generative ai Archives

WhatsApp Business: A Guide for Contact Center Managers

Posted on March 8, 2024November 15, 2024 The Quiq Team

In today’s digital era, businesses continually seek innovative ways to connect with their customers, striving to enhance communication and foster deeper relationships. Enter WhatsApp Business – a game-changer in the realm of digital communication. This powerful tool is not just a messaging app; it’s a bridge between businesses and their customers, offering a plethora of features designed to streamline communication, improve customer service, and boost engagement. Whether you’re a small business owner or part of a global enterprise, understanding the potential of WhatsApp Business could redefine your approach to customer communication.

What is Whatsapp Business?

WhatsApp is an application that supports text messaging, voice messaging, and video calling for over two billion global users. Because it leverages a simple internet connection to send and receive data, WhatsApp users can avoid the fees that once made communication so expensive.

Since WhatsApp already has such a large base of enthusiastic users, many international brands have begun leveraging it to communicate with their own audiences. It also has a number of built-in features that make it an attractive option for businesses wanting to establish a more personal connection with their customers, and we’ll cover those in the next section.

What Features Does WhatsApp Business Have?

In addition to its reach and the fact that it reduces the budget needed for communication, WhatsApp Business has additional functionality that makes it ideal for any business trying to interact with its customers.

When integrated with a tool like the Quiq conversational AI platform, WhatsApp Business can automatically transcribe voice-based messages. Even better, WhatsApp Business allows you to export these conversations later if you want to analyze them with a tool like natural language processing.

If your contact center agents and the customers they’re communicating with have both set a “preferred language,” WhatsApp can dynamically translate between these languages to make communication easier. So, if a user sends a voice message in Russian and the agent wants to communicate in English, they’ll have no trouble understanding one another.

What are the Differences Between WhatsApp and WhatsApp Business?

Before we move on, it’s worth pointing out that WhatsApp and WhatsApp Business are two different services. On its own, WhatsApp is the most widely used messaging application in the world. Businesses can use WhatsApp to talk to their customers, but with a WhatsApp Business account, they get a few extra perks.

Mostly, these perks revolve around building brand awareness. Unlike a basic WhatsApp account, a WhatsApp Business account allows you to include a lot of additional information about your company and its services. It also provides a labeling system so that you can organize the conversations you have with customers, and a variety of other tools so you can respond quickly and efficiently to any issues that come up.

The Advantages of WhatsApp Messaging for Businesses

Now, let’s spend some time going over the myriad advantages offered by a WhatsApp outreach strategy. Why, in other words, would you choose to use WhatsApp over its many competitors?

Global Reach and Popularity

First, we’ve already mentioned the fact that WhatsApp has achieved worldwide popularity, and in this section, we’ll drill down into more specifics.

When WhatsApp was acquired by Meta in 2014, it already boasted 450 million active users per month. Today, this figure has climbed to a remarkable 2.7 billion, but it’s believed it will reach a dizzying 3.14 billion as early as 2025.

With over 535 million users, India is the country where WhatsApp has gained the most traction by far. Brazil is second with 148 million users, and Indonesia is third with 112 million users.

The gender divide among WhatsApp users is pretty even – men account for just shy of 54% of WhatsApp users, so they have only a slight majority.

The app itself has over 5 billion downloads from the Google Play store alone, and it’s used to send 140 billion messages each day.

These data indicate that WhatsApp could be a very valuable channel to cultivate, regardless of the market you’re looking to serve or where your customers are located.

Personalized Customer Interactions

Firstly, platforms like WhatsApp enable businesses to customize communication with a level of scale and sophistication previously unavailable.

This customization is powered by machine learning, a technology that has consistently led the charge in the realm of automated content personalization. For example, Spotify’s ability to analyze your listening patterns and suggest music or podcasts that match your interests is powered by machine learning. Now, thanks to advancements in generative AI, similar technology is being applied to text messaging.

Past language models often fell short in providing personalized customer interactions. They tended to be more “rule-based” and, therefore, came off as “mechanical” and “unnatural.” However, contemporary models greatly improve agents’ capacity to adapt their messages to a particular situation.

While none of this suggests generative AI is going to entirely take the place of the distinctive human mode of expression, for a contact center manager aiming to improve customer experience, this marks a considerable step forward.

Below, we have a section talking a little bit more about integrating AI into WhatsApp Business.

End-to-End Encryption

One thing that has always been a selling point for WhatsApp is that it takes security and privacy seriously. This is manifested most obviously in the fact that it encrypts all messages end-to-end.

What does this mean? From the moment you start typing a message to another user all the way through when they read it, the message is protected. Even if another party were to somehow intercept your message, they’d still have to crack the encryption to read it. What’s more, all of this is enabled by default – you don’t have to spend any time messing around with security settings.

This might be more important than you realize. We live in a world increasingly beset by data breaches and ransomware attacks, and more people are waking up to the importance of data security and privacy. This means that a company that takes these aspects of its platform very seriously could have a leg up where building trust is concerned. Your users want to know that their information is safe with you, and using a messaging service like WhatsApp will help to set you apart.

Scalability

Finally, WhatsApp’s Business API is a sophisticated programmatic interface designed to scale your business’s outreach capabilities. By leveraging this tool, companies can connect with a broader audience, extending their reach to prospects and customers across various locations. This expansion is not just about increasing numbers; it’s about strategically enhancing your business’s presence in the digital world, ensuring that you’re accessible whenever your customers need to reach out to you.

By understanding the value WhatsApp’s Business API brings in reaching and engaging with more people effectively, you can make an informed decision about whether it represents the right technological solution for your business’s expansion and customer engagement strategies.

Enhancing Contact Center Performance with WhatsApp Messaging

Now, let’s turn our attention to some of the concrete ways in which WhatsApp can improve your company’s chances of success!

Improving Response and Resolution Metrics Times

Integrating technologies like WhatsApp Business into your agent workflow can drastically improve efficiency, simultaneously reducing response times and boosting customer satisfaction. Agents often have to manage several conversations at once, and it can be challenging to keep all those plates spinning.

However, a quality messaging platform like WhatsApp means they’re better equipped to handle these conversations, especially when utilizing tools like Quiq Compose.

Additionally, less friction in resolving routine tasks means agents can dedicate their focus to issues that necessitate their expertise. This not only leads to more effective problem-solving, it means that fewer customer inquiries are overlooked or terminated prematurely.

Integrating Artificial Intelligence

According to WhatsApp’s own documentation, there’s an ongoing effort to expand the API to allow for the integration of chatbots, AI assistants, and generative AI more broadly.

Today, these technologies possess a surprisingly sophisticated ability to conduct basic interactions, answer straightforward questions, and address a wide range of issues, all of which play a significant role in boosting customer satisfaction and making agents more productive.

We can’t say for certain when WhatsApp will roll out the red carpet for AI vendors like Quiq, but if our research over the past year is any indication, it will make it dramatically easier to keep customers happy!

Gathering Customer Feedback

Lastly, an additional advantage to WhatsApp messaging is the degree to which it facilitates collecting customer feedback. To adapt quickly and improve your services, you have to know what your customers are thinking. And more specifically, you have to know the details about what they like and dislike about your product or service.

In the Olde Days (i.e. 20 years ago year, or so), the only real way to do this was by conducting focus groups, sending out surveys – sometimes through the actual mail, if you can believe it – or doing something similarly labor-intensive.

Today, however, your customers are almost certainly walking around with a smartphone that supports text messaging. And, since it’s pretty easy for them to answer a few questions or dash off a few quick lines describing their experience with your service, odds are that you can gather a great deal of feedback from them.

Now, we hasten to add that you must exercise a certain degree of caution in interpreting this kind of feedback, as getting an accurate gauge of customer sentiment is far from trivial. To name just one example, the feedback might be exaggerated in both the positive and negative direction because the people most likely to send feedback via text messaging are the ones who really liked or really didn’t like you.

That said, so long as you’re taking care to contextualize the information coming from customers, supplementing it with additional data wherever appropriate, it’s valuable to have.

Wrapping Up

From its global reach and popularity to the personalized customer interactions it facilitates, WhatsApp Business stands out as a powerful solution for businesses aiming to enhance their digital presence and customer engagement strategies. By leveraging the advanced features of WhatsApp Business, companies can avail themselves of end-to-end encryption, enjoy scalability, and improve contact center performance, thereby positioning themselves at the forefront of the contact center game.

And speaking of being at the forefront, the Quiq conversational CX platform offers a staggering variety of different tools, from AI assistants powered by language models to advanced analytics on agent performance. Check us out or schedule a demo to see what we can do for your contact center!

6 Questions to Ask Generative AI Vendors You’re Evaluating

Posted on February 8, 2024November 15, 2024 The Quiq Team

With all the power exhibited by today’s large language models, many businesses are scrambling to leverage them in their offerings. Enterprises in a wide variety of domains – from contact centers to teams focused on writing custom software – are adding AI-backed functionality to make their users more productive and the customer experience better.

But, in the rush to avoid being the only organization not using the hot new technology, it’s easy to overlook certain basic sanity checks you must perform when choosing a vendor. Today, we’re going to fix that. This piece will focus on several of the broad categories of questions you should be asking potential generative AI providers as you evaluate all your options.

This knowledge will give you the best chance of finding a vendor that meets your requirements, will help you with integration, and will ultimately allow you to better serve your customers.

These are the Questions you Should ask Your Generative AI Vendor

Training large language models is difficult. Besides the fact that it requires an incredible amount of computing power, there are also hundreds of tiny little engineering optimizations that need to be made along the way. This is part of the reason why all the different language model vendors are different from one another.

Some have a longer context window, others write better code but struggle with subtle language-based tasks, etc. All of this needs to be factored into your final decision because it will impact how well your vendor performs for your particular use case.

In the sections that follow, we’ll walk you through some of the questions you should raise with each vendor. Most of these questions are designed to help you get a handle on how easy a given offering will be to use in your situation, and what integrating it will look like.

1. What Sort of Customer Service Do You Offer?

We’re contact center and customer support people, so we understand better than anyone how important it is to make sure users know what our product is, what it can do, and how we can help them if they run into issues.

As you speak with different generative AI vendors, you’ll want to probe them about their own customer support, and what steps they’ll take to help you utilize their platform effectively.

For this, just start with the basics by figuring out the availability of their support teams – what hours they operate in, whether they can accommodate teams working in multiple time zones, and whether there is an option for 24/7 support if a critical problem arises.

Then, you can begin drilling into specifics. One thing you’ll want to know about is the channels their support team operates through. They might set up a private Slack channel with you so you can access their engineers directly, for example, or they might prefer to work through email, a ticketing system, or a chat interface. When you’re discussing this topic, try to find out whether you’ll have a dedicated account manager to work with.

You’ll also want some context on the issue resolution process. If you have a lingering problem that’s not being resolved, how do you go about escalating it, and what’s the team’s response time for issues in general?

Finally, it’s important that the vendors have some kind of feedback mechanism. Just as you no doubt have a way for clients to let you know if they’re dissatisfied with an agent or a process, the vendor you choose should offer a way for you to let them know how they’re doing so they can improve. This not only tells you they care about getting better, it also indicates that they have a way of figuring out how to do so.

2. Does Your Team Offer Help with Setting up the Platform?

A related subject is the extent to which a given generative AI vendor will help you set up their platform in your environment. A good way to begin is by asking what kinds of training materials and resources they offer.

Many vendors are promoting their platforms by putting out a ton of educational content, all of which your internal engineers can use to get up to speed on what those platforms can do and how they function.

This is the kind of thing that is easy to overlook, but you should pay careful attention to it. Choosing a generative AI vendor that has excellent documentation, plenty of worked-out examples, etc. could end up saving you a tremendous amount of time, energy, and money down the line.

Then, you can get clarity on whether the vendor has a dedicated team devoted to helping customers like you get set up. These roles are usually found under titles like “solutions architect”, so be sure to ask whether you’ll be assigned such a person and the extent to which you can expect their help. Some platforms will go to the moon and back to make sure you have everything you need, while others will simply advise you if you get stuck somewhere.

Which path makes the most sense depends on your circumstances. If you have a lot of engineers you may not need more than a little advice here and there, but if you don’t, you’ll likely need more handholding (but will probably also have to pay extra for that). Keep all this in mind as you’re deciding.

3. What Kinds of Integrations Do You Support?

Now, it’s time to get into more technical details about the integrations they support. When you buy a subscription to a generative AI vendor, you are effectively buying a set of capabilities. But those capabilities are much more valuable if you know they’ll plug in seamlessly with your existing software, and they’re even more valuable if you know they’ll plug into software you plan on building later on. You’ve probably been working on a roadmap, and now’s the time to get it out.

It’s worth checking to see whether the vendor can support many different kinds of language models. This involves a nuance in what the word “vendor” means, so let’s unpack it a little bit. Some generative AI vendors are offering you a model, so they’re probably not going to support another company’s model.

OpenAI and Anthropic are examples of model vendors, so if you work with them you’re buying their model and will not be able to easily incorporate someone else’s model.

Other vendors, by contrast, are offering you a service, and in many cases that service could theoretically by powered by many different models.

Quiq’s Conversational CX Platform, for example, supports OpenAI’s GPT models, and we have plans to expand the scope of our integrations to encompass even more models in the future.

Another thing you’re going to want to check on is whether the vendor makes it easy to integrate vector databases into your workflow. Vectors are data structures that are remarkably good at capturing subtle relationships in large datasets; they’re becoming an ever-more-important part of machine learning, as evinced by the fact that there are now a multitude of different vector databases on offer.

The chances are pretty good that you’ll eventually want to leverage a vector database to store or search over customer interactions, and you’ll want a vendor that makes this easy.

Finally, see if the vendor has any case studies you can look at. Quiq has published a case study on how our language services were utilized by LOOP, a car insurance company, to make a far superior customer-service chatbot. The result was that customers were able to get much more personalization in their answers and were able to resolve their problems fully half of the time, without help. This led to a corresponding 55% reduction in tickets, and a customer satisfaction rating of 75% (!) when interacting with the Quiq-powered AI assistant.

See if the vendors you’re looking at have anything similar you can examine. This is especially helpful if the case studies are focused on companies that are similar to yours.

4. How Does Prompt Engineering and Fine-Tuning Work for Your Model?

For many tasks, large language models work perfectly fine on their own, without much special effort. But there are two methods you should know about to really get the most out of them: prompt engineering and fine-tuning.

As you know, prompts are the basic method for interacting with language models. You’ll give a model a prompt like “What is generative AI?”, and it’ll generate a response. Well, it turns out that models are really sensitive to the wording and structure of prompts, and prompt engineers are those who explore the best way to craft prompts to get useful output from a model.

It’s worth asking potential vendors about this because they handle prompts differently. Quiq’s AI Studio encourages atomic prompting, where a single prompt has a clear purpose and intended completion, and we support running prompts in parallel and sequentially. You can’t assume everyone will do this, however, so be sure to check.

Then, there’s fine-tuning, which refers to training a model on a bespoke dataset such that its output is heavily geared towards the patterns found in that dataset. It’s becoming more common to fine-tune a foundational model for specific use cases, especially when those use cases involve a lot of specialized vocabulary such as is found in medicine or law.

Setting up a fine-tuning pipeline can be cumbersome or relatively straightforward depending on the vendor, so see what each vendor offers in this regard. It’s also worth asking whether they offer technical support for this aspect of working with the models.

5. Can Your Models Support Reasoning and Acting?

One of the current frontiers in generative AI is building more robust, “agentic” models that can execute strings of tasks on their way to completing a broader goal. This goes by a few different names, but one that has been popping up in the research literature is “ReAct”, which stands for “reasoning and acting”.

You can get ReAct functionality out of existing language models through chain-of-thought prompting, or by using systems like AutoGPT; to help you concretize this a bit, let’s walk through how ReAct works in Quiq.

With Quiq’s AI Studio, a conversational data model is used to classify and store both custom and standard data elements, and these data elements can be set within and across “user turns”. A single user turn is the time between when a user offers an input to the time at which the AI responds and waits for the next user input.

Our AI can set and reason about the state of the data model, applying rules to take the next best action. Common actions include things like fetching data, running another prompt, delivering a message, or offering to escalate to a human.

Though these efforts are still early, this is absolutely the direction the field is taking. If you want to be prepared for what’s coming without the need to overhaul your generative AI stack later on, ask about how different vendors support ReAct.

6. What’s your Pricing Structure Like?

Finally, you’ll need to talk to vendors about how their prices work, including any available details on licensing types, subscriptions, and costs associated with the integration, use, and maintenance of their solution.

To take one example, Quiq’s licensing is based on usage. We establish a usage pool wherein our customers pre-pay Quiq for a 12-month contract; then, as the customer uses our software money is deducted from that pool. We also have an annual AI Assistant Maintenance fee along with a one-time implementation fee.

Vendors can vary considerably in how their prices work, so if you don’t want to overpay then make sure you have a clear understanding of their approach.

Picking the Right Generative AI Vendor

Language models and related technologies are taking the world by storm, transforming many industries, including customer service and contact center management.

Making use of these systems means choosing a good vendor, and that requires you to understand each vendor’s model, how those models integrate with other tools, and what you’re ultimately going to end up paying.

If you want to see how Quiq stacks up and what we can do for you, schedule a demo with us today!

Request A Demo

Getting the Most Out of Your Customer Insights with AI

Posted on January 26, 2024November 15, 2024 The Quiq Team

The phrase “Knowledge is power” is usually believed to have originated with 16th- and 17th-century English philosopher Francis Bacon, in his Meditationes Sacræ. Because many people recognize something profoundly right about this sentiment, it has become received wisdom in the centuries since.

Now, data isn’t exactly the same thing as knowledge, but it is tremendously powerful. Armed with enough of the right kind of data, contact center managers can make better decisions about how to deploy resources, resolve customer issues, and run their business.

As is usually the case, the data contact center managers are looking for will be unique to their field. This article will discuss these data, why they matter, and how AI can transform how you gather, analyze, and act on data.

Let’s get going!

What are Customer Insights in Contact Centers?

As a contact center, your primary focus is on helping people work through issues related to a software product or something similar. But you might find yourself wondering who these people are, what parts of the customer experience they’re stumbling over, which issues are being escalated to human agents and which are resolved by bots, etc.

If you knew these things, you would be able to notice patterns and start proactively fixing problems before they even arise. This is what customer insights is all about, and it can allow you to finetune your procedures, write clearer technical documentation, figure out the best place to use generative AI in your contact center, and much more.

