Artificial Intelligence (AI)-driven user interfaces are the most recent trend in digital transformation. For end users, voice-driven chatbots provide a streamlined interface to accomplish a task in a fun, engaging, informative, intelligent manner – and for brands, they represent a chance to engage their customers better, ultimately leading to increased loyalty and new revenue opportunities.

We know that consumers consistently gravitate towards the easiest available channel for brand interaction – even when that means moving between suppliers – and streamlined interactions with customer services can be make or break for organisations. And, with more than 50% of consumers reporting that they would rather interact with a brand over messaging than over the phone, it’s not surprising that serious companies are betting big on AI.

 When Bots Go Bad

But, it’s not quite as simple as throwing money at developing voice-activated services and watching customers gravitate to a new way of doing business. According to analyst firm Botanalytics, while a projected 35.6 million people will use voice-activated assistants at least once a month this year, 40% of bot users disengage after just one interaction. So – the stakes are high for the many brands and developers delivering audio experiences.

And, while there are many examples of good uses of this technology, there are also enough bad ones to demonstrate the risks of not taking quality seriously enough. As we’ve seen in recent bot blunders, not all chatbots are created equal. A poorly designed chatbot can easily turn a potential customer engagement into a horrible user experience.

Microsoft’s recent experience was a warning for many. In March this year, the company launched a chatbot named ‘Tay’ designed to have conversations with Twitter users, and learn how to mimic a human by copying their speech patterns. It was supposed to engage with people aged 18–24 but a brush with the dark side of the net, led by users of the notorious 4chan forum, instead taught her to tweet offensive phrases and left Microsoft with a tricky damage limitation exercise.

Facebook, too, was forced to admit the limitations of its foray into chatbots on its messenger platform when the bots deviated from the script and started communicating in a language which wasn’t comprehensible. And, unlike Microsoft’s experience, which led to a bit of brand damage, the Facebook blunder went one stage further, causing panic – as dramatic headlines painted a scary picture scary versions of what a future with advanced artificial intelligence may hold. “Facebook AI creates its own language in creepy preview of our potential future”, and “Creepy Facebook bots talked to each other in a secret language” reported the newspapers. And although many of the Facebook chatbot headlines exaggerated what actually happened, this example shows just how high the stakes are, and reminds us of the pressure to get it right.

Getting The Basics Right

So, how do companies assure the quality of service which is so crucial in maintaining customer relationships, building their business and managing their reputation?

The short answer is it isn’t easy – but for many, simplicity is the crucial starting point. While Cortana, Siri and Alexa might eventually develop “ask me anything” capabilities, without unlimited budgets and huge development teams, it’s better to deploy a specific, targeted bot to engage your audience. And of course, brands should focus on repetitive tasks or those that might create unexpected delight, rather than those they see once a year or once a quarter.

So, my message to organisations is to set clear goals and identify the use cases for your chatbot. Don’t attempt to address problems beyond your scope. Instead, manage customer expectations by keeping the conversation within your comfort zone. And, remember that strong natural language engines are best to deliver a voice, tone and syntax that your customers are used to, and that’s accessible and easy.

But, of course, however simple your objective is, and however rudimentary you want your chatbot to be, like any other emerging technology, chatbots inevitably add complexity to applications. A growing set of call centre functions, together with the difficulty of processing open-ended conversations, means that the development of this type of application is extremely complicated. Development teams are required to integrate an AI engine (like IBM Watson), together with a speech engine (such as Nuance) to power these capabilities – and they must work hard to create a platform where these different systems can work together to power a seamless customer experience.

Overcoming Challenges With Continuous Testing

For me, continuous testing is the answer to delivering flawless experiences at the speed of today’s market. Any developer burned by late night de-bugging appreciates a robust testing suite, and its ability to ensure well-functioning code and developer sanity. Continuous testing allows developers to iterate faster, cheaper, and with confidence that they’re not introducing new bugs along the way.

For many teams, initial testing efforts are manual – it’s not an oversimplification to imagine several engineers in a room talking to “Kate” using their smartphone, trying to find out the balance of their current bank account or inquiring about insurance options. But, automation is critical in quality assurance. Moving voice and chatbot testing from lengthy manual processes to automated systems is the best way to increase the effectiveness, efficiency and coverage of testing. And – simply – having an automated solution for testing means you’ll test earlier and more often.

Embedding Test Processes Throughout The Development Lifecycle

By embedding testing throughout the development process, uncertainty is reduced and feedback loops are made smaller, ensuring that development teams’ assumptions are correct and that they’re building in the right direction. In chatbot technology, just like any other software product, the earlier quality issues are dealt with; the less focus is taken from teams’ primary goal of building really valuable services.

Agile development methods are also a key component in ensuring speed – and in chatbot technology, velocity is critical to introducing the new innovative capabilities which help enterprises stay one step ahead of competition. The need for speed means that agile development, and automated processes, is a must-have rather than a nice to have.  Manual testing means slowing down feedback to developers after an issue has been introduced – and makes the development process cumbersome and unnecessarily extended.

A Bright Future, With The Right Testing

So, I believe that voice technology is going to fundamentally change the way users interact with applications. But deploying software robots that are truly helpful, and not just annoying or useless – or even scary – takes some savvy.

Like the old saying that a jack of all trades is a master of none, so are chatbots. I believe that instead of building a general purpose bot, like Siri, that answers everything, organisations must focus on specific high-value use cases. Even if the bot does just one thing right, it’s good enough for users – but if the user experience is poor, brand reputation can be irretrievably damaged.

The companies who get it right be those who start from firm foundations – investing in agile development, automated processes – and software which can help to put testing first – right at the heart of innovation.