large language models Archives

8 Strategies to Improve Customer Retention

Posted on May 19, 2025May 19, 2025 Cristina Bravo-Olmo

Recruiting new customers costs seven to nine times as much as required to keep current customers from leaving. Besides the obvious foregone revenue, dissatisfied customers are not going to recommend you to the people they know, and they might even go out of their way to tell their friends and family about their negative experiences. This kind of fallout can have long-term consequences for customer retention.

For all these reasons, it’s imperative not to let customers slip away – and one of the best ways of doing that is to implement an effective customer retention strategy.

Even a small increase in customer retention could substantially improve your bottom line, but customer retention can be extremely challenging. Having said that, enhancing customer retention can be challenging and generally requires an intentional strategy that many companies don’t choose to prioritize.

In this post, we will examine the big picture of why improving customer retention is important and offer advice that any customer experience team can use to keep its customers happy and loyal.

What Is Customer Retention?

“Customer retention” refers to any effort to keep a customer satisfied enough with you to keep them using your product or service.

Customer retention is an important aspect of business strategy and, done correctly, can help you gain a competitive advantage. Tragically, many businesses don’t invest enough in it – they spend vast amounts of time and money trying to bring in new customers while neglecting the ones they’ve already worked so hard to get.

But with the right approach and high-quality service, there’s no reason that excellent customer retention can’t be one of the things setting you apart.

Why Is Customer Retention Important?

We’ve already established that getting new customers is more expensive than keeping old ones, but it’s also worth pointing out that existing customers spend an average of almost 70% more than new customers.

Even better, loyal customers are far more likely to share their experiences with their social circles and purchase from your company again.

These customers are not only your best cheerleaders, they also help you better understand your brand in various other ways, like via CSAT and NPS (Net Promoter Score®) surveys. If you ask them, they will provide honest feedback about your product and customer service, allowing you to make the course corrections required to succeed. We’ll have more to say about all of this in the section on improving customer retention strategies that drive long-term customer retention.

Calculating Customer Retention

Determining your current customer retention rate (CRR) is an important first step in improving customer retention.

The CRR measures how many customers are retained over a particular period (usually one year) and allows you to gauge the long-term profitability of your marketing and sales efforts. It’s also a key metric for evaluating the success of your overall customer retention initiatives. The math is pretty straightforward: we just need to divide the number of repeat customers by the total number of active customers over the same time period.

So, if we have 50 return customers and 200 active customers for the year 2023, our CRR would be 25%.

A related metric worth tracking is the cost per acquisition (CPA). The CPA measures the cost a company incurs to acquire one new customer (ideally, a new customer who becomes loyal to the company’s brand).

If you have both the CRR and the CPA, you should have a good chunk of the context needed to make smart, data-driven decisions. If you want to increase your retention rate, read the next section.

8 Customer Retention Strategies That Work

Now that we’ve made a strong case for trying to enhance customer retention, let’s discuss specific strategies that’ll help you actually do it.

1. Good Values Build Good Relationships

Many companies have “mission” or “vision” statements that explicitly state the values they live by. Though these statements are sometimes viewed as hot air that only serves to give the marketing team something to put on the company website, the truth is that your processes, the quality of your products, and the way you treat your customers are all a reflection of them.

This is a long way to say that values are important, but you don’t have to take our word for it. When asked, many customers who stated they had a relationship with a brand indicated that it was due to shared values. This isn’t surprising – customers will naturally be attracted to brands that mirror their beliefs while enhancing their lifestyles, especially when they’re younger.

Building a brand that your customers can easily relate to will foster trust. This is key to creating strong relationships and, by extension, a successful business. Let your customers know what you stand for, and be sure to act on these convictions (by donating to worthy causes, for example). Having common values with your customers makes it easier to attract and retain them.

2. Empower Your Customer Service Team to Build Trust

As a CX leader tasked with building, operationalizing, and scaling your contact center, you undoubtedly think about human agents’ interactions with customers. An important element in that equation is how you empower your team of customer service representatives to build trust with your customers.

To achieve this, focus on comprehensive training programs that emphasize empathy, active listening, and effective problem-solving. For instance, role-playing scenarios can prepare agents to handle various customer concerns with confidence and care. Keep your team up to date on best practices and emerging trends with regular workshops and continuous learning opportunities, too.

Implementing a customer feedback loop can help your team understand and respond to customer needs more effectively. Encourage your agents to ask for feedback after interactions and use this information to improve service delivery. Monitoring key performance indicators (KPIs) such as customer satisfaction scores (CSAT), Net Promoter Scores® (NPS), and first-call resolution rates can provide valuable insights into how well your team is building trust.

That validation helps to reinforce your team’s hard work, deepening a healthy internal culture. Speaking of culture, creating an internal culture centered around customer love, advocacy, and even “customer obsession” is foundational to trust building.

But as a CX leader, you must also factor in ways to highlight your team members’ success in putting customers first. This could involve recognizing and rewarding team members who exemplify customer-first values. For example, a monthly “Customer Hero” award can highlight and incentivize exceptional service.

3. Make Yourself Transparent and Easy to Work With

A great way to stand out is by making it as easy as possible for customers to find what they need. If your documentation or website is complex or confusing, this is certain to become a problem at one point or another. Clear, concise information, on the other hand, can help enhance customer retention.

Take the issue of refunds. If a customer is looking for a refund, they’re obviously dissatisfied. How much worse will they feel if they must then struggle to find a way to contact you, only to be faced with a maze of robotic voices endlessly repeating a menu of options?

If your agents are sympathetic and your information is easy to navigate, a refund needn’t be the end of a professional relationship. More broadly, it pays to invest the time required to make your content easy to follow and your agents easy to contact. Frustration at this level can erode trust and severely impact customer retention.

4. Meet Your Customers Where They Are

Customers love great offers and discounts, but they also love it when they can get help solving problems with as little friction as possible.

A good way to do this (and improve customer retention simultaneously) is to provide support through the channels that make the most sense for your customers. There are a few other advantages to this omnichannel approach:

It enables you to respond very quickly to incoming queries, which can be a huge advantage for reasons already discussed above.
By integrating with technology like large language models, you can personalize your replies at scale and even offer services like real-time translation.
You can drive faster resolution times, contributing to customer satisfaction and retention.

5. Prioritize Quick Turnarounds

As a general rule, people have never enjoyed waiting around. But now that we’ve grown accustomed to 30-minute DoorDash deliveries and same-day shipping from Amazon, it’s only gotten worse.

For this reason, it pays to focus on replying to issues as quickly as possible.

Note, however, that this doesn’t necessarily mean you have to resolve an issue right off the bat. Many customers will feel less anxious and frustrated simply by knowing they’ve been heard and someone is working on a solution. Respond immediately, even if it’s just to say, “We’re sorry you’re running into issues, and we’re committed to getting you up and running again as soon as possible.”

You can also take this initial message as an opportunity to manage expectations about how long it will take to find a solution. Obviously, some problems are relatively straightforward, while others are more substantial, and you can communicate that to the customer (assuming it’s appropriate to do so). It’s never fun to hear that you’ll have to wait a week to get some issue sorted out, but it’s far worse to find that out after you’ve already made a bunch of plans that are difficult to change.

6. Be Sure to Personalize Your Communications

Artificial intelligence has a long history of delivering personalized content. You’re probably familiar with Spotify, which can discover patterns in the music and podcasts you enjoy and use algorithms to recommend songs and artists that align with your tastes.

With the power of generative AI, platforms like Quiq are elevating this to unprecedented levels.

Once upon a time, only human agents could analyze a customer’s profile and tailor their responses with relevant information. Now, a well-optimized generative language model can achieve this almost instantaneously – and on a much larger scale.

For a contact center manager focused on enhancing customer experience, this is a significant step forward.

7. Let Customer Data Work for You

Customer data can help determine your customers’ needs, and surveys are an effective way to gather that data, including NPS (Net Promoter Score®) surveys. Some of the benefits of conducting customer surveys include:

They’re a great way to interact with your customers
Customers tend to give honest and open feedback
These customers will be more likely to give feedback in the future if they see changes implemented based on prior concerns
Survey feedback can result in positive adjustments to your products, services, or processes
Surveys show your customers that you value their opinions and are willing to do whatever it takes to make them happy.
It can help ensure you’re pursuing the right targeting strategy
They can help you identify dissatisfied customers before they leave and create campaigns or offers to win them back

Of course, surveys aren’t the only way to do this; you can also treat customer complaints that come through other feedback channels in a similar manner.

Regardless of how you choose to proceed, interacting with your customers in this productive, proactive way is a great opportunity. Seventy percent of customers who complain will purchase your product again if their complaints are favorably resolved.

8. Reward Loyalty

Though nothing beats exceptional customer service, thoughtful gestures go a long way. In addition to standard discounts and other offers, think of things that will make your customers feel good about using your product.

A thank you note or any positive acknowledgment can keep your customers coming back, thus enhancing your customer retention rate.

Building Customer Relationships

Customers are the foundation of any business. But it’s not enough to just get customers, you must also ensure that you invest in improving customer retention. In today’s competitive landscape, customer retention is what separates sustainable growth from short-lived success. You can do this by using the strategies presented in this post to build world-class relationships with your customers.

To find even more such strategies, check out our free ebook on resolving common customer-service pain points. It’s got excellent advice on dealing with angry or frustrated customers, elucidating their expectations, and more. With it, you’ll have everything you need to send your customer retention rates into the stratosphere!

How to Automate Customer Service – The Ultimate Guide

Posted on April 1, 2025May 1, 2025 Michael Hartsog

From graph databases to automated machine learning pipelines and beyond, a lot of attention gets paid to new technologies. But the truth is, none of it matters if users aren’t able to handle the more mundane tasks of managing permissions, resolving mysterious errors, and getting the tools installed and working on their native systems.

This is where customer service comes in. Though they don’t often get the credit they deserve, customer service agents are the ones who are responsible for showing up every day to help countless others actually use the latest and greatest technology.

Like every job since the beginning of jobs, there are large components of customer service that have been automated, are currently being automated, or will be automated at some point soon.

That’s our focus for today. We want to explore customer service as a discipline and then talk about how Agentic AI can automate substantial parts of the standard workflow.

What is Customer Service?

To begin with, we’ll try to clarify what customer service is and why it matters. This will inform our later discussion of automated customer service and help us think through the value that can be added through automation.

Customer service is more or less what it sounds like: serving your customers – your users, or clients – as they go about the process of utilizing your product. A software company might employ customer service agents to help onboard new users and troubleshoot failures in their product, while a services company might use them for canceling appointments and rescheduling.

Over the prior few decades, customer service has evolved alongside many other industries. As mobile phones have become firmly ensconced in everyone’s life, for example, it has become more common for businesses to supplement the traditional avenues of phone calls and emails by adding text messaging and chatbot customer support to their customer service toolkit. This is part of what is known as an omni-channel strategy, in which more effort is made to meet customers where they’re at rather than expecting them to conform to the communication pathways a business already has in place.

Naturally, many of these kinds of interactions can be automated, especially with the rise of tools like large language models. We’ll have more to say about that shortly.

Why is Customer Service Important?

It may be tempting for those writing the code to think that customer service is a “nice to have”, but that’s not the case at all. However good a product’s documentation is, there will simply always be weird behaviors and edge cases in which a skilled customer service agent (perhaps helped along with AI) needs to step in and aid a user in getting everything running properly.

But there are other advantages as well. Besides simply getting a product to function, customer service agents contribute to a company’s overall brand, and the general emotional response users have to the company and its offerings.

High-quality customer service agents can do a lot to contribute to the impression that a company is considerate and genuinely cares about its users.

What Are Examples of Good Customer Service?

There are many ways in which customer service agents can do this. For example, it helps a lot when customer service agents try to transmit a kind of warmth over the line.

Because so many people spend their days interacting with others through screens, it can be easy to forget what that’s like, as tone of voice and facial expression are hard to digitally convey. But when customer service agents greet a person enthusiastically and go beyond “How may I help you” by exchanging some opening pleasantries, they feel more valued and more at ease. This matters a lot when they’ve been banging their head against a software problem for half a day.

Customer service agents have also adapted to the digital age by utilizing emojis, exclamation points, and various other kinds of internet-speak. We live in a more casual age, and under most circumstances, it’s appropriate to drop the stiffness and formalities when helping someone with a product issue.

That said, you should also remember that you’re talking to customers, and you should be polite. Use words like “please” when asking for something, and don’t forget to add a “thank you.” It can be difficult to remember this when you’re dealing with a customer who is simply being rude, especially when you’ve had several such customers in a row. Nevertheless, it’s part of the job.

Finally, always remember that a customer gets in touch with you when they’re having a problem, and above all else, your job is to get them what they need. From the perspective of contact center managers, this means you need periodic testing or retraining to make sure your agents know the product thoroughly.

It’s reasonable to expect that agents will sometimes need to look up the answer to a question, but if they’re doing that constantly it will not only increase the time it takes to resolve an issue, but it will also contribute to customer frustration and a general sense that you don’t have things well in hand.

Automation in Customer Service

Now that we’ve covered what customer service is, why it matters, and how to do it well, we have the context we need to turn to the topic of automated customer service.

For all intents and purposes, “automation” simply refers to outsourcing all or some of a task to a machine. In industries like manufacturing and agriculture, automation has been steadily increasing for hundreds of years.

Until fairly recently, however, the technology didn’t yet exist to automate substantial portions of customer service worth. With the rise of machine learning, and especially large language models like ChatGPT, that’s begun to change dramatically.

Let’s dive into this in more detail.

Examples of Automated Customer Service

There are many ways in which customer service is being automated. Here are a few examples:

Automated questions answering – Many questions are fairly prosaic (“How do I reset my password”), and can effectively be outsourced to a properly finetuned large language model. When such a model is trained on a company’s documentation, it’s often powerful enough to handle these kinds of low-level requests.
Summarization – There have long been models that could do an adequate job of summarization, but large language models have kicked this functionality into high gear. With an endless stream of new emails, Slack messages, etc. constantly being generated, having an agent that can summarize their contents and keep agents in the loop will do a lot to boost their productivity.
Classifying incoming messages – Classification is another thing that models have been able to do for a while, and it’s also something that helps a lot. Having an agent manually sort through different messages to figure out how to prioritize them and where they should go is no longer a good use of time, as algorithms are now good enough to do a major chunk of this kind of work.
Translation – One of the first useful things anyone attempted to do with machine learning was translating between different natural languages (i.e. from Russian into English). Once squarely in the purview of human beings, this is now a task that machines can do almost as well, at least for customer service work.

Should We Automate Customer Service?

All this having been said, you may still have questions about the wisdom of automating customer service work. Sure, no one wants to spend hours every day looking up words in Mandarin to answer a question or prioritizing tickets by hand, but aren’t we in danger of losing something important as customer service agents? Might we not automate ourselves out of a job?

Because these models are (usually) finetuned on conversations with more experienced agents, they’re able to capture a lot of how those agents handle issues. Typical response patterns, politeness, etc. become “baked into” the models. Junior agents using these models are able to climb the learning curve more quickly and, feeling less strained in their new roles, are less likely to quit. This, in turn, puts less of a burden on managers and makes the organization overall more stable. Everyone ends up happier and more productive.

So far, it’s looking like AI-based automation in contact centers will be like automation almost everywhere else: machines will gradually remove the need for human attention in tedious or otherwise low-value tasks, freeing them up to focus on places where they have more of an advantage.

If agents don’t have to sort tickets anymore or resolve routine issues, they can spend more time working on the really thorny problems, and do so with more care.