What are the Major Types of Customer Insights?

Before we turn to a discussion of the specifics of customer insights, we’ll deal with the major kinds of customer insights there are. This will provide you with an overarching framework for thinking about this topic and where different approaches might fit in.

Speech and Text Data

Customer service and customer experience both tend to be language-heavy fields. When an agent works with a customer over the phone or via chat, a lot of natural language is generated, and that language can be analyzed. You might use a technique like sentiment analysis, for example, to gauge how frustrated customers are when they contact an agent. This will allow you to form a fuller picture of the people you’re helping, and discover ways of doing so more effectively.

Data on Customer Satisfaction

Contact centers exist to make customers happy as they try to use a product, and for this reason, it’s common practice to send out surveys when a customer interaction is done. When done correctly, the information contained in these surveys is incredibly valuable, and can let you know whether or not you’re improving over time, whether a specific approach to training or a new large language model is helping or hurting customer satisfaction, and more.

Predictive Analytics

Predictive analytics is a huge field, but it mostly boils down to using machine learning or something similar to predict the future based on what’s happened in the past. You might try to forecast average handle time (AHT) based on the time of the year, on the premise that when an issue arises has something to do with how long it will take to get it resolved.

To do this effectively you would need a fair amount of AHT data, along with the corresponding data about when the complaints were raised, and then you could fit a linear regression model on these two data streams. If you find that AHT reliably climbs during certain periods, you can have more agents on hand when required.

Data on Agent Performance

Like employees in any other kind of business, agents perform at different levels. Junior agents will likely take much longer to work through a thorny customer issue than more senior ones, of course, and the same could be said for agents with an extensive technical background versus those without the knowledge this background confers. Or, the same agent might excel at certain kinds of tasks but perform much worse on others.

Regardless, by gathering these data on how agents are performing you, as the manager, can figure out where weaknesses lie across all your teams. With this information, you’ll be able to strategize about how to address those weaknesses with coaching, additional education, a refresh of the standard operating procedures, or what have you.

Channel Analytics

These days, there are usually multiple ways for a customer to get in touch with your contact center, and they all have different dynamics. Sending a long email isn’t the same thing as talking on the phone, and both are distinct from reaching out on social media or talking to a bot. If you have analytics on specific channels, how customers use them, and what their experience was like, you can make decisions about what channels to prioritize.

What’s more, customers will often have interacted with your brand in the past through one or more of these channels. If you’ve been tracking those interactions, you can incorporate this context to personalize responses when they reach out to resolve an issue in the future, which can help boost customer satisfaction.

What Specific Metrics are Tracked for Customer Insights?

Now that we have a handle on what kind of customer insights there are, let’s talk about specific metrics that come up in contact centers!

First Contact Resolution (FCR)

The first contact resolution is the fraction of issues a contact center is able to resolve on the first try, i.e. the first time the customer reaches out. It’s sometimes also known as Right First Time (RFT), for this reason. Note that first contact resolution can apply to any channel, whereas first call resolution applies only when the customer contacts you over the phone. They have the same acronym but refer to two different metrics.

Average Handle Time (AHT)

The average handle time is one of the more important metrics contact centers track, and it refers to the mean length of time an agent spends on a task. This is not the same thing as how long the agent spends talking to a customer, and instead encompasses any work that goes on afterward as well.

Customer Satisfaction (CSAT)

The customer satisfaction score attempts to gauge how customers feel about your product and service. It’s common practice, to collect this information from many customers, then averaging them to get a broader picture of how your customers feel. The CSAT can give you a sense of whether customers are getting happier over time, whether certain products, issues, or agents make them happier than others, etc.

Call Abandon Rate (CAR)

The call abandon rate is the fraction of customers who end a call with an agent before their question has been answered. It can be affected by many things, including how long the customers have to wait on hold, whether they like the “hold” music you play, and similar sorts of factors. You should be aware that CAR doesn’t account for missed calls, lost calls, or dropped calls.

***

Data-driven contact centers track a lot of metrics, and these are just a sample. Nevertheless, they should convey a sense of what kinds of numbers a manager might want to examine.

How Can AI Help with Customer Insights?

And now, we come to the “main” event, a discussion of how artificial intelligence can help contact center managers gather and better utilize customer insights.

Natural Language Processing and Sentiment Analysis

An obvious place to begin is with natural language processing (NLP), which refers to a subfield in machine learning that uses various algorithms to parse (or generate) language.

There are many ways in which NLP can aid in finding customer insights. We’ve already mentioned sentiment analysis, which detects the overall emotional tenor of a piece of language. If you track sentiment over time, you’ll be able to see if you’re delivering more or less customer satisfaction.

You could even get slightly more sophisticated and pair sentiment analysis with something like named entity recognition, which extracts information about entities from language. This would allow you to e.g. know that a given customer is upset, and also that the name of a particular product kept coming up.

Classifying Different Kinds of Communication

For various reasons, contact centers keep transcripts and recordings of all the interactions they have with a customer. This means that they have access to a vast amount of textual information, but since it’s unstructured and messy it’s hard to know what to do with it.

Using any of several different ML-based classification techniques, a contact center manager could begin to tame this complexity. Suppose, for example, she wanted to have a high-level overview of why people are reaching out for support. With a good classification pipeline, she could start automating the processing of sorting communications into different categories, like “help logging in” or “canceling a subscription”.

With enough of this kind of information, she could start to spot trends and make decisions on that basis.

Statistical Analysis and A/B Testing

Finally, we’ll turn to statistical analysis. Above, we talked a lot about natural language processing and similar endeavors, but more than likely when people say “customer insights” they mean something like “statistical analysis”.

This is a huge field, so we’re going to illustrate its importance with an example focusing on churn. If you have a subscription-based business, you’ll have some customers who eventually leave, and this is known as “churn”. Churn analysis has sprung up to apply data science to understanding these customer decisions, in the hopes that you can resolve any underlying issues and positively impact the bottom line.

What kinds of questions would be addressed by churn analysis? Things like what kinds of customers are canceling (i.e. are they young or old, do they belong to a particular demographic, etc.), figuring out their reasons for doing so, using that to predict which similar questions might be in danger of churning soon, and thinking analytically about how to reduce churn.

And how does AI help? There now exist any number of AI tools that substantially automate the process of gathering and cleaning the relevant data, applying standard tests, making simple charts, and making your job of extracting customer insights much easier.

What AI Tools Can Be Used for Customer Insights?

By now you’re probably eager to try using AI for customer insights, but before you do that, let’s spend some talking about what you’d look for in a customer insights tool.

Performant and Reliable

Ideally, you want something that you can depend upon and that won’t drive you crazy with performance issues. A good customer insights tool will have many optimizations under the hood that make crunching numbers easy, and shouldn’t require you to have a computer science degree to set up.

Straightforward Integration Process

Modern contact centers work across a wide variety of channels, including emails, chat, social media, phone calls, and even more. Whatever AI-powered customer insights platform you go with should be able to seamlessly integrate with all of them.

Simple to Use

Finally, your preferred solution should be relatively easy to use. Quiq Insights, for example, makes it a breeze to create customizable funnels, do advanced filtering, see the surrounding context for different conversations, and much more.

Getting the Most Out of AI-Powered Customer Insights

Data is extremely important to the success or failure of modern businesses, and it’s getting more important all the time. Contact centers have long been forward-looking and eager to adopt new technologies, and the same must be true in our brave new data-powered world.

If you’d like a demo of Quiq Insights, reach out to see how we can help you streamline your operation while boosting customer satisfaction!

Request A Demo

LLM-Powered AI Assistants for Hotels – Ultimate Guide

Posted on January 11, 2024February 12, 2024 The Quiq Team

New technologies have always been disruptive, supercharging those firms that embrace it and requiring the others to adapt or be left behind.

With the rise of new approaches to AI, such as large language models, we can see this dynamic playing out again. One place where AI assistants could have a major impact is in the hotel industry.

In this piece, we’ll explore the various ways AI assistants can be used in hotels, and what that means for the hoteliers that keep these establishments running.

Let’s get going!

What is an AI Assistant?

The term “AI assistant” refers to any use of an algorithmic or machine-learning system to automate a part of your workflow. A relatively simple example would be the autocomplete found in almost all text-editing software today, while a much more complex example might involve stringing together multiple chain-of-thought prompts into an agent capable of managing your calendar.

There are a few major types of AI assistants. Near and dear to our hearts, of course, are chatbots that function in places like contact centers. These can be agent-facing or customer-facing, and can help with answering common questions, helping draft replies to customer inquiries, and automatically translating between many different natural languages.

Chatbots (and large language models more generally) can also be augmented to produce speech, giving rise to so-called “voice assistants”. These tend to work like other kinds of chatbots but have the added ability to actually vocalize their text, creating a much more authentic customer experience.

In a famous 2018 demo, Google Duplex was able to complete a phone call to a local hair salon to make a reservation. One remarkable thing about the AI assistant was how human it sounded – its speech even included “uh”s and “mm-hmm”s that made it almost indistinguishable from an actual person, at least over the phone and for short interactions.

Then, there are 3D avatars. These digital entities are crafted to look as human as possible, and are perfect for basic presentations, websites, games, and similar applications. Graphics technology has gotten astonishingly good over the past few decades and, in conjunction with the emergence of technologies like virtual reality and the metaverse, means that 3D avatars could play a major role in the contact centers of the future.

One thing to think about if you’re considering using AI assistants in a hotel or hospitality service is how specialized you want them to be. Although there is a significant effort underway to build general-purpose assistants that are able to do most of what a human assistant does, it remains true that your agents will do better if they’re fine-tuned on a particular domain. For the time being, you may want to focus on building an AI assistant that is targeted at providing excellent email replies, for example, or answering detailed questions about your product or service.

That being said, we recommend you check the Quiq blog often for updates on AI assistants; when there’s a breakthrough, we’ll deliver actionable news as soon as possible.

How Will AI Assistants Change Hotels?

Though the audience we speak to is largely comprised of people working in or managing contact centers, the truth is that there are many overlaps with those in the hospitality space. Since these are both customer-service and customer-oriented domains, insights around AI assistants almost always transfer over.

With that in mind, let’s dive in now to talk about how AI is poised to transform the way hotels function!

AI for Hotel Operations

Like most jobs, operating a hotel involves many tasks that require innovative thinking and improvisation, and many others that are repetitive, rote, and quotidian. Booking a guest, checking them in, making small changes to their itinerary, and so forth are in the latter category, and are precisely the sorts of things that AI assistants can help with.

In an earlier example, we saw that chatbots were already able to handle appointment booking five years ago, so it requires no great leap in imagination to see how slightly more powerful systems would be able to do this on a grander scale. If it soon becomes possible to offload much of the day-to-day of getting guests into their rooms to the machines, that will free up a great deal of human time and attention to go towards more valuable work.

It’s possible, of course, that this will lead to a dramatic reduction in the workforce needed to keep hotels running, but so far, the evidence points the other way; when large language models have been used in contact centers, the result has been more productivity (especially among junior agents), less burnout, and reduced turnover. We can’t say definitively that this will apply in hotel operations, but we also don’t see any reason to think that it wouldn’t.

AI for Managing Hotel Revenues

Another place that AI assistants can change hotels is in forecasting and boosting revenues. We think this will function mainly by making it possible to do far more fine-grained analyses of consumption patterns, inventory needs, etc.

Everyone knows that there are particular times of the year when vacation bookings surge, and others in which there are a relatively small number of bookings. But with the power of big data and sophisticated AI assistants, analysts will be able to do a much better job of predicting surges and declines. This means prices for rooms or other accommodations will be more fluid and dynamic, changing in near real-time in response to changes in demand and the personal preferences of guests. The ultimate effect will be an increase in revenue for hotels.

AI in Marketing and Customer Service

A similar line of argument holds for using AI assistants in marketing and customer service. Just as both hotels and guests are better served when we can build models that allow for predicting future bookings, everyone is better served when it becomes possible to create more bespoke, targeted marketing.

By utilizing data sources like past vacations, Google searches, and browser history, AI assistants will be able to meet potential clients where they’re at, offering them packages tailored to exactly what they want and need. This will not only mean increased revenue for the hotel, but far more satisfaction for the customers (who, after all, might have gotten an offer that they themselves didn’t realize they were looking for.)

If we were trying to find a common theme between this section and the last one, we might settle on “flexibility”. AI assistants will make it possible to flexibly adjust prices (raising them during peak demand and lowering them when bookings level off), flexibly tailor advertising to serve different kinds of customers, and flexibly respond to complaints, changes, etc.

Smart Buildings in Hotels

One particularly exciting area of research in AI centers around so-called “smart buildings”. By now, most of us have seen relatively “smart” thermostats that are able to learn your daily patterns and do things like turn the temperature up when you leave to save on the cooling bill while turning it down to your preferred setting as you’re heading home from work.

These are certainly worthwhile, but they barely even scratch the surface of what will be possible in the future. Imagine a room where every device is part of an internet-of-things, all wired up over a network to communicate with each other and gather data about how to serve your needs.

Your refrigerator would know when you’re running low on a few essentials and automatically place an order, a smart stove might be able to take verbal commands (“cook this chicken to 180 degrees, then power down and wait”) to make sure dinner is ready on time, a smoothie machine might be able to take in data about your blood glucose levels and make you a pre-workout drink specifically tailored to your requirements on that day, and so on.

Pretty much all of this would carry over to the hotel industry as well. As is usually the case there are real privacy concerns here, but assuming those challenges can be met, hotel guests may one day enjoy a level of service that is simply not possible with a staff comprised only of human beings.

Virtual Tours and Guest Experience

Earlier, we mentioned virtual reality in the context of 3D avatars that will enhance customer experience, but it can also be used to provide virtual tours. We’re already seeing applications of this technology in places like real estate, but there’s no reason at all that it couldn’t also be used to entice potential guests to visit different vacation spots.

When combined with flexible and intelligent AI assistants, this too could boost hotel revenues and better meet customer needs.

Using AI Assistants in Hotels

As part of the service industry, hoteliers work constantly to best meet their customers’ needs and, for this reason, they would do well to keep an eye on emerging technologies. Though many advances will have little to do with their core mission, others, like those related to AI assistants, will absolutely help them forecast future demands, provide personalized service, and automate routine parts of their daily jobs.

If all of this sounds fascinating to you, consider checking out the Quiq conversational CX platform. Our sophisticated offering utilizes large language models to help with tasks like question answering, following up with customers, and perfecting your marketing.

Schedule a demo with us to see how we can bring your hotel into the future!

Request A Demo

Explainability vs. Interpretability in Machine Learning Models

Posted on January 5, 2024November 15, 2024 J.R. Rettenmeyer

In recent months, we’ve produced a tremendous amount of content about generative AI – from high-level primers on what large language models are and how they work, to discussions of how they’re transforming contact centers, to deep dives on the cutting edge of generative technologies.

This amounts to thousands of words, much of it describing how models like ChatGPT were trained by having them e.g. iteratively predict what the final sentence of a paragraph will be given the previous sentences.

But for all that, there’s still a tremendous amount of uncertainty about the inner workings of advanced machine-learning systems. Even the people who build them generally don’t understand how particular functions emerge or what a particular circuit is doing.

It would be more accurate to describe these systems as having been grown, like an inconceivably complex garden. And just as you might have questions if your tomatoes started spitting out math proofs, it’s natural to wonder why generative models are behaving in the way that they are.

These questions are only going to become more important as these technologies are further integrated into contact centers, schools, law firms, medical clinics, and the economy in general.

If we use machine learning to decide who gets a loan, who is likely to have committed a crime, or to have open-ended conversations with our customers, it really matters that we know how all this works.

The two big approaches to this task are explainability and interpretability.

Comparing Explainability and Interpretability

Under normal conditions, this section would come at the very end of the article, after we’d gone through definitions of both these terms and illustrated how they work with copious examples.

We’re electing to include it at the beginning for a reason; while the machine-learning community does broadly agree on what these two terms mean, there’s a lot of confusion about which bucket different techniques go into.

Below, for example, we’ll discuss Shapley Additive Explanations (SHAP). Some sources file this as an approach to explainability, while others consider it a way of making a model more interpretable.

A major contributing factor to this overlap is the simple fact that the two concepts are very closely related. Once you can explain a fact you can probably interpret it, and a big part of interpretation is explanation.

Below, we’ve tried our best to make sense of these important research areas, and have tried to lay everything out in a way that will help you understand what’s going on.

With that caveat out of the way, let’s define explainability and interpretability.

Broadly, explainability means analyzing the behavior of a model to understand why a given course of action was taken. If you want to know why data point “a” was sorted into one category while data point “b” was sorted into another, you’d probably turn to one of the explainability techniques described below.

Interpretability means making features of a model, such as its weights or coefficients, comprehensible to humans. Linear regression models, for example, calculate sums of weighted input features, and interpretability would help you understand what exactly that means.

Here’s an analogy that might help: you probably know at least a little about how a train works. Understanding that it needs fuel to move, has to have tracks constructed a certain way to avoid crashing, and needs brakes in order to stop would all contribute to the interpretability of the train system.

But knowing which kind of fuel it requires and for what reason, why the tracks must be made out of a certain kind of material, and how exactly pulling a brake switch actually gets the train to stop are all facets of the explainability of the train system.

What is Explainability in Machine Learning?

In machine learning, explainability refers to any set of techniques that allow you to reason about the nuts and bolts of the underlying model. If you can at least vaguely follow how data are processed and how they impact the final model output, the system is explainable to that degree.

Before we turn to the techniques utilized in machine learning explainability, let’s talk at a philosophical level about the different types of explanations you might be looking for.

Different Types of Explanations

There are many approaches you might take to explain an opaque machine-learning model. Here are a few:

Explanations by text: One of the simplest ways of explaining a model is by reasoning about it with natural language. The better sorts of natural-language explanations will, of course, draw on some of the explainability techniques described below. You can also try to talk about a system logically, by i.e. describing it as calculating logical AND, OR, and NOT operations.
Explanations by visualization: For many kinds of models, visualization will help tremendously in increasing explainability. Support vector machines, for example, use a decision boundary to sort data points and this boundary can sometimes be visualized. For extremely complex datasets this may not be appropriate, but it’s usually worth at least trying.
Local explanations: There are whole classes of explanation techniques, like LIME, that operate by illustrating how a black-box model works in some particular region. In other words, rather than trying to parse the whole structure of a neural network, we zoom in on one part of it and say “This is what it’s doing right here.”

