To enable Alexa users to easier find skills among 30,000 others, Amazon has introduced a new feature that lets users ask questions to receive skill recommendations.
When users say “Alexa, I need a ride,” for instance, the voice assistant will suggest skills like Uber or Lyft; when users say “Alexa, help me cook dinner,” skills like Allrecipes or Food Network may be suggested.
On the development side, the feature is called the CanFulfillIntentRequest interface. Alexa skill developers in the U.S. can already add questions for their skills which they may be able to answer to fulfill needs.
It hasn’t been easy for Alexa users to discover new skills. Although they could browse in the app to find new skills. it is not a smooth user experience as it’s a voice-centric application.
The new feature can benefit both Alexa users and developers – allowing users to find useful skills in an easier way while making developers’ work more visible to users.
“Alexa combines this information (CanFulfillIntentRequest) with a machine-learning model to choose the right skill to use when a customer makes a request without an invocation name. As a result, customers find the right skill faster, using the search terms they say most naturally,” Amazon says in an announcement.
Google Assistant, on the other hand, provides a feature called Implicit Invocation, which allows users to invoke the Actions without saying its name. Its function is similar to Amazon’s description of CanFulfillIntentRequest. Both have the same goal of recommending voice applications to users.
Amazon hasn’t mentioned whether Alexa developers will be able to track the amount of traffic generated by Alexa referrals.
Amazon also didn’t specify whether skill recommendations will differ for those using Echo speakers and those using Echo devices with a screen.
The CanFulfillIntentRequest interface is now in beta. Alexa developers can try the new feature out and provide feedback to the company.