Strategies for Implementing Automated Customer Service

Once you’ve decided to bring automation into your customer service strategy, the next step is implementation. Here are some key strategies to help you get started and ensure a smooth transition that benefits both your team and your customers.

Assess Your Current Customer Service Needs

Start by reviewing your support data. Which questions pop up most often? Where do your agents spend the most time? Identifying these patterns will help you pinpoint which tasks can—and should—be automated. Look for high-volume, repetitive inquiries that don’t require much nuance. These are prime candidates for automation that won’t sacrifice the quality of your customer experience.

Choose the Right Automation Tools

Not all automation tools are created equal. Consider solutions like AI agents, automated ticket routing, or self-service portals. The key is to choose platforms that work well with your existing CRM and communication tools, so everything stays connected. Look for tools that are flexible, scalable, and easy for your team to manage over time.

Develop a Knowledge Base and Self-Service Options

A well-organized knowledge base can deflect tickets before they ever hit your queue. Build out FAQs, how-to articles, and video tutorials that answer your customers’ most common questions. Use AI-powered search features to surface the right content quickly. And don’t forget to update your content regularly based on feedback and emerging issues—your knowledge base should evolve alongside your customers.

Set Up Automated Responses and Workflows

Automation isn’t just about answering questions—it’s about streamlining entire workflows. Set up automated messages for order updates, appointment reminders, or common troubleshooting steps. Use branching logic and triggers to guide customers through resolutions, and ensure these flows are intuitive. The goal is to help customers solve issues faster, without needing to wait on hold.

Balance Automation with Human Support

Even the best bots have their limits. Make sure customers can easily escalate to a live agent when necessary—especially for complex or sensitive issues. Train your human support team to step in smoothly when automation reaches its edge. And whenever possible, personalize the experience by using data to greet customers by name or tailor responses based on their history.

Monitor Performance and Continuously Optimize

The work doesn’t stop after launch. Keep an eye on key metrics like resolution time, deflection rate, and customer satisfaction scores. Collect feedback from users to understand where automation is helping—or where it might be falling short. With the right data, you can train your AI and machine learning models to recognize patterns, refine workflows, and improve response accuracy—so your automated service keeps getting smarter with every interaction.

Moving Quiq-ly into the Future!

Where the rubber of technology meets the road of real-world use cases, customer service agents are extremely important. They not only make sure customers can use a company’s tools, but they also contribute to the company brand through their tone, mannerisms, and helpfulness.

Like most other professions, customer service agents are being impacted by automation. So far, this impact has been overwhelmingly positive and is likely to prove a competitive advantage in the decades ahead.

If you’re intrigued by this possibility, Quiq has created a suite of industry-leading agentic AI tools, both for customer-facing applications and agent-facing applications. Check them out or schedule a demo with us to see what all the fuss is about.

Request A Demo

The 5 Most Asked Questions About AI

Posted on March 3, 2025May 1, 2025 Lauren Winder

The term “artificial intelligence” was coined at the famous Dartmouth Conference in 1956, put on by luminaries like John McCarthy, Marvin Minsky, and Claude Shannon, among others.

These organizers wanted to create machines that “use language, form abstractions and concepts, solve kinds of problems now reserved for humans, and improve themselves.” They went on to claim that “…a significant advance can be made in one or more of these problems if a carefully selected group of scientists work on it together for a summer.”

Half a century later, it’s fair to say that this has not come to pass; brilliant as they were, it would seem as though McCarthy et al. underestimated how difficult it would be to scale the heights of the human intellect.

Nevertheless, remarkable advances have been made over the past decade, so much so that they’ve ignited a firestorm of controversy around this technology. People are questioning the ways in which it can be used negatively, and whether it might ultimately pose an extinction risk to humanity; they’re probing fundamental issues around whether machines can be conscious, exercise free will, and think in the way a living organism does; they’re rethinking the basis of intelligence, concept formation, and what it means to be human.

These are deep waters to be sure, and we’re not going to swim them all today. But as contact center managers and others begin the process of thinking about using AI, it’s worth being at least aware of what this broader conversation is about. It will likely come up in meetings, in the press, or in Slack channels in exchanges between employees.

And that’s the subject of our piece today. We’re going to start by asking what artificial intelligence is and how it’s being used, before turning to address some of the concerns about its long-term potential. Our goal is not to answer all these concerns, but to make you aware of what people are thinking and saying.

What is Artificial Intelligence?

Artificial intelligence is famous for having many, many definitions. There are those, for example, who believe that in order to be intelligent computers must think like humans, and those who reply that we didn’t make airplanes by designing them to fly like birds.

For our part, we prefer to sidestep the question somewhat by utilizing the approach taken in one of the leading textbooks in the field, Stuart Russell and Peter Norvig’s “Artificial Intelligence: A Modern Approach”.

They propose a multi-part system for thinking about different approaches to AI. One set of approaches is human-centric and focuses on designing machines that either think like humans – i.e., engage in analogous cognitive and perceptual processes – or act like humans – i.e. by behaving in a way that’s indistinguishable from a human, regardless of what’s happening under the hood (think: the Turing Test).

The other set of approaches is ideal-centric and focuses on designing machines that either think in a totally rational way – conformant with the rules of Bayesian epistemology, for example – or behave in a totally rational way – utilizing logic and probability, but also acting instinctively to remove itself from danger, without going through any lengthy calculations.

What we have here, in other words, is a framework. Using the framework not only gives us a way to think about almost every AI project in existence, it also saves us from needing to spend all weekend coming up with a clever new definition of AI.

Joking aside, we think this is a productive lens through which to view the whole debate, and we offer it here for your information.

What is Artificial Intelligence Good For?

Given all the hype around ChatGPT, this might seem like a quaint question. But not that long ago, many people were asking it in earnest. The basic insights upon which large language models like ChatGPT are built go back to the 1960s, but it wasn’t until 1) vast quantities of data became available, and 2) compute cycles became extremely cheap that much of its potential was realized.

Today, large language models are changing (or poised to change) many different fields. Our audience is focused on contact centers, so that’s what we’ll focus on as well.

There are a number of ways that generative AI is changing contact centers. Because of its remarkable abilities with natural language, it’s able to dramatically speed up agents in their work by answering questions and formatting replies. These same abilities allow it to handle other important tasks, like summarizing articles and documentation and parsing the sentiment in customer messages to enable semi-automated prioritization of their requests.

Though we’re still in the early days, the evidence so far suggests that large language models like Quiq’s conversational CX platform will do a lot to increase the efficiency of contact center agents.

Will AI be Dangerous?

One thing that’s burst into public imagination recently has been the debate around the risks of artificial intelligence, which fall into two broad categories.

The first category is what we’ll call “social and political risks”. These are the risks that large language models will make it dramatically easier to manufacture propaganda at scale, and perhaps tailor it to specific audiences or even individuals. When combined with the astonishing progress in deepfakes, it’s not hard to see how there could be real issues in the future. Most people (including us) are poorly equipped to figure out when a video is fake, and if the underlying technology gets much better, there may come a day when it’s simply not possible to tell.

Political operatives are already quite skilled at cherry-picking quotes and stitching together soundbites into a damning portrait of a candidate – imagine what’ll be possible when they don’t even need to bother.

But the bigger (and more speculative) danger is around really advanced artificial intelligence. Because this case is harder to understand, it’s what we’ll spend the rest of this section on.

Artificial Superintelligence and Existential Risk

As we understand it, the basic case for existential risk from artificial intelligence goes something like this:

“Someday soon, humanity will build or grow an artificial general intelligence (AGI). It’s going to want things, which means that it’ll be steering the world in the direction of achieving its ambitions. Because it’s smart, it’ll do this quite well, and because it’s a very alien sort of mind, it’ll be making moves that are hard for us to predict or understand. Unless we solve some major technological problems around how to design reward structures and goal architectures in advanced agentive systems, what it wants will almost certainly conflict in subtle ways with what we want. If all this happens, we’ll find ourselves in conflict with an opponent unlike any we’ve faced in the history of our species, and it’s not at all clear we’ll prevail.”

This is heady stuff, so let’s unpack it bit by bit. The opening sentence, “…humanity will build or grow an artificial general intelligence”, was chosen carefully. If you understand how LLMs and deep learning systems are trained, the process is more akin to growing an enormous structure than it is to building one.

This has a few implications. First, their internal workings remain almost completely inscrutable. Though researchers in fields like mechanistic interpretability are going a long way toward unpacking how neural networks function, the truth is, we’ve still got a long way to go.

What this means is that we’ve built one of the most powerful artifacts in the history of Earth, and no one is really sure how it works.

Another implication is that no one has any good theoretical or empirical reason to bound the capabilities and behavior of future systems. The leap from GPT-2 to GPT-3.5 was astonishing, as was the leap from GPT-3.5 to GPT-4. The basic approach so far has been to throw more data and more compute at the training algorithms; it’s possible that this paradigm will begin to level off soon, but it’s also possible that it won’t. If the gap between GPT-4 and GPT-5 is as big as the gap between GPT-3 and GPT-4, and if the gap between GPT-6 and GPT-5 is just as big, it’s not hard to see that the consequences could be staggering.

As things stand, it’s anyone’s guess how this will play out. But that’s not necessarily a comforting thought.

Next, let’s talk about pointing a system at a task. Does ChatGPT want anything? The short answer is: as far as we can tell, it doesn’t. ChatGPT isn’t an agent, in the sense that it’s trying to achieve something in the world, but work into agentive systems is ongoing. Remember that 10 years ago most neural networks were basically toys, and today we have ChatGPT. If breakthroughs in agency follow a similar pace (and they very well may not), then we could have systems able to pursue open-ended courses of action in the real world in relatively short order.

Another sobering possibility is that this capacity will simply emerge from the training of huge deep learning systems. This is, after all, the way human agency emerged in the first place. Through the relentless grind of natural selection, our ancestors went from chipping flint arrowheads to industrialization, quantum computing, and synthetic biology.

To be clear, this is far from a foregone conclusion, as the algorithms used to train large language models are quite different from natural selection. Still, we want to relay this line of argumentation, because it comes up a lot in these discussions.

Finally, we’ll address one more important claim, “…what it wants will almost certainly conflict in subtle ways with what we want.” Why do we think this is true? Aren’t these systems that we design and, if so, can’t we just tell it what we want it to go after?

Unfortunately, it’s not so simple. Whether you’re talking about reinforcement learning or something more exotic like evolutionary programming, the simple fact is that our algorithms often find remarkable mechanisms by which to maximize their reward in ways we didn’t intend.

There are thousands of examples of this (ask any reinforcement-learning engineer you know), but a famous one comes from the classic Coast Runners video game. The engineers who built the system tried to set up the algorithm’s rewards so that it would try to race a boat as well as it could. What it actually did, however, was maximize its reward by spinning in a circle to hit a set of green blocks over and over again.

Now, this may seem almost silly – do we really have anything to fear from an algorithm too stupid to understand the concept of a “race”?

But this would be missing the thrust of the argument. If you had access to a superintelligent AI and asked it to maximize human happiness, what happened next would depend almost entirely on what it understood “happiness” to mean.

If it were properly designed, it would work in tandem with us to usher in a utopia. But if it understood it to mean “maximize the number of smiles”, it would be incentivized to start paying people to get plastic surgery to fix their faces into permanent smiles (or something similarly unintuitive).

Does AI Pose an Existential Risk?

Above, we’ve briefly outlined the case that sufficiently advanced AI could pose a serious risk to humanity by being powerful, unpredictable, and prone to pursuing goals that weren’t-quite-what-we-meant.

So, does this hold water? Honestly, it’s too early to tell. The argument has hundreds of moving parts, some well-established and others much more speculative. Our purpose here isn’t to come down on one side of this debate or the other, but to let you know (in broad strokes) what people are saying.

At any rate, we are confident that the current version of ChatGPT doesn’t pose any existential risks. On the contrary, it could end up being one of the greatest advancements in productivity ever seen in contact centers. And that’s what we’d like to discuss in the next section.

What is the Biggest Concern with AI?

Ethical Challenges

While AI’s potential is vast, so are the concerns surrounding its rapid advancement. One of the most pressing concerns is the ethical challenge of transparency. AI models often operate as “black boxes,” making decisions without clear explanations. This lack of visibility raises concerns about hidden biases that can lead to unfair or even discriminatory outcomes, especially in areas like hiring, lending, and law enforcement.

Economic Ramifications

Beyond ethics, AI’s economic impact is another major concern: automation is reshaping entire industries. While it creates new opportunities, it also threatens traditional jobs, particularly in sectors reliant on repetitive tasks. This shift could complicate wealth disparities, favoring companies and individuals who own or develop AI technologies while leaving others behind.

Social Impacts

On a broader scale, AI’s social implications are hard to ignore. The displacement of jobs, increasing socio-economic inequality, and reduced human oversight in decision-making all point to a future where AI plays an even greater role in shaping society. This raises questions about the balance between automation and human oversight.

Will AI Take All the Jobs?

The concern that someday a new technology will render human labor obsolete is hardly new. It was heard when mechanized weaving machines were created, when computers emerged, when the internet emerged, and when ChatGPT came onto the scene.

We’re not economists and we’re not qualified to take a definitive stand, but we do have some early evidence that is showing that large language models are not only not resulting in layoffs, they’re making agents much more productive.

Erik Brynjolfsson, Danielle Li, and Lindsey R. Raymond, three MIT economists, looked at the ways in which generative AI was being used in a large contact center. They found that it was actually doing a good job of internalizing the ways in which senior agents were doing their jobs, which allowed more junior agents to climb the learning curve more quickly and perform at a much higher level. This had the knock-on effect of making them feel less stressed about their work, thus reducing turnover.

Now, this doesn’t rule out the possibility that GPT-10 will be the big job killer. But so far, large language models are shaping up to be like every prior technological advance, i.e., increasing employment rather than reducing it.

What is the Future of AI?

The rise of AI is raising stock valuations, raising deep philosophical questions, and raising expectations and fears about the future. We don’t know for sure how all this will play out, but we do know contact centers, and we know that they stand to benefit greatly from the current iteration of large language models.

These tools are helping agents answer more queries per hour, do so more thoroughly, and make for a better customer experience in the process.

If you want to get in on the action, set up a demo of our technology today.

Request A Demo

LLM vs Generative AI vs Agentic AI: What’s the Difference?

Posted on February 27, 2025May 1, 2025 J.R. Rettenmeyer

The release of ChatGPT was one of the first times an extremely powerful AI system was broadly available, and it has ignited a firestorm of controversy and conversation.

Proponents believe current and future AI tools will revolutionize productivity in almost every domain.

Skeptics wonder whether advanced systems like GPT-4 will even end up being all that useful.

And a third group believes they’re the first sparks of artificial general intelligence and could be as transformative for life on Earth as the emergence of homo sapiens.

Frankly, it’s enough to make a person’s head spin. One of the difficulties in making sense of this rapidly-evolving space is the fact that many terms, like “generative AI,” “large language models” (LLMs) and now “agentic AI” are thrown around very casually.

In this piece, our goal is to disambiguate these three terms by discussing the differences between generative AI, large language models, and agentic AI. Whether you’re pondering deep questions about the nature of machine intelligence, or just trying to decide whether the time is right to use conversational AI in customer-facing applications, this context will help.

What Is Generative AI?

Of the three terms, “generative AI” is broader, referring to any machine learning model capable of dynamically creating output after it has been trained.

