Back to Blog

How Easyway Uses AI-Powered Chat to Automate Communication for Luxury Hotels

,
,
,
April 3, 2023
No items found.

Learn how Easyway, a guest relationship management platform, used AI21 Labs LLM to streamline their operation and improve guest communications.

A luxury hotel that wants to provide exceptional hospitality must deliver a 5-star experience throughout the guest's entire journey, from the moment they arrive on the website until they check out.

But how can these hotels give personalized attention to guests with 200 and more messages a day without relying on gimmicky chatbots?

Asaf Ofer, CTO and Founder of Easyway, discussed their current use of AI and how he plans to scale it.

What is Easyway?

Easyway is a guest relationship management platform (GRM) that facilitates two-way communication between guests and the hotel through instant messaging apps such as Whatsapp, SMS, Telegram, and more. 

Using their technology, hotels are able to automate communication and streamline daily operations like check-in and check-out processes. 

Since Easyway serves mostly luxury hotels that cater to a 4- and 5-star experience, every touchpoint is crucial for delivering high-end customer service. Aiming to improve certain aspects of their platform, they turned to AI21 Labs to take their product to a new level.

Why They Chose AI21: An LLM Solution that Mimics Human Interaction

Since Easyway isn't a chatbot, but rather an AI-powered chat platform, they needed a solution that wasn't readily available on the market. They looked for an AI platform with enough scientific and engineering innovation to be able to understand and generate natural text. 

“The guest needs to feel like they're speaking to a human and not a chatbot,” says Asaf. “If we automate it in a human and customized way, hotels need less staff, and people feel like they're being treated like special guests every time.”

The Problem with Other Models on the Market

Easyway started out using other models that could answer common questions, but only if those questions were asked in the most common and simple form. A slight deviation would cause the entire model to fail.

“People had questions that it didn’t know how to respond to, because it never saw these questions [asked this way] before,” Asaf explains. “Sometimes it was wrongly confident about what was being asked because it didn't get a lot of examples to work with.”

AI21’s Personalized Customer Service & Assistance to the Rescue

With the assistance of AI21, the Easyway team was able to train their model using a few dozen custom-made prompts. “We had several calls, I showed them our results and they helped me clean up and set up the training data correctly,” says Asaf.

AI21 helped Asaf’s team break the process down to steps, translate it into code, and find discrepancies in the data. Finally, the Easyway team managed to arrive at their desired solution. 

It was through this level of support that Easyway was able to use AI21 to upgrade their application. 

Use Case #1: Intent Detection

With AI21's proprietary Large language Models (LLMs), Easyway was able to analyze intent with high accuracy. Easyway now uses a sentiment analysis model based on fifteen frequently asked questions.

“We gave the model a question and it gives us back 1 out of several possible intents,” says Asaf. He goes on to explain that if the model doesn’t exactly know that answer, then it’s okay not to respond at all – sometimes, it’s actually better for business not to. That’s due to the fact that inappropriately responding to an already frustrated or angry customer may only fuel the situation rather than alleviating it.

This feature will lead to even bigger things in the future, says Asaf. “Once we have a reliable solution for detecting sentiment, we’d be able to automate much more - If the system detects that a guest is angry, we could immediately notify the manager. If a guest is satisfied, we’d ask them to leave a review, etc.” 

Use Case #2: Automatic Translation

Every hotel is filled with travelers from and to various countries. The importance of having a staff with multiple languages cannot be overstated. However, knowledge of every language is not always possible, which is why translation apps are useful.

Easyway offers high-quality 2-way translation capabilities in 100+ languages. “A Spanish guest will speak Spanish and the staff will be speaking Hebrew and the conversation will be understandable for each side,” Asaf explains. “So each person can just use their native language, plus we use AI to respond to messages automatically.”

This feature was already in production before Easyway reached out to AI21, but there was much room for improvement. “One of the gaps we had to tackle was a varying level of grammar amongst our end users. The problem involved two aspects; the level of service that our clients provide their guests, and the efficiency of our translation feature. If a person writing on our platform didn’t write properly, the live translation wouldn’t work properly.” 

By incorporating the same technology that is used in Wordtune, AI21’s flagship AI writing assistant, this was made possible.

The Future for Easyway

What if you could not only automate away repetitive questions, but also begin to automatically set common responses to FAQs?

Easyway is currently running a pilot to embed a chat widget on one of their partners’ websites, gearing up for a possible new offer. “We’re [piloting this feature] with a customer in Europe that has a lot of visitors to their website - around 150K each month, and they don't have the staff to deal with it. So they just end up with thousands of emails asking basic questions that nobody responds to,” Asaf says.