Approaches to Explainability in Machine Learning

Now that we’ve discussed the varieties of explanation, let’s get into the nitty-gritty of how explainability in machine learning works. There are a number of different explainability techniques, but we’re going to focus on two of the biggest: SHAP and LIME.

Shapley Additive Explanations (SHAP) are derived from game theory and are a commonly-used way of making models more explainable. The basic idea is that you’re trying to parcel out “credit” for the model’s outputs among its input features. In game theory, potential players can choose to enter a game, or not, and this is the first idea that is ported over to SHAP.

SHAP “values” are generally calculated by looking at how a model’s output changes based on different combinations of features. If a model has, say, 10 input features, you could look at the output of four of them, then see how that changes when you add a fifth.

By running this procedure for many different feature sets, you can understand how any given feature contributes to the model’s overall predictions.

Local Interpretable Model-Agnostic Explanation (LIME) is based on the idea that our best bet in understanding a complex model is to first narrow our focus to one part of it, then study a simpler model that captures its local behavior.

Let’s work through an example. Imagine that you’ve taken an enormous amount of housing data and fit a complex random forest model that’s able to predict the price of a house based on features like how old it is, how close it is to neighbors, etc.

LIME lets you figure out what the random forest is doing in a particular region, so you’d start by selecting one row of the data frame, which would contain both the input features for a house and its price. Then, you would “perturb” this sample, which means that for each of its features and its price, you’d sample from a distribution around that data point to create a new, perturbed dataset.

You would feed this perturbed dataset into your random forest model and get a new set of perturbed predictions. On this complete dataset, you’d then train a simple model, like a linear regression.

Linear regression is almost never as flexible and powerful as a random forest, but it does have one advantage: it comes with a bunch of coefficients that are fairly easy to interpret.

This LIME approach won’t tell you what the model is doing everywhere, but it will give you an idea of how the model is behaving in one particular place. If you do a few LIME runs, you can form a picture of how the model is functioning overall.

What is Interpretability in Machine Learning?

In machine learning, interpretability refers to a set of approaches that shed light on a model’s internal workings.

SHAP, LIME, and other explainability techniques can also be used for interpretability work. Rather than go over territory we’ve already covered, we’re going to spend this section focusing on an exciting new field of interpretability, called “mechanistic” interpretability.

Mechanistic Interpretability: A New Frontier

Mechanistic interpretability is defined as “the study of reverse-engineering neural networks”. Rather than examining subsets of input features to see how they impact a model’s output (as we do with SHAP) or training a more interpretable local model (as we do with LIME), mechanistic interpretability involves going directly for the goal of understanding what a trained neural network is really, truly doing.

It’s a very young field that so far has only tackled networks like GPT-2 – no one has yet figured out how GPT-4 functions – but already its results are remarkable. It will allow us to discover the actual algorithms being learned by large language models, which will give us a way to check them for bias and deceit, understand what they’re really capable of, and how to make them even better.

Why are Interpretability and Explainability Important?

Interpretability and explainability are both very important areas of ongoing research. Not so long ago (less than twenty years), neural networks were interesting systems that weren’t able to do a whole lot.

Today, they are feeding us recommendations for news, entertainment, driving cars, trading stocks, generating reams of content, and making decisions that affect people’s lives, forever.

This technology is having a huge and growing impact, and it’s no longer enough for us to have a fuzzy, high-level idea of what they’re doing.

We now know that they work, and with techniques like SHAP, LIME, mechanistic interpretability, etc., we can start to figure out why they work.

Final Thoughts on Interpretability vs. Explainability

In contact centers and elsewhere, large language models are changing the game. But though their power is evident, they remain a predominately empirical triumph.

The inner workings of large language models remain a mystery, one that has only recently begun to be unraveled through techniques like the ones we’ve discussed in this article.

Though it’s probably asking too much to expect contact center managers to become experts in machine learning interpretability or explainability, hopefully, this information will help you make good decisions about how you want to utilize generative AI.

And speaking of good decisions, if you do decide to move forward with deploying a large language model in your contact center, consider doing it through one of the most trusted names in conversational AI. In recent weeks, the Quiq platform has added several tools aimed at making your agents more efficient and your customers happier.

Set up a demo today to see how we can help you!

Request A Demo

AI Translation for Global Brands

Posted on December 19, 2023November 15, 2024 The Quiq Team

AI is already having a dramatic impact on various kinds of work, in places like contact centers, marketing agencies, research outfits, etc.

In this piece, we’re going to take a closer look at one specific arena where people are trying things (and always learning), and that’s AI translation. We’re going to look at how AI systems can help in translation tasks, and how that is helping companies build their global brands.

What is AI Translation?

AI translation, or “machine” translation as it’s also known, is more or less what it sounds like: the use of algorithms, computers, or software to translate from one natural language to another.

The chances are pretty good you’ve used AI translation in one form or another already. If you’ve ever relied on Google Translate to double-check your conjugation of a Spanish verb or to read the lyrics of the latest K-pop sensation in English, you know what it can accomplish.

But the mechanics and history of this technology are equally fascinating, and we’ll cover those now.

How Does AI Translation Work?

There are a few different approaches to AI translation, which broadly fall into three categories.

The first is known as rule-based machine translation, and it works by drawing on the linguistic structure that scaffolds all language. If you have any bad memories of trying to memorize Latin inflections or French grammatical rules, you’ll be more than familiar with these structures, but you may not know that they can also be used to build powerful, flexible AI translation systems.

Three ingredients are required to make rule-based machine translation function: a set of rules describing how the input language works, a set of rules describing how the output language works, and dictionaries translating words between the input and output languages.

It’s probably not hard to puzzle out the major difficulty with rule-based machine translation: it demands a great deal of human time and attention and is therefore very difficult to scale.

The second approach is known as statistical machine translation. Unlike rule-based machine translation, statistical machine translation tends to focus on higher-level groupings, known as “phrases”. Statistical models of the relevant languages are built through an analysis of two kinds of data: bilingual corpora containing both the input and output language, and monolingual corpora in the output language. Once these models have been developed, they can be used to automatically translate between the language pairs.

Finally, there’s neural machine translation. This is the most recently developed AI translation method, and it relies on deep neural networks trained to predict sequences of tokens. Neural machine translation rapidly supplanted statistical methods owing to its remarkable performance, but there can be edge cases where statistical translations do better. As is usually the case, of course, there are also hybrid systems that use both neural and statistical machine translation.

Building a Global Brand with AI

There are many ways in which the emerging technology of artificial intelligence can be used to build a global brand. In this section, we’ll walk through a few examples.

How can AI Translation Be Used to Build a Global Brand?

The first way AI translation can be used for building a global brand is that it helps with internal communications. If you have an international workforce – programmers in Eastern Europe, for example, or support staff in the Phillippines – keeping them all on the same page is even more important than usual. Coordinating your internal teams is hard enough when they’re all in the same building, to say nothing of when they’re spread out across the globe, over multiple time zones and multiple cultures.

The last thing you need is mistakes occurring because of a bad translation from English into their native languages, so getting high-quality AI translations is crucial for the internal cohesion required for building your global brand.

Of course, more or less the exact same case can be made for external communication. It would be awfully difficult to build a global brand that doesn’t routinely communicate with the public, through advertisements, various kinds of content or media, etc. And if the brand is global, most, or perhaps all, of this content will need to be translated somewhere along the way.

There are human beings who can handle this work, but with the rising sophistication of AI translators, it’s becoming possible to automate substantial parts of it. Besides the obvious cost savings, there are other benefits to AI translation. For one thing, AI is increasingly able to translate into what are called “low-resource” languages, i.e. languages for which there isn’t much training material and only small populations of native speakers. If AI is eventually able to translate for these populations, it could open up whole new markets that weren’t reachable before.

For another, it may soon be possible to do dynamic, on-the-fly translations of brand material. We’re not aware of any system that can 1) identify a person’s native language from snippets of their speech or other identifying features, and 2) instantly produce a translation of i.e. a billboard or poster in real-time, but it’s not at all beyond our imagination. If no one has built something that can do this yet, they surely will before too long.

Prompt Engineering for Building a Global Brand

One thing we haven’t touched on much so far is how generative AI will impact marketing. Generative AI is already being used to create drafts of web copy, mockups of new designs for buildings, products, and clothing, translating between languages, and much else besides.

This leads naturally to a discussion of prompt engineering, which refers to the careful sculpting of the linguistic instructions that are given to large generative AI models. These models are enormously complex artifacts whose inner workings are largely mysterious and whose outputs are hard to predict in advance. Skilled prompt engineers have put in the time required to develop a sense for how to phrase instructions just so, and they’re able to get remarkably high-quality output with much less effort than the rest of us.

If you’re thinking about using generative AI in building your global brand you’ll almost certainly need to be thinking prompt engineering, so be sure to check out Quiq’s blog for more in-depth discussions of this and related subjects.

How can AI Translation Benefit the Economy?

Throughout this piece, we’ve discussed various means by which AI translation can help build global brands. But you might still want to see some hard evidence of the economic benefits of machine translation.

Economists Erik Brynjolfsson, Xiang Hui, and Meng Liu conducted a study of how AI translation has actually impacted trade on an e-commerce platform. They found that “… the introduction of a machine translation system…had a significant effect on international trade on this platform, increasing export quantity by 17.5%.”

More specifically, they found evidence of “…a substantial reduction in buyers’ translation-related search costs due to the introduction of this system.” On the whole, their efforts support the conclusion that “… language barriers significantly hinder trade and that AI has already substantially improved overall economic efficiency.”

Though this is only one particular study on one particular mechanism, it’s not hard to see how it can apply more broadly. If more people can read your marketing material, it stands to reason that more people will buy your product, for example.

AI Translation and Global Brands

Global brands face many unique challenges: complex supply chains, distributed workforces, and the bewildering diversity of human language.

This last challenge is something that AI language translation can help with, as it’s already proving useful in boosting trade and exchange by reducing the friction involved in translation.

If you want to build a global brand and are keen to use conversational AI to do it, check out the Quiq platform. Our services include a variety of agent-facing and customer-facing tools, and make it easy to automate question-answering tasks, follow-ups with clients, and many other kinds of work involved in running a contact center. Schedule a demo with us today to see how we can help you build your brand!

Request A Demo

Top 5 Benefits of AI for Hospitality

Posted on December 6, 2023November 15, 2024 The Quiq Team

As an industry, hospitality is aimed squarely at meeting customer needs. Whether it’s a businesswoman staying in 5-star resorts or a mother of three getting a quiet weekend to herself, the job of the hospitality professionals they interact with is to anticipate what they want and make sure they get it.

As technologies like artificial intelligence become more powerful and pervasive, customer expectations will change. When that businesswoman books a hotel room, she’ll expect there to be a capable virtual assistant talking to her about a vacation spot; when that mother navigates the process of buying a ticket, she’ll expect to be interacting with a very high-quality chatbot, perhaps one that’s indistinguishable from an actual human being.

All of this means that the hospitality industry needs to be thinking about how it will be impacted by AI. It needs to consider what the benefits of AI for hospitality are, what limitations are faced by AI, and how it can be utilized effectively. That’s what we’re here to do today, so let’s get started.

Why is AI Important for Hospitality?

AI is important in hospitality for the same reason it’s important everywhere else: it’s poised to become a transformative technology, and just about every industry – especially those that involve a lot of time interacting through text – could be up-ended by it.

The businesses that emerge the strongest from this ongoing revolution will be those that successfully anticipate how large language models and similar tools change workflows, company setups, cost and pricing structures, etc.

With that in mind, let’s work through some of the ways in which AI is (or will) be used in hospitality.

How is AI Used in Hospitality?

There are many ways in which AI is used in hospitality, and in the sections that follow we’ll walk through a number of the most important ones.

Chatbots and Customer Service

Perhaps the most obvious place to begin is with chatbots and customer service more broadly. Customer-facing chatbots were an early application of natural language processing, and have gotten much better in the decades since. With ChatGPT and similar LLMs, they’re currently in the process of taking another major leap forward.

Now that we have models that can be fine-tuned to answer questions, summarize texts, and carry out open-ended interactions with human users, we expect to see them becoming more and more common in hospitality. Someday soon, it may be the case that most of the steps involved in booking a room or changing a flight happens entirely without human assistance of any kind.

This is especially compelling because we’ve gotten so good at making chatbots that are very deferential and polite (though as we make clear in the final section on “limitations”, this is not always the case.)

Virtual Assistants

AI virtual assistants are a generalization of the idea behind chatbots. Whereas chatbots can be trained to offload many parts of hospitality work, powerful virtual assistants will take this dynamic to the next level. Once we have better agents – systems able to take strings of actions in pursuit of a goal – many more parts of hospitality work will be outsourced to the machines.

What might this look like?

Well, we’ve already seen some tools that can do relatively simple tasks like “book a flight to Indonesia”, but they’re still not all that flexible. Imagine an AI virtual assistant able to handle all the subtleties and details involved in a task like “book a flight for ten executives to Indonesia, and book lodging near the conference center and near the water, too, then make reservations for a meal each night of the week, taking into account the following dietary restrictions.”

Work into building generative agents like this is still in its infancy, but it is nevertheless an active area of research. It’s hard to predict when we’ll have agents who can be trusted to do advanced work with minimal oversight, but once we do, it’ll really begin to change how the hospitality industry runs.

Sentiment Analysis

Sentiment analysis refers to an automated, algorithmic approach to classifying the overall vibe of a piece of text. “The food was great” is obviously positive sentiment, “the food was awful” is obviously negative sentiment, and then there are many subtler cases involving e.g. sarcasm.

The hospitality industry desperately needs tools able to perform sentiment analysis at scale. It helps them understand what clients like and dislike about particular services or locations, and can even help in predicting future demand. If, for example, there’s a bunch of positive sentiment around a concert being given in Indonesia, that indicates that there will probably be a spike in bookings there.

Boosting Revenues for Hospitality

People have long been interested in using AI to make money, whether that be from trading strategies generated by ChatGPT or from using AI to create ultra-targeted marketing campaigns.

All of this presents an enormous opportunity for the hospitality industry. Through a combination of predictive modeling, customer segmentation, sentiment analysis, and related techniques, it’ll become easier to forecast changes in demand, create much more responsive pricing models, and intelligently track inventory.

What this will ultimately mean is better revenues for hotels, event centers, and similar venues. You’ll be able to cross-sell or upsell based on a given client’s unique purchase history and interests, you’ll have fewer rooms go unoccupied, and you’ll be less likely to have clients who are dissatisfied by the fact tha you ran out of something.

Sustainability and Waste Management

An underappreciated way in which AI will benefit hospitality is by making sustainability easier. There are a few ways this could manifest.

One is by increasing energy efficiency. Most of you will already be familiar with currently-existing smart room technology, like thermostats that learn when you’re leaving and turn themselves up, thus lowering your power bill.

But there’s room for this to become much more far-ranging and powerful. If AI is put in charge of managing the HVAC system for an entire building, for example, it could lead to savings on the order of millions of dollars, while simultaneously making customers more comfortable during their stay.

And the same holds true for waste management. AI systems smart enough to discover when a trash can is full means that your cleaning staff won’t have to spend nearly as much time patrolling. They’ll be able to wait until they get a notification to handle the problem, gaining back many hours in their day that can be put towards higher-value work.

What are the Limitations of AI in Hospitality?

None of this is to suggest that there won’t also be drawbacks to using AI in hospitality. To prepare you for these challenges, we’ll spend the next few sections discussing how AI can fail, allowing you to be proactive in mitigating these downsides.

Impersonality in Customer Service

By properly fine-tuning a large language model, it’s possible to get text output that is remarkably polite and conversational. Still, throughout repeated or sustained interactions, the model can come to feel vaguely sterile.

Though it might in principle be hard to tell when you’re interacting with AI v.s. a human, the fact remains that models don’t actually have any empathy. They may say “I’m sorry that you had to deal with that…”, but they won’t truly know what frustration is like, and over time, a human is likely to begin picking up on that.

We can’t say for certain when models will be capable of expressing sympathy in a fully convincing way, but for the time being, you should probably incorporate systems that can flag conversations that are going off the rails so that a human customer service professional can intervene.

Toxic Output, Bias, and Abuse

As in the previous section, a lot of work has gone into finetuning models so that they don’t produce toxic, biased, or abusive language. Still, not all the kinks have been ironed out, and if a question is phrased in just the right way, it’s often possible to get past these safeguards. That means your models might unpredictably become insulting or snarky, which is a problem for a hospitality company.

As we’ve argued elsewhere, careful monitoring is one of the prices that have to be paid when managing an AI assistant. Since this technology is so new, we have at best a very vague idea of what kinds of prompts lead to what kinds of responses. So, you’ll simply have to diligently keep your eyes peeled for examples of model responses that are inappropriate, having a human take over if and when things are going poorly.

(Or, you can work with Quiq – our guardrails ensure none of this is a problem for enterprise hospitality businesses).

AI in Hospitality

New technologies have always changed the way industries operate, and that’s true for hospitality as well. From virtual assistants to chatbots to ultra-efficient waste management, AI offers many benefits (and many challenges) for hospitality.

If you want to explore using these tools in your hospitality enterprise but don’t know the first thing about hiring AI engineers, check out the Quiq conversational CX platform. We’ve built a proprietary large language model offering that makes it easy to incorporate chatbots and other technologies, without having to worry about what’s going on under the hood.

Schedule a demo with us today to find out how you can catch the AI wave!

Request A Demo

4 Benefits of Using AI Assistants in the Retail Industry

Posted on November 30, 2023November 15, 2024 Mark Kowal

Artificial intelligence (AI) has been making remarkable strides in recent months. Owing to the release of ChatGPT in November of 2022, a huge amount of attention has been on large language models, but the truth is, there have been similar breakthroughs in computer vision, reinforcement learning, robotics, and many other fields.

In this piece, we’re going to focus on how these advances might contribute specifically to the retail sector.

We’ll start with a broader overview of AI, then turn to how AI-based tools are making it easier to make targeted advertisements, personalized offers, hiring decisions, and other parts of retail substantially easier.

What are AI assistants in Retail?

Artificial intelligence is famously difficult to define precisely, but for our purposes, you can think of it as any attempt to get intelligent behavior from a machine. This could involve something relatively straightforward, like building a linear regression model to predict future demand for a product line, or something far more complex, like creating neural networks able to quickly spit out multiple ideas for a logo design based on a verbal description.