This ability to generate complex forms of output, like sonnets or code, is what distinguishes generative AI from linear regression, k-means clustering, or other types of machine learning.

Besides being much simpler, these models can only “generate” output in the sense that they can make a prediction on a new data point.

Once a linear regression model has been trained to predict test scores based on number of hours studied, for example, it can generate a new prediction when you feed it the hours a new student spent studying.

But you couldn’t use prompt engineering to have it help you brainstorm the way these two values are connected, which you can do with ChatGPT.

There are many key features of generative AI, so let’s spend a few minutes discussing how it can be used and the benefits it can provide.

Key Features of Generative AI

Generative AI is designed to create new content, learning from vast datasets to produce text, images, audio, and video. Its capabilities extend beyond simple data processing, making it a powerful tool for creativity, automation, and personalization.

Content Generation

At its core, Generative AI excels at producing unique and original content across multiple formats, including text, images, audio, and video. Unlike traditional AI systems that rely on predefined rules, generative models leverage deep learning to generate coherent and contextually relevant outputs. This creative capability has revolutionized industries ranging from marketing to entertainment.

Data-Driven Learning

Generative AI models are trained on vast datasets, allowing them to learn complex patterns and relationships within the data. These models use deep neural networks, particularly transformer-based architectures, to process and generate information in a way that mimics human cognition. By continuously analyzing new data, generative AI can refine its outputs and improve over time, making it increasingly reliable for content generation, automation, and decision-making.

Adaptability & Versatility

One of the most powerful aspects of Generative AI is its ability to function across diverse industries and use cases. Whether it’s generating realistic human-like conversations in chatbots, composing music, or designing virtual environments, the technology adapts seamlessly to different applications. Its versatility allows businesses to leverage AI-driven creativity without being limited to a single domain.

Customization & Personalization

Generative AI can tailor its outputs based on user inputs, preferences, or specific guidelines. This makes it an invaluable tool for personalized content creation, such as crafting targeted marketing messages, customizing chatbot responses, or even generating personalized artwork. By adjusting parameters or fine-tuning models with proprietary data, businesses can ensure that the AI-generated content aligns with their brand voice and audience expectations.

Effeciency & Automation

Beyond creativity, Generative AI significantly enhances efficiency by automating tasks that traditionally require human effort. Whether it’s generating reports, summarizing large volumes of text, or producing high-quality design assets, AI-driven automation saves time and resources. This efficiency allows businesses to scale their operations while reducing costs and freeing up human talent for higher-level strategic work.

What Are Large Language Models?

Now that we’ve covered generative AI, let’s turn our attention to large language models (LLMs).

LLMs are a particular type of generative AI.

Unlike with MusicLM or DALL-E, LLMs are trained on textual data and then used to output new text, whether that be a sales email or an ongoing dialogue with a customer.

(A technical note: though people are mostly using GPT-4 for text generation, it is an example of a “multimodal” LLM because it has also been trained on images. According to OpenAI’s documentation, image input functionality is currently being tested, and is expected to roll out to the broader public soon.)

What Are Examples of Large Language Models?

By far the most well-known example of an LLM is OpenAI’s “GPT” series, the latest of which is GPT-4. The acronym “GPT” stands for “Generative Pre-Trained Transformer”, and it hints at many underlying details about the model.

GPT models are based on the transformer architecture, for example, and they are pre-trained on a huge corpus of textual data taken predominately from the internet.

GPT, however, is not the only example of an LLM.

The BigScience Large Open-science Open-access Multilingual Language Model – known more commonly by its mercifully short nickname, “BLOOM” – was built by more than 1,000 AI researchers as an open-source alternative to GPT.

BLOOM is capable of generating text in almost 50 natural languages, and more than a dozen programming languages. Being open-sourced means that its code is freely available, and no doubt there will be many who experiment with it in the future.

In March, Google announced Bard, a generative language model built atop its Language Model for Dialogue Applications (LaMDA) transformer technology.

As with ChatGPT, Bard is able to work across a wide variety of different domains, offering help with planning baby showers, explaining scientific concepts to children, or helping you make lunch based on what you already have in your fridge

Key Features of Large Language Models

LLMs represent a breakthrough in AI-powered language processing, offering unparalleled natural language capabilities, scalability, and adaptability. Their ability to understand and generate text with contextual awareness makes them invaluable across industries. Below, we explore the key features that make LLMs so powerful and their significance in real-world applications.

Natural Language Understanding & Generation

One of the defining characteristics of LLMs is their ability to comprehend and generate human language with contextually relevant and coherent output. Unlike traditional rule-based NLP systems, LLMs leverage deep learning to process vast amounts of text, enabling them to recognize nuances, idioms, and contextual dependencies.

Why this matters: This enables more natural interactions in chatbots, virtual assistants, and customer support tools. It also improves content generation for marketing, reporting, and creative writing, while multilingual capabilities enhance accessibility and global communication.

Scalability & Versatility:

LLMs are designed to process and generate text at an unprecedented scale, making them versatile across a wide range of applications. They can analyze large datasets, respond to queries in real-time, and generate text in multiple formats—from technical documentation to creative storytelling.

Why this matters: Their scalability allows businesses to automate tasks, improve decision-making, and generate personalized content efficiently. This versatility makes them useful across industries like healthcare, finance, and education, streamlining operations and enhancing user engagement.

Adaptability Through Fine-Tuning

While general-purpose LLMs are highly capable, their performance can be further enhanced through fine-tuning—a process that tailors the model to specific domains or tasks. By training an LLM on industry-specific data, organizations can improve accuracy, reduce bias, and align responses with their unique needs.

Why this matters: Fine-tuning increases accuracy for specialized tasks, ensuring better performance in industries like healthcare and law. It also helps businesses maintain brand consistency and reduces the need for manual corrections, leading to more efficient workflows.

What is Agentic AI?

Agentic AI refers to artificial intelligence systems that go beyond passive data processing to actively pursue objectives with minimal human intervention. Unlike traditional AI models that rely on explicit prompts or predefined workflows, agentic AI autonomously takes initiative, gathers information, and makes decisions in pursuit of a goal.

At its core, agentic AI operates with a level of autonomy that allows it to dynamically adapt to new information, refine its approach, and execute tasks with greater independence. These systems can analyze complex scenarios, break down multi-step problems, and determine the best course of action without requiring constant human oversight.

Advancements in AI, from reinforcement learning to multi-agent collaboration, have enabled agentic AI to evolve from passive tools into autonomous problem-solvers. Businesses now use it to streamline workflows, enhance decision-making, and drive efficiency, signaling a shift toward proactive AI systems.

What are some of the key features of Agentic AI?

As stated before, Agentic AI represents a significant evolution beyond traditional AI models, offering enhanced autonomy and decision-making capabilities. Let’s discuss some of Agentic AI’s key features:

Autonomous Action

One of the defining characteristics of Agentic AI is its ability to operate without constant human intervention. Rather than waiting for step-by-step instructions, it executes tasks independently, identifying the necessary actions to reach an objective. This autonomy allows it to function in dynamic environments, where manual oversight would be inefficient or impractical.

Dynamic Decision Making

Agentic AI leverages real-time data to continuously refine its decision-making process. It evaluates multiple factors, adapts to changing conditions, and optimizes its approach based on the latest available information. This ability to course-correct and adjust strategies in real-time makes it particularly effective for complex problem-solving and unpredictable scenarios.

Goal-Oriented Behavior

Unlike conventional AI models that react to prompts, Agentic AI operates with a clear end goal in mind. It identifies obstacles, prioritizes tasks, and makes trade-offs to achieve its objectives efficiently. Whether optimizing workflows, automating multi-step processes, or navigating constraints, it maintains a results-driven approach.

Proactive Resource Gathering

To function effectively, Agentic AI does not simply wait for relevant data or tools to be provided—it actively seeks out the necessary resources. This can include retrieving information from databases, leveraging APIs, integrating with other systems, or even initiating sub-tasks to support the primary goal. This proactive approach enhances efficiency and reduces dependency on human input.

Self-Improvement Through Feedback

Agentic AI continuously refines its performance through iterative learning. By analyzing the outcomes of past actions, it identifies areas for improvement and adjusts future behaviors accordingly. This feedback loop allows it to become more effective over time, reducing errors and increasing efficiency in completing assigned tasks.

What Are Some Examples of Agentic AI?

Now that we have explained what Agentic AI is and some of its key features, you may be wondering how businesses in various industries are using Agentic AI. Here are a few examples:

1. Personalized AI Assistants: Beyond Basic Task Execution

AI assistants have come a long way from setting reminders and answering basic questions. Today’s agentic AI assistants can handle entire workflows, making life a whole lot easier.

Imagine having an AI-powered executive assistant that not only manages your calendar but also rearranges meetings when scheduling conflicts pop up, prioritizes your emails, and even drafts responses for you. In sales, AI agents integrated into CRMs can track conversations, spot promising leads, and automatically schedule follow-ups—no manual input required.

2. AI in Healthcare: Keeping an Eye on Your Health

Healthcare is another area where agentic AI is making a real difference. Instead of passively analyzing data, these AI systems can continuously monitor patient health, detect problems early, and even adjust treatment plans on the fly.

For example, some AI-powered health monitoring tools track vital signs in real-time, alerting doctors if something seems off. Others can analyze medical records and suggest personalized treatments based on a patient’s history. In some cases, AI can even adjust medication dosages automatically, ensuring patients get the right treatment without constant doctor intervention.

3. AI That Actually Solves Customer Support Issues

We’ve all had frustrating experiences with chatbots that don’t understand what we’re asking. Agentic AI is fixing that by powering virtual support agents that don’t just respond to questions—they solve problems.

Picture this: You need to return an item, and instead of navigating through endless menus, an AI agent processes your return, updates your order, and even schedules a pickup without you lifting a finger. In IT support, AI-powered agents can troubleshoot issues, restart systems, and even execute fixes automatically. No more waiting on hold for help—AI’s got it covered.

How Do Agentic AI, Generative AI, and LLM’s Compare?

Artificial intelligence has rapidly evolved, with distinct categories emerging to define different capabilities and use cases. While Generative AI, Large Language Models (LLMs), and Agentic AI share foundational principles, they each serve unique purposes.

Key Differences Between Generative AI, LLMs, and Agentic AI

Generative AI: This is the broad umbrella term for AI models that create content, whether text, images, music, or video. These models generate outputs based on patterns learned from large datasets but typically require user input to function effectively.
Large Language Models: A subset of Generative AI, LLMs specialize in language-based tasks such as text generation, summarization, translation, and answering questions. They process vast amounts of textual data to produce human-like responses but do not inherently make decisions or take autonomous action.
Agentic AI: Unlike Generative AI and LLMs, Agentic AI goes a step further by incorporating autonomy and goal-driven behavior. It not only generates outputs but also plans, executes, and adapts actions based on objectives. This makes Agentic AI well-suited for tasks that require decision-making, iterative problem-solving, and multi-step execution.

How These AI Systems Can Work Together

Agentic AI, Generative AI, and LLMs are not mutually exclusive; rather, they complement each other in complex workflows. For example:

A Generative AI model might generate a marketing email.
An LLM could refine the email’s tone and structure based on customer preferences.
An Agentic AI system could autonomously schedule and send the email, analyze customer responses, and iterate on the next campaign.

This synergy enables businesses and organizations to streamline operations, automate complex workflows, and improve decision-making at scale.

When to Use Generative AI, LLMs, or Agentic AI

As AI continues to evolve, different types of AI serve distinct roles in automation, content creation, and decision-making. Choosing the right approach—Generative AI, Large Language Models (LLMs), or Agentic AI—depends on the complexity of the task, the level of autonomy required, and the desired outcome. Here’s when to use each.

When to Use Generative AI

Generative AI is best suited for tasks that involve creativity, personalization, and idea generation. It excels at producing original content and enhancing user engagement by tailoring outputs dynamically.

For Creative Content Generation: Generative AI shines when creating unique visuals, music, text, or videos. It’s widely used in industries like marketing, design, and entertainment.
For Prototyping and Idea Generation: When brainstorming ideas or rapidly iterating on design concepts, generative AI can provide inspiration and streamline workflows.
For Enhancing Personalization: Generative AI helps tailor content for individual users, making it a powerful tool in marketing, product recommendations, and customer engagement.

When to Use Large Language Models (LLMs)

LLMs specialize in processing and generating human-like text, making them ideal for knowledge work, communication, and conversational AI.

For Text-Based Tasks: LLMs handle content creation, summarization, translation, and text analysis with high efficiency.
For Conversational AI: They power chatbots, virtual assistants, and customer support tools by enabling natural, context-aware conversations.
For Knowledge Work and Research: LLMs assist in research, code generation, and complex problem-solving, making them valuable for technical fields.

When to Use Agentic AI

Agentic AI goes beyond content generation and text processing—it autonomously executes tasks, makes decisions, and manages workflows with minimal human input.

For Automating Multi-Step Tasks: Agentic AI can plan, make decisions, and execute complex workflows without constant human oversight.
For Goal-Oriented, CX-Focused Systems: In scenarios where AI needs to take action toward a specific objective, agentic AI ensures execution beyond just responding to queries.
For Enhancing Productivity in Complex Workflows: When managing multiple tools or systems, agentic AI improves efficiency by handling strategic yet repetitive tasks.

Utilizing Generative AI In Your Business

AI is evolving fast, but not all AI is created equal. Generative AI is great for creativity, LLMs handle text-based tasks, but agentic AI is the game-changer—turning AI from an assistant into an autonomous problem-solver. That’s where Quiq stands out. Instead of just generating responses, Quiq’s agentic AI takes action, automating complex tasks and making real decisions so businesses can scale without the bottlenecks. It’s AI that doesn’t just assist—it gets things done.

Quiq is the leader in enterprise agentic AI for CX. If you’re an enterprise wondering how you can use advanced AI technologies such as agentic AI, generative AI, and large language models for applications like customer service, schedule a demo to see what the Quiq platform can offer you!

Why LLM Observability Matters (and Strategies for Getting it Right)

Posted on October 9, 2024December 11, 2024 J.R. Rettenmeyer

When integrating Large Language Models (LLMs), or generative AI, into applications, you can’t afford to treat them like “black boxes.” As your LLM application scales and becomes more complex, the need to monitor, troubleshoot, and understand how the LLM impacts your application becomes critical. In this article, we’ll explore the observability strategies we’ve found useful here at Quiq.

Key Elements of an Effective LLM Observability Strategy

Provide Access: Encourage business users to engage actively in testing and optimization.
Encourage Exploration: Make it easy to explore the application under different scenarios.
Create Transparency: Clearly show how the model interacts within your application, reveal decision-making processes, system interactions, and how outputs are verified.
Handle Errors Gracefully: Proactively identify and handle deviations or errors.
Track System Performance: Expose metrics like response times, token usage, and errors.

LLMs add a layer of unpredictability and complexity to an application. Your observability tooling should allow you to actively explore both known and unknown issues while fostering an environment where engineers and business users can collaborate to create a new kind of application.

5 Strategies for LLM Observability

We will discuss strategies from the perspective of a real world event. An “event” triggers an application to process input and provides output back to the world.

A few examples of events include:

Chat user message input > Chat response
An email arriving into a ticketing system > Suggested reply
A case being closed > Case updated for topic or other classifications

You may have heard of these events referred to as prompt chains, prompt pipelines, agentic workflows, or conversational turns. The key takeaway; an event will require more than a single call to an LLM. Your LLM application’s job is to orchestrate LLM prompts, data requests, decisions and actions. The following strategies will help you understand what’s happening inside your LLM application.