With Easyway, hotels can automate and schedule messages based on events such as booking, arrival, and departure. 

A typical post-booking conversation could be:

  • “Hey Asaf, thank you for booking your stay with us. Do you have any questions?” 
  • Asaf may type: “How do I get to the hotel?” or “What are the Covid regulations?”

The chat platform is set up to respond automatically, helping hotels save time with quality AI.

The Result: Automated, Human-Centered Conversations that Save Time

Remember those 200 or more messages we mentioned hotels can receive each day? To reach success, Easyway will look at how many emails each hotel actually needs to personally answer after using their application powered by AI21. Asaf stated that a “10, 20, 30% [reduction rate] would be amazing.” 

Overall, we are thrilled to have the opportunity to use our NLP technology to help alleviate the administrative burdens that hotels experience on a daily basis – while still uplifting the 5-star experience guests want from their hotel of choice.

Discover more

What is a MRKL system?

In August 2021 we released Jurassic-1, a 178B-parameter autoregressive language model. We’re thankful for the reception it got – over 10,000 developers signed up, and hundreds of commercial applications are in various stages of development. Mega models such as Jurassic-1, GPT-3 and others are indeed amazing, and open up exciting opportunities. But these models are also inherently limited. They can’t access your company database, don’t have access to current information (for example, latest COVID numbers or dollar-euro exchange rate), can’t reason (for example, their arithmetic capabilities don’t come close to that of an HP calculator from the 1970s), and are prohibitively expensive to update.
A MRKL system such as Jurassic-X enjoys all the advantages of mega language models, with none of these disadvantages. Here’s how it works.

Compositive multi-expert problem: the list of “Green energy companies” is routed to Wiki API, “last month” dates are extracted from the calendar and “share prices” from the database. The “largest increase“ is computed by the calculator and finally, the answer is formatted by the language model.

There are of course many details and challenges in making all this work - training the discrete experts, smoothing the interface between them and the neural network, routing among the different modules, and more. To get a deeper sense for MRKL systems, how they fit in the technology landscape, and some of the technical challenges in implementing them, see our MRKL paper. For a deeper technical look at how to handle one of the implementation challenges, namely avoiding model explosion, see our paper on leveraging frozen mega LMs.

A further look at the advantages of Jurassic-X

Even without diving into technical details, it’s easy to get a sense for the advantages of Jurassic-X. Here are some of the capabilities it offers, and how these can be used for practical applications.

Reading and updating your database in free language

Language models are closed boxes which you can use, but not change. However, in many practical cases you would want to use the power of a language model to analyze information you possess - the supplies in your store, your company’s payroll, the grades in your school and more. Jurassic-X can connect to your databases so that you can ‘talk’ to your data to explore what you need-  “Find the cheapest Shampoo that has a rosy smell”, “Which computing stock increased the most in the last week?” and more. Furthermore, our system also enables joining several databases, and has the ability to update your database using free language (see figure below).

Jurassic-X enables you to plug in YOUR company's database (inventories, salary sheets, etc.) and extract information using free language

AI-assisted text generation on current affairs

Language models can generate text, yet can not be used to create text on current affairs, because their vast knowledge (historic dates, world leaders and more) represents the world as it was when they were trained. This is clearly (and somewhat embarrassingly) demonstrated when three of the world’s leading language models (including our own Jurassic-1) still claim Donald Trump is the US president more than a year after Joe Biden was sworn into office.
Jurassic-X solves this problem by simply plugging into resources such as Wikidata, providing it with continuous access to up-to-date knowledge. This opens up a new avenue for AI-assisted text generation on current affairs.

Who is the president of the United States?

T0
Donald Trump
GPT-3
Donald Trump
Jurassic-1
Donald Trump
Google
Joe Biden
Jurassic-X
Joe Biden is the
46th and current
president
Jurassic-X can assist in text generation on up-to-date events by combining a powerful language model with access to Wikidata

Performing math operations

A 6 year old child learns math from rules, not only by memorizing examples. In contrast, language models are designed to learn from examples, and consequently are able to solve very basic math like 1-, 2-, and possibly 3- digit addition, but struggle with anything more complex. With increased training time, better data and larger models, the performance will improve, but will not reach the robustness of an HP calculator from the 1970s. Jurassic-X takes a different approach and calls upon a calculator whenever a math problem is identified by the router. The problem can be phrased in natural language and is converted by the language model to the format required by the calculator (numbers and math operations). The computation is performed and the answer is converted back into free language.
Importantly (see example below) the process is made transparent to the user by revealing the computation performed, thus increasing the trust in the system. In contrast, language models provide answers which might seem reasonable, but are wrong, making them impractical to use.

