It’s hard to imagine where today’s businesses would be without conversational AI. This technology, which powers both chatbots and conversational IVR systems, proved essential for navigating a changing service economy through a global pandemic.

Even before COVID-19, Gartner predicted that 70% of white-collar workers would interact with conversational AI platforms every day by 2022. The market for this technology is now expected to grow at a compound annual growth rate (CAGR) of 21.8%, reaching $18.4 billion by 2026.

This is thanks, in no small part, to how much this technology has improved in recent years. Chatbots, in particular, can now support the customer experience in many ways, enabling more customer self-service and reducing the demand on human agents.

Nonetheless, success is not a given when contact centers deploy chatbots and other conversational AI solutions. A chatbot comes with powerful AI capabilities, but it still hasn’t been tailored to fit your needs or tested in your business. Before contact centers take the plunge, they must consider what it really takes to ensure their conversational AI solutions will support and enhance the customer experience.

The growing demand for chatbots in the contact center

In large part, contact center executives don’t need to be convinced that they should adopt conversational AI in the form of either chatbots or intelligent voice assistants. Most are overly eager to bring these solutions into the mix. According to Canam Research, 78% of contact centers planned to deploy AI by 2023, with the largest portion (55%) pointing to chatbots as their primary AI solution. The CAGR for chatbots is expected to grow even faster than conversational AI in general, at 30.29% from 2022–2027.

There are good reasons for this, too. Across the board, contact center executives see the fruits of deploying chatbot solutions. A recent survey of Fast Company Executive Board members noted that adding a chatbot solution to their website enhanced customer engagement, accelerated service, enhanced personalized support, and increased customer satisfaction — just to name a few outcomes.

These positive results are encouraging, but that doesn’t mean chatbots and other conversational AI technologies are now flawless. They still fall short in many ways, from misinterpreted customer intents to delayed handoffs and security failures. And the resulting poor customer experiences can lead to customer churn and other negative impacts on a brand. These possibilities should make any contact center executive pause before jumping on the chatbot bandwagon unprepared.

The chatbot testing conundrum

That’s not to say contact center leaders shouldn’t embrace this technology — only that they should do it in the right way. As responsive and smart as AI is, it’s still limited by its programming. Ultimately, chatbot misfires still occur because bots can’t possibly account for all potential human interactions. The nuances and quirks of human communication are so vast and varied that there’s no way to prepare a chatbot for all possibilities out of the box.

Consider, for instance, how many possible ways someone could ask a chatbot to order a vegetarian pizza.  They may ask for a “veggie pizza,” a “pizza with no meat,” a “meatless pizza,” or use one of any number of other phrases. On top of that, any given person might bring their own quirks, like spelling errors, colloquial ways of saying something, limited tech capabilities — you name it. How do you know if your bot is capable of handling all these variations and nuances? You need to test it.

But truly testing for all these and the many other options for how someone could order pizza is an extensive job. Doing it manually would require many hours, or possibly even days, first to come up with the types of tests to run and then to run them. To do it efficiently, you need a solution that can accomplish all the necessary steps for you — a testing platform that allows you to quickly and efficiently expose these limitations so you can send the bot back to development and teach it new skills.

AI testing AI: the true path to flawless CX

Fundamentally, this kind of testing must cover the entire process so your testers don’t have to test your chatbots manually or spend hours developing test cases.

It means testing from end to end with automated natural language processing (NLP) score testing, conversational flow testing, security testing, performance testing, and chatbot monitoring. Ideally, the testing process should be simple and intuitive, with no coding, scripting, or programming involved.

Let’s return to the veggie pizza example. It would take a person (or a team of people) an incredibly long time to come up with all the ways someone could order their veggie pizza; and even then, they’d probably miss some. The only way to effectively come up with all possibilities would be to leverage AI to generate the test data. AI could select a question, such as “Can I have a vegetarian pizza,” and then automatically generate a list of ways to say the same thing. It could then automatically test the chatbot with those variations to see how it responds.

Going a step further, how many different ways could a person actually say each of those variations? AI can be used to further drill into the unique human quirks that different customers might bring to an interaction. For instance, AI could add layers to testing for customers who type sloppily, type in all caps, misuse homophones, add extra spaces or emojis, and more. “Pizza with no meat” could then become “pizza with no meet,” “PIZZA NO MEAT,” and any number of other possibilities.

These are just examples, but what’s important is that your testers don’t have to come up with all these options or run the tests themselves. You need a testing solution that will do it for them, with minimal manual effort. What you want is, effectively, AI testing AI so you can run these kinds of comprehensive, detailed tests much more quickly and frequently. This allows your testers to expose more chatbot weaknesses so your developers can teach and improve your bots more often and with greater precision, ultimately providing a better-quality experience for your chatbot using customers.