1. Tracing Execution Paths

Any given event may follow different execution paths. Tracing the execution path should allow you to understand what state is set, which knowledge was retrieved, functions called, and generally how and why the LLM generated and verified the response. The ability to trace the execution path of an event will provide invaluable visibility into your application behavior.

For example, if your application delivers a message that offers a live agent; was it because the topic was sensitive, the user was frustrated or there was a gap in the knowledge resources? Tracing the execution path will help you pinpoint the prompt, knowledge or logic that drove the response. This is the first step in monitoring and optimizing an AI application. Your LLM observability should provide a full trace of the execution path that led to a response being delivered.

2. Replay Mechanisms for Faster Debugging

In real-world applications, being able to reproduce and fix errors quickly is critical. Implementing an event replay mechanism—where past events can be replayed against the current system configuration will provide a fast feedback loop.

Replaying events also helps when modifying prompts, upgrading models, adding knowledge or editing business rules. Changing your LLM application should be done in a controlled environment where you can replay events and ensure the desired effect without introducing new issues.

3. State Management & Monitoring

Another key aspect of LLM observability is capturing how your application’s field values or state changes during an event, as well as, across related events such as a conversation. Understanding the state of different variables can help you better understand and recreate the results of your LLM application.

Many use cases will also make use of memory. You should strive to manage this memory consistently and use caching for order or product info to reduce unnecessary network calls. In addition to data caches, multi-turn conversations may react differently based on the memory state. Suppose a user types “I need help” and you have implemented a next-best-action classifier with the following options:

Clarify the inquiry
Find Information
Escalate to live agent

The action taken may depend on whether “I need help” is the 1st or 5th message of the conversation. The response could also depend on whether the inquiry type is something you want your live agents handling.

The key takeaway – LLMs introduce a new kind of intelligence, but you’ll still need to manage state and domain specific logic to ensure your application is aware of its context. Clear visibility into the state of your application and your ability to reproduce it are vital parts of your observability strategy.

4. Claims Verification

A critical challenge with LLMs is ensuring the validity of the information they generate. Some refer to these made up answers as hallucinations. A hallucination is a statement made up by the LLM, usually because it makes semantic sense.

A claims verification process provides confidence that a response is grounded, attributable and verified by approved evidence from known knowledge or API resources. A dedicated verification model should be used to provide a confidence score and handling should be put in place to align answers that fail verification. The verification process should use metrics such as the maximum, minimum, and average scores and attribute answers to one or many resources.

For example:

On Verified: Define actions to take when a claim is verified. This could involve attributing the answer to one or many articles or API responses and then delivering a response to the end user.
On Unverified: Set workflows for unverified claims, such as retrying a prompt pipeline, aligning a corrective response, or escalating the issue to a human agent.

By integrating a claims verification model and process into your LLM application, you gain the ability to prevent hallucinations and attribute responses to known resources. This clear and traceable attribution will equip you with the information you need to field questions from stakeholders and provide insight into how you can improve your knowledge.

5. Regression Tests

After optimizing prompts, upgrading models, or introducing new knowledge; you’ll want to ensure that these changes don’t introduce new problems. Earlier, we talked about replaying events and this replay capability should be the basis for creating your test cases. You should be able to save any event as a regression test. Your test-sets should be run individually or in batch as part of a continuous integration pipeline.

The models are moving fast and your LLM application will be under constant pressure to get faster, smarter and cheaper. Test sets will give you the visibility and confidence you need to stay ahead of your competition.

Setting Performance Goals

While the above strategies are essential, it’s also important to evaluate how well your system is achieving its higher-level objectives. This is where performance goals come into play. Goals should be instrumented to track whether your application is successfully meeting the business objectives.

Goal Success: Measure how often your application achieves a defined objective, such as confirming an upcoming appointment, rendering an order status, or receiving positive user feedback.
Goal Failure: Track instances where the LLM fails to complete a task or requires human assistance.

Keep in mind that an event such as a live agent escalation could be considered success for one type of inquiry, and a failure in a different scenario. Goal instrumentation should provide a high degree of flexibility. By setting clear success and failure criteria for your application, you will be better positioned to evaluate its performance over time and identify areas for improvement.

Applying Segmentation to Hone In

Segmentation is a powerful tool for diving deeper into your LLM application’s performance. By grouping conversations or events based on specific criteria, such as inquiry type, user type or product category; you can focus your analysis on areas that matter most to your application.

For instance, you may want to segment conversations to see if your application behaves differently on web versus mobile, or across sales versus service inquiries. You can also create more complex segments that filter interactions based on specific events, such as when an error occurred or when a specific topic category was in play. Segmentation allows you to tailor your observability efforts to the use cases and specific needs of your business.

Using Funnels for Conversion and Performance Insights

Funnels provide another layer of insight by showing how users progress through a series of steps within a customer journey or conversation. A funnel allows you to visualize drop-offs, identify where users disengage, and track how many complete the intended goal. For example, you can track the steps a customer takes when engaging with your LLM application, from initial inquiry to task completion, and analyze where drop-offs occur.

Funnels can be segmented just like other data, allowing you to drill down by platform, customer type, or interaction type. This helps you understand where improvements are needed and how adjustments to prompts or knowledge bases can enhance the overall experience.

By combining segmentation with funnel analysis, you get a comprehensive view of your LLM’s effectiveness and can pinpoint specific areas for optimization.

A/B Testing for Continuous Improvement

A/B testing is a vital tool for systematically improving LLM application performance by comparing different versions of prompts, responses, or workflows. This method allows you to experiment with variations of the same interaction and measure which version produces better results. For instance, you can test two different prompts to see which one leads to more successful goal completions or fewer errors.

By running A/B tests, you can refine your prompt design, optimize the LLM’s decision-making logic, and improve overall user experience. The results of these tests give you data-backed insights, helping you implement changes with confidence that they’ll positively impact performance.

Additionally, A/B testing can be combined with funnel analysis, allowing you to track how changes affect customer behavior at each step of the journey. This ensures that your optimizations not only improve specific interactions but also lead to better conversion rates and task completions overall.

Final Thoughts on LLM Observability

LLM observability is not just a technical necessity but a strategic advantage. Whether you’re dealing with prompt optimization, function call validation, or auditing sensitive interactions, observability helps you maintain control over the outputs of your LLM application. By leveraging tools such as event debug-replay, regression tests, segmentation, funnel analysis, A/B testing, and claims verification, you will build trust that you have a safe and effective LLM application.

Curious about how Quiq approaches LLM observability? Get in touch with us.

Everything You Need to Know About LLM Integration

Posted on October 3, 2024December 11, 2024 Kyle McIntyre

It’s hard to imagine an application, website or workflow that wouldn’t benefit in some way from the new electricity that is generative AI. But what does it look like to integrate an LLM into an application? Is it just a matter of hitting a REST API with some basic auth credentials, or is there more to it than that?

In this article, we’ll enumerate the things you should consider when planning an LLM integration.

Why Integrate an LLM?

At first glance, it might not seem like LLMs make sense for your application—and maybe they don’t. After all, is the ability to write a compelling poem about a lost Highland Cow named Bo actually useful in your context? Or perhaps you’re not working on anything that remotely resembles a chatbot. Do LLMs still make sense?

The important thing to know about ‘Generative AI’ is that it’s not just about generating creative content like poems or chat responses. Generative AI (LLMs) can be used to solve a bevy of other problems that roughly fall into three categories:

Making decisions (classification)
Transforming data
Extracting information

Let’s use the example of an inbound email from a customer to your business. How might we use LLMs to streamline that experience?

Making Decisions
- Is this email relevant to the business?
- Is this email low, medium or high priority?
- Does this email contain inappropriate content?
- What person or department should this email be routed to?
Transforming data
- Summarize the email for human handoff or record keeping
- Redact offensive language from the email subject and body
Extracting information
- Extract information such as a phone number, business name, job title etc from the email body to be used by other systems
Generating Responses
- Generate a personalized, contextually-aware auto-response informing the customer that help is on the way
- Alternatively, deploy a more sophisticated LLM flow (likely involving RAG) to directly address the customer’s need

It’s easy to see how solving these tasks would increase user satisfaction while also improving operational efficiency. All of these use cases are utilizing ‘Generative AI’, but some feel more generative than others.

When we consider decision making, data transformation and information extraction in addition to the more stereotypical generative AI use cases, it becomes harder to imagine a system that wouldn’t benefit from an LLM integration. Why? Because nearly all systems have some amount of human-generated ‘natural’ data (like text) that is no longer opaque in the age of LLMs.

Prior to LLMs, it was possible to solve most of the tasks listed above. But, it was exponentially harder. Let’s consider ‘is this email relevant to the business’. What would it have taken to solve this before LLMs?

A dataset of example emails labeled true if they’re relevant to the business and false if not (the bigger the better)
A training pipeline to produce a custom machine learning model for this task
Specialized hardware or cloud resources for training & inferencing
Data scientists, data curators, and Ops people to make it all happen

LLMs can solve many of these problems with radically lower effort and complexity, and they will often do a better job. With traditional machine learning models, your model is, at best, as good as the data you give it. With generative AI you can coach and refine the LLM’s behavior until it matches what you desire – regardless of historical data.

For these reasons LLMs are being deployed everywhere—and consumers’ expectations continue to rise.

How Do You Feel About LLM Vendor Lock-In?

Once you’ve decided to pursue an LLM integration, the first issue to consider is whether you’re comfortable with vendor lock-in. The LLM market is moving at lightspeed with the constant release of new models featuring new capabilities like function calls, multimodal prompting, and of course increased intelligence at higher speeds. Simultaneously, costs are plummeting. For this reason, it’s likely that your preferred LLM vendor today may not be your preferred vendor tomorrow.

Even at a fixed point in time, you may need more than a single LLM vendor.

In our recent experience, there are certain classification problems that Anthropic’s Claude does a better job of handling than comparable models from OpenAI. Similarly, we often prefer OpenAI models for truly generative tasks like generating responses. All of these LLM tasks might be in support of the same integration so you may want to look at the project not so much as integrating a single LLM or vendor, but rather a suite of tools.

If your use case is simple and low volume, a single vendor is probably fine. But if you plan to do anything moderately complex or high scale you should plan on integrating multiple LLM vendors to have access to the right models at the best price.

Resiliency & Scalability are Earned—Not Given

Making API calls to an LLM is trivial. Ensuring that your LLM integration is resilient and scalable requires more elbow grease. In fact, LLM API integrations pose unique challenges:

Challenge	Solutions
They are pretty slow	If your application is high-scale and you’re doing synchronous (threaded) network calls, your application won’t scale very well since most threads will be blocked on LLM calls. Consider switching to async I/O. You’ll also want to support running multiple prompts in parallel to reduce visible latency to the user.
They are throttled by requests per minute and tokens per minute	Attempt to estimate your LLM usage in terms of requests and LLM tokens per minute and work with your provider(s) to ensure sufficient bandwidth for peak load
They are (still) kinda flakey (unpredictable response times, unresponsive connections)	Employ various retry schemes in response to timeouts, 500s, 429s (rate limit) etc.

The above remediations will help your application be scalable and resilient while your LLM service is up. But what if it’s down? If your LLM integration is on a critical execution path you’ll want to support automatic failover. Some LLMs are available from multiple providers:

OpenAI models are hosted by OpenAI itself as well as Azure
Anthropic models are hosted by Anthropic itself as well as AWS

Even if an LLM only has a single provider, or even if it has multiple, you can also provision the same logical LLM in multiple cloud regions to achieve a failover resource. Typically you’ll want the provider failover to be built into your retry scheme. Our failover mechanisms get tripped regularly out in production at Quiq, no doubt partially because of how rapidly the AI world is moving.

Are You Actually Building an Agentic Workflow?

Oftentimes you have a task that you know is well-suited for an LLM. For example, let’s say you’re planning to use an LLM to analyze the sentiment of product reviews. On the surface, this seems like a simple task that will require one LLM call that passes in the product review and asks the LLM to decide the sentiment. Will a single prompt suffice? What if we also want to determine if a given review contains profanity or personal information? What if we want to ask three LLMs and average their results?

Many tasks require multiple prompts, prompt chaining and possibly RAG (Retrieval Augmented Generation) to best solve a problem. Just like humans, AI produces better results when a problem is broken down into pieces. Such solutions are variously known as AI Agents, Agentic Workflows or Agent Networks and are why open source tools like LangChain were originally developed.

In our experience, pretty much every prompt eventually grows up to be an Agentic Workflow, which has interesting implications for how it’s configured & monitored.

Be Ready for the Snowball Effect

Introducing LLMs can result in a technological snowball effect, particularly if you need to use Retrieval Augmented Generation (RAG). LLMs are trained on mostly public data that was available at a fixed point in the past. If you want an LLM to behave in light of up-to-date and/or proprietary data sources (which most non-trivial applications do) you’ll need to do RAG.

RAG refers to retrieving the up-to-date and/or proprietary data you want the LLM to use in its decision making and passing it to the LLM as part of your prompt.

Assuming you need to search a reference dataset like a knowledge base, product catalog or product manual, the retrieval part of RAG typically entails adding the following entities to your system:

1. An embedding model

An embedding model is roughly half of an LLM – it does a great job of reading and understanding information you pass it but instead of generating a completion it produces a numeric vector that encodes its understanding of the source material.

You’ll typically run the embeddings model on all of the business data you want to search and retrieve for the LLM. Most LLM providers also have embedding models, or you can hit one via any major cloud.

2. A vector database

Once you have embeddings for all of your business data, you need to store them somewhere that facilitates speedy search based on numeric vectors. Solutions like Pinecone and MilvusDB fill this need, but that means integrating a new vendor or hosting a new database internally.

After implementing embeddings and a vector search solution, you can now retrieve information to include in the prompts you send to your LLM(s). But how can you trust that the LLM’s response is grounded in the information you provided and not something based on stale information or purely made up?

There are specialized deep learning models that exist solely for the purpose of ensuring that an LLM’s generative claims are grounded in facts you provide. This practice is variously referred to as hallucination detection, claim verification, NLI, etc. We believe NLI models are an essential part of a trustworthy RAG pipeline, but managed cloud solutions are scarce and you may need to host one yourself on GPU-enabled hardware.

Is a Black Box Sustainable?

If you bake your LLM integration directly into your app, you will effectively end up with a black box that can only be understood and improved by engineers. This could make sense if you have a decent size software shop and they’re the only folks likely to monitor or maintain the integration.

However, your best software engineers may not be your best (or most willing) prompt engineers, and you may wish to involve other personas like product and experience designers since an LLM’s output is often part of your application’s presentation layer & brand.

For these reasons, prompts will quickly need to move from code to configuration – no big deal. However, as an LLM integration matures it will likely become an Agentic Workflow involving:

More prompts, prompt parallelization & chaining
More prompt engineering
RAG and other orchestration

Moving these concerns into configuration is significantly more complex but necessary on larger projects. In addition, people will inevitably want to observe and understand the behavior of the integration to some degree.

For this reason it might make sense to embrace a visual framework for developing Agentic Workflows from the get-go. By doing so you open up the project to collaboration from non-engineers while promoting observability into the integration. If you don’t go this route be prepared to continually build out configurability and observability tools on the side.

Quiq’s AI Automations Take Care of LLM Integration Headaches For You

Hopefully we’ve given you a sense for what it takes to build an enterprise LLM integration. Now it’s time for the plug. The considerations outlined above are exactly why we built AI Studio and particularly our AI Automations product.