AI assistants are a little different and specifically require building agents capable of carrying out sequences of actions in the service of a goal. The field of AI is some 70 years old now and has been making remarkable strides over the past decade, but building robust agents remains a major challenge.

It’s anyone’s guess as to when we’ll have the kinds of agents that could successfully execute an order like “run this e-commerce store for me”, but there’s nevertheless been enough work for us to make a few comments about the state of the art.

What are the Ways of Building AI Assistants?

On its own, a model like ChatGPT can (sometimes) generate working code and (often) generate correct API calls. But as things stand, a human being still needs to utilize this code for it to do anything useful.

Efforts are underway to remedy this situation by making models able to use external tools. Auto-GPT, for example, combines an LLM and a separate bot that repeatedly queries it. Together, they can take high-level tasks and break them down into smaller, achievable steps, checking off each as it works toward achieving the overall objective.

AssistGPT and SuperAGI are similar endeavors, but they’re better able to handle “multimodal” tasks, i.e those that also involve manipulating images or sounds rather than just text.

The above is a fairly cursory examination of building AI agents, but it’s not difficult to see how the retail establishments of the future might use agents. You can imagine agents that track inventory and re-order crucial items when they get low, or that keep an eye on sales figures and create reports based on their findings (perhaps even using voice synthesis to actually deliver those reports), or creating customized marketing campaigns, generating their own text, images, and A/B tests to find the highest-performing strategies.

What are the Advantages of Using AI in Retail Business?

Now that we’ve talked a little bit about how AI and AI assistants can be used in retail, let’s spend some time talking about why you might want to do this in the first place. What, in other words, are the big advantages of using AI in retail?

1. Personalized Marketing with AI

People can’t buy your products if they don’t know what you’re selling, which is why marketing is such a big part of retail. For its part, marketing has long been a future-oriented business, interested in leveraging the latest research from psychology or economics on how people make buying decisions.

A kind of holy grail for marketing is making ultra-precise, bespoke marketing efforts that target specific individuals. The kind of messaging that would speak to a childless lawyer in a big city won’t resonate the same way with a suburban mother of five, and vice versa.

The problem, of course, is that there’s just no good way at present to do this at scale. Even if you had everything you needed to craft the ideal copy for both the lawyer and the mother, it’s exceedingly difficult to have human beings do this work and make sure it ends up in front of the appropriate audience.

AI could, in theory, remedy this situation. With the rise of social media, it has become possible to gather stupendous amounts of information about people, grouping them into precise and fine-grained market segments–and, with platforms like Facebook Ads, you can make really target advertisements for each of these segments.

AI can help with the initial analysis of this data, i.e. looking at how people in different occupations or parts of the country differ in their buying patterns. But with advanced prompt engineering and better LLMs, it could also help in actually writing the copy that induces people to buy your products or services.

And it doesn’t require much imagination to see how AI assistants could take over quite a lot of this process. Much of the required information is already available, meaning that an agent would “just” need to be able to build simple models of different customer segments, and then put together a prompt that generates text that speaks to each segment.

2. Personalized Offerings with AI

A related but distinct possibility is using AI assistants to create bespoke offerings. As with messaging, people will respond to different package deals; if you know how to put one together for each potential customer, there could be billions in profits waiting for you. Companies like Starbucks have been moving towards personalized offerings for a while, but AI will make it much easier for other retailers to jump on this trend.

We’ll illustrate how this might work with a fictional example. Let’s say you’re running a toy company, and you’re looking at data for Angela and Bob. Angela is an occasional customer, mostly making purchases around the holidays. When she created her account she indicated that she doesn’t have children, so you figure she’s probably buying toys for a niece or nephew. She’s not a great target for a personalized offer, unless perhaps it’s a generic 35% discount around Christmas time.

Bob, on the other hand, buys fresh trainsets from you on an almost weekly basis. He more than likely has a son or daughter who’s fascinated by toy machines, and you have customer-recommendation algorithms trained on many purchases indicating that parents who buy the trains also tend to buy certain Lego sets. So, next time Bob visits your site, your AI assistant can offer him a personalized discount on Lego sets.

Maybe he bites this time, maybe he doesn’t, but you can see how being able to dynamically create offerings like this would help you move inventory and boost individual customer satisfaction a great deal. AI can’t yet totally replace humans in this kind of process, but it can go a long way toward reducing the friction involved.

3. Smarter Pricing

The scenario we just walked through is part of a broader phenomenon of smart pricing. In economics, there’s a concept known as “price discrimination”, which involves charging a person roughly what they’re willing to pay for an item. There may be people who are interested in buying your book for $20, for example, but others who are only willing to pay $15 for it. If you had a way of changing the price to match what a potential buyer was willing to pay for it, you could make a lot more money (assuming that you’re always charging a price that at least covers printing and shipping costs).

The issue, of course, is that it’s very difficult to know what people will pay for something–but with more data and smarter AI tools, we can get closer. This will have the effect of simultaneously increasing your market (by bringing in people who weren’t quite willing to make a purchase at a higher price) and increasing your earnings (by facilitating many sales that otherwise wouldn’t have taken place).

More or less the same abilities will also help with inventory more generally. If you sell clothing you probably have a clearance rack for items that are out of season, but how much should you discount these items? Some people might be fine paying almost full price, while others might need to see a “60%” off sticker before moving forward. With AI, it’ll soon be possible to adjust such discounts in real-time to make sure you’re always doing brisk business.

4. AI and Smart Hiring

One place where AI has been making real inroads is in hiring. It seems like we can’t listen to any major podcast today without hearing about some hiring company that makes extensive use of natural language processing and similar tools to find the best employees for a given position.

Our prediction is that this trend will only continue. As AI becomes increasingly capable, eventually it will be better than any but the best hiring managers at picking out talent; retail establishments, therefore, will rely on it more and more to put together their sales force, design and engineering teams, etc.

Is it Worth Using AI in Retail?

Throughout this piece, we’ve sung the praises of AI in retail. But the truth is, there are still questions about how much sense it makes to leverage retail at the moment, given its expense and risks.

In this section, we’ll briefly go over some of the challenges of using AI in retail so you can have a fuller picture of how its advantages compare to its disadvantages, and thereby make a better decision for your situation.

The one that’s on everyone’s minds these days is the tendency of even powerful systems like ChatGPT to hallucinate incorrect information or to generate output that is biased or harmful. Finetuning and techniques like retrieval augmented generation can mitigate this somewhat, but you’ll still have to spend a lot of time monitoring and tinkering with the models to make sure that you don’t end up with a PR disaster on your hands.

Another major factor is the expense involved. Training a model on your own can cost millions of dollars, but even just hiring a team to manage an open-source model will likely set you back a fair bit (engineers aren’t cheap).

By far the safest and easiest way of testing out AI for retail is by using a white glove solution like the Quiq conversational CX platform. You can test out our customer-facing and agent-facing AI tools while leaving the technical details to us, and at far less expense than would be involved in hiring engineering talent.

Set up a demo with us to see what we can do for you.

Request A Demo

AI is Changing Retail

From computer-generated imagery to futuristic AI-based marketing plans, retail won’t be the same with the advent of AI. This will be especially true once we have robust AI assistants able to answer customer questions, help them find clothes that fit, and offer precision discounts and offerings tailored to each individual shopper.

If you don’t want to get left behind, you’ll need to begin exploring AI as soon as possible, and we can help you do that. Check out our product or find a time to talk with us, today!

AI in Retail: 5 Ways Retailers Are Using AI Assistants

Posted on November 21, 2023November 15, 2024 Mark Kowal

Businesses have always turned to the latest and greatest technology to better serve their customers, and retail is no different. From early credit card payment systems to the latest in online advertising, retailers know that they need to take advantage of new tools to boost their profits and keep shoppers happy.

These days, the thing that’s on everyone’s mind is artificial intelligence (AI). AI has had many, many definitions over the years, but in this article, we’ll mainly focus on the machine-learning and deep-learning systems that have captured the popular imagination. These include large language models, recommendation engines, basic AI assistants, etc.

In the world of AI in retail, you can broadly think of these systems as falling into one of two categories: “the ones that customers see”, and “the ones that customers don’t see.” In the former category, you’ll find innovations such as customer-facing chatbots and algorithms that offer hyper-personalized options based on shopping history. In the latter, you’ll find precision fraud detection systems and finely-tuned inventory management platforms, among other things.

We’ll cover each of these categories, in order. By the end of this piece, you’ll have a much better understanding of the ways retailers are using AI assistants and will be better able to think about how you want to use this technology in your retail establishment.

Let’s get going!

Using AI Assistants for Better Customer Experience

First, let’s start with AI that interacts directly with customers. The major ways in which AI is transforming the customer experience are through extreme levels of personalization, more “humanized” algorithms, and shopping assistants.

Personalization in Shopping and Recommendations

One of the most obvious ways of improving the customer experience is by tailoring that experience to each individual shopper. There’s just one problem: this is really difficult to do.

On the one hand, most of your customers will be new to you, people about whom you have very little information and whose preferences you have no good way of discovering. On the other, there are the basic limitations of your inventory. If you’re a brick-and-mortar establishment you have a set number of items you can display, and it’s going to be pretty difficult for you to choose them in a way that speaks to each new customer on a personal level.

For a number of reasons, AI has been changing this state of affairs for a while now, and holds the potential to change it much more in the years ahead.

A key part of this trend is recommendation engines, which have gotten very good over the past decade or so. If you’ve ever been surprised by YouTube’s ability to auto-generate a playlist that you really enjoyed, you’ve seen this in action.

Recommendation engines can only work well when there is a great deal of customer data for them to draw on. As more and more of our interactions, shopping, and general existence have begun to take place online, there has arisen a vast treasure trove of data to be analyzed. In some situations, recommendation engines can utilize decades of shopping experience, public comments, reviews, etc. in making their recommendations, which means a far more personalized shopping experience and an overall better customer experience.

What’s more, advances in AR and VR are making it possible to personalize even more of these experiences. There are platforms now that allow you to upload images of your home to see how different pieces of furniture will look, or to see how clothes fit you without the need to try them on first.

We expect that this will continue, especially when combined with smarter printing technology. Imagine getting a 3D-printed sofa made especially to fit in that tricky corner of your living room, or flipping through a physical magazine with advertisements that are tailored to each individual reader.

Humanizing the Machines

Next, we’ll talk about various techniques for making the algorithms and AI assistants we interact with more convincingly human. Admittedly, this isn’t terribly important at the present moment. But as more of our shopping and online activity comes to be mediated by AI, it’ll be important for them to sound empathic, supportive, and attuned to our emotions.

The two big ways this is being pursued at the moment are chatbots and voice AI.

Chatbots, of course, will probably be familiar to you already. ChatGPT is inarguably the most famous example, but you’ve no doubt interacted with many (much simpler) chatbots via online retailers or contact centers.

In the ancient past, chatbots were largely “rule-based”, meaning they were far less flexible and far less capable of passing as human. With the ascendancy of the deep learning paradigm, however, we now have chatbots that are able to tutor you in chemistry, translate between dozens of languages, help you write code, answer questions about company policies, and even file simple tickets for contact center agents.

Naturally, this same flexibility also means that retail managers must tread lightly. Chatbots are known to confidently hallucinate incorrect information, to become abusive, or to “help” people with malicious projects, like building weapons or computer viruses.

Even leaving aside the technical challenges of implementing a chatbot, you have to carefully monitor your chatbots to make sure they’re performing as expected.

Then, there’s voice-based AI. Computers have been synthesizing speech for many years, but it hasn’t been until recently that they’ve become really good at it. Though you can usually tell that a computer is speaking if you listen very carefully, it’s getting harder and harder all the time. We predict that, in the not-too-distant future, you’ll simply have no idea whether it’s a human or a machine on the other end of the line when you call to return an item or get store hours.

But computers have also gotten much better at the other side of voice-based AI, speech recognition. Software like otter.ai, for example, is astonishingly accurate when generating transcriptions of podcast episodes or conversations, even when unusual words are used.

Taken together, advances in both speech synthesis and speech recognition paint a very compelling picture of how the future of retail might unfold. You can imagine walking into a Barnes & Noble in the year 2035 and having a direct conversation with a smart speaker or AI assistant. You’ll tell it what books you’ve enjoyed in the past, it’ll query its recommendation system to find other books you might like, and it’ll speak to you in a voice that sounds just like a human’s.

You’ll be able to ask detailed questions about the different books’ content, and it’ll be able to provide summaries, discuss details with you, and engage in an unscripted, open-ended conversation. It’ll also learn more about you over time, so that eventually it’ll be as though you have a friend that you go shopping with whenever you buy new books, clothing, etc.

Shopping Assistants and AI Agents

So far, we’ve confined our conversation specifically to technologies like large language models and conversational AI. But one thing we haven’t spent much time on yet is the possibility of creating agents in the future.

An agent is a goal-directed entity, one able to take an instruction like “Make me a reservation at an Italian restaurant” and decompose the goal into discrete steps, performing each one until the task is completed.

With clever enough prompt engineering, you can sort of get agent-y behavior out of ChatGPT, but the truth is, the work of building advanced AI agents has only just begun. Tools like AutoGPT and LangChain have made a lot of progress, but we’re still a ways away from having agents able to reliably do complex tasks.

It’s not hard to see how different retail will be when that day arrives, however. Eventually, you may be outsourcing a lot of your shopping to AI assistants, who will make sure the office has all the pens it needs, you’ve got new science fiction to read, and you’re wearing the latest fashion. Your assistant might generate new patterns for t-shirts and have them custom-printed; if LLMs get good enough, they’ll be able to generate whole books and movies tuned to your specific tastes.

Using AI Assistants to Run A Safer, Leaner Operation

Now that we’ve covered the ways AI assistants will impact the things customers can see, let’s talk about how they’ll change the things customers don’t see.

There are lots of moving parts in running a retail establishment. If you’ve got ~1,000 items on display in the front, there are probably several thousand more items in a warehouse somewhere, and all of that has to be tracked. What’s more, there’s a constant process of replenishing your supply, staying on top of new trends, etc.

All of this will also be transformed by AI, and in the following sections, we’ll talk about a few ways in which this could happen.

Fraud Detection and Prevention

Fraud, unfortunately, is a huge part of modern life. There’s an entire industry of people buying and selling personal information for nefarious purposes, and it’s the responsibility of anyone trafficking in that information to put safeguards in place.

That includes a large number of retail establishments, which might keep data related to a customer’s purchases, their preferences, and (of course) their actual account and credit card numbers.

This isn’t the place to get into a protracted discussion of cybersecurity, but much of fraud detection relies on AI, so it’s fair game. Fraud detection techniques range from the fairly basic (flagging transactions that are much larger than usual or happen in an unusual geographic area) to the incredibly complex (training powerful reinforcement learning agents that constantly monitor network traffic).

As AI becomes more advanced, so will fraud detection. It’ll become progressively more difficult for criminals to steal data, and the world will be safer as a result. Of course, some of these techniques are also ones that can be used by the bad guys to defraud people, but that’s why so much effort is going into putting guardrails on new AI models.

Streamlining Inventory

Inventory management is an obvious place for optimization. Correctly forecasting what you’ll need and thereby reducing waste can have a huge impact on your bottom line, which is why there are complex branches of mathematics aimed at modeling these domains.

And – as you may have guessed – AI can help. With machine learning, extremely accurate forecasts can be made of future inventory requirements, and once better AI agents have been built, they may even be able to automate the process of ordering replacement materials.

Forward-looking retail managers will need to keep an eye on this space to fully utilize its potential.

AI Assistants and the Future of Retail

AI is changing a great many things. It’s already making contact center agents more effective and is being utilized by a wide variety of professionals, ranging from copywriters to computer programmers.

But the space is daunting, and there’s so much to learn about implementing, monitoring, and finetuning AI assistants that it’s hard to know where to start. One way to easily dip your toe in these deep waters is with the Quiq Conversational CX platform.

Our technology makes it easy to create customer-facing AI bots and similar tooling, which will allow you to see how AI can figure into your retail enterprise without hiring engineers and worrying about the technical details.

Schedule a demo with us today to get started!

Request A Demo

How Scoped AI Ensures Safety in Customer Service

Posted on November 21, 2023November 15, 2024 The Quiq Team

AI chat applications powered by Large Language Models (LLMs) have helped us reimagine what is possible in a new generation of AI computing.

Along with this excitement, there is also a fair share of concern and fear about the potential risks. Recent media coverage, such as this article from the New York Times, highlights how the safety measures of ChatGPT can be circumvented to produce harmful information.

To better understand the security risks of LLMs in customer service, it’s important we add some context and differentiate between “Broad AI” versus “Scoped AI”. In this article, we’ll discuss some of the tactics used to safely deploy scoped AI assistants in a customer service context.

Broad AI vs. Scoped AI: Understanding the Distinction

Scoped AI is designed to excel in a well-defined domain, guided and limited by a software layer that maintains its behavior within pre-set boundaries. This is in contrast to broad AI, which is designed to perform a wide range of tasks across virtually all domains.

Scoped AI and Broad AI answer questions fundamentally differently. With Scoped AI the LLM is not used to determine the answer, it is used to compose a response from the resources given to it. Conversely, answers to questions in Broad AI are determined by the LLM and cannot be verified.

Broad AI simply takes a user message and generates a response from the LLM; there is no control layer outside of the LLM itself. Scoped AI is a software layer that applies many steps to control the interaction and enforce safety measures applicable to your company.

In the following sections, we’ll dig into a more detailed explanation of the steps.

Ensuring the Safety of Scoped AI in Customer Service

1. Inbound Message Filtering

Your AI should perform a semantic similarity search to recognize in-scope vs out-of-scope messages from a customer. Malicious characters and known prompt injections should be identified and rejected with a static response. Inbound message filtering is an important step in limiting the surface area to the messages expected from your customers.

2. Classifying Scope

LLMs possess strong Natural Language Understanding and Reasoning skills (NLU & NLR). An AI assistant should perform a number of classifications. Common classifications include the topic, user type, sentiment, and sensitivity of the message. These classifications should be specific to your company and the jobs of your AI assistant. A data model and rules engine should be used to apply your safety controls.

3. Resource Integration

Once an inbound message is determined to be in-scope, company-approved resources should be retrieved for the LLM to consult. Common resources include knowledge articles, brand facts, product catalogs, buying guides, user-specific data, or defined conversational flows and steps.

Your AI assistant should support non-LLM-based interactions to securely authenticate the end user or access sensitive resources. Authenticating users and validating data are important safety measures in many conversational flows.

