18 September 2021 Luke Goldsworthy

Artificial Intelligence and the Development of Chatbots

Photo by Alex Knight on Unsplash

Chatbots are an increasingly important part of the online sales experience, enabling automated interactions with potential customers, providing everything from information like marketing videos to sales receipts, to upselling through different or complementary product recommendations. In short, they give a merchant a head start to generating revenue and removing barriers to sale.

Great news for Magento users is that a free live chat agent has been part of the standard out-of-the-box offering since release 2.3.4 last year. At the time Adobe explained: “Live Chat powered by dotdigital enables merchants to increase conversion rates, and keep customers coming back with real-time engagement. All Magento 2.3.x merchants (both Magento Open Source and Magento Commerce) can receive a free live chat agent without the need for a full dotdigital Engagement Cloud license.”

Chatbots carry the advantage of not coming with the human frailties of tiredness, time off and mistakes, and they are able to act based on extensive data analysis. However, they are only as good as they are created to be. This is where Artificial Intelligence (AI) comes in. The object of AI is to effectively engage with potential customers in a way that maximises sales. As customers search for more personalised experiences, the quality of the AI behind the chatbots will have a significant impact on their success. 

What is unique about AI is its ability to make computers seem like they are human. This is done through a combination of machine learning and Natural Language Processing (NLP). Put simply, machine learning gets the chatbot to look at other interactions to determine which responses were most successful, while NLP helps it interpret human input and to provide output that is consistent with human expectations.

Without AI, a chatbot is just a FAQ lookup. But getting it wrong can leave customers feeling unvalued. “I can’t speak for all chatbot deployments in the world – there are some that aren’t done very well,” says Salesforce chief scientist Richard Socher.

“But in our case we’ve heard very positive feedback because when a bot correctly answers questions or fills your requirements it does it very, very fast… In the end, users just want a quick answer, and originally people thought they wanted to talk to a person because the alternative was to go through a ten minute menu or to listen to ten options and then have to press a button – that’s not fun and its not fast and efficient.”

As businesses look to scale, it is essential that their customer engagement can handle volatile volume demands, provide a broad scope of support across products and services, and is able to quickly respond to changes to consumer tastes. AI-powered chatbots assist businesses in meeting these demands.

Specifically in relation to retail and eCommerce chatbot use, the technology: improves the customer experience by quickly and accurately providing requested information such as product details, shipping costs and delivery times; enhances the shopping journey by offering personalised shopping advice to assist customers while on site to ultimately boost conversion and revenue; and personalises marketing communication by collecting and analysing information generated through conversations, to better understand the customer’s needs and preferences and to anticipate user behaviour with customised offers and marketing messages.

Get in touch with our team and we can talk to you about this or any eCommerce questions you may have.