With AI automations you can create a serverless API that handles all the complexities of a fully orchestrated AI-flow, including support for multiple LLMs, chaining, RAG, resiliency, observability and more. With AI Automations your LLM integration can go back to being ‘just an API call with basic auth’.

Want to learn more? Dive into AI Studio or reach out to our team.

Request A Demo

Current Large Language Models and How They Compare

Posted on August 15, 2024November 15, 2024 J.R. Rettenmeyer

From ChatGPT and Bard to BLOOM and Claude, there is a veritable ocean of current LLMs (large language models) for you to choose from. Some are specialized for specific use cases, some are open-source, and there’s a huge variance in the number of parameters they contain.

If you’re a CX leader and find yourself fascinated by the potential of using this technology in your contact center, it can be hard to know how to run proper LLM comparisons.

Today, we’re going to tackle this issue head-on by talking about specific criteria you can use to compare LLMs, sources of additional information, and some of the better-known options.

But always remember that the point of using an LLM is to deliver a world-class customer experience, and the best option is usually the one that delivers multi-model functionality with a minimum of technical overhead.

With that in mind, let’s get started!

What is Generative AI?

While it may seem like large language models (LLMs) and generative AI have only recently emerged, the work they’re based on goes back decades. The journey began in the 1940s with Walter Pitts and Warren McCulloch, who designed artificial neurons based on early brain research. However, practical applications became feasible only after the development of the backpropagation algorithm in 1985, which enabled effective training of larger neural networks.

By 1989, researchers had developed a convolutional system capable of recognizing handwritten numbers. Innovations such as long short-term memory networks further enhanced machine learning capabilities during this period, setting the stage for more complex applications.

The 2000s ushered in the era of big data, crucial for training generative pre-trained models like ChatGPT. This combination of decades of foundational research and vast datasets culminated in the sophisticated generative AI and current LLMs we see transforming contact centers and related industries today.

What’s the Best Way to do a Large Language Models Comparison?

If you’re shopping around for a current LLM for a particular application, it makes sense to first clarify the evaluation criteria you should be using. We’ll cover that in the sections below.

Large Language Models Comparison By Industry Use Case

One of the more remarkable aspects of current LLMs is that they’re good at so many things. Out of the box, most can do very well at answering questions, summarizing text, translating between natural languages, and much more.

But there might be situations in which you’d want to boost the performance of one of the current LLMs on certain tasks. The two most popular ways of doing this are retrieval-augmented generation (RAG) and fine-tuning a pre-trained model.

Here’s a quick recap of what both of these are:

Retrieval-augmented generation refers to getting one of the general-purpose, current LLMs to perform better by giving them access to additional resources they can use to improve their outputs. You might hook it up to a contact-center CRM so that it can provide specific details about orders, for example.
Fine-tuning refers to taking a pre-trained model and honing it for specific tasks by continuing its training on data related to that task. A generic model might be shown hundreds of polite interactions between customers and CX agents, for example, so that it’s more courteous and helpful.

So, if you’re considering using one of the current LLMs in your business, there are a few questions you should ask yourself. First, are any of them perfectly adequate as-is? If they’re not, the next question is how “adaptable” they are. It’s possible to use RAG or fine-tuning with most of the current LLMs, the question is how easy they make it.

Of course, by far the easiest option would be to leverage a model-agnostic conversational AI platform for CX. These can switch seamlessly between different models, and some support RAG out of the box, meaning you aren’t locked into one current LLM and can always reach for the right tool when needed.

What’s a Good Way To Think About an Open-Source or Closed-Source Large Language Models Comparison?

You’ve probably heard of “open-source,” which refers to the practice of releasing source code to the public so that it can be forked, modified, and scrutinized.

The open-source approach has become incredibly popular, and this enthusiasm has partially bled over into artificial intelligence and machine learning. It is now fairly common to open-source software, datasets, and training frameworks like TensorFlow.

How does this translate to the realm of large language models? In truth, it’s a bit of a mixture. Some models are proudly open-sourced, while others jealously guard their model’s weights, training data, and source code.

This is one thing you might want to consider as you carry out your LLM comparisons. Some of the very best models, like ChatGPT, are closed-source. The downside of using such a model is that you’re entirely beholden to the team that built it. If they make updates or go bankrupt, you could be left scrambling at the last minute to find an alternative solution.

There’s no one-size-fits-all approach here, but it’s worth pointing out that a high-quality enterprise solution will support customization by allowing you to choose between different models (both close-source and open-source). This way, you needn’t concern yourself with forking repos or fret over looming updates, you can just use whichever model performs the best for your particular application.

Getting A Large Language Models Comparison Through Leaderboards and Websites

Instead of doing your LLM comparisons yourself, you could avail yourself of a service built for this purpose.

Whatever rumors you may have heard, programmers are human beings, and human beings have a fondness for ranking and categorizing pretty much everything – sports teams, guitar solos, classic video games, you name it.

Naturally, as current LLMs have become better known, leaderboards and websites have popped up comparing them along all sorts of different dimensions. Here are a few you can use as you search around for the best current LLMs.

Leaderboards for Comparing LLMs

In the past couple of months, leaderboards have emerged which directly compare various current LLMs.

One is AlpacaEval, which uses a custom dataset to compare ChatGPT, Claude, Cohere, and other LLMs on how well they can follow instructions. AlpacaEval boasts high agreement with human evaluators, so in our estimation, it’s probably a suitable way of initially comparing LLMs, though more extensive checks might be required to settle on a final list.

Another good choice is Chatbot Arena, which pits two anonymous models side-by-side, has you rank which one is better, then aggregates all the scores into a leaderboard.

Finally, there is Hugging Face’s Open LLM Leaderboard, which is similar. Anyone can submit a new model for evaluation, which is then assessed based on a small set of key benchmarks from the Eleuther AI Language Model Evaluation Harness. These capture how well the models do in answering simple science questions, common-sense queries, and more, which will be of interest to CX leaders.

When combined with the criteria we discussed earlier, these leaderboards and comparison websites ought to give you everything you need to execute a constructive large language models comparison.

What are the Currently-Available Large Language Models?

Okay! Now that we’ve worked through all this background material, let’s turn to discussing some of the major LLMs that are available today. We make no promises about these entries being comprehensive (and even if they were, there’d be new models out next week), but they should be sufficient to give you an idea as to the range of options you have.

ChatGPT and GPT

Obviously, the titan in the field is OpenAI’s ChatGPT, which is really just a version of GPT that has been fine-tuned through reinforcement learning from human feedback to be especially good at sustained dialogue.

ChatGPT and GPT have been used in many domains, including customer service, question answering, and many others. As of this writing, the most recent GPT is version 4o (note: that’s the letter ‘o’, not the number ‘0’).

LLaMA

In April 2024, Facebook’s AI team released version three of its Large Language Model Meta AI (LLaMa 3). At 70 billion parameters it is not quite as big as GPT; this is intentional, as its purpose is to aid researchers who may not have the budget or expertise required to provision a behemoth LLM.

Gemini

Like GPT-4, Google’s Gemini is aimed squarely at dialogue. It is able to converse on a nearly infinite number of subjects, and from the beginning, the Google team has focused on having Gemini produce interesting responses that are nevertheless absent of abuse and harmful language.

StableLM

StableLM is a lightweight, open-source language model built by Stability AI. It’s trained on a new dataset called “The Pile”, which is itself made up of over 20 smaller, high-quality datasets which together amount to over 825 GB of natural language.

GPT4All

What would you get if you trained an LLM on “…on a massive curated corpus of assistant interactions, which included word problems, multi-turn dialogue, code, poems, songs, and stories,” and then released it on an Apache 2.0 license? The answer is GPT4All, an open-source model whose purpose is to encourage research into what these technologies can accomplish.

BLOOM

The BigScience Large Open-Science Open-Access Multilingual Language Model (BLOOM) was released in late 2022. The team that put it together consisted of more than a thousand researchers from all over the worlds, and unlike the other models on this list, it’s specifically meant to be interpretable.

Pathways Language Model (PaLM)

PaLM is from Google, and is also enormous (540 billion parameters). It excels in many language-related tasks, and became famous when it produced really high-level explanations of tricky jokes. The most recent version is PaLM 2.

Claude

Anthropic’s Claude is billed as a “next-generation AI assistant.” The recent release of Claude 3.5 Sonnet “sets new industry benchmarks” in speed and intelligence, according to materials put out by the company. We haven’t looked at all the data ourselves, but we have played with the model and we know it’s very high-quality.

Command and Command R+

These are models created by Cohere, one of the major commercial platforms for current LLMs. They are comparable to most of the other big models, but Cohere has placed a special focus on enterprise applications, like agents, tools, and RAG.

What are the Best Ways of Overcoming the Limitations of Large Language Models?

Large language models are remarkable tools, but they nevertheless suffer from some well-known limitations. They tend to hallucinate facts, for example, sometimes fail at basic arithmetic, and can get lost in the course of lengthy conversations.

Overcoming the limitations of large language models is mostly a matter of either monitoring them and building scaffolding to enable RAG, or partnering with a conversational AI platform for CX that handles this tedium for you.

An additional wrinkle involves tradeoffs between different models. As we discuss below, sometimes models may outperform the competition on a task like code generation while being notably worse at a task like faithfully following instructions; in such cases, many opt to have an ensemble of models so they can pick and choose which to deploy in a given scenario. (It’s worth pointing out that even if you want to use one model for everything, you’ll absolutely need to swap in an upgraded version of that model eventually, so you still have the same model-management problem.)

This, too, is a place where a conversational AI platform for CX will make your life easier. The best such platforms are model-agnostic, meaning that they can use ChatGPT, Claude, Gemini, or whatever makes sense in a particular situation. This removes yet another headache, smoothing the way for you to use generative AI in your contact center with little fuss.

What are the Best Large Language Models?

Having read the foregoing, it’s natural to wonder if there’s a single model that best suits your enterprise. The answer is “it depends on the specifics of your use case.” You’ll have to think about whether you want an open-source model you control or you’re comfortable hitting an API, whether your use case is outside the scope of ChatGPT and better handled with a bespoke model, etc.

Speaking of use cases, in the next few sections, we’ll offer some advice on which current LLMs are best suited for which applications. However, this advice is based mostly on personal experience and other people’s reports of their experiences. This should be good enough to get you started, but bear in mind that these claims haven’t been born out by rigorous testing and hard evidence—the field is too young for most of that to exist yet.

What’s the Best LLM if I’m on a Budget?

Pretty much any open-source model is given away for free, by definition. You can just Google “free open-source LLMs”, but one of the more frequently recommended open-source models is LLaMA 2 (there’s also the new LLaMA 3), both of which are free.

But many LLMs (both free and paid) also use the data you feed them for training purposes, which means you could be exposing proprietary or sensitive data if you’re not careful. Your best bet is to find a cost-effective platform that has an explicit promise not to use your data for training.

When you deal with an open-source model, you also have to pay for hosting, either your own or through a cloud service like Amazon Bedrock.

What’s the Best LLM for a Large Context Window?

The context window is the amount of text an LLM can handle at a time. When ChatGPT was released, it had a context window of around 4,000 tokens. (A “token” isn’t exactly a word, but it’s close enough for our purposes.)

Generally (and up to a point), the longer the context window the better the model is able to perform. Today’s models generally have context windows of at least a few tens of thousands, and some getting into the lower 100,000 range.

But, at a staggering 1 million tokens–equivalent to an hour-long video or the full text of a long novel–Google’s Gemini simply towers over the others like Hagrid in the Shire.

That having been said, this space moves quickly, and context window length is an active area of research and development. These figures will likely be different next month, so be sure to check the latest information as you begin shopping for a model.

Choosing Among the Current Large Language Models

With all the different LLMs on offer, it’s hard to narrow the search down to the one that’s best for you. By carefully weighing the different metrics we’ve discussed in this article, you can choose an LLM that meets your needs with as little hassle as possible.

Pulling back a bit, let’s close by recalling that the whole purpose of choosing among current LLMs in the first place is to better meet the needs of our customers.

For this reason, you might want to consider working with a conversational AI platform for CX, like Quiq, that puts a plethora of LLMs at your fingertips through one simple interface.

Request A Demo

The Truth About APIs for AI: What You Need to Know

Posted on August 7, 2024November 15, 2024 The Quiq Team

Large language models hold a lot of power to improve your customer experience and make your agents more effective, but they won’t do you much good if you don’t have a way to actually access them.

This is where application programming interfaces (APIs) come into play. If you want to leverage LLMs, you’ll either have to build one in-house, use an AI API deployment to interact with an external model, or go with a customer-centric AI for CX platform. The latter choice is most ideal because it offers a guided building environment that removes complexity while providing the tools you need for scalability, observability, hallucination prevention, and more.

From a cost and ease-of-use perspective this third option is almost always best, but there are many misconceptions that could potentially stand in the way of AI API adoption.

In fact, a stronger claim is warranted: to maximize AI API effectiveness, you need a platform to orchestrate between AI, your business logic, and the rest of your CX stack.

Otherwise, it’s useless.

This article aims to bridge the gap between what CX leaders might think is required to integrate a platform, and what’s actually involved. By the end, you’ll understand what APIs are, their role in personalization and scalability, and why they work best in the context of a customer-centric AI for CX platform.

How APIs Facilitate Access to AI Capabilities

Let’s start by defining an API. As the name suggests, APIs are essentially structured protocols that allow two systems (“applications”) to communicate with one another (“interface”). For instance, if you’re using a third-party CRM to track your contacts, you’ll probably update it through an API.

All the well-known foundation model providers (e.g., OpenAI, Anthropic, etc.) have a real-world AI API implementation that allows you to use their service. For an AI API practical example, let’s look at OpenAI’s documentation:

(Let’s take a second to understand what we’re looking at. Don’t worry – we’ll break it down for you. Understanding the basics will give you a sense for what your engineers will be doing.)

The top line points us to a URL where we can access OpenAI’s models, and the next three lines require us to pass in an API key (which is kind of like a password giving access to the platform), our organization ID (a unique designator for our particular company, not unlike a username), and a project ID (a way to refer to this specific project, useful if you’re working on a few different projects at once).

This is only one example, but you can reasonably assume that most protocols built according to AI API best practices will have a similar structure.

This alone isn’t enough to support most AI API use cases, but it illustrates the key takeaway of this section: APIs are attractive because they make it easy to access the capabilities of LLMs without needing to manage them on your own infrastructure, though they’re still best when used as part of a move to a customer-centric AI orchestration platform.

How Do APIs Facilitate Customer Support AI Assistants?

It’s good to understand what APIs are used for in AI assistants. It’s pretty straightforward—here’s the bulk of it:

Personalizing customer communications: One of the most exciting real-world benefits of AI is that it enables personalization at scale because you can integrate an LLM with trusted systems containing customer profiles, transaction data, etc., which can be incorporated into a model’s reply. So, for example, when a customer asks for shipping information, you’re not limited to generic responses like “your item will be shipped within 3 days of your order date.” Instead, you can take a more customer-centric approach and offer specific details, such as, “The order for your new couch was placed on Monday, and will be sent out on Wednesday. According to your location, we expect that it’ll arrive by Friday. Would you like to select a delivery window or upgrade to white glove service?”
Improving response quality: Generative AI is plagued by a tendency to fabricate information. With an AI API, work can be decomposed into smaller, concrete tasks before being passed to an LLM, which improves performance. You can also do other things to get better outputs, such as create bespoke modifications of the prompt that change the model’s tone, the length of its reply, etc.
Scalability and flexibility in deployment: A good customer-centric, AI-for-CX platform will offer volume-based pricing, meaning you can scale up or down as needed. If customer issues are coming in thick and fast (such as might occur during a new product release, or over a holiday), just keep passing them to the API while paying a bit more for the increased load; if things are quiet because it’s 2 a.m., the API just sits there, waiting to spring into action when required and costing you very little.
Analyzing customer feedback and sentiment: Incredible insights are waiting within your spreadsheets and databases, if you only know how to find them. This, too, is something APIs help with. If, for example, you need to unify measurements across your organization to send them to a VOC (voice of customer) platform, you can do that with an API.