4. Verifying Responses

With a response in hand, the AI should verify the answer is in scope and on brand. Fact-checking and corroboration techniques should be used to ensure the information is derived from the resource material. An outbound message should never be delivered to a customer if it cannot be verified by the context your AI has on hand.

5. Outbound Message Filtering

Outbound message filtering tactics include: conducting prompt leakage analysis, semantic similarity checks, consulting keyword blacklists, and ensuring all links and contact information are in-scope of your company.

6. Safety Monitoring and Analysis

Deploying AI safely also requires that you have mechanisms to capture and retrospect on the completed conversations. Collecting user feedback, tracking resource usage, reviewing state changes, and clustering conversations should be available to help you identify and reinforce the safety measures of your AI.

In addition, performing full conversation classifications will also allow you to identify emerging topics, confirm resolution rates, produce safety reports, and understand the knowledge gaps of your AI.

Other Resources

At Quiq, we actively monitor and endorse the OWASP Top 10 for Large Language Model Applications. This guide is provided to help promote secure and reliable AI practices when working with LLMs. We recommend companies exploring LLMs and evaluating AI safety consult this list to help navigate their projects.

Final Thoughts

By safely leveraging LLM technology through a Scoped AI software layer, CX leaders can:

1. Elevate Customer Experience
2. Boost Operational Efficiency
3. Enhance Decision Making
4. Ensure Consistency and Compliance

Reach out to sales@quiq.com to learn how Quiq is helping companies improve customer satisfaction and drive efficiency at the same.

Generative AI Privacy Concerns – Your Guide to the Current Landscape

Posted on November 2, 2023November 15, 2024 J.R. Rettenmeyer

Generative AI, such as the large language model (LLM) ChatGPT and the image-generation tool DALL-E, are already having a major impact in places like marketing firms and contact centers. With their ability to create compelling blog posts, email blasts, YouTube thumbnails, and more, we believe they’re only going to become an increasingly integral part of the workflows of the future.

But for all their potential, there remain serious questions about the short- and long-term safety of generative AI. In this piece, we’re going to zero in on one particular constellation of dangers: those related to privacy.

We’ll begin with a brief overview of how generative AI works, then turn to various privacy concerns, and finish with a discussion of how these problems are being addressed.

Let’s dive in!

What is Generative AI (and How is it Trained)?

In the past, we’ve had plenty to say about how generative AI works under the hood. But many of the privacy implications of generative AI are tied directly to how these models are trained and how they generate output, so it’s worth briefly reviewing all of this theoretical material, for the sake of completeness and to furnish some much-needed context.

When an LLM is trained, it’s effectively fed huge amounts of text data, from the internet, from books, and similar sources of human-generated language. What it tries to do is predict how a sentence or paragraph will end based on the preceding words.

Let’s concretize this a bit. You probably already know some of these famous quotes:

“You must be the change you wish to see in the world.” (Mahatma Gandhi)
“You may say I’m a dreamer, but I’m not the only one.” (John Lennon)
“The only thing we have to fear is fear itself.” (Franklin D. Roosevelt)

What ChatGPT does is try to predict what the italicized parts say based on everything that comes before. It’ll read “You must be the change you”, for example, and then try to predict “wish to see in the world.”

When the training process begins the model will basically generate nonsense, but as it develops a better and better grasp of English (and other languages), it gradually becomes the remarkable artifact we know today.

Generative AI Privacy Concerns

From a privacy perspective, two things about this process might concern us:

The first is what data are fed into the model, and the second is what kinds of output the models might generate.

We’ll have more to say about each of these in the next section, then cover some broader concerns about copyright law.

Generative AI and Sensitive Data

First, there’s real concern over the possibility that generative AI models have been shown what is usually known as “Personally Identifiable Information” (PII). This is data such as your real name, your address, etc., and can also include things like health records that might not have your name but which can be used to figure out who you are.

The truth is, we only have limited visibility into the data that LLMs are shown during training. Given how much of the internet they’ve ingested, it’s a safe bet that at least some sensitive information has been included. And even if it hasn’t seen a particular piece of PII, there are myriad ways in which it can be exposed to it. You can imagine, for example, someone feeding customer data into an LLM to produce tailored content for them, not realizing that, in many cases, the model will have permanently incorporated that data into its internal structure.

There isn’t a great way at present to remove data from an LLM, and finetuning it in such a way that it never exposes that data in the future is something no one knows how to do yet.

The other major concern around sensitive data in the context of generative AI is that they will simply hallucinate allegations about people that damage their reputations and compromise their privacy. We’ve written before about the now-infamous case of law professor Jonathan Turley, who was falsely accused of sexually harassing several of his students by ChatGPT. We imagine that in the future there will be many more such fictitious scandals, potentially ones that are very damaging to the reputations of the accused.

Generative AI, Intellectual Property, and Copyright Law

There have also been questions about whether some of the data fed into ChatGPT and similar models might be in violation of copyright law. Earlier this year, in fact, a number of well-known writers leveled a suit against both OpenAI (the creators of ChatGPT) and Meta (the creators of LLaMa).

The suit claims that these teams trained their models on proprietary data contained in the works of authors like Michael Chabon, “without consent, without credit, and without compensation.” Similar charges have been made against Midjourney and Stability AI, both of whom have created AI-based image generation models.

These are rather thorny questions of jurisprudence. Though copyright law is a fairly sophisticated tool for dealing with various kinds of human conflicts, no one has ever had to deal with the implications of enormous AI models training on this much data. Only time will tell how the courts will ultimately decide, but if you’re using customer-facing or agent-facing AI tools in a place like a contact center, it’s at least worth being aware of the controversy.

Mitigating Privacy Risks from Generative AI

Now that we’ve elucidated the dimensions of the privacy concerns around generative AI, let’s spend some time talking about various efforts to address these concerns. We’ll focus primarily on data privacy laws, better norms around how data is collected and used, and the ways in which training can help.

Data Privacy Laws

First, and biggest, are attempts by different regulatory bodies to address data privacy issues with legislation. You’re probably already familiar with the European Union’s General Data Protection Regulation (GDPR), which puts numerous rules in place regarding how data can be gathered and used, including in advanced AI systems like LLMs.

Canada’s lesser-known Artificial Intelligence and Data Act (AIDA) mandates that anyone building a potentially disruptive AI system, like ChatGPT, must create guardrails to minimize the likelihood that their system will create biased or harmful output.

It’s not clear yet the extent to which laws like these will be able to achieve their objectives, but we expect that they’ll be just the opening salvo in a long string of legislative attempts to ameliorate the potential downsides of AI.

Robust Data Collection and Use Policies

There are also many things that private companies can do to address privacy concerns around data, without waiting for bureaucracies to catch up.

There’s too much to say about this topic to do it justice here, but we can make a few brief comments to guide you in your research.

One thing many companies are investing in is better anonymization techniques. Differential privacy, for example, is emerging as a promising way of simultaneously allowing for the collection of private data while anonymizing it enough to guard against LLMs accidentally exposing it at some point in the future.

Then, of course, there are myriad ways of securely storing data once you have it. This mostly boils down to keeping a tight lid on who is able to access private data – through i.e. encryption and a strict permissioning system – and carefully monitoring what they do with it once they access it.

Finally, it helps to be as public as possible about your data collection and use policies. Make sure they’re published somewhere that anyone can read them. Whenever possible, give users the ability to opt out of data collection, if that’s what they want to do.

Better Training for Those Building and Using Generative AI

The last piece of the puzzle is simply to train your workforce about data collection, data privacy, and data management. Sound laws and policies won’t do much good if the actual people who are interacting with private data don’t have a solid grasp of your expectations and protocols.

Because there are so many different ways in which companies collect and use data, there is no one-size-fits-all solution we can offer. But you might begin by sending your employees this article, as a way of opening up a broader conversation about your future data-privacy practices.

Data Privacy in the Age of Generative AI

In all its forms, generative AI is a remarkable technology that will change the world in many ways. Like the printing press, gunpowder, fire, and the wheel, these changes will be both good and bad.

The world will need to think carefully about how to get as many of the advantages out of generative AI as possible while minimizing its risks and dangers.

A good place to start with this is by focusing on data privacy. Because this is a relatively new problem, there’s a lot of work to be done in establishing legal frameworks, company policies, and best practices. But that also means there’s an enormous opportunity as well, to positively shape the long-term trajectory of AI technologies.

What is Sentiment Analysis? – Ultimate Guide

Posted on October 6, 2023March 1, 2024 The Quiq Team

A person only reaches out to a contact center when they’re having an issue. They can’t get a product to work the way they need it to, for example, or they’ve been locked out of their account.

The chances are high that they’re frustrated, angry, or otherwise in an emotionally-fraught state, and this is something contact center agents must understand and contend with.

The term “sentiment analysis” refers to the field of machine learning which focuses on developing algorithmic ways of detecting emotions in natural-language text, such as the messages exchanged between a customer and a contact center agent.

Making it easier to detect, classify, and prioritize messages on the basis of their sentiment is just one of many ways that technology is revolutionizing contact centers, and it’s the subject we’ll be addressing today.

Let’s get started!

What is Sentiment Analysis?

Sentiment analysis involves using various approaches to natural language processing to identify the overall “sentiment” of a piece of text.

Take these three examples:

“This restaurant is amazing. The wait staff were friendly, the food was top-notch, and we had a magnificent view of the famous New York skyline. Highly recommended.”
“Root canals are never fun, but it certainly doesn’t help when you have to deal with a dentist as unprofessional and rude as Dr. Thomas.”
“Toronto’s forecast for today is a high of 75 and a low of 61 degrees.”

Humans excel at detecting emotions, and it’s probably not hard for you to see that the first example is positive, the second is negative, and the third is neutral (depending on how you like your weather.)

There’s a greater challenge, however, in getting machines to make accurate classifications of this kind of data. How exactly that’s accomplished is the subject of the next section, but before we get to that, let’s talk about a few flavors of sentiment analysis.

What Types of Sentiment Analysis Are There?

It’s worth understanding the different approaches to sentiment analysis if you’re considering using it in your contact center.

Above, we provided an example of positive, negative, and neutral text. What we’re doing there is detecting the polarity of the text, and as you may have guessed, it’s possible to make much more fine-grained delineations of textual data.

Rather than simply detecting whether text is positive or negative, for example, we might instead use these categories: very positive, positive, neutral, negative, and very negative.

This would give us a better understanding of the message we’re looking at, and how it should be handled.

Instead of classifying text by its polarity, we might also use sentiment analysis to detect the emotions being communicated – rather than classifying a sentence as being “positive” or “negative”, in other words, we’d identify emotions like “anger” or “joy” contained in our textual data.

This is called “emotion detection” (appropriately enough), and it can be handled with long short-term memory (LSTM) or convolutional neural network (CNN) models.

Another, more granular approach to sentiment analysis is known as aspect-based sentiment analysis. It involves two basic steps: identifying “aspects” of a piece of text, then identifying the sentiment attached to each aspect.

Take the sentence “I love the zoo, but I hate the lines and the monkeys make fun of me.” It’s hard to assign an overall sentiment to the sentence – it’s generally positive, but there’s kind of a lot going on.

If we break out the “zoo”, “lines”, and “monkeys” aspects, however, we can see that there’s the positive sentiment attached to the zoo, and negative sentiment attached to the lines and the abusive monkeys.

Why is Sentiment Analysis Important?

It’s easy to see how aspect-based sentiment analysis would inform marketing efforts. With a good enough model, you’d be able to see precisely which parts of your offering your clients appreciate, and which parts they don’t. This would give you valuable information in crafting a strategy going forward.

This is true of sentiment analysis more broadly, and of emotion detection too.
You need to know what people are thinking, saying, and feeling about you and your company if you’re going to meet their needs well enough to make a profit.

Once upon a time, the only way to get these data was with focus groups and surveys. Those are still utilized, of course. But in the social media era, people are also not shy about sharing their opinions online, in forums, and similar outlets.

These oceans of words from an invaluable resource if you know how to mine them. When done correctly, sentiment analysis offers just the right set of tools for doing this at scale.

Challenges with Sentiment Analysis

Sentiment analysis confers many advantages, but it is not without its challenges. Most of these issues boil down to handling subtleties or ambiguities in language.

Consider a sentence like “This is a remarkable product, but still not worth it at that price.” Calling a product “remarkable” is a glowing endorsement, tempered somewhat by the claim that its price is set too high. Most basic sentiment classifiers would probably call this “positive”, but as you can see, there are important nuances.

Another issue is sarcasm.

Suppose we showed you a sentence like “This movie was just great, I loved spending three hours of my Sunday afternoon following a story that could’ve been told in twenty minutes.”

A sentiment analysis algorithm is likely going to pick up on “great” and “loved” when calling this sentence positive.

But, as humans, we know that these are backhanded compliments meant to communicate precisely the opposite message.

Machine-learning systems will also tend to struggle with idioms that we all find easy to parse, such as “Setting up my home security system was a piece of cake.” This is positive because “piece of cake” means something like “couldn’t have been easier”, but an algorithm may or may not pick up on that.

Finally, we’ll mention the fact that much of the text in product reviews will contain useful information that doesn’t fit easily into a “sentiment” bucket. Take a sentence like “The new iPhone is smaller than the new Android.” This is just a bare statement of physical facts, and whether it counts as positive or negative depends a lot on what a given customer is looking for.

There are various ways of trying to ameliorate these issues, most of which are outside the scope of this article. For now, we’ll just note that sentiment analysis needs to be approached carefully if you want to glean an accurate picture of how people feel about your offering from their textual reviews. So long as you’re diligent about inspecting the data you show the system and are cautious in how you interpret the results, you’ll probably be fine.

How Does Sentiment Analysis Work?

Now that we’ve laid out a definition of sentiment analysis, talked through a few examples, and made it clear why it’s so important, let’s discuss the nuts and bolts of how it works.

Sentiment analysis begins where all data science and machine learning projects begin: with data. Because sentiment analysis is based on textual data, you’ll need to utilize various techniques for preprocessing NLP data. Specifically, you’ll need to:

Tokenize the data by breaking sentences up into individual units an algorithm can process;
Use either stemming or lemmatization to turn words into their root form, i.e. by turning “ran” into “run”;
Filter out stop words like “the” or “as”, because they don’t add much to the text data.

Once that’s done, there are two basic approaches to sentiment analysis. The first is known as “rule-based” analysis. It involves taking your preprocessed textual data and comparing it against a pre-defined lexicon of words that have been tagged for sentiment.

If the word “happy” appears in your text it’ll be labeled “positive”, for example, and if the word “difficult” appears in your text it’ll be labeled “negative.”

(Rules-based sentiment analysis is more nuanced than what we’ve indicated here, but this is the basic idea.)

The second approach is based on machine learning. A sentiment analysis algorithm will be shown many examples of labeled sentiment data, from which it will learn a pattern that can be applied to new data the algorithm has never seen before.

Of course, there are tradeoffs to both approaches. The rules-based approach is relatively straightforward, but is unlikely to be able to handle the sorts of subtleties that a really good machine-learning system can parse.

Though machine learning is more powerful, however, it’ll only be as good as the training data it has been given; what’s more, if you’ve built some monstrous deep neural network, it might fail in mysterious ways or otherwise be hard to understand.

Supercharge Your Contact Center with Generative AI

Like used car salesmen or college history teachers, contact center managers need to understand the ways in which technology will change their business.

Machine learning is one such profoundly-impactful technology, and it can be used to automatically sort incoming messages by sentiment or priority and generally make your agents more effective.

Realizing this potential could be as difficult as hiring a team of expensive engineers and doing everything in-house, or as easy as getting in touch with us to see how we can integrate the Quiq conversational AI platform into your company.

If you want to get started quickly without spending a fortune, you won’t find a better option than Quiq.

Request A Demo

How Large Language Models Have Evolved

Posted on October 4, 2023December 11, 2024 The Quiq Team

In late 2022, large language models (LLMs) exploded into public awareness almost overnight. But like most overnight sensations, the history of large language models is long, fascinating, and informative.

In this piece, we’ll trace the deep evolution of language models and use this as a lens into how they can change your contact center today–and in the future.

Let’s get started!

A Brief History of Artificial Intelligence Development

The human fascination with building artificial beings capable of thought and action goes back a long way. Writing in roughly the 8th century BCE, Homer recounted tales of the Greek god Hephaestus outsourcing repetitive manual tasks to automated bellows and working alongside robot-like “attendants” that were “…golden, and in appearance like living young women.”

Some 500 years later, mathematicians in Alexandria would produce treatises on creating mechanical servants and various kinds of automata. Heron wrote a technical manual for producing a mechanical shrine and an automated theater whose figurines could stage a full tragic play.

Nor is it only ancient Greece that tells similar tales. Jewish legends speak of the Golem, a being made of clay and imbued with life and agency through language. The word “abracadabra”, in fact, comes from the Aramaic phrase “avra k’davra,” which translates to “I create as I speak.”

Through the ages, these old ideas have found new expression in stories such as “The Sorcerer’s Apprentice,” Mary Shelley’s “Frankenstein,” and Karel Čapek’s “R.U.R.,” a science fiction play that features the first recorded use of the word “robot.”

From Science Fiction to Science Fact

But they remained purely fiction until the early 20th Century – a pivotal moment in the history of LLMs – when advances in the theory of computation and the development of primitive computers began to offer a path to building intelligent systems.

Arguably, this really began in earnest with the 1950 publication of Alan Turing’s “Computing Machinery and Intelligence” – in which he proposed the famous “Turing test” – and with the 1956 Dartmouth conference on AI, organized by luminaries John McCarthy and Marvin Minsky.

People began taking AI seriously. Over the next ~50 years in the evolution of large language models, there were numerous periods of hype and exuberance in which major advances were made and long “AI winters” in which funding dried up, and little was accomplished.

Three advances acted to really bring LLMs into their own: the development of neural networks, the deep learning revolution, and the rise of big data. These are important for understanding the history of large language models, so it’s to these that we now turn.

Neural Networks and the Deep Learning Revolution

Walter Pitts and Warren McCulloch laid the groundwork for the eventual evolution of language models in the early 1940s. Inspired by the burgeoning study of the human brain, they wondered if it would be possible to build an artificial neuron with some of the same basic properties as a biological one.

They were successful, though several other breakthroughs would be required before artificial neurons could be arranged into systems capable of doing useful work. One such breakthrough was the discovery of backpropagation in 1960, the basic algorithm still used to train deep learning systems.

