interaction with an emoji will go a lot further than a wall of text in your chat window.

Start simple, then move on to more complex cases: What’s the biggest reason users interact with your site or Facebook Page? If it’s ordering a pizza, design your bot around that core function. Once that experience is flawless, build your out chatbot with key secondary interactions.

Whole foods

The Whole Foods Facebook Messenger Bot is famed for its recipes, product recommendations, and cooking inspiration. Their chatbot helps shoppers find recipes on the spot and drives traffic to their site from Messenger.

How it helps

The same principles that work for any marketing channel apply even to chatbot conversations. Identify what resonates with your audiences, and build features to benefit them:

• Make searching for desired information easy: Whether shoppers need to look up a recipe at the store quickly, or are browsing from the couch — Whole Foods make it easy for users to find the recipes they are looking for. It narrows down information with filters, gives a preview of dishes, then sends users to their website for the full recipe.

• Talk with users how people talk: One of the biggest challenges in building a chatbot. Whole Foods lets users search for recipes using emojis, just like they’d react to a friends post or laugh at a funny meme.

• Be inclusive to everyone: Personalization is often half-baked and poorly executed, but with careful understanding, it can create an interactive experience. By letting users get diet-specific recipes, it helps promote a culture of inclusivity and wellbeing that welcomes everyone to Whole Foods.

Chatbot examples in Education

Duolingo 

Learning a new language is no easy task. You have the words in your head, but they never come out as you want. Turns out — embarrassment when talking with native speakers is real. And Duolingo curved that fear with an AI-powered chatbot app. 

Key Takeaways

Although the Duolingo Bot is for language learning, it taught us three lessons for building a chatbot for any industry.

• Build around existing pains to see success: Listen to your users and build sequences based on their pains. Doing this provides a strong incentive for them to use it. Not sure what to write? Simply reach out and talk to your customers about their goals.

• Make it easily available for maximum usage: Shutting down your bot at any time leads to missed opportunities and revenue. Instead, make your bot available at any time of the day, for any reason. 

• Design your bot to be interactive and enjoyable: Chatbots that retread the same script, for the same people, don’t make an exciting experience.

Dalî

What is Dalî?

Dalî stands for Dialog-based Artificial Learning Intelligence. DALI is a conversation agent that is capable of not only answering questions but teaching people.

DALI is a crowd-editable online conversational learning and tutoring system, in which the content creation process is broken down into elementary contributions. 

Key Takeaways

Our goal is that even a single utterance can be an acknowledged and rewarded contribution in a collaborative, crowd-based effort to build a complex educational conversation. DALI can be briefly described as an expert yet curious entity whose knowledge is accessible to everyone, teaches everyone and learns from everyone through conversations.

Chatbot Examples in News

When you don’t have time to browse news websites and follow current events, it may be a good idea to subscribe to one of the news chatbots. Many popular newspapers and television networks introduced chatbot services. Chatbots inform about breaking news and recommend top stories to read.

Wall Street Journal Chatbot

Imagine that your favourite magazine is able to send you articles that will probably be interesting for you to read. Day after day to your morning coffee, you have a list of the most interesting articles, so that you don’t have to wade through a magazine by yourself. It’s like a personal assistant!

That’s how the chatbot of The Wall Street Journal works. Yes, this magazine — as one of the greatest providers of economic news — adapts to the modern world, by enabling us to receive the most important information directly from their professional newsroom!

CNN Chatbot

CNN chatbot provides news through different channels such as Kik, Facebook Messenger, and voice assistants (for example, Alexa). The format differs for each of these platforms. Some of them allow open-ended queries and the chatbot-suggested personalized news, while others use decision trees. 

The Kik version of the CNN bot was used to increase the engagement of teenagers around Election Day. It worked, and the users of Kik platform exchanged almost 5 million messages with the CNN chatbot during the campaign and election.  

Chatbot examples in mental health

Replika

Replika is a mental wellness chatbot that helps people reduce stress, relieve anxiety, and combat loneliness, as well as get to know themselves better and be happier.

It has a tragic origin story. In 2015, Eugenia Kuyda, the creator of Replika, lost her best friend Roman Mazurenko who died in a car accident.

A month after his death, she could feel her memory of him fading away, so she went through their chat history as a way to rekindle it. Then, she had an idea. What if she could create a replica of Roman from the digital traces that he left behind?

She used text messages and emails, both between her and Roman and between Roman and his other friends and family, to create a chatbot that sounded like the friend she had lost.

Eugenia then made it public. She noticed that people were interacting with the bot in a way she hadn’t expected: they were sharing things about themselves. So she and a friend of hers started working on a new chatbot that became Replika.

When you register, you are asked about your goals and your daily routine, and then you are prompted to create your personal Replika by giving it a name and choosing its gender.

Over time, as it learns more about you, it will start mimicking you, providing you with someone you can talk to that is a lot like you.

It might seem like a strange idea, but a lot of people worldwide say that talking to someone who is always there for them and never judges them has a positive effect on their lives.

Woebot

Woebot claims to be an automated conversational agent or chatbot that monitors the moods of users and provides a venue in which users can express their thoughts and emotions through therapeutic conversations.

Originally built for young adults and graduate school students, Woebot is built on a platform of Cognitive Behavioral Therapy (CBT) – a process that the UK National Health Service describes as a talking therapy that can help patients manage mental health condition by changing the way they think and behave by enabling patients to reframe their negative thoughts into positive ones – natural language processing, clinical expertise, and light-hearted daily talk intended to create a therapeutic experience for the user.

The app asks users how they’re feeling and what is going on in their lives, talks to them about mental health and wellness, and sends videos and other useful tools depending on the user’s current mood and needs.

Woebot’s clinical team is led by founder and CEO psychologist and healthcare designer Dr. Alison Darcy, Ph.D., who has with over 15 years experience in health tech, supported by Chief Clinical Officer Athena Robinson, Ph.D., and Laurel Hart a specialist in natural language processing (NLP). Meanwhile, the technical aspect is overseen by Joseph Doyle, Head of Engineering, and Colin Parsons, Lead Mobile Engineer.

Together, this team developed Woebot on the Facebook Messenger platform, where the app initiates conversations in English and creates a weekly graph to monitor any changes in the user’s mood. The company claims that the more frequent and regular the chats become, the better Woebot is able to gather data about the user and provide a first-defence line of mental health support.

Chatbot examples in Legal

Businesses and enterprises make use of chatbots and AI systems to solve many problems related to networking, recruitment, and legal paperwork. Here are some of the best chatbot examples which improve company workflow and productivity.

DoNotPay Chatbot

DoNotPay is a chatbot which can help with legal problems of any kind. Originally, it was created by Joshua Browder to appeal parking fines. The app had been successfully used by hundreds of thousands of motorists, and it has become more and more diverse ever since.

Recently, DoNotPay has joined forces with Robot Lawyer LISA, an AI system that can create legally binding agreements. The DoNotPay chatbot available in the app offers legal advice on common legal problems.

Chatbot examples in Hospitality

Not every hotel is a Marriot chain, but each should offer the following basic services:

  • Room availability
  • Guest Reservations
  • Connect to front desk agent or concierge from room

Marriot

As far as hotels go, no one can compare to Marriot when it comes to Chatbot examples. In my opinion, they have one of the best chatbots by far. 

Their boutique brand Aloft Hotels recently introduced the ChatBotlr, available to guests through text message. Using it, guests can request basic hotel services, essentially acting as an in-phone concierge.

Marriot’s chatbot example

Hotel guests cant text to request services, information about the hotel, listen to the brand’s playlist and connect with the front desk team during their stay, even when the guest is not on hotel property.

And it’s working: early studies show that 2 out of 3 Aloft guests are interacting with the ChatBotlr.

Outside of that, Marriott Rewards members can interact with bots on Facebook Messenger and Slack, and research and book travel at more than 4,700 hotels.

Key Takeaways: When it comes to hotels, Chatbots are all about guest services. Whether it’s checking in and out or services and travel recommendations throughout a stay, hotels should be for ways to leverage Chatbots as an addition to typical front desk and concierge services

Enterprise Bot Manager © 2020 Filament Consultancy Group. Registered in England and Wales -  Company Number 10180537.  © 2020 Filament Consultancy Group Canada Limited. Registered in Ontario, Corporation Number 1995332.