Contact center executives’ instincts are right: Investing in chatbots is a smart move. But doing so without adequate testing support could lead to more harm than good. Cyara Botium does exactly what we have described here and can provide the testing support your contact center’s chatbot technology needs. Learn more and try a demo to see for yourself.

Artificial Intelligence, Machine Learning

By Milan Shetti, CEO Rocket Software

In today’s volatile markets, agile and adaptable business operations have become a necessity to keep up with constantly evolving customer and industry demands. To remain resilient to change and deliver innovative experiences and offerings fast, organizations have introduced DevOps testing into their infrastructures. DevOps environments give development teams the flexibility and structure needed to drive productivity and implement early and often “shift left” testing to ensure application optimization.

While DevOps testing ecosystems require cloud technology, DevOps modernization software has allowed businesses that utilize mainframe infrastructure to successfully implement DevOps testing processes into their multi-code environments. However, introducing DevOps to mainframe infrastructure can be nearly impossible for companies that do not adequately standardize and automate testing processes before implementation.

The problem with unstructured manual testing processes

The benefits of DevOps testing revolve around increased speed and flexibility. In order to reach the full potential of these benefits and ensure a successful DevOps adoption, organizations should work to unify testing operations and eliminate any threats to productivity long before implementation begins. 

While it is important to equip developers with tools they are comfortable with, businesses working within multi-code environments must shift away from processes that require multiple vendors or lack integration. Operations that force development teams to jump from software to software to perform tasks create a complicated testing environment that can slow processes and create a disconnect between teams and departments. 

Manual testing also creates barriers to optimizing DevOps. While manual processes will still play an essential role in Quality Assurance (QA) testing, the potential for human error and the tedious, time-consuming tasks that come with manual testing make it impossible to create the speed and accuracy required for DevOps testing. And, if your testing is done using a specific developer script, you’re likely not capturing key metrics to improve your software development lifecycle, such as how the code changes the database. DevOps and true “shift left” testing environments demand structure and flexibility throughout operations that can only be achieved through standardization and automation.

Elevating testing with standardized and automated processes

To ensure successful DevOps implementation, businesses must start with an entire audit of their current operations and value stream — which is all the activities required to turn a customer request or need into a product or service. In doing so, teams can determine which software or processes create disconnects or slow operations and where automation can be integrated to enhance speed and accuracy.

Opting for vendors that offer user-friendly, code-agnostic and highly comprehensive DevOps platforms enable teams to create a central point of visibility, reporting and collaboration for processes. This standardized approach eliminates silos between teams, minimizes onboarding and allows teams a common means to rapidly commit, document and test changes to code and applications. Integrating systems and operations into a unified DevOps environment allows development and QA teams to track and schedule testing times between departments effortlessly.

From there, development teams should look to automate as many testing processes as possible. Leveraging automation in testing allows teams to implement automatic, continuous testing that eliminates human error and ensures all bugs are squashed before production. Teams can create multiple test environments and processes like unit testing, integration testing and regression testing. Standardization allows multi-code testing to be done with greater predictability and by different people — reducing the reliance on a few gifted developers and creating a more stable production phase.

Development teams can also create knowledge bases of automated testing templates to quickly pull and use or adjust to fit new and evolving testing needs. And, by leveraging automated DevOps tools, teams can configure software with controls that automatically test and vet any new coding introduced into the environment to quickly identify and address any bugs in the code or changes to the application.

The future of the mainframe and DevOps testing

A recent Rocket survey of over 500 U.S. IT professional businesses showed that the mainframe is here to stay, with more than half of the companies (56%) stating the mainframe still makes up the majority of its IT infrastructure due to its security and reliability. Thanks to highly integrative and intuitive DevOps modernization software, multi-code environments can reap the benefits of increased productivity and enhanced innovation through continuous “shift left” testing methods.

Just as the mainframe continues to modernize, so too does DevOps modernization software. Future DevOps testing software looks to leverage Artificial Intelligence (AI) and Machine Learning (ML) technology to further strengthen and streamline testing environments. Organizations like Rocket Software are working to develop technologies that use AI to study testing processes to help teams identify where testing is required and what needs to be tested more accurately. ML software will be used to track relationships in testing environments to identify patterns that help teams predict future testing needs and take a more proactive approach.

As agility and speed become more important in today’s digital market, the ability of teams working within multi-code environments to implement DevOps testing into operations will become a greater necessity. Businesses that standardize processes and utilize automation throughout testing will set their teams up for success. By creating structured and flexible DevOps testing environments, teams will enhance innovation and increase speed to market to help their business pull ahead and stay ahead of the competition.

To learn more about Rocket Software’s DevOps tools and solutions, visit the Rocket DevOps product page.

Software Development