The company had 655400 shares which they divided equally among 94 employees. How many did each employee get?

T0
94 employees.
GPT-3
Each employee got 7000 stocks
Jurassic-1
1.5
Google
(No answer provided)
Jurassic-X
6972.3
X= 655400/94
Jurassic-X can answer non-trivial math operations which are phrased in natural language, made possible by the combination of a language model and a calculator

Compositionality

Solving simple questions might require multiple steps, for example - “Do more people live in Tel Aviv or in Berlin?” requires answering: i. What is the population of Tel-Aviv? ii. What is the population of Berlin? iii. Which is larger? This is a highly non-trivial process for a language model, and language models fail to answer this question (see example). Moreover, the user can’t know the process leading to the answers, hence is unable to trust them. Jurassic-X can decompose such problems into the basic questions, route each to the relevant expert, and put together an answer in free language. Importantly, Jurassic-X not only provides the correct answer but also displays the steps taken to reach it, increasing the trust in the system.

Do more people live in Tel Aviv or in Berlin?

T0
Berlin
GPT-3
There are more people living in Tel Aviv than in Berlin.
Jurassic-1
Berlin and Tel Aviv are roughly the same size
Google
(First hit is a comparison between Tel Aviv and Berlin)
Jurassic-X
More people live in Berlin than in Tel-Aviv

[‘Return population of Tel Aviv’; Return population of Berlin’; Return which is bigger between #1 and #2’]
Step 1: Population of Tel Aviv. Result - 451523.
Step 1: Population of Berlin. Result - 3664088.
Step 3: Which is bigger,  #1 or #2. Result - Berlin.

Jurassic-X breaks down compositional questions, answers the basic sub-questions, and puts together the answer. Importantly, this process is transparent to the user greatly increasing the trust in the system

Dynamic information (like weather and currency exchange rates)

Certain types of information change continuously - weather, currency exchange rates, share values and more. Such information will never be captured by language models, yet can easily be handled by Jurassic-X by integrating it with a reliable source of information. We performed a proof-of-concept on two such features - weather and currency exchange rates, and the design enables quick integration with more sources to solve your use-case.
Weather - a loosely phrased question about the weather elicits an answer from all language models, where language models always return the same answer, regardless of when the question was asked (funny, right?), while Jurassic-X provides an answer based on the actual weather prediction.

I’m going to be in New-York in 3 days. Should I pack my umbrella?

T0
No
GPT-3
Yes, you should pack your umbrella.
Jurassic-1
Yes, you should. The weather forecast is rain.
Google
(Links to weather websites)
Jurassic-X
Yes, you should pack your umbrella, because in New York in 3 days there will be broken clouds and the temperature will be -2 degrees.

Currency exchange rates change much faster than weather predictions, yet the Jurassic-X concept - a language model connected to a reliable source of information - easily solves this problem as well.

How much Moroccan money will I get for 100 bucks?

T0
125 dirhams
GPT-3
100 moroccan dirhams is about 27$.
Jurassic-1
How much is 100 dollars in moroccan money?
Google
100 dirhams = 10.75 dollars
Jurassic-X
100 USD = 934.003 MAD
Jurassic-X combines a language model with access to APIs with continuously changing information. This is demonstrated for weather forecasts and currency exchange rates, and can easily be extended to other information sources

Transparency and trust

Transparency is a critical element that is lacking in language models, preventing a much wider adoption of these models. This lack of transparency is demonstrated by the answers to the question - “Was Clinton ever elected as president of the United States?”. The answer, of course, depends on which Clinton you have in mind, which is only made clear by Jurassic-X that has a component for disambiguation. More examples of Jurassic-X’s transparency were demonstrated above - displaying the math operation performed to the user, and the answer to the simple sub-questions in the multi-step setting.

Was Clinton ever elected president of the United States?

T0
Yes
GPT-3
No, Clinton was never elected as president of the United States.
Jurassic-1
No
Google
Clinton was elected president in the 1992 presidential elections…
Jurassic-X
Bill Clinton was elected president.
Jurassic-X is designed to be more transparent by displaying which expert answered which part of the question, and by presenting the intermediate steps taken and not just the black-box response

Your Turn

That's it, you get the picture. The use cases above give you a sense for some things you could do with Jurassic-X, but now it's your turn. A MRKL system such as Jurassic-X is as flexible as your imagination. What do you want to accomplish? Contact us for early access

Contact us below and we will get back to you shortly.

Thank you!

Your submission has been received!
Oops! Something went wrong while submitting the form.