How to Make Conversational Interfaces Speak Our Language

Paul BlundenMarch 14, 20183min0
With the advancement of Artificial Intelligence (AI) technologies, conversational interfaces are dominating the tech world and it is no surprise why; conversations are the most natural way for humans to communicate.


Products like Amazon’s ‘Alexa’ and Google’s ‘Google Home’ have made this the technology available to the masses and integrated this form of communication into people’s everyday lives.

With these interfaces becoming more common in all industries the need to make them more user-centred is essential. So how can we make artificial technologies speak our language?

User research lets us understand the capabilities and limitations of these interfaces and helps keep a focus on the core tasks users want to accomplish. It all comes down to understanding the user, their needs, frustrations and behaviours so that the design and communications can be optimised and the best experience delivered to users.

The key components of conversational interfaces

Working with conversational interfaces through projects involving artificial the intelligence we have discovered 7 areas that determine their effectiveness.

These are:

  1. Navigation – How effectively the interface offered choices to the user to speed up responses.
  2. Content – The informative value delivered by the interface to a user. (i.e. the completeness of responses provided, and when in context would meet the user’s information needs)
  3. Presentation – The tone of voice and the cohesiveness of the responses with expected behaviour/brand image.
  4. Function – Testing the efficiency with which the AI solves a problem (user request), the goal being to use the least number of questions to provide responses.
  5. Feedback – Measuring the effectiveness of recommendations provided in case of an error.
  6. Personalisation – Whether the AI is able to remember historical interactions, and the user's preferences to improve its understanding of current context.
  7. Evolution – The increase in intelligence over time.

By evaluating AI driven conversational interfaces against these criteria we can understand how to make them more user centred and more effective. Whichever method you choose, the key is to always test your conversational interface with these areas and throughout development before taking it to market.
An effective user experience will be the most important element of the success of your product.

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *