Best

Here are the tools and techniques you need to build a chatbot.

In the mid-2000s, virtual agents and customer service chatbots received a lot of adulation, even though they were not very conversational, and under the hood they were merely composed of data exchanges with web servers. 

Nowadays, even though a huge number of examples of ‘weak AI’ exist (including Siri, Alexa, web search engines, automated translators and facial recognition) and other topics such as responsive web design are hogging the limelight, chatbots are still causing a stir. With major investment from big companies, there remain plenty of opportunities to hack the conversational interfaces of the future.

• How to design a chatbot experience

Sometimes they get a bad reputation, but chatbots can be useful. They don’t need to feel like a basic replacement for a standard web form, where the user fills in input fields and waits for validation – they can provide a conversational experience. 

Essentially we’re enhancing the user experience to feel more natural, like conversing with an expert or a friend, instead of web browser point-and-clicks or mobile gestures. The aim is that by providing empathetic, contextual responses, this technology will become embedded directly in people’s lives.

Watch the video or read on to discover a practical way to design and build a chatbot, based on a real project-intake application in a service design practice.

Chatbots are programs that mimic conversation with people using artificial intelligence. With recent advances in AI these have become much more accurate, especially when focused on a specific domain. Combine these advances with the consumer trend towards messaging —  people are now spending more time in messaging apps than in social media — and it seems we might be about to enter the age of the chatbot.