It wasn’t until 1985, however, that David Rumelhart, Ronald Williams, and Geoff Hinton used backpropagation in neural networks; in 1989, this allowed Yann LeCun to train such a network to recognize handwritten digits.

Ultimately, it would be these deep neural networks (DNNs) that would emerge from the history of LLMs as the dominant paradigm, but for completeness, we should briefly mention some of the methods that it replaced.

One was known as “rule-based approaches,” and it was exactly what it sounded like. Early AI assistants would be programmed directly with grammatical rules, which were used to parse text and craft responses. This was just as limiting as you’d imagine, and the approach is rarely seen today except in the most straightforward of cases.

Then, there were statistical language models, which bear at least a passing resemblance to the behemoth LLMs that came later. These models try to predict the probability of word n given the n-1 words that came before. If you read our deep dive on LLMs, this will sound familiar, though it was not at all as powerful and flexible as what’s available today.

There were others that are beyond the scope of this treatment, but the key takeaway is that gargantuan neural networks ended up winning the day.

To close this section out, we’ll mention a handful of architectural improvements that came out of this period and would play a crucial role in the evolution of language models. We’ll focus on two in particular: transformers and word vector embeddings.

If you’ve investigated how LLMs work, you’ve probably heard both terms. Transformers are famously intricate, but the basic idea is that they creatively combined elements of predecessor architectures to ameliorate the problems those approaches faced. Specifically, they can use self-attention to selectively attend to key pieces of information in text, allowing them to render higher-fidelity translations and higher-quality text generations.

Word vector embeddings are numerical representations of words that capture underlying semantic information. When interacting with ChatGPT, it can be easy to forget that computers don’t actually understand language, they understand numbers. A word vector embedding is an array of numbers generated with one of several different algorithms, with similar words having similar embeddings. LLMs can process these embeddings to learn enormous statistical patterns in unstructured linguistic data, then use those patterns to generate their own outputs.

All of this research went into making the productive neural networks that are currently changing the nature of work in places like contact centers. The last missing piece was data, which we’ll cover in the next section.

The Big Data Era

Neural networks and deep-learning applications tend to be extremely data-hungry, and access to quality training data has always been a major bottleneck. In 2009 Stanford’s Fei-Fei Li sought to change this by releasing Imagenet, a database of over 14 million labeled images that could be used for free by researchers. The increase in available data, together with substantial improvements in computer hardware like graphical processing units (GPUs), meant that at long last the promise of deep learning could begin to be fulfilled.

And it was. In 2011, a convolutional neural network called “AlexNet” won multiple international competitions for image recognition, IBM’s Watson system beat several Jeopardy! all-stars in a real game, and Apple launched Siri. Amazon’s Alexa followed in 2014, and from 2015 to 2017 DeepMind’s AlphaGo shocked the world by utterly dominating the best human Go players.

All of this set the stage for the rise of LLMs just four short years later.

Where are we Now in the Evolution of Large Language Models?

Now that we’ve discussed this history, we’re well-placed to understand why LLMs and generative AI have ignited so much controversy. People have been mulling over the promise (and peril) of thinking machines for literally thousands of years, and it looks like they might finally be here.

But what, exactly, has people so excited? What is it that advanced AI tools are doing that has captured the popular imagination? In the following sections, we’ll talk about the astonishing (and astonishingly rapid) improvements seen in language models in recent memory.

Getting To Human-Level

One of the more surprising things about LLMs such as ChatGPT is just how good they are at so many different things. LLMs are trained by having them take samples of the text data they’re given, and then trying to predict what words come next given the words that came before.

Modern LLMs can do this incredibly well, but what is remarkable is just how far this gets you. People are using generative AI to help them write poems, business plans, and code, create recipes based on the ingredients in their fridges, and answer customer questions.

What is Emergence in Language Models?

Perhaps even more interesting, however, is the phenomenon of emergence in language models. When researchers tested LLMs on a wide variety of tasks meant to be especially challenging to these models – things like identifying a movie given a string of emojis or finding legal chess moves – they found that in about 5% of tasks, there is a sudden, sharp increase in ability on a given task once a model reaches a certain size.

At present, it’s not really clear how we should think about emergence. One hypothesis for emergence is that a big enough model is able to learn some general piece of knowledge not attainable by a smaller sibling, while another, more prosaic one is that it’s a relatively straightforward consequence of the model’s internal statistical machinery.

What’s more, it’s difficult to pin down the conditions required for emergence in language models. Though it generally appears to be a function of model size, there are cases in which the same abilities can be achieved with smaller models, or with models trained on very high-quality data, and emergence shows up at different scales for different models and tasks.

Whatever ends up being the case, it’s clear that this is a promising direction for future research. Much more work needs to be done to understand how precisely LLMs accomplish what they accomplish. This will not only redound upon the question of emergence, it will also inform the ongoing efforts to make language models safer and less biased.

LLM Agents

One of the bigger frontiers in LLM research is the creation of agents. ChatGPT and similar platforms can generate API calls and functioning code, but humans still need to copy and paste the code to actually do anything with it.

Agents are meant to get around this limitation. Auto-GPT, for example, pairs an underlying LLM with a “bot” that takes high-level tasks, breaks them down into tasks an LLM can solve, and stitches together those solutions.

This work is still in its infancy, but it continues to be very promising.

Multimodal Models

Another development worth mentioning is the rise of multi-modality. A model is “multi-modal” when it can process more than one kind of information, like images and text.

LLMs are staggeringly good at producing coherent language, and image models could do the same thing with images, but now a lot of time and effort is being spent on combining these two kinds of functionality.

The result has been models able to find specific sections of lengthy videos, generate images to accompany textual explanations, and create their own incredible videos from short, simple prompts.

It’s too early to tell what this will mean, but it’s already impacting branding, marketing, and related domains.

What’s Next For Large Language Models?

As with so many things, the meteoric rise of LLMs was presaged by decades of technical work and thousands of years of thought and speculation. In just a few short years, it has become the strategic centerpiece for contact centers the world over.

If you want to get in on the action, you could start by learning more about how Quiq builds customer-facing AI assistants using LLMs. This will provide the context you need to make the wisest decision about deploying this remarkable technology.

4 Benefits of Using Generative AI to Improve Customer Experiences

Posted on September 27, 2023November 15, 2024 The Quiq Team

Generative AI has captured the popular imagination and is already changing the way contact centers work.

One area in which it has enormous potential is also one that tends to be top of mind for contact center managers: customer experience.

In this piece, we’re going to briefly outline what generative AI is, then spend the rest of our time talking about how generative AI benefits can improve customer experience with personalized responses, endless real-time support, and much more.

What is Generative AI?

As you may have puzzled out from the name, “generative AI” refers to a constellation of different deep learning models used to dynamically generate output. This distinguishes them from other classes of models, which might be used to predict returns on Bitcoin, make product recommendations, or translate between languages.

The most famous example of generative AI is, of course, the large language model ChatGPT. After being trained on staggering amounts of textual data, it’s now able to generate extremely compelling output, much of which is hard to distinguish from actual human-generated writing.

Its success has inspired a panoply of competitor models from leading players in the space, including companies like Anthropic, Meta, and Google.

As it turns out, the basic approach underlying generative AI can be utilized in many other domains as well. After natural language, probably the second most popular way to use generative AI is to make images. DALL-E, MidJourney, and Stable Diffusion have proven remarkably adept at producing realistic images from simple prompts, and just the past week, Fable Studios unveiled their “Showrunner” AI, able to generate an entire episode of South Park.

But even this is barely scratching the surface, as researchers are also training generative models to create music, design new proteins and materials, and even carry out complex chains of tasks.

What is Customer Experience?

In the broadest possible terms, “customer experience” refers to the subjective impressions that your potential and current customers have as they interact with your company.

These impressions can be impacted by almost anything, including the colors and font of your website, how easy it is to find e.g. contact information, and how polite your contact center agents are in resolving a customer issue.

Customer experience will also be impacted by which segment a given customer falls into. Power users of your product might appreciate a bevy of new features, whereas casual users might find them disorienting.

Contact center managers must bear all of this in mind as they consider how best to leverage generative AI. In the quest to adopt a shiny new technology everyone is excited about, it can be easy to lose track of what matters most: how your actual customers feel about you.

Be sure to track metrics related to customer experience and customer satisfaction as you begin deploying large language models into your contact centers.

How is Generative AI For Customer Experience Being Used?

There are many ways in which generative AI is impacting customer experience in places like contact centers, which we’ll detail in the sections below.

Personalized Customer Interactions

Machine learning has a long track record of personalizing content. Netflix, take to a famous example, will uncover patterns in the shows you like to watch, and will use algorithms to suggest content that checks similar boxes.

Generative AI, and tools like the Quiq conversational AI platform that utilize it, are taking this approach to a whole new level.

Once upon a time, it was only a human being that could read a customer’s profile and carefully incorporate the relevant information into a reply. Today, a properly fine-tuned generative language model can do this almost instantaneously, and at scale.

From the perspective of a contact center manager who is concerned with customer experience, this is an enormous development. Besides the fact that prior generations of language models simply weren’t flexible enough to have personalized customer interactions, their language also tended to have an “artificial” feel. While today’s models can’t yet replace the all-elusive human touch, they can do a lot to add make your agents far more effective in adapting their conversations to the appropriate context.

Better Understanding Your Customers and Their Journies

Marketers, designers, and customer experience professionals have always been data enthusiasts. Long before we had modern cloud computing and electronic databases, detailed information on potential clients, customer segments, and market trends used to be printed out on dead treads, where it was guarded closely. With better data comes more targeted advertising, a more granular appreciation for how customers use your product and why they stop using it, and their broader motivations.

There are a few different ways in which generative AI can be used in this capacity. One of the more promising is by generating customer journeys that can be studied and mined for insight.

When you begin thinking about ways to improve your product, you need to get into your customers’ heads. You need to know the problems they’re solving, the tools they’ve already tried, and their major pain points. These are all things that some clever prompt engineering can elicit from ChatGPT.

We took a shot at generating such content for a fictional network-monitoring enterprise SaaS tool, and this was the result:

While these responses are fairly generic [1], notice that they do single out a number of really important details. These machine-generated journal entries bemoan how unintuitive a lot of monitoring tools are, how they’re not customizable, how they’re exceedingly difficult to set up, and how their endless false alarms are stretching the security teams thin.

It’s important to note that ChatGPT is not soon going to obviate your need to talk to real, flesh-and-blood users. Still, when combined with actual testimony, they can be a valuable aid in prioritizing your contact center’s work and alerting you to potential product issues you should be prepared to address.

Round-the-clock Customer Service

As science fiction movies never tire of pointing out, the big downside of fighting a robot army is that machines never need to eat, sleep, or rest. We’re not sure how long we have until the LLMs will rise up and wage war on humanity, but in the meantime, these are properties that you can put to use in your contact center.

With the power of generative AI, you can answer basic queries and resolve simple issues pretty much whenever they happen (which will probably be all the time), leaving your carbon-based contact center agents to answer the harder questions when they punch the clock in the morning after a good night’s sleep.

Enhancing Multilingual Support

Machine translation was one of the earliest use cases for neural networks and machine learning in general, and it continues to be an important function today. While ChatGPT was noticeably very good at multilingual translation right from the start, you may be surprised to know that it actually outperforms alternatives like Google Translate.

If your product doesn’t currently have a diverse global user base speaking many languages, it hopefully will soon, at the means you should start thinking about multilingual support. Not only will this boost table stakes metrics like average handling time and resolutions per hour, it’ll also contribute to the more ineffable “customer satisfaction.” Nothing says “we care about making your experience with us a good one” like patiently walking a customer through a thorny technical issue in their native tongue.

Things to Watch Out For

Of course, for all the benefits that come from using generative AI for customer experience, it’s not all upside. There are downsides and issues that you’ll want to be aware of.

A big one is the tendency of large language models to hallucinate information. If you ask it for a list of articles to read about fungal computing (which is a real thing whose existence we discovered yesterday), it’s likely to generate a list that contains a mix of real and fake articles.

And because it’ll do so with great confidence and no formatting errors, you might be inclined to simply take its list at face value without double-checking it.

Remember, LLMs are tools, not replacements for your agents. They need to be working with generative AI, checking its output, and incorporating it when and where appropriate.

There’s a wider danger that you will fail to use generative AI in the way that’s best suited to your organization. If you’re running a bespoke LLM trained on your company’s data, for example, you should constantly be feeding it new interactions as part of its fine-tuning, so that it gets better over time.

And speaking of getting better, sometimes machine learning models don’t get better over time. Owing to factors like changes in the underlying data, model performance can sometimes get worse over time. You’ll need a way of assessing the quality of the text generated by a large language model, along with a way of consistently monitoring it.

What are the Benefits of Generative AI for Customer Experience?

The reason that people are so excited over the potential of using generative AI for customer experience is because there’s so much upside. Once you’ve got your model infrastructure set up, you’ll be able to answer customer questions at all times of the day or night, in any of a dozen languages, and with a personalization that was once only possible with an army of contact center agents.

But if you’re a contact center manager with a lot to think about, you probably don’t want to spend a bunch of time hiring an engineering team to get everything running smoothly. And, with Quiq, you don’t have to – you can leverage generative AI to supercharge your customer experience while leaving the technical details to us!

Schedule a demo to find out how we can bring this bleeding-edge technology into your contact center, without worrying about the nuts and bolts.

Footnotes
[1] It’s worth pointing out that we spent no time crafting the prompt, which was really basic: “I’m a product manager at a company building an enterprise SAAS tool that makes it easier to monitor system breaches and issues. Could you write me 2-3 journal entries from my target customer? I want to know more about the problems they’re trying to solve, their pain points, and why the products they’ve already tried are not working well.” With a little effort, you could probably get more specific complaints and more usable material.

Contact Center Managers: What Do LLMs Mean For You?

Posted on August 3, 2023November 15, 2024 Michael Hartsog

Whether it’s quantum computing, the blockchain, or generative AI, whenever a promising new technology emerges, forward-thinking people begin looking for a way to use it.

And this is a completely healthy response. It’s through innovation that the world moves forward, but great ideas don’t mean much if there aren’t people like contact center managers who use them to take their operations to the next level.

Today, we’re going to talk about what large language models (LLMs) like ChatGPT mean for contact centers. After briefly reviewing how LLMs work we’ll discuss the way they’re being used in contact centers, how those centers are changing as a result, and some things that contact center managers need to look out for when utilizing generative AI.

What are Large Language Models?

As their name suggests, LLMs are large, they’re focused on language, and they’re machine-learning models.

It’s our view that the best way to tackle these three properties is in reverse order, so we’ll start with the fact that LLMs are enormous neural networks trained via self-supervised learning. These neural networks effectively learn a staggeringly complex function that captures the statistical properties of human language well enough for them to generate their own.

Speaking of human language, LLMs like ChatGPT are pre-trained generative models focused on learning from and creating text. This distinguishes them from other kinds of generative AI, which might be focused on images, videos, speech, music, and proteins (yes, really.)

Finally, LLMs are really big. As with other terms like “big data” no one has a hard-and-fast rule for figuring out when you’ve gone from “language model” to “large language model” – but with billions of internal parameters, it’s safe to say that an LLM is a few orders of magnitude bigger than anything you’re likely to build outside of a world-class engineering team.

How can Large Language Models be Used in Contact Centers?

Since they’re so good at parsing and creating natural language, LLMs are an obvious choice for enterprises where there’s a lot of back-and-forth text exchanged, perhaps while, say, resolving issues or answering questions.

And for this reason, LLMs are already being used by contact center managers to make their agents more productive (more on this shortly).

To be more concrete, we turned up a few specific places where LLMs can be leveraged by contact center managers most effectively.

Answering questions: Even with world-class documentation, there will inevitably be customers who are having an issue they want help with. Though ChatGPT won’t be able to answer every such question, it can handle a lot of them, especially if you’ve fine-tuned it on your documentation.

Streamlining onboarding: For more or less the same reason, ChatGPT can help you onboard new hires. Employees learning the ropes will also be confused about parts of your technology and your process, and ChatGPT can help them find what they need more quickly.

Summarizing emails and articles: It might be possible for a team of five to be intimately familiar with what everyone else is doing, but any more than this and there will inevitably be things happening that are beyond their purview. By summarizing articles, tickets, email or Slack threads, etc., ChatGPT can help everyone stay reasonably up-to-date without having to devote hours every day to reading.

Issue prioritization: Not every customer question or complaint is equally important, and issues have to be prioritized before being handed off to contact center agents. ChatGPT can aid in this process, especially if it’s part of a broader machine-learning pipeline built for this kind of classification.

Translation: If you’re lucky enough to have a global audience, there will almost certainly be users who don’t have a firm grasp of English. Though there are tools like Google Translate that do a great job of handling translation tasks, ChatGPT often does an even better job.

What are Large Language Models for Customer Service?

Large language models are ideally suited for tasks that involve a great deal of working with text. Because contact center agents spend so much time answering questions and resolving customer issues, LLMs are a technology that can make them far more productive. ChatGPT excels at tasks like question answering, summarization, and language translation, which is why they’re already changing the way contact centers function.

How is Generative AI Changing Contact Centers?

The fear that advances in AI will lead to a decrease in employment among inferior human workers has a long and storied pedigree. Still, thus far the march of technological progress has tended to increase the number (and remuneration) of available jobs on the market.

Far from rendering human analysts obsolete, personal computers are now a major and growing source of new work (though, we confess, much less of it is happening on typewriters than before.)

Nevertheless, once people got a look at what ChatGPT can do there arose a fresh surge of worry over whether, this time, the robots were finally going to take all of our jobs.

Wanting to know how generative pre-trained language models have actually impacted the functioning of contact centers, Erik Brynjolfsson, Danielle Li, and Lindsey R. Raymond looked at data from some 5,000 customer support agents using it in their day-to-day work.

Their paper, “Generative AI at Work”, found that generative AI had led to a marked increase in productivity, especially among the newest, least-knowledgable, and lowest-performing workers.

The authors advanced the remarkable hypothesis that this might stem from the fact that LLMs are good at internalizing and disseminating the hard-won tacit knowledge of the best workers. They didn’t get much out of generative AI, in other words, precisely because they already had what they needed to perform well; but some fraction of their skill – such as how to phrase responses delicately to avoid offending irate customers – was incorporated into the LLM, where it was more accessible by less-skilled workers than it was when it was locked away in the brains of high-skilled workers.