Looking Beyond an API for AI Assistants

For all this, it’s worth pointing out that there’s still many real-world AI API challenges. By far the quickest way to begin building an AI assistant for CX is to pair with a customer-centric AI platform that removes as much of the difficulty as possible.

The best such platforms not only allow you to utilize a bevy of underlying LLM models, they also facilitate gathering and analyzing data, monitoring and supporting your agents, and automating substantial parts of your workflow.

Crucially, almost all of those critical tasks are facilitated through APIs, but they can be united in a good platform.

3 Common Misconceptions about Customer-Centric AI for CX Platforms.

Now, let’s address some of the biggest myths surrounding the use of AI orchestration platforms.

Myth 1: Working with a customer-centric AI for CX Platform Will be a Hassle

Some CX leaders may worry that working with a platform will be too difficult. There are challenges, to be sure, but a well-designed platform with an intuitive user interface is easy to slip into a broader engineering project.

Such platforms are designed to support easy integration with existing systems, and they generally have ample documentation available to make this task as straightforward as possible.

Myth 2: AI Platforms Cost Too Much

Another concern CX leaders have is the cost of using an AI orchestration platform. Platform costs can add up over time, but this pales in comparison to the cost of building in-house solutions. Not to mention the potential costs associated with the risks that come with building AI in an environment that doesn’t protect you from things like hallucinations.

When you weigh all the factors impacting your decision to use AI in your contact center, the long-run return on using an AI orchestration platform is almost always better.

Myth 3: Customer-Centric AI Platforms are Just Too Insecure

The smart CX leader always has one eye on the overall security of their enterprise, so they may be worried about vulnerabilities introduced by using an AI platform.

This is a perfectly reasonable concern. If you’re trying to choose between a few different providers, it’s worth investigating the security measures they’ve implemented. Specifically, you want to figure out what data encryption and protection protocols they use, and how they think about compliance with industry standards and regulations.

At a minimum, the provider should be taking basic steps to make sure data transmitted to the platform isn’t exposed.

Is an AI Platform Right for Me?

With a platform focused on optimizing CX outcomes, you can quickly bring the awesome power and flexibility of generative AI into your contact center – without ever spinning up a server or fretting over what “backpropagation” means. To the best of our knowledge, this is the cheapest and fastest way to demo this API technology in your workflow to determine whether it warrants a deeper investment.

To parse out more generative AI facts from fiction, download our e-book on AI misconceptions and how to overcome them. If you’re concerned about hallucinations, data privacy, and similar issues, you won’t find a better one-stop read!

Request A Demo

Does Quiq Train Models on Your Data? No (And Here’s Why.)

Posted on June 28, 2024November 15, 2024 The Quiq Team

Customer experience directors tend to have a lot of questions about AI, especially as it becomes more and more important to the way modern contact centers function.

These can range from “Will generative AI’s well-known tendency to hallucinate eventually hurt my brand?” to “How are large language models trained in the first place?” along with many others.

Speaking of training, one question that’s often top of mind for prospective users of Quiq’s conversational AI platform is whether we train the LLMs we use with your data. This is a perfectly reasonable question, especially given famous examples of LLMs exposing proprietary data, such as happened at Samsung. Needless to say, if you have sensitive customer information, you absolutely don’t want it getting leaked – and if you’re not clear on what is going on with an LLM, you might not have the confidence you need to use one in your contact center.

The purpose of this piece is to assure you that no, we do not train LLMs with your data. To hammer that point home, we’ll briefly cover how models are trained, then discuss the two ways that Quiq optimizes model behavior: prompt engineering and retrieval augmented generation.

How are Large Language Models Trained?

Part of the confusion stems from the fact that the term ‘training’ means different things to different people. Let’s start by clarifying what this term means, but don’t worry–we’ll go very light on technical details!

First, generative language models work with tokens, which are units of language such as a part of a word (“kitch”), a whole word (“kitchen”), or sometimes small clusters of words (“kitchen sink”). When a model is trained, it’s learning to predict the token that’s most likely to follow a string of prior tokens.

Once a model has seen a great deal of text, for example, it learns that “Mary had a little ____” probably ends with the token “lamb” rather than the token “lightbulb.”

Crucially, this process involves changing the model’s internal weights, i.e. its internal structure. Quiq has various ways of optimizing a model to perform in settings such as contact centers (discussed in the next section), but we do not change any model’s weights.

How Does Quiq Optimize Model Behavior?

There are a few basic ways to influence a model’s output. The two used by Quiq are prompt engineering and retrieval augmented generation (RAG), neither of which does anything whatsoever to modify a model’s weights or its structure.

In the next two sections, we’ll briefly cover each so that you have a bit more context on what’s going on under the hood.

Prompt Engineering

Prompt engineering involves changing how you format the query you feed the model to elicit a slightly different response. Rather than saying, “Write me some social media copy,” for example, you might also include an example outline you want the model to follow.

Quiq uses an approach to prompt engineering called “atomic prompting,” wherein the process of generating an answer to a question is broken down into multiple subtasks. This ensures you’re instructing a Large Language Model in a smaller context with specific, relevant task information, which can help the model perform better.

This is not the same thing as training. If you were to train or fine-tune a model on company-specific data, then the model’s internal structure would change to represent that data, and it might inadvertently reveal it in a future reply. However, including the data in a prompt doesn’t carry that risk because prompt engineering doesn’t change a model’s weights.

Retrieval Augmented Generation (RAG)

RAG refers to giving a language model an information source – such as a database or the Internet – that it can use to improve its output. It has emerged as the most popular technique to control the information the model needs to know when generating answers.

As before, that is not the same thing as training because it does not change the model’s weights.

RAG doesn’t modify the underlying model, but if you connect it to sensitive information and then ask it a question, it may very well reveal something sensitive. RAG is very powerful, but you need to use it with caution. Your AI development platform should provide ways to securely connect to APIs that can help authenticate and retrieve account information, thus allowing you to provide customers with personalized responses.

This is why you still need to think about security when using RAG. Whatever tools or information sources you give your model must meet the strictest security standards and be certified, as appropriate.

Quiq is one such platform, built from the ground-up with data security (encryption in transit) and compliance (SOC 2 certified) in mind. We never store or use data without permission, and we’ve crafted our tools so it’s as easy as possible to utilize RAG on just the information stores you want to plug a model into. Being a security-first company, this extends to our utilization of Large Language Models and agreements with AI providers like Microsoft Open AI.

Wrapping Up on How Quiq Trains LLMs

Hopefully, you now have a much clearer picture of what Quiq does to ensure the models we use are as performant and useful as possible. With them, you can make your customers happier, improve your agents’ performance, and reduce turnover at your contact center.

If you’re interested in exploring some other common misconceptions that CX leaders face when considering incorporating generative AI into their technology stack, check out our ebook on the subject. It contains a great deal of information to help you make the best possible decision!

Request A Demo

Does GenAI Leak Your Sensitive Data? Exposing Common AI Misconceptions (Part Three)

Posted on June 18, 2024November 15, 2024 The Quiq Team

This is the final post in a three-part series clarifying the biggest misconceptions holding CX leaders like you back from integrating GenAI into their CX strategies. Our goal? To assuage your fears and help you start getting real about adding an AI Assistant to your contact center — all in a fun “two truths and a lie” format.

There are few faux pas as damaging and embarrassing for brands as sensitive data getting into the wrong hands. So it makes sense that data security concerns are a major deterrent for CX leaders thinking about getting started with GenAI.

In the first post of our AI Misconceptions series, we discussed why your data is definitely good enough to make GenAI work for your business. Next, we explored the different types of hallucinations that CX leaders should be aware of, and how they are 100% preventable with the right guardrails in place.

Now, let’s wrap up our series by exposing the truth about GenAI potentially leaking your company or customer data.

Misconception #3: “GenAI inadvertently leaks sensitive data.”

As we discussed in part one, AI needs training data to work. One way to collect that data is from the questions users ask. For example, if a large language model (LLM) is asked to summarize a paragraph of text, that text could be stored and used to train future models.

Unfortunately, there have been some famous examples of companies’ sensitive information becoming part of datasets used to train LLMs — take Samsung, for instance. Because of this, CX leaders often fear that using GenAI will result in their company’s proprietary data being disclosed when users interact with these models.

Truth #1: Public GenAI tools use conversation data to train their models.

Tools like OpenAI’s ChatGPT and Google Gemini (formerly Bard) are public-facing and often free — and that’s because their purpose is to collect training data. This means that any information that users enter while using these tools is free game to be used for training future models.

This is precisely how the Samsung data leak happened. The company’s semiconductor division allowed its engineers to use ChatGPT to check their source code. Not only did multiple employees copy/paste confidential code into ChatGPT, but one team member even used the tool to transcribe a recording of an internal-only meeting!

Truth #2: Properly licensed GenAI is safe.

People often confuse ChatGPT, the application or web portal, with the LLM behind it. While the free version of ChatGPT collects conversation data, OpenAI offers an enterprise LLM that does not. Other LLM providers offer similar enterprise licenses that specify that all interactions with the LLM and any data provided will not be stored or used for training purposes.

When used through an enterprise license, LLMs are also Service Organization Control Type 2, or SOC 2, compliant. This means they have to undergo regular audits from third parties to prove that they have the processes and procedures in place to protect companies’ proprietary data and customers’ personally identifiable information (PII).

The Lie: Enterprises must use internally-developed models only to protect their data.

Given these concerns over data leaks and hallucinations, some organizations believe that the only safe way to use GenAI is to build their own AI models. Case in point: Samsung is now “considering building its own internal AI chatbot to prevent future embarrassing mishaps.”

However, it’s simply not feasible for companies whose core business is not AI to build AI that is as powerful as commercially available LLMs — even if the company is as big and successful as Samsung. Not to mention the opportunity cost and risk of having your technical resources tied up in AI instead of continuing to innovate on your core business.

It’s estimated that training the LLM behind ChatGPT cost upwards of $4 million. It also required specialized supercomputers and access to a data set equivalent to nearly the entire Internet. And don’t forget about maintenance: AI startup Hugging Face recently revealed that retraining its Bloom LLM cost around $10 million.

Using a commercially available LLM provides enterprises with the most powerful AI available without breaking the bank— and it’s perfectly safe when properly licensed. However, it’s also important to remember that building a successful AI Assistant requires much more than developing basic question/answer functionality.

Finding a Conversational CX Platform that harnesses an enterprise-licensed LLM, empowers teams to build complex conversation flows, and makes it easy to monitor and measure Assistant performance is a CX leader’s safest bet. Not to mention, your engineering team will thank you for giving them optionality for the control and visibility they want—without the risk and overhead of building it themselves!

Feel Secure About GenAI Data Security

Companies that use free, public-facing GenAI tools should be aware that any information employees enter can (and most likely will) be used for future model-training purposes.

However, properly-licensed GenAI will not collect or use your data to train the model. Building your own GenAI tools for security purposes is completely unnecessary — and very expensive!

Want to read more or revisit the first two misconceptions in our series? Check out our full guide, Two Truths and a Lie: Breaking Down the Major GenAI Misconceptions Holding CX Leaders Back.

Will GenAI Hallucinate and Hurt Your Brand? Exposing Common AI Misconceptions (Part Two)

Posted on June 13, 2024November 15, 2024 The Quiq Team

This is the second post in a three-part series clarifying the biggest misconceptions holding CX leaders like you back from integrating GenAI into their CX strategies. Our goal? To assuage your fears and help you start getting real about adding an AI Assistant to your contact center — all in a fun “two truths and a lie” format.

Did you know that the Golden Gate Bridge was transported for the second time across Egypt in October of 2016?

Or that the world record for crossing the English Channel entirely on foot is held by Christof Wandratsch of Germany, who completed the crossing in 14 hours and 51 minutes on August 14, 2020?

Probably not, because GenAI made these “facts” up. They’re called hallucinations, and AI hallucination misconceptions are holding a lot of CX leaders back from getting started with GenAI.

In the first post of our AI Misconceptions series, we discussed why your data is definitely good enough to make GenAI work for your business. In fact, you actually need a lot less data to get started with an AI Assistant than you probably think.

Now, we’re debunking AI hallucination myths and separating some of the biggest AI hallucination facts from fiction. Could adding an AI Assistant to your contact center put your brand at risk? Let’s find out.

Misconception #2: “GenAI will hallucinate and hurt my brand.”

While the example hallucinations provided above are harmless and even a little funny, this isn’t always the case. Unfortunately, there are many examples of times chatbots have cussed out customers or made racist or sexist remarks. This causes a lot of concern among CX leaders looking to use an AI Assistant to represent their brand.

Truth #1: Hallucinations are real (no pun intended).

Understanding AI hallucinations hinges on realizing that GenAI wants to provide answers — whether or not it has the right data. Hallucinations like those in the examples above occur for two common reasons.

AI-Induced Hallucinations Explained:

The large language model (LLM) simply does not have the correct information it needs to answer a given question. This is what causes GenAI to get overly creative and start making up stories that it presents as truth.
The LLM has been given an overly broad and/or contradictory dataset. In other words, the model gets confused and begins to draw conclusions that are not directly supported in the data, much like a human would do if they were inundated with irrelevant and conflicting information on a particular topic.

Truth #2: There’s more than one type of hallucination.

Contrary to popular belief, hallucinations aren’t just incorrect answers: They can also be classified as correct answers to the wrong questions. And these types of hallucinations are actually more common and more difficult to control.

For example, imagine a company’s AI Assistant is asked to help troubleshoot a problem that a customer is having with their TV. The Assistant could give the customer correct troubleshooting instructions — but for the wrong television model. In this case, GenAI isn’t wrong, it just didn’t fully understand the context of the question.

The Lie: There’s no way to prevent your AI Assistant from hallucinating.

Many GenAI “bot” vendors attempt to fine-tune an LLM, connect clients’ knowledge bases, and then trust it to generate responses to their customers’ questions. This approach will always result in hallucinations. A common workaround is to pre-program “canned” responses to specific questions. However, this leads to unhelpful and unnatural-sounding answers even to basic questions, which then wind up being escalated to live agents.

In contrast, true AI Assistants powered by the latest Conversational CX Platforms leverage LLMs as a tool to understand and generate language — but there’s a lot more going on under the hood.

First of all, preventing hallucinations is not just a technical task. It requires a layer of business logic that controls the flow of the conversation by providing a framework for how the Assistant should respond to users’ questions.

This framework guides a user down a specific path that enables the Assistant to gather the information the LLM needs to give the right answer to the right question. This is very similar to how you would train a human agent to ask a specific series of questions before diagnosing an issue and offering a solution. Meanwhile, in addition to understanding what the intent of the customer’s question is, the LLM can be used to extract additional information from the question.

