top of page

Products

At Nopaque, we believe there is a space in the market to vastly improve validating the quality of customer experiences that organisations offer via telephony and chat. To do this, it is not only the functionality that needs to be tested. We are also focused on being able to test for performance and broadness of coverage.

"Heritage"

We often hear the term heritage used to describe products and services that were created a long time ago. Some of them remain valuable, more often than not, what they really are is legacy, or worse still, technical and operational debt. Consider some of the behaviours in the past that led to Marketing buying a new telephone number and expecting a new journey, for every product and service created. Now imagine being a heavily constrained contact centre engineering team, who by now have probably rotated staff long since the original journeys and numbers were created. This "Mess" can be hidden by the term heritage and it's important to understand what needs to be improved, or just stopped.

mapped IVR dtmf audio journey

To move forward and really begin providing First Point of Contact resolution to customers, these teams need to understand the starting point from which they are going to transform, by mapping out these journeys. Many of those services still operate as DTMF and/or poorly built Voice Driven menus and the documentation about them is limited. This results in what we call "IVR Entanglement" and mapping these out manually is an onerous and costly task, which doesn't create much customer value. We have seen people spend days, just mapping out a single product, it's journeys and the capabilities they provides.

Our mapping product helps to prevent this low value time drain on strained engineering teams. By creating maps automatically, engineers can begin making informed decisions about how to proceed in improving products and services, or rebuilding them with new technology, ensuring customers get the expected experience. Furthermore, our mapping tool output, forms the basis of Test Plans, vastly reducing the time it takes to create the monitoring needed to assure journeys are working as expected.

Now that our product has launched, customers are able to sign up and self-serve. Mapping out a journey is as simple as providing a number, then submitting the mapping task. Users can then interact with and explore the results helping them understand existing configuration and/or issues. We estimate this product will reduce the time it takes to map out a complex product by ~5 days.

Consultancy

Sometimes, organisations can get blinded by the internal view of what they provide to their customers. We engage with our clients by understanding what their customers are really asking for, rather than directly with what our clients ask for. By doing so, we can be sure we're providing the right service, setting a shared view on what a great experience is, using data and inbound facing tooling to unlock true customer intent.

Power vs. Constraint

It's impossible to talk about Prompt Engineering and avoid a mention of the new buzz phrase of "Generative AI". No matter, it's hear to stay and the potential it has isn't even fully understood yet. You wouldn't think constraining it would be the first topic we mention, however that's essentially what's needed to hone the benefits you can gain from using. Many of the available models like Bard, GPT-3/4 and Llama 2 are built from immense collections of data. One thing to note, is that they can contain the good and the bad. An unconstrained usage of a service in your customer interactions could have damaging and lasting impact on customers.

engineered prompt ai generative conversational

You could be just starting out, or an advanced consumer looking into building your own, however you still need to consider the intended outcome of using this in the context of positive results and experience, for your customers or your employees.

Nopaque have experience with LLMs, having used them to integrate into the products we are building, projects we've engaged with and the creation of content relevant to the clients we serve. The value within LLMs is accessed through prompts and this is where we need to look at how to constrain them. Have a read of our blog on prompting to learn more through a real word example of how to create prompts. While this is a simple example, we think it gives the reader a good basic understanding of constraining what the model responds with, and how it can be used in utilities like discerning what a customer is contacting you for. 

There are a myriad of other examples for it's use. If you're considering plugging this into your customer journeys, feel free to get in touch and talk about what you're trying to achieve.

Find out about our roadmap

If you're interested in knowing more about what we plan to offer and how we intend to deliver it, please get in touch.

Thanks for submitting!

bottom of page