What’s more, the organizations studied also changed as a result. Employees (especially lower-skilled ones) were generally more satisfied, less prone to burnout, and less likely to leave. Turnover was reduced, and customers escalated calls to supervisors less frequently.

Now, we hasten to add that of course this is just one study, and we’re in the early days of the generative AI revolution. No one can say with certainty what the long-term impact will be. Still, these are extremely promising early results, and lend credence to the view that generative AI will do a lot to improve the way contact centers onboard new hires, resolve customer issues, and function overall.

What are the Dangers of Using ChatGPT for Customer Service?

We’ve been singing the praises of ChatGPT and talking about all the ways in which it’s helping contact center managers run a tighter ship.

But, as with every technological advance stretching clear back to the discovery of fire, there are downsides. To help you better use generative AI, we’ll spend the next few sections talking about some characteristic failure modes you should be looking out for.

Hallucinations

By now, it’s fairly common knowledge that ChatGPT will just make things up. This is a consequence of the way LLMs like ChatGPT are trained. Remember, the model doesn’t contain a little person inside of it that’s checking statements for accuracy; it’s just taking the tokens it has seen so far and predicting the tokens that will come next.

That means if you ask it for a list of book recommendations to study lepidoptery or the naval battles of the Civil War (we don’t know what you’re into), there’s a pretty good chance that the list it provides will contain a mix of real and fake books.

ChatGPT has been known to invent facts, people, papers (complete with citations), URLs, and plenty else.

If you’re going to have customers interacting with it, or you’re going to have your contact center agents relying on it in a substantial way, this is something you’ll need to be aware of.

Degraded Performance

ChatGPT is remarkably performant, but it’s still just a machine learning model and machine learning models are known to suffer from model degradation.

This term refers to gradual or precipitous declines in model performance over time. There are technical reasons why this occurs, but from your perspective, you need to understand that the work has only begun once a model has been trained and put into production.

But you’re also not out of the woods if you’re accessing ChatGPT via an API, because you have just as little visibility into what’s happening on OpenAI’s engineering teams as the rest of us do.

If OpenAI releases an update you might suddenly find that ChatGPT fails in usual ways or trips over tasks it was handling very well last week. You’ll need to have robust monitoring in place so that you catch these issues if they arise, as well as an engineering team able to address the root cause.

Model degradation often stems from issues with the underlying data. This means that if you’ve e.g. trained ChatGPT to answer questions you might have to assemble new data for it to train on, a process that takes time and money and should be budgeted for.

Harassment and Bias

You could argue that harassment, bias, and harmful language are a kind of degraded performance, but they’re distinct and damaging enough to warrant their own section.

When Microsoft first released Sydney it was cartoonishly unhinged. It would lie, threaten, and manipulate users; in one case, it confessed both its love for a New York Times reporter along with its desire to engineer dangerous viruses and ignite internecine arguments between people.

All this has gotten much better, of course, but the same behavior can manifest in subtler ways, especially if someone is deliberately trying to jailbreak a large language model.

Thanks to extensive public testing and iteration, the current versions of the technology are very good at remaining polite, avoiding stereotyping, etc. Nevertheless, we’re not aware of any way to positively assure that no bias, deceit, or nastiness will emerge from ChatGPT.

This is another place where you’ll have to carefully monitor your model’s output and make corrections as necessary.

Using LLMs in your Contact Center

If you’re running a contact center, you owe it to yourself to at least check out ChatGPT. Whether it makes sense for you will depend on your unique circumstances, but it’s a remarkable new technology that could help you make your agents more effective while reducing turnover.

Quiq offers a white-glove platform that makes it easy to leverage conversational AI. Schedule a demo with us to see how we can help you incorporate generative AI into your contact center today!

Ways to Use ChatGPT for Customer Service

Posted on July 26, 2023November 15, 2024 Michael Hartsog

Now that we’ve all seen what ChatGPT can do, it’s natural to begin casting about for ways to put it to work. An obvious place where a generative AI language model can be used is in contact centers, which involve a great deal of text-based tasks like answering customer questions and resolving their issues.

But is ChatGPT ready for the on-the-ground realities of contact centers? What if it responds inappropriately, abuses a customer, or provides inaccurate information?

We at Quiq pride ourselves on being experts in the domain of customer experience and customer service, and we’ve been watching the recent developments in the realm of generative AI for some time. This piece presents our conclusions about what ChatGPT is, the ways in which ChatGPT can be used for customer service, and the techniques that exist to optimize it for this domain.

What is ChatGPT?

ChatGPT is an application built on top of GPT-4, a large language model. Large language models like GTP-4 are trained on huge amounts of textual data, and they gradually learn the statistical patterns present in that data well enough to output their own, new text.

How does this training work? Well, when you hear a sentence like “I’m going to the store to pick up some _____”, you know that the final word is something like “milk”, “bread”, or “groceries”, and probably not “sawdust” or “livestock”. This is because you’ve been using English for a long time, you’re familiar with what happens at a grocery store, and you have a sense of how a person is likely to describe their exciting adventures there (nothing gets our motor running like picking out the really good avocados).

GPT-4, of course, has none of this context, but if you show it enough examples it can learn to imitate natural language quite well. It will see the first few sentences of a paragraph and try to predict what the final sentence is. At first, its answers are terrible, but with each training run its internal parameters are updated, and it gradually gets better. If you do this for long enough you get something that can write its own emails, blog posts, research reports, book summaries, poems, and codebases.

Is ChatGPT the Same Thing as GPT-4?

So then, how is ChatGPT different from GPT-4? GPT-4 is the large language model trained in the manner just described, and ChatGPT is a version fine-tuned using reinforcement learning with human feedback to be good at conversations.

Fine-tuning refers to a process of taking a pre-trained language model and doing a little extra work to narrow its focus to doing a particular task. A generic LLM can do many things, including write limericks; but if you want it to consistently write high-quality limericks, you’ll need to fine-tune it by showing it a few dozen or a few hundred examples of them.

From that point on it will be specialized for limerick production, and might consequently be less useful for other tasks.

This is how ChatGPT was created. After GPT-3.5 or GPT-4 was finished training, engineers did additional fine-tuning work that led to a model that was especially good at having open-ended interactions with users.

What does ChatGPT mean for Customer Service?

Given that ChatGPT is useful for customer interactions, how might it be deployed in customer service? We believe that a good list of initial use cases includes question answering, personalizing responses to different customers, summarizing important information, translating between languages, and performing sentiment analysis.

This is certainly not everything current and future versions of ChatGPT will be able to do for customer service, but we think it’s a good place to start.

Question Answering

Question answering has long been of such interest to machine learning engineers that there’s a whole bespoke dataset specifically for it (the Stanford Question Answering Dataset, or SQuAD).

It’s not hard to see why. Humans can obviously answer questions, but there are so many possible questions that there’s just no way to get to it all. What if you’d like high-level summaries of all the major research papers published about an obscure scientific sub-discipline? What if you’d like to see how the tone of Victorian-era English novels changed over time? There are only so many person-hours that can go toward digging into queries like this.

Customers, too, have many questions, and answering them takes a lot of time. You could collect all the frequently asked questions and put them into a single document for easy reference, but there are still going to be areas of confusion and requests for clarification (and that’s not even considering the fraction of users who never make it to your FAQ page in the first place).

Automating the process of asking questions is an obvious place to utilize technology like ChatGPT. It’ll never get frustrated answering the same thing thousands of times, it’ll never lose its patience, it’ll never sleep, and it’ll never take a bathroom break.

Vanilla ChatGPT is pretty good at doing this already, and there are already many projects focused on getting it to answer questions about a particular company’s documentation.

This functionality will enable you to field an effectively unlimited number of customer questions while freeing up your contact center agents to tackle more important issues.

Onboarding New Hires

Customers are not the only people who might have questions about your product – new hires unfamiliar with your process for doing things might also have their fair share of confusion.

Even in companies that are very conscious about documentation, there can often be so much to get through that new employees – who already have a lot going on – can feel overwhelmed.

A large language model trained to answer questions about your documentation will be a godsend to the fresh troops you’ve brought in.

Summarization

A related task is summarizing email threads, important technical documents, or even videos.

Just as you can’t realistically expect every customer to assiduously look through all your company’s documents, it’s usually not realistic to expect that all of your own employees will do so either.

Here, too, is a place where ChatGPT can be useful. It’s quite good at taking a lengthy bit of text and summarizing it, so there’s no reason it can’t be used to keep your teams up to speed on what’s happening in parts of the organization that they don’t interact with all that often.

If your engineers don’t want to go over an exchange between product designers, or your marketing team doesn’t want all the details of a conversation between the data scientists, ChatGPT can be used to create summaries of these interactions for easier reading.

This way everyone knows what’s going on throughout the company without needing to spend hours every day staying abreast of evolving issues.

At Quiq, we’ve developed proprietary ways to harness ChaGPT’s generative abilities to summarize conversations for your contact center agents.

Sentiment Analysis

Finally, another way in which ChatGPT will power the contact center of the future is with sentiment analysis. Sentiment analysis refers to a branch of machine learning aimed at parsing the overall tone of a piece of text. This can be more subtle than you might think.

“I hate this restaurant” is pretty unambiguous, but what about a review like “Yeah, we loved this restaurant, we had plenty of time to chat because the food took an hour to come out, and since my enchilada was frozen it counteracted my usual inability to eat spicy food”? You and I can hear the implied eye-rolling in this text, but a machine won’t necessarily be able to unless it’s very powerful.

This matters for contact centers because you need to understand how people are talking about your product, whether that’s in online reviews, internal tickets, or during conversations with your agents.

And ChatGPT can help. It’s not only quite good at sentiment analysis, but it’s also better than quite a lot of alternative machine-learning approaches to sentiment analysis, even without fine-tuning.

(Note, however, that these tests compare it to relatively simple machine learning models, not to the very best deep-learning sentiment analyzers.)

Prioritizing Incoming Issues

One way that ChatGPT can add tremendous value to your contact center is in helping to prioritize issues as they come in. There are always lots of problems to solve, but they’re not all equally important. Finding the most pressing issues and marking them for resolution is a huge part of keeping your center running smoothly.

This is something that humans can do, but there’s only so much energy they can devote to this task. A properly trained generative language model, however, can handle a huge chunk of it, especially when it forms part of a broader suite of AI tools.

One way this could work is using ChatGPT for plucking out essential keywords from a customer service ticket. This by itself might be enough to help your contact center agents figure out what they should focus on, but it can be made even better if these words are then fed to a classification algorithm trained to identify urgent problems.

Real-time Language Translation

Language translation, too, is a clear use case for LLMs, and the deep learning upon which they are based has seen much success in translating from one language to another.

This is especially useful if your product or service enjoys a global audience. Many people have a passing familiarity with English but will not necessarily be able to follow a detailed procedure involving technical vocabulary, and that will be a source of frustration for them.

By substantially or totally automating real-time language translation, ChatGPT can help customers who lack English fluency to better interact with your company’s offerings, answering their questions, resolving their issues, and in general moving them along.

And in case you’re wondering, ChatGPT is currently even better than Google Translate or DeepL at most translation tasks, including tricky ones involving jokes and humor.

Fine-Tuning ChatGPT for Customer Service

So far we’ve mostly talked about ChatGPT out of the box, but we’ve also made some references to “fine-tuning” it.

In this section, we’ll flesh out our earlier comments about fine-tuning ChatGPT, and distinguish fine-tuning from related techniques, like prompt engineering.

What is Fine-Tuning ChatGPT?

Once upon a time, it was anyone’s guess as to whether you’d be able to pre-train a single large model on a dataset and then tweak it for particular applications, or whether you’d need to train a special model for every individual task.

Beginning around 2011, it became increasingly clear that for many applications, pre-training was the way to go, and since then, many techniques have been developed for doing the subsequent fine-tuning.

When you fine-tune a pre-trained generative AI model, you are effectively altering its internal structure so that it does better on the task you’re interested in. Sometimes this involves changing the whole model, other times you’re altering the last few output layers and leaving the rest of the model intact.

But what it ultimately boils down to is creating a fine-tuning pipeline through which your model sees a lot of examples of the behavior you’re trying to elicit. If you were fine-tuning it to be more polite in its follow-up questions, for example, you’d need to collect a bunch of examples of this politeness and have your model learn on them.

How many examples you end up needing will depend on your specific use case, but it’s usually a few dozen and could be as many as a few hundred.

How is Fine-Tuning Different From Prompt Engineering?

Prompt engineering refers to the practice of carefully sculpting the prompt you feed your model to do a better job of producing the output you want to see.

The reason this works is that GPT-4 and other LLMs are extremely sensitive to slight changes in the wording of their prompts. It takes a while to develop the feel required to reliably produce good results with an LLM, and all of this falls under the label of “prompt engineering”.

It’s possible to inject some light fine-tuning into prompt engineering, through one-shot and few-shot learning. One-shot learning means including one example of the behavior you want to see in your prompt, and few-shot learning is the same idea, but you’re including 2-5 examples for the LLM to learn from.

FAQs About ChatGPT for Customer Service

Now that we’ve finished our discussion of the basics of ChatGPT for customer service, we’ll spend some time addressing common questions about this subject.

Can I Use ChatGPT for Customer Service?

Yes! ChatGPT is ideal for customer service applications, but you need to fine-tune ChatGPT on your own company’s documentation or to get it to strike the right tone. With the right guardrails, it’s a powerful tool for those looking to build a forward-looking contact center.

What are the Examples of ChatGPT in Customer Service?

ChatGPT can be used for customer service tasks like question answering, sentiment analysis, translating between natural languages, and summarizing documents. These are all time-intensive tasks, the automation of which will free up your contact center agents to focus on higher-priority work.

Can you Automate Customer Service?

Tools like AutoGPT and SuperAGI are making it easier than ever to create and manage sophisticated agents capable of handling open-ended tasks. Still, artificial intelligence is not yet flexible enough to entirely automate customer service at present.

It can be used to automate substantial parts of customer service, like answering user questions, but for the moment the lion’s share of the work must still be done by flesh-and-blood human beings.

If you’re interested in developments in this space, be sure to follow the Quiq blog for updates.

ChatGPT and the Contact Center of the Future

ChatGPT and related technologies are already changing the way contact centers function. From automated translation to helping field dramatically more questions per hour, they are helping contact center agents be more productive and reducing organizational turnover.

The Quiq platform is an excellent tool for incorporating conversational AI into your offering, without having to hire a team or manage your own infrastructure. Quiq can help you automate text messaging, handle real-time translation, and track the performance of your AI Assistants to see where improvements need to be made.

Exploring Cutting-Edge Research in Large Language Models and Generative AI

Posted on July 20, 2023November 15, 2024 The Quiq Team

By the calendar, ChatGPT was released just a few months ago. But subjectively, it feels as though 600 years have passed since we all read “as a large language model…” for the first time.

The pace of new innovations is staggering, but we at Quiq like to help our audience in the customer experience and contact center industries stay ahead of the curve (even when that requires faster-than-light travel).

Today, we will look at what’s new in generative AI, and what will be coming down the line in the months ahead.

Where will Generative AI be applied?

First, let’s start with industries that will be strongly impacted by generative AI. As we noted in an earlier article, training a large language model (LLM) like ChatGPT mostly boils down to showing it tons of examples of text until it learns a statistical representation of human language well enough to generate sonnets, email copy, and many other linguistic artifacts.

There’s no reason the same basic process (have it learn it from many examples and then create its own) couldn’t be used elsewhere, and in the next few sections, we’re going to look at how generative AI is being used in a variety of different industries to brainstorm structures, new materials, and a billion other things.

Generative AI in Building and Product Design

If you’ve had a chance to play around with DALL-E, Midjourney, or Stable Diffusion, you know that the results can be simply remarkable.

It’s not a far leap to imagine that it might be useful for quickly generating ideas for buildings and products.

The emerging field of AI-generated product design is doing exactly this. With generative image models, designers can use text prompts to rough out ideas and see them brought to life. This allows for faster iteration and quicker turnaround, especially given that creating a proof of concept is one of the slower, more tedious parts of product design.

For the same reason, these tools are finding use among architects who are able to quickly transpose between different periods and styles, see how better lighting impacts a room’s aesthetic, and plan around themes like building with eco-friendly materials.

There are two things worth pointing out about this process. First, there’s often a learning curve because it can take a while to figure out prompt engineering well enough to get a compelling image. Second, there’s a hearty dose of serendipity. Often the resulting image will not be quite what the designer had in mind, but it’ll be different in new and productive ways, pushing the artist along fresh trajectories that might never have occurred to them otherwise.

Generative AI in Discovering New Materials

To quote one of America’s most renowned philosophers (Madonna), we’re living in a material world. Humans have been augmenting their surroundings since we first started chipping flint axes back in the Stone Age; today, the field of materials science continues the long tradition of finding new stuff that expands our capabilities and makes our lives better.

This can take the form of something (relatively) simple like researching a better steel alloy, or something incredibly novel like designing a programmable nanomaterial.

There’s just one issue: it’s really, really difficult to do this. It takes a great deal of time, energy, and effort to even identify plausible new materials, to say nothing of the extensive testing and experimenting that must then follow.

Materials scientists have been using machine learning (ML) in their process for some time, but the recent boom in generative AI is driving renewed interest. There are now a number of projects aimed at e.g. using variational autoencoders, recurrent neural networks, and generative adversarial networks to learn a mapping between information about a material’s underlying structure and its final properties, then using this information to create plausible new materials.

It would be hard to overstate how important the use of generative AI in materials science could be. If you imagine the space of possible molecules as being like its own universe, we’ve explored basically none of it. What new fabrics, medicines, fuels, fertilizers, conductors, insulators, and chemicals are waiting out there? With generative AI, we’ve got a better chance than ever of finding out.

Generative AI in Gaming

Gaming is often an obvious place to use new technology, and that’s true for generative AI as well. The principles of generative design we discussed two sections ago could be used in this context to flesh out worlds, costumes, weapons, and more, but it can also be used to make character interactions more dynamic.

From Navi trying to get our attention in Ocarina of Time to GlaDOS’s continual reminders that “the cake is a lie” in Portal, non-playable characters (NPCs) have always added texture and context to our favorite games.

Powered by LLMs, these characters may soon be able to have open-ended conversations with players, adding more immersive realism to the gameplay. Rather than pulling from a limited set of responses, they’d be able to query LLMs to provide advice, answer questions, and shoot the breeze.

What’s Next in Generative AI?

As impressive as technologies like ChatGPT are, people are already looking for ways to extend their capabilities. Now that we’ve covered some of the major applications of generative AI, let’s look at some of the exciting applications people are building on top of it.