Referred to as “pre-generation checks,” these filters are used to determine attributes such as whether the question was from an existing customer or prospect, which of the company’s products or services the question is about, and more. These checks happen in the background in mere seconds and can be used to select the right information to answer the question. Only once the Assistant understands the context of the client’s question and knows that it’s within scope of what it’s allowed to talk about does it ask the LLM to craft a response.

But the checks and balances don’t end there: The LLM is only allowed to generate responses using information from specific, trusted sources that have been pre-approved, and not from the dataset it was trained on.

In other words, humans are responsible for providing the LLM with a source of truth that it must “ground” its response in. In technical terms, this is called Retrieval Augmented Generation, or RAG — and if you want to get nerdy, you can read all about it here!

Last but not least, once a response has been crafted, a series of “post- generation checks” happens in the background before returning it to the user. You can check out the end-to-end process in the diagram below:

Give Hallucination Concerns the Heave-Ho

To sum it up: Yes, hallucinations happen. In fact, there’s more than one type of hallucination that CX leaders should be aware of.

However, now that you understand the reality of AI hallucination, you know that it’s totally preventable. All you need are the proper checks, balances, and guardrails in place, both from a technical and a business logic standpoint.

Now that you’ve had your biggest misconceptions about AI hallucination debunked, keep an eye out for the next blog in our series, all about GenAI data leaks. Or, learn the truth about all three of CX leaders’ biggest GenAI misconceptions now when you download our guide, Two Truths and a Lie: Breaking Down the Major GenAI Misconceptions Holding CX Leaders Back.

Request A Demo

Is Your CX Data Good Enough for GenAI? Exposing Common AI Misconceptions (Part One)

Posted on June 5, 2024November 15, 2024 The Quiq Team

If you’re feeling unprepared for the impact of generative artificial intelligence (GenAI), you’re not alone. In fact, nearly 85% of CX leaders feel the same way. But the truth is that the transformative nature of this technology simply can’t be ignored — and neither can your boss, who asked you to look into it.

We’ve all heard horror stories of racist chatbots and massive data leaks ruining brands’ reputations. But we’ve also seen statistics around the massive time and cost savings brands can achieve by offloading customers’ frequently asked questions to AI Assistants. So which is it?

This is the first post in a three-part series clarifying the biggest misconceptions holding CX leaders like you back from integrating GenAI into their CX strategies. Our goal? To assuage your fears and help you start getting real about adding an AI Assistant to your contact center — all in a fun “two truths and a lie” format. Prepare to have your most common AI misconceptions debunked!

Misconception #1: “My data isn’t good enough for GenAI.”

Answering customer inquiries usually requires two types of data:

Knowledge (e.g. an order return policy) and
Information from internal systems (e.g. the specific details of an order).

It’s easy to get caught up in overthinking the impact of data quality on AI performance and wondering whether or not your knowledge is even good enough to make an AI Assistant useful for your customers.

Updating hundreds of help desk articles is no small task, let alone building an entire knowledge base from scratch. Many CX leaders are worried about the amount of work it will require to clean up their data and whether their team has enough resources to support a GenAI initiative. In order for GenAI to be as effective as a human agent, it needs the same level of access to internal systems as human agents.

Truth #1: You have to have some amount of data.

Data is necessary to make AI work — there’s no way around it. You must provide some data for the model to access in order to generate answers. This is one of the most basic AI performance factors.

But we have good news: You need a lot less data than you think.

One of the most common myths about AI and data in CX is that it’s necessary to answer every possible customer question. Instead, focus on ensuring you have the knowledge necessary to answer your most frequently asked questions. This small step forward will have a major impact for your team without requiring a ton of time and resources to get started

Truth #2: Quality matters more than quantity.

Given the importance of relevant data in AI, a few succinct paragraphs of accurate information is better than volumes of outdated or conflicting documentation. But even then, don’t sweat the small stuff.

For example, did a product name change fail to make its way through half of your help desk articles? Are there unnecessary hyperlinks scattered throughout? Was it written for live agents versus customers?

No problem — the right Conversational CX Platform can easily address these AI data dependency concerns without requiring additional support from your team.

The Lie: Your data has to be perfectly unified and specifically formatted to train an AI Assistant.

Don’t worry if your data isn’t well-organized or perfectly formatted. The reality is that most companies have services and support materials scattered across websites, knowledge bases, PDFs, .csvs, and dozens of other places — and that’s okay!

Today, the tools and technology exist to make aggregating this fragmented data a breeze. They’re then able to cleanse and format it in a way that makes sense for a large language model (LLM) to use.

For example if you have an agent training manual in Google Docs and a product manual in PDF, this information can be disassembled, reformatted, and rewritten by an AI-powered transformation that makes it subsequently usable.

What’s more, the data used by your AI Assistant should be consistent with the data you use to train your human agents. This means that not only is it not required to build a special repository of information for your AI Assistant to learn from, but it’s not recommended. The very best AI platforms take on the work of maintaining this continuity by automatically processing and formatting new information for your Assistant as it’s published, as well as removing any information that’s been deleted.

Put Those Data Doubts to Bed

Now you know that your data is definitely good enough for GenAI to work for your business. Yes, quality matters more than quantity, but it doesn’t have to be perfect.

The technology exists to unify and format your data so that it’s usable by an LLM. And providing knowledge around even a handful of frequently asked questions can give your team a major lift right out the gate.

Keep an eye out for the next blog in our series, all about GenAI hallucinations. Or, learn the truth about all three of CX leaders’ biggest GenAI misconceptions now when you download our guide, Two Truths and a Lie: Breaking Down the Major GenAI Misconceptions Holding CX Leaders Back.

Request A Demo

5 Tips for Coaching Your Contact Center Agents to Work with AI

Posted on April 25, 2024November 15, 2024 Michael Hartsog

Generative AI has enormous potential to change the work done at places like contact centers. For this reason, we’ve spent a lot of energy covering it, from deep dives into the nuts and bolts of large language models to detailed advice for managers considering adopting it.

Here, we will provide tips on using AI tools to coach, manage, and improve your agents.

How Will AI Make My Agents More Productive?

Contact centers can be stressful places to work, but much of that stems from a paucity of good training and feedback. If an agent doesn’t feel confident in assuming their responsibilities or doesn’t know how to handle a tricky situation, that will cause stress.

Tip #1: Make Collaboration Easier

With the right AI tools for coaching agents, you can get state-of-the-art collaboration tools that allow agents to invite their managers or colleagues to silently appear in the background of a challenging issue. The customer never knows there’s a team operating on their behalf, but the agent won’t feel as overwhelmed. These same tools also let managers dynamically monitor all their agents’ ongoing conversations, intervening directly if a situation gets out of hand.

Agents can learn from these experiences to become more performant over time.

Tip #2: Use Data-Driven Management

Speaking of improvement, a good AI platform will have resources that help managers get the most out of their agents in a rigorous, data-driven way. Of course, you’re probably already monitoring contact center metrics, such as CSAT and FCR scores, but this barely scratches the surface.

What you really need is a granular look into agent interactions and their long-term trends. This will let you answer questions like “Am I overstaffed?” and “Who are my top performers?” This is the only way to run a tight ship and keep all the pieces moving effectively.

Tip #3: Use AI To Supercharge Your Agents

As its name implies, generative AI excels at generating text, and there are several ways this can improve your contact center’s performance.

To start, these systems can sometimes answer simple questions directly, which reduces the demands on your team. Even when that’s not the case, however, they can help agents draft replies, or clean up already-drafted replies to correct errors in spelling and grammar. This, too, reduces their stress, but it also contributes to customers having a smooth, consistent, high-quality experience.

Tip #4: Use AI to Power Your Workflows

A related (but distinct) point concerns how AI can be used to structure the broader work your agents are engaged in.

Let’s illustrate using sentiment analysis, which makes it possible to assess the emotional state of a person doing something like filing a complaint. This can form part of a pipeline that sorts and routes tickets based on their priority, and it can also detect when an issue needs to be escalated to a skilled human professional.

Tip #5: Train Your Agents to Use AI Effectively

It’s easy to get excited about what AI can do to increase your efficiency, but you mustn’t lose sight of the fact that it’s a complex tool your team needs to be trained to use. Otherwise, it’s just going to be one more source of stress.

You need to have policies around the situations in which it’s appropriate to use AI and the situations in which it’s not. These policies should address how agents should deal with phenomena like “hallucination,” in which a language model will fabricate information.

They should also contain procedures for monitoring the performance of the model over time. Because these models are stochastic, they can generate surprising output, and their behavior can change.

You need to know what your model is doing to intervene appropriately.

Wrapping Up

Hopefully, you’re more optimistic about what AI can do for your contact center, and this has helped you understand how to make the most out of it.

If there’s anything else you’d like to go over, you’re always welcome to request a demo of the Quiq platform. Since we focus on contact centers we take customer service pretty seriously ourselves, and we’d love to give you the context you need to make the best possible decision!

Request A Demo

AI Gold Rush: How Quiq Won the Land Grab for AI Contact Centers (& How You Can Benefit)

Posted on April 10, 2024November 15, 2024 Michael Hartsog

There have been many transformational moments throughout the history of the United States, going back all the way to its unique founding.

Take for instance the year 1849.

For all of you SFO 49ers fans (sorry, maybe next year), you are very well aware of the land grab that was the birth of the state of California. That year, tens of thousands of people from the Eastern United States flocked to the California Territory hoping to strike it rich in a placer gold strike.

A lesser-known fact of that moment in history is that the gold strike in California was actually in 1848. And while all of those easterners were lining up for the rush, a small number of people from Latin America and Hawaii were already in production, stuffing their pockets full of nuggets.

176 years later, AI is the new gold rush.

Fast forward to 2024, a new crowd is forming, working toward the land grab once again. Only this time, it’s not physical.

It’s AI in the contact center.

Companies are building infrastructure, hiring engineers, inventing tools, and trying to figure out how to build a wagon that won’t disintegrate on the trail (AKA hallucinate).

While many of those companies are going to make it to the gold fields, one has been there since 2023, and that is Quiq.

Yes, we’ve been mining LLM gold in the contact center since July of 2023 when we released our first customer-facing Generative AI assistant for Loop Insurance. Since then, we have released over a dozen more and have dozens more under construction. More about the quality of that gold in a bit.

This new gold rush in the AI space is becoming more crowded every day.

Everyone is saying they do Generative AI in one way, shape, or form. Most are offering some form of Agent Assist using LLM technologies, keeping that human in the loop and relying on small increments of improvement in AHT (Average Handle Time) and FCR (First Contact Resolution).

However, there is a difference when it comes to how platforms are approaching customer-facing AI Assistants.

Actually, there are a lot of differences. That’s a big reason we invented AI Studio.

AI Studio: Get your shovels and pick axes.

Since we’ve been on the bleeding edge of Generative AI CX deployments, we created called AI Studio. We saw that there was a gap for CX teams, with the myriad of tools they would have had to stitch together and stay focused on business outcomes.

AI Studio is a complete toolkit to empower companies to explore nuances in their AI use within a conversational development environment that’s tailored for customer-facing CX.

That last part is important: Customer-facing AI assistants, which teams can create together using AI Studio. Going back to our gold rush comparison, AI Studio is akin to the pick axes and shovels you need.

Only success is guaranteed and the proverbial gold at the end of the journey is much, much more enticing—precisely because customer-facing AI applications tend to move the needle dramatically further than simpler Agent Assist LLM builds.

That brings me to the results.

So how good is our gold?

Early results are showing that our LLM implementations are increasing resolution rates 50% to 100% above what was achieved using legacy NLU intent-based models, with resolution rates north of 60% in some FAQ-heavy assistants.

Loop Insurance saw a 55% reduction in email tickets in their contact center.

Secondly, intent matching has more than doubled, meaning the percentage of correctly identified intents (especially when there are multiple intents) are being correctly recognized and responded to, which directly correlates to correct answers, fewer agent contacts, and satisfied customers.

That’s just the start though. Molekule hit a 60% resolution rate with a Quiq-built LLM-powered AI assistant. You can read all about that in our case study here.

And then there’s Accor, whose AI assistant across four Rixos properties has doubled (yes, 2X’ed) click-outs on booking links. Check out that case study here.

What’s next?

Like the miners in 1848, digging as much gold out of the ground as possible before the land rush, Quiq sits alone, out in front of a crowd lining up for a land grab.

With a dozen customer-facing LLM-powered AI assistants already living in the market producing incredible results, we have pioneered a space that will be remembered in history as a new day in Customer Experience.

Interested in harnessing Quiq’s power for your CX or contact center? Send us a demo request or get in touch another way and let’s talk.

Request A Demo

Google Business Messages: Meet Your Customers Where They’re At

Posted on April 5, 2024November 15, 2024 Max Fortis

The world is a distracted and distracting place; between all the alerts, the celebrity drama on Twitter, and the fact that there are more hilarious animal videos on YouTube than you could ever hope to watch even if it were your full-time job, it takes a lot to break through the noise.

That’s one reason customer service-oriented businesses like contact centers are increasingly turning to text messaging. Not only are cell phones all but ubiquitous, but many people have begun to prefer text-message-based interactions to calls, emails, or in-person visits.

In this article, we’ll cover one of the biggest text-messaging channels: Google Business Messages. We’ll discuss what it is, what features it offers, and various ways of leveraging it to the fullest.

Let’s get going!

Learn More About the End of Google Business Messages

What is Google Business Messages?

Given that more than nine out of ten online searches go through Google, we will go out on a limb and assume you’ve heard of the Mountain View behemoth. But you may not be aware that Google has a Business Message service that is very popular among companies, like contact centers, that understand the advantages of texting their customers.

Business Messages allows you to create a “messaging surface” on Android or Apple devices. In practice, this essentially means that you can create a little “chat” button that your customers can use to reach out to you.

Behind the scenes, you will have to register for Business Messages, creating an “agent” that your customers will interact with. You have many configuration options for your Business Messages workflows; it’s possible to dynamically route a given message to contact center agents at a specific location, have an AI assistant powered by large language models generate a reply (more on this later), etc.

Regardless of how the reply is generated, it is then routed through the API to your agent, which is what actually interacts with the customer. A conversation is considered over when both the customer and your agent cease replying, but you can resume a conversation up to 30 days later.

What’s the Difference Between Google RCS and Google Business Messages?

It’s easy to confuse Google’s Rich Communication Services (RCS) and Google Business Messages. Although the two are similar, it’s nevertheless worth remembering their differences.

Long ago, text messages had to be short, sweet, and contain nothing but words. But as we all began to lean more on text messaging to communicate, it became necessary to upgrade the basic underlying protocol. This way, we could also use video, images, GIFs, etc., in our conversations.

“Rich” communication is this upgrade, but it’s not relegated to emojis and such. RCS is also quickly becoming a staple for businesses that want to invest in livelier exchanges with their customers. RCS allows for custom logos and consistent branding, for example; it also makes it easier to collect analytics, insert QR codes, link out to calendars or Maps, etc.

As discussed above, Business Messages is a mobile messaging channel that integrates with Google Maps, Search, and brand websites, offering rich, asynchronous communication experiences. This platform not only makes customers happy but also contributes to your business’s bottom line through reduced call volumes, improved CSAT, and better conversion rates.

Importantly, Business Messages are sometimes also prominently featured in Google search results, such as answer cards, place cards, and site links.

In short, there is a great deal of overlap between Google Business Messages and Google RCS. But two major distinctions are that RCS is not available on all Android devices (where Business Messages is), and Business Messages doesn’t require you to have a messaging app installed (where RCS does).

The Advantages of Google Business Messaging

Google Business Messaging has many distinct advantages to offer the contact center entrepreneur. In the next few sections, we’ll discuss some of the biggest.

It Supports Robust Encryption

A key feature of Business Messages is that its commitment to security and privacy is embodied through powerful, end-to-end encryption.

What exactly does end-to-end encryption entail? In short, it ensures that a message remains secure and unreadable from the moment the sender types it to whenever the recipient opens it, even if it’s intercepted in transit. This level of security is baked in, requiring no additional setup or adjustments to security settings by the user.

The significance of this feature cannot be overstated. Today, it’s not at all uncommon to read about yet another multi-million-dollar ransomware attack or a data breach of staggering proportions. This has engendered a growing awareness of (and concern for) data security, meaning that present and future customers will value those platforms that make it a central priority of their offering.

By our estimates, this will only become more important with the rise of generative AI, which has made it increasingly difficult to trust text, images, and even movies seen online—none of which was particularly trustworthy even before it became possible to mass-produce them.

If you successfully position yourself as a pillar your customers can lean on, that will go a long way toward making you stand out in a crowded market.

It Makes Connecting With Customers Easier

Another advantage of Google Business Messages is that it makes it much easier to meet customers where they are. And where we are is “on our phones.”

Now, this may seem too obvious to need pointing out. After all, if your customers are texting all day and you’re launching a text-messaging channel of communication, then of course you’ll be more accessible.

But there’s more to this story. Google Business Messaging allows you to seamlessly integrate with other Google services, like Google Maps. If a customer is trying to find the number for your contact center, therefore, they could instead get in touch simply by clicking the “CHAT” button.

This, too, may seem rather uninspiring because it’s not as though it’s difficult to grab the number and call. But even leaving aside the rising generations’ aversion to making phone calls, there’s a concept known as “trivial inconvenience” that’s worth discussing in this context.

Here’s an example: if you want to stop yourself from snacking on cookies throughout the day, you don’t have to put them on the moon (though that would help). Usually, it’s enough to put them in the next room or downstairs.

Though this only slightly increases the difficulty of accessing your cookie supply, in most cases, it introduces just enough friction to substantially reduce the number of cookies you eat (depending on the severity of your Oreo addiction, of course).

Well, the exact same dynamic works in reverse. Though grabbing your contact center’s phone number from Google and calling you requires only one or two additional steps, that added work will be sufficient to deter some fraction of customers from reaching out. If you want to make yourself easy to contact, there’s no substitute for a clean integration directly into the applications your customers are using, and that’s something Google Business Messages can do extremely well.

It’s Scalable and Supports Integrations

According to legend, the name “Google” originally came from a play on the word “Googol,” which is a “1” followed by a 100 “0”s. Google, in other words, has always been about scale, and that is reflected in the way its software operates today. For our purposes, the most important manifestation of this is the scalability of their API. Though you may currently be operating at a few hundred or a few thousand messages per day, if you plan on growing, you’ll want to invest early in communication channels that can grow along with you.

But this is hardly the end of what integrations can do for you. If you’re in the contact center business there’s a strong possibility that you’ll eventually end up using a large language model like ChatGPT in order to answer questions more quickly, offboard more routine tasks, etc. Unless you plan on dropping millions of dollars to build one in-house, you’ll want to partner with an AI-powered conversational platform. As you go about finding a good vendor, make sure to assess the features they support. The best platforms have many options for increasing the efficiency of your agents, such as reusable snippets, auto-generated suggestions that clean up language and tone, and dashboarding tools that help you track your operation in detail.

Best Practices for Using Google Business Messages

Here, in the penultimate section, we’ll cover a few optimal ways of utilizing Google Business Messages.

Reply in a Timely Fashion

First, it’s important that you get back to customers as quickly as you’re able to. As we noted in the introduction, today’s consumers are perpetually drinking from a firehose of digital information. If it takes you a while to respond to their query, there’s a good chance they’ll either forget they reached out (if you’re lucky) or perceive it as an unpardonable affront and leave you a bad review (if you’re not).

An obvious way to answer immediately is with an automated message that says something like, “Thanks for your question. We’ll respond to you soon!” But you can’t just leave things there, especially if the question requires a human agent to intervene.

Whatever automated system you implement, you need to monitor how well your filters identify and escalate the most urgent queries. Remember that an agent might need a few hours to answer a tricky question, so factor that into your procedures.

This isn’t just something Google suggests; it’s codified in its policies. If you leave a Business Messages chat unanswered for 24 hours, Google might actually deactivate your company’s ability to use chat features.

Don’t Ask for Personal Information

As hackers have gotten more sophisticated, everyday consumers have responded by raising their guard.

On the whole, this is a good thing and will lead to a safer and more secure world. But it also means that you need to be extremely careful not to ask for anything like a social security number or a confirmation code via a service like Business Messages. What’s more, many companies are opting to include a disclaimer to this effect near the beginning of any interactions with customers.

Earlier, we pointed out that Business Messages supports end-to-end encryption, and having a clear, consistent policy about not collecting sensitive information fits into this broader picture. People will trust you more if they know you take their privacy seriously.

Make Business Messages Part of Your Overall Vision

Google Business Messages is a great service, but you’ll get the most out of it if you consider how it is part of a more far-reaching strategy.

At a minimum, this should include investing in other good communication channels, like Apple Messages and WhatsApp. People have had bitter, decades-long battles with each other over which code editor or word processor is best, so we know that they have strong opinions about the technology that they use. If you have many options for customers wanting to contact you, that’ll boost their satisfaction and their overall impression of your contact center.

The prior discussion of trivial inconveniences is also relevant here. It’s not hard to open a different messaging app under most circumstances, but if you don’t force a person to do that, they’re more likely to interact with you.

Schedule a Demo with Quiq

Google has been so monumentally successful its name is now synonymous with “online search.” Even leaving aside rich messaging, encryption, and everything else we covered in this article, you can’t afford to ignore Business Messages for this reason alone.

But setting up an account is only the first step in the process, and it’s much easier when you have ready-made tools that you can integrate on day one. The Quiq conversational AI platform is one such tool, and it has a bevy of features that’ll allow you to reduce the workloads on your agents while making your customers even happier. Check us out or schedule a demo to see what we can do for you!

Request A Demo

Retrieval Augmented Generation – Ultimate Guide

Posted on February 23, 2024November 21, 2024 J.R. Rettenmeyer

A lot has changed since the advent of large language models a little over a year ago. But, incredibly, there are already many attempts at extending the functionality of the underlying technology.

One broad category of these attempts is known as “tool use”, and consists of augmenting language models by giving them access to things like calculators. Stories of these models failing at simple arithmetic abound, and the basic idea is that we can begin to shore up their weaknesses by connecting them to specific external resources.

Because these models are famously prone to “hallucinating” incorrect information, the technique of retrieval augmented generation (RAG) has been developed to ground model output more effectively. So far, this has shown promise as a way of reducing hallucinations and creating much more trustworthy replies to queries.

In this piece, we’re going to discuss what retrieval augmented generation is, how it works, and how it can make your models even more robust.

Understanding Retrieval Augmented Generation

To begin, let’s get clear on exactly what we’re talking about. The next few sections will overview retrieval augmented generation, break down how it works, and briefly cover its myriad benefits.

What is Retrieval Augmented Generation?

Retrieval augmented generation refers to a large and growing cluster of techniques meant to help large language models ground their output in facts obtained from an external source.

By now, you’re probably aware that language models can do a remarkably good job of generating everything from code to poetry. But, owing to the way they’re trained and the way they operate, they’re also prone to simply fabricating confident-sounding nonsense. If you ask for a bunch of papers about the connection between a supplement and mental performance, for example, you might get a mix of real papers and ones that are completely fictitious.

If you could somehow hook the model up to a database of papers, however, then perhaps that would ameliorate this tendency. That’s where RAG comes in.

We will discuss some specifics in the next section, but in the broadest possible terms, you can think of RAG as having two components: the generative model, and a retrieval system that allows it to augment its outputs with data obtained from an authoritative external source.

The difference between using a foundation model and using a foundation model with RAG has been likened to the difference between taking a closed-book and an open-booked test – the metaphor is an apt one. If you were to poll all your friends about their knowledge of photosynthesis, you’d probably get a pretty big range of replies. Some friends would remember a lot about the process from high school biology, while others would barely even know that it’s related to plants.

Now, imagine what would happen if you gave these same friends a botany textbook and asked them to cite their sources. You’d still get a range of replies, of course, but they’d be far more comprehensive, grounded, and replete with up-to-date details. [1]

How RAG Works

Now that we’ve discussed what RAG is, let’s talk about how it functions. Though there are many subtleties involved, there are only a handful of overall steps.

First, you have to create a source of external data or utilize an existing one. There are already many such external resources, including databases filled with scientific papers, genomics data, time series data on the movements of stock prices, etc., which are often accessible via an API. If there isn’t already a repository containing the information you’ll need, you’ll have to make one. It’s also common to hook generative models up to internal technical documentation, of the kind utilized by e.g. contact center agents.

Then, you’ll have to do a search for relevancy. This involves converting queries into vectors, or numerical representations that capture important semantic information, then matching that representation against the vectorized contents of the external data source. Don’t worry too much if this doesn’t make a lot of sense, the important thing to remember is that this technique is far better than basic keyword matching at turning up documents related to a query.

With that done, you’ll have to augment the original user query with whatever data came up during the relevancy search. In the systems we’ve seen this all occurs silently, behind the scenes, with the user being unaware that any such changes have been made. But, with the additional context, the output generated by the model will likely be much more grounded and sensible. Modern RAG systems are also sometimes built to include citations to the specific documents they drew from, allowing a user to fact-check the output for accuracy.

And finally, you’ll need to think continuously about whether the external data source you’ve tied your model to needs to be updated. It doesn’t do much good to ground a model’s reply if the information it’s using is stale and inaccurate, so this step is important.

The Benefits of RAG

Language models equipped with retrieval augmented generation have many advantages over their more fanciful, non-RAG counterparts. As we’ve alluded to throughout, such RAG models tend to be vastly more accurate. RAG, of course, doesn’t guarantee that a model’s output will be correct. They can still hallucinate, just as one of your friends reading a botany book might misunderstand or misquote a passage. Still, it makes hallucinations far less prevalent and, if the model adds citations, gives you what you need to rectify any errors.

For this same reason, it’s easier to trust a RAG-powered language model, and they’re (usually) easier to use. As we said above a lot of the tricky technical detail is hidden from the end user, so all they see is a better-grounded output complete with a list of documents they can use to check that the output they’ve gotten is right.

Applications of Retrieval Augmented Generation

We’ve said a lot about how awesome RAG is, but what are some of its primary use cases? That will be our focus here, over the next few sections.

Enhancing Question Answering Systems

Perhaps the most obvious way RAG could be used is to supercharge the function of question-answering systems. This is already a very strong use case of generative AI, as attested to by the fact that many people are turning to tools like ChatGPT instead of Google when they want to take a first stab at understanding a new subject.

With RAG, they can get more precise and contextually relevant answers, enabling them to overcome hurdles and progress more quickly.

Of course, this dynamic will also play out in contact centers, which are more often leaning on question-answering systems to either make their agents more effective, or to give customers the resources they need to solve their own problems.

Chatbots and Conversational Agents

Chatbots are another technology that could be substantially upgraded through RAG. Because this is so closely related to the previous section we’ll keep our comments brief; suffice it to say, a chatbot able to ground its replies in internal documentation or a good external database will be much better than one that can’t.

Revolutionizing Content Creation

Because generative models are so, well, generative, they’ve already become staples in the workflows of many creative sorts, such as writers, marketers, etc. A writer might use a generative model to outline a piece, paraphrase their own earlier work, or take the other side of a contentious issue.

This, too, is a place where RAG shines. Whether you’re tinkering with the structure of a new article or trying to build a full-fledged research assistant to master an arcane part of computer science, it can only help to have more factual, grounded output.

Recommendation Systems

Finally, recommendation systems could see a boost from RAG. As you can probably tell from their name, recommendation systems are machine-learning tools that find patterns in a set of preferences and use them to make new recommendations that fit that pattern.

With grounding through RAG, this could become even better. Imagine not only having recommendations, but also specific details about why a particular recommendation was made, to say nothing of recommendations that are tied to a vast set of external resources.

Conclusion

For all the change we’ve already seen from generative AI, RAG has yet more more potential to transform our interaction with AI. With retrieval augmented generation, we could see substantial upgrades in the way we access information and use it to create new things.

If you’re intrigued by the promise of generative AI and the ways in which it could supercharge your contact center, set up a demo of the Quiq platform today!

Request A Demo

Footnotes

[1] This assumes that the book you’re giving them is itself up-to-date, and the same is true with RAG. A generative model is only as good as its data.

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

Featured Resource

AI Readiness Self-Assessment

Featured Resource

AI Readiness Self-Assessment

What Is Customer Retention?

Why Is Customer Retention Important?

Calculating Customer Retention

8 Customer Retention Strategies That Work

1. Good Values Build Good Relationships

2. Empower Your Customer Service Team to Build Trust

3. Make Yourself Transparent and Easy to Work With

4. Meet Your Customers Where They Are

5. Prioritize Quick Turnarounds

6. Be Sure to Personalize Your Communications

7. Let Customer Data Work for You

8. Reward Loyalty

Building Customer Relationships

What is Customer Service?

Why is Customer Service Important?

What Are Examples of Good Customer Service?

Automation in Customer Service

Examples of Automated Customer Service

Should We Automate Customer Service?

Strategies for Implementing Automated Customer Service

Assess Your Current Customer Service Needs

Choose the Right Automation Tools

Develop a Knowledge Base and Self-Service Options

Set Up Automated Responses and Workflows

Balance Automation with Human Support

Monitor Performance and Continuously Optimize

Moving Quiq-ly into the Future!

What is Artificial Intelligence?

What is Artificial Intelligence Good For?

Will AI be Dangerous?

Artificial Superintelligence and Existential Risk

Does AI Pose an Existential Risk?

What is the Biggest Concern with AI?

Ethical Challenges

Economic Ramifications

Social Impacts

Will AI Take All the Jobs?

What is the Future of AI?

What Is Generative AI?

Key Features of Generative AI

Content Generation

Data-Driven Learning

Adaptability & Versatility

Customization & Personalization

Effeciency & Automation

What Are Large Language Models?

What Are Examples of Large Language Models?

Key Features of Large Language Models

Natural Language Understanding & Generation

Scalability & Versatility:

Adaptability Through Fine-Tuning

What is Agentic AI?

What are some of the key features of Agentic AI?

Autonomous Action

Dynamic Decision Making

Goal-Oriented Behavior

Proactive Resource Gathering

Self-Improvement Through Feedback

What Are Some Examples of Agentic AI?

Now that we have explained what Agentic AI is and some of its key features, you may be wondering how businesses in various industries are using Agentic AI. Here are a few examples:

1. Personalized AI Assistants: Beyond Basic Task Execution

2. AI in Healthcare: Keeping an Eye on Your Health

3. AI That Actually Solves Customer Support Issues

How Do Agentic AI, Generative AI, and LLM’s Compare?

Key Differences Between Generative AI, LLMs, and Agentic AI

How These AI Systems Can Work Together

When to Use Generative AI, LLMs, or Agentic AI

When to Use Generative AI

When to Use Large Language Models (LLMs)

When to Use Agentic AI

Utilizing Generative AI In Your Business

5 Strategies for LLM Observability

1. Tracing Execution Paths

2. Replay Mechanisms for Faster Debugging

3. State Management & Monitoring

4. Claims Verification