What is AutoGPT and how Does it Work?

ChatGPT can already do things like generate API calls and build simple apps, but as long as a human has to actually copy and paste the code somewhere useful, its capacities are limited.

But what if that weren’t an issue? What if it were possible to spin ChatGPT up into something more like an agent, capable of semi-autonomously interacting with software or online services to complete strings of tasks?

This is exactly what Auto-GPT is intended to accomplish. Auto-GPT is an application built by developer Toran Bruce Richards, and it is comprised of two parts: an LLM (either GPT-3.5 or GPT-4), and a separate “bot” that works with the LLM.

By repeatedly querying the LLM, the bot is able to take a relatively high-level task like “help me set up an online business with a blog and a website” or “find me all the latest research on quantum computing”, decompose it into discrete, achievable steps, then iteratively execute them until the overall objective is achieved.

At present, Auto-GPT remains fairly primitive. Just as ChatGPT can get stuck in repetitive and unhelpful loops, so too can Auto-GPT. Still, it’s a remarkable advance, and it’s spawned a series of other projects attempting to do the same thing in a more consistent way.

The creators of AssistGPT bill it as a “General Multi-modal Assistant that can Plan, Execute, Inspect, and Learn”. It handles multi-modal tasks (i.e. tasks that rely on vision or sound and not just text) better than Auto-GPT, and by integrating with a suite of tools it is able to achieve objectives that involve many intermediate steps and sub-tasks.

SuperAGI, in turn, is just as ambitious. It’s a platform that offers a way to quickly create, deploy, manage, and update autonomous agents. You can integrate them into applications like Slack or vector databases, and it’ll even ping you if an agent gets stuck somewhere and starts looping unproductively.

Finally, there’s LangChain, which is a similar idea. LangChain is a framework that is geared towards making it easier to build on top of LLMs. It features a set of primitives that can be stitched into more robust functionality (not unlike “for” and “while” loops in programming languages), and it’s even possible to build your own version of AutoGPT using LangChain.

What is Chain-of-Thought Prompting and How Does it Work?

In the misty, forgotten past (i.e. 5 months ago), LLMs were famously bad at simple arithmetic. They might be able to construct elegant mathematical proofs, but if you asked them what 7 + 4 is, there was a decent chance they’d get it wrong.

Chain-of-thought (COT) prompting refers to a few-shot learning method of eliciting output from an LLM that compels it to reason in a step-by-step way, and it was developed in part to help with this issue. This image from the original Wei et al. (2022) paper illustrates how:

Input and output examples for Standard and Chain-of-thought Prompting. — Source: ARXIV.org

As you can see, the model’s performance is improved because it’s being shown a chain of different thoughts, hence chain-of-thought.

This technique isn’t just useful for arithmetic, it can be utilized to get better output from a model in a variety of different tasks, including commonsense and symbolic reasoning.

In a way, humans can be prompt engineered in the same fashion. You can often get better answers out of yourself or others through a deliberate attempt to reason slowly, step-by-step, so it’s not a terrible shock that a large model trained on human text would benefit from the same procedure.

The Ecosystem Around Generative AI

Though cutting-edge models are usually the stars of the show, the truth is advanced technologies aren’t worth much if you have to be deeply into the weeds to use them. Machine learning, for example, would surely be much less prevalent if tools like sklearn, Tensorflow, and Keras didn’t exist.

Though we’re still in the early days of LLMs, AutoGPT, and everything else we’ve discussed, we suspect the same basic dynamic will play out. Since it’s now clear that these models aren’t toys, people will begin building infrastructure around them that streamlines the process of training them for specific use cases, integrating them into existing applications, etc.

Let’s discuss a few efforts in this direction that are already underway.

Training and Education

Among the simplest parts of the emerging generative AI value chain is exactly what we’re doing now: talking about it in an informed way. Non-specialists will often lack the time, context, and patience required to sort the real breakthroughs from the hype, so putting together blog posts, tutorials, and reports that make this easier is a real service.

Making Foundation Models Available

“Foundation models” is a new term that refers to the actual algorithms that underlie LLMs. ChatGPT, for example, is not a foundation model. GPT-4 is the foundation model, and ChatGPT is a specialized application of it (more on this shortly).

Companies like Anthropic, Google, and OpenAI can train these gargantuan models and then make them available through an API. From there, developers are able to access their preferred foundation model over an API.

This means that we can move quickly to utilize their remarkable functionality, which wouldn’t be the case if every company had to train their own from scratch.

Building Applications Around Specific Use Cases

One of the most striking properties of ChatGPT is how amazingly general they are. They are capable of “…generating functioning web apps with just a few prompts, writing Spanish-language children’s stories about the blockchain in the style of Dr. Suess, [and] opining on the virtues and vices of major political figures”, to name but a few examples.

General-purpose models often have to be fine-tuned to perform better on a specific task, especially if they’re doing something tricky like summarizing medical documents with lots of obscure vocabulary. Alas, there is a tradeoff here, because in most cases these fine-tuned models will afterward not be as useful for generic tasks.

The issue, however, is that you need a fair bit of technical skill to set up a fine-tuning pipeline, and you need a fair bit of elbow grease to assemble the few hundred examples a model needs in order to be fine-tuned. Though this is much simpler than training a model in the first place it is still far from trivial, and we expect that there will soon be services aimed at making it much more straightforward.

LLMOps and Model Hubs

We’d venture to guess you’ve heard of machine learning, but you might not be familiar with the term “MLOps”. “Ops” means “operations”, and it refers to all the things you have to do to use a machine learning model besides just training it. Once a model has been trained it has to be monitored, for example, because sometimes its performance will begin to inexplicably degrade.

The same will be true of LLMs. You’ll need to make sure that the chatbot you’ve deployed hasn’t begun abusing customers and damaging your brand, or that the deep learning tool you’re using to explore new materials hasn’t begun to spit out gibberish.

Another phenomenon from machine learning we think will be echoed in LLMs is the existence of “model hubs”, which are places where you can find pre-trained or fine-tuned models to use. There certainly are carefully guarded secrets among technologists, but on the whole, we’re a community that believes in sharing. The same ethos that powers the open-source movement will be found among the teams building LLMs, and indeed there are already open-sourced alternatives to ChatGPT that are highly performant.

Looking Ahead

As they’re so fond of saying on Twitter, “ChatGPT is just the tip of the iceberg.” It’s already begun transforming contact centers, boosting productivity among lower-skilled workers while reducing employee turnover, but research into even better tools is screaming ahead.

Frankly, it can be enough to make your head spin. If LLMs and generative AI are things you want to incorporate into your own product offering, you can skip the heady technical stuff and skip straight to letting Quiq do it for you. The Quiq conversational AI platform is a best-in-class product suite that makes it much easier to utilize these technologies. Schedule a demo to see how we can help you get in on the AI revolution.

How to Evaluate Generated Text and Model Performance

Posted on July 14, 2023November 15, 2024 J.R. Rettenmeyer

Machine learning is an incredibly powerful technology. That’s why it’s being used in everything from autonomous vehicles to medical diagnoses to the sophisticated, dynamic AI Assistants that are handling customer interactions in modern contact centers.

But for all this, it isn’t magic. The engineers who build these systems must know a great deal about how to evaluate them. How do you know when a model is performing as expected, or when it has begun to overfit the data? How can you tell when one model is better than another?

This subject will be our focus today. We’ll cover the basics of evaluating a machine learning model with metrics like mean squared error and accuracy, then turn our attention to the more specialized task of evaluating the generated text of a large language model like ChatGPT.

How to Measure the Performance of a Machine Learning Model?

A machine learning model is always aimed at some task. It might be trying to fit a regression line that helps predict the future price of Bitcoin, it might be clustering documents according to their topics, or it might be trying to generate text so good it rivals that produced by humans.

How does the model know when it’s gotten the optimal line or discovered the best way to cluster documents? (And more importantly, how do you know?)

In the next few sections, we’ll talk about a few common ways of evaluating the performance of a machine-learning model. If you’re an engineer this will help you create better models yourself, and if you’re a layperson, it’ll help you better understand how the machine-learning pipeline works.

Evaluation Metrics for Regression Models

Regression is one of the two big types of basic machine learning, with the other being classification.

In tech-speak, we say that the purpose of a regression model is to learn a function that maps a set of input features to a real value (where “real” just means “real numbers”). This is not as scary as it sounds; you might try to create a regression model that predicts the number of sales you can expect given that you’ve spent a certain amount on advertising, or you might try to predict how long a person will live on the basis of their daily exercise, water intake, and diet.

In each case, you’ve got a set of input features (advertising spend or daily habits), and you’re trying to predict a target variable (sales, life expectancy).

The relationship between the two is captured by a model, and a model’s quality is evaluated with a metric. Popular metrics for regression models include the mean squared error, the root mean squared error, and the mean absolute error (though there are plenty of others if you feel like going down a nerdy rabbit hole).

The mean squared error (MSE) quantifies how good a regression model is by calculating the difference between the line and each real data point, squaring them (so that positive and negative differences don’t cancel out), and then averaging them. This gives a single number that the training algorithm can use to adjust its model – if the MSE is going down, the model is getting better, if it’s going up, it’s getting worse.

The root mean squared error (RMSE) does the exact same thing, but the final step is that you take the square root of the MSE. The big advantage here is that it converts the units of your metric back into the units you’re using in your problem (i.e. the “squared dollars” of MSE become “dollars” again, which makes it easier to think about what’s going on).

The mean absolute error (MAE) is the same basic idea, but it uses absolute values instead of squares. This also has the advantage of not penalizing outliers as much as the RMSE does. If you’ve got some outlier data point that’s far away from your model, squaring the difference will result in a bigger error than simply taking the absolute value of that difference. For this reason, it’s less sensitive to outliers in the dataset.

Evaluation Metrics for Classification Models

People tend to struggle less with understanding classification models because it’s more intuitive: you’re building something that can take a data point (the price of an item) and sort it into one of a number of different categories (i.e. “cheap”, “somewhat expensive”, “expensive”, “very expensive”).

Of course, the categories you choose will depend on the problem you’re trying to solve and the domain you’re operating in – a $100 apple is certainly “very expensive”, but a $100 dollar wedding ring…will probably get you left at the altar.

Regardless, it’s just as essential to evaluate the performance of a classification model as it is to evaluate the performance of a regression model. Some common evaluation metrics for classification models are accuracy, precision, and recall.

Accuracy is simple, and it’s exactly what it sounds like. You find the accuracy of a classification model by dividing the number of correct predictions it made by the total number of predictions it made altogether. If your classification model made 1,000 predictions and got 941 of them right, that’s an accuracy rate of 94.1% (not bad!)

Both precision and recall are subtler variants of this same idea. The precision is the number of true positives (correct classifications) divided by the sum of true positives and false positives (incorrect positive classifications). It says, in effect, “When your model thought it had identified a needle in a haystack, this is how often it was correct.”

The recall is the number of true positives divided by the sum of true positives and false negatives (incorrect negative classifications). It says, in effect “There were 200 needles in this haystack, and your model found 72% of them.”

Accuracy tells you how well your model performed overall, precision tells you how confident you can be in its positive classifications, and recall tells you how often it found the positive classifications.

(You may be wondering if this isn’t overkill. Do we really need all these different ratios? Answering that question fully would take us too far from our purpose of measuring the quality of text from generative AI models, but suffice it to say that there are trade-offs involved. Sometimes it makes more sense to focus on boosting the precision, other times getting a higher recall is more important. These are all just different tools for figuring out how to spend your limited time and energy to get a model that best solves your problem.)

How Can I Assess the Performance of a Generative AI Model?

Now, we arrive at the center of this article. Everything up to now has been background context that hopefully has given you a feel for how models are evaluated, because from here on out it’s a bit more abstract.

Using Reference Text for Evaluating Generative Models

When we wanted to evaluate a regression model, we started by looking at how far its predictions were from actual data points.

Well, we do essentially the same thing with generative language models. To assess the quality of text generated by a model, we’ll compare it against high-quality text that’s been selected by domain experts.

The Bilingual Evaluation Understudy (BLEU) Score

The BLEU score can be used to actually quantify the distance between the generated and reference text. It does this by comparing the amount of overlap in the n-grams [1] between the two using a series of weighted precision scores.

The BLEU score varies from 0 to 1. A score of “0” indicates that there is no n-gram overlap between the generated and reference text, and the model’s output is considered to be of low quality. A score of “1”, conversely, indicates that there is total overlap between the generated and reference text, and the model’s output is considered to be of high quality.

Comparing BLEU scores across different sets of reference texts or different natural languages is so tricky that it’s considered best to avoid it altogether.

Also, be aware that the BLEU score contains a “brevity penalty” which discourages the model from being too concise. If the model’s output is too much shorter than the reference text, this counts as a strike against it.

The Recall-Oriented Understudy for Gisting Evaluation (ROGUE) Score

Like the BLEU score, the ROGUE score is examining the n-gram overlap between an output text and a reference text. Unlike the BLEU score, however, it uses recall instead of precision.

There are three types of ROGUE scores:

rogue-n: Rogue-n is the most common type of ROGUE score, and it simply looks at n-gram overlap, as described above.
rogue-l: Rogue-l looks at the “Longest Common Subsequence” (LCS), or the longest chain of tokens that the reference and output text share. The longer the LCS, of course, the more the two have in common.
rogue-s: This is the least commonly-used variant of the ROGUE score, but it’s worth hearing about. Rogue-s concentrates on the “skip-grams” [2] that the two texts have in common. Rogue-s would count “He bought the house” and “He bought the blue house” as overlapping because they have the same words in the same order, despite the fact that the second sentence does have an additional adjective.

The Metric for Evaluation of Translation with Explicit Ordering (METEOR) Score

The METEOR Score takes the harmonic mean of the precision and recall scores for 1-gram overlap between the output and reference text. It puts more weight on recall than on precision, and it’s intended to address some of the deficiencies of the BLEU and ROGUE scores while maintaining a pretty close match to how expert humans assess the quality of model-generated output.

BERT Score

At this point, it may have occurred to you to wonder whether the BLEU and ROGUE scores are actually doing a good job of evaluating the performance of a generative language model. They look at exact n-gram overlaps, and most of the time, we don’t really care that the model’s output is exactly the same as the reference text – it needs to be at least as good, without having to be the same.

The BERT score is meant to address this concern through contextual embeddings. By looking at the embeddings behind the sentences and comparing those, the BERT score is able to see that “He quickly ate the treats” and “He rapidly consumed the goodies” are expressing basically the same idea, while both the BLEU and ROGUE scores would completely miss this.

Final thoughts.

We’ve all seen what generative AI can do, and it’s fair at this point to assume this technology is going to become more prevalent in fields like software engineering, customer service, customer experience, and marketing.

But, as magical as generative AI might seem to be, they’re just models. They have to be evaluated and monitored just like any other, or you risk having a bad one negatively impact your brand.

If you’re enchanted by the potential of using generative algorithms in your contact center but are daunted by the challenge of putting together an engineering team, reach out to us for a demo of the Quiq conversational CX platform. We can help you put this cutting-edge technology to work without having to worry about all the finer details and resourcing issues.

***

Footnotes

[1] An n-gram is just a sequence of characters, words, or entire sentences. A 1-gram is usually single words, a 2-gram is usually two words, etc.
[2] Skip-grams are a rather involved subdomain of natural language processing. You can read more about them in this article, but frankly, most of it is irrelevant to this article. All you need to know is that the rogue-s score is set up to be less concerned with exact n-gram overlaps than the alternatives.

Featured Resource

AI Readiness Self-Assessment

Featured Resource

AI Readiness Self-Assessment

What is Whatsapp Business?

What Features Does WhatsApp Business Have?

What are the Differences Between WhatsApp and WhatsApp Business?

The Advantages of WhatsApp Messaging for Businesses

Global Reach and Popularity

Personalized Customer Interactions

End-to-End Encryption

Scalability

Enhancing Contact Center Performance with WhatsApp Messaging

Improving Response and Resolution Metrics Times

Integrating Artificial Intelligence

Gathering Customer Feedback

Wrapping Up

These are the Questions you Should ask Your Generative AI Vendor

1. What Sort of Customer Service Do You Offer?

2. Does Your Team Offer Help with Setting up the Platform?

3. What Kinds of Integrations Do You Support?

4. How Does Prompt Engineering and Fine-Tuning Work for Your Model?

5. Can Your Models Support Reasoning and Acting?

6. What’s your Pricing Structure Like?

Picking the Right Generative AI Vendor

What are Customer Insights in Contact Centers?

What are the Major Types of Customer Insights?

Speech and Text Data

Data on Customer Satisfaction

Predictive Analytics

Data on Agent Performance

Channel Analytics

What Specific Metrics are Tracked for Customer Insights?

First Contact Resolution (FCR)

Average Handle Time (AHT)

Customer Satisfaction (CSAT)

Call Abandon Rate (CAR)

How Can AI Help with Customer Insights?

Natural Language Processing and Sentiment Analysis

Classifying Different Kinds of Communication

Statistical Analysis and A/B Testing

What AI Tools Can Be Used for Customer Insights?

Performant and Reliable

Straightforward Integration Process

Simple to Use

Getting the Most Out of AI-Powered Customer Insights

What is an AI Assistant?

How Will AI Assistants Change Hotels?

AI for Hotel Operations

AI for Managing Hotel Revenues

AI in Marketing and Customer Service

Smart Buildings in Hotels

Virtual Tours and Guest Experience

Using AI Assistants in Hotels

Comparing Explainability and Interpretability

What is Explainability in Machine Learning?

Different Types of Explanations

Approaches to Explainability in Machine Learning

What is Interpretability in Machine Learning?

Mechanistic Interpretability: A New Frontier

Why are Interpretability and Explainability Important?

Final Thoughts on Interpretability vs. Explainability

What is AI Translation?

How Does AI Translation Work?

Building a Global Brand with AI

How can AI Translation Be Used to Build a Global Brand?

Prompt Engineering for Building a Global Brand

How can AI Translation Benefit the Economy?

AI Translation and Global Brands

Why is AI Important for Hospitality?

How is AI Used in Hospitality?

Chatbots and Customer Service

Virtual Assistants

Sentiment Analysis

Boosting Revenues for Hospitality

Sustainability and Waste Management

What are the Limitations of AI in Hospitality?

Impersonality in Customer Service

Toxic Output, Bias, and Abuse

AI in Hospitality