Imagine having an on-hand assistant to help you give your car the ultimate clean and wash. All you need to do is ask: “Alexa, ask Kärcher info, how do I clean my car?” Or how about the ability to control your Kärcher Watering System Duo Smart Kit via voice control? Try: “Alexa, start Kärcher and open the left sprinkler valve for 60 minutes.” With Kärcher and Contentful, there are two new Alexa Skills that allow customers to control watering systems and get cleaning advice.
Kärcher is one of the world's largest manufacturers of functional, resource-conserving cleaning systems. With over 12,000 employees and three billion in revenue, they operate in more than 140 markets across the globe. Their commitment to providing the most effective tools has made them a leader in digital transformation. It’s what led them to develop Alexa Skills. Now customers can interact with their products on a new level with voice control.
The content challenge
Kärcher wanted to be the first in its field to give customers the ability to ask questions and control devices using voice control. They enlisted the innovation hub Zoi and took up the challenge. Amazon provided the framework and hardware, and Kärcher already had content to work with. But the problem of content storage, management and delivery remained.
Content models needed to meet standards of the voice provider while remaining accessible to editors. If the models weren’t built correctly, Alexa wouldn’t be able to process prompts or return the requested information. Editors needed to publish content in several languages and have long-term, easy access. The ability to update live content was also crucial.
Building Alexa Skills
In the building phase, developers and editors were able to work side-by-side in Contentful. Developers connected the GraphQL Content API and the Alexa API, which let editors manage voice content through the Contentful web app. Editors began rewriting and adapting content for voice.
With their content stored in Contentful, iterating was painless. The team did three iterations of the content model with practitioner testing. Working this way enabled them to fail fast to make necessary adjustments. They learned helpful and unexpected information this way. For example, prompts can only use a word once. Using the same word multiple times causes the Alexa to stall.
Contentful made localization easier for the team too. They were able to scale across four markets and three languages. Their content is ready for reuse in chatbots and the Kärcher IoT-enabled machines.
Kärcher created a unique experience for their customers, powered by Contentful and Amazon Alexa. Now customers can interact with Kärcher and their products in a whole new way.
Along the way, the team gained some important insights:
Test repetitively with real people. Include feedback from users who test the product from the beginning of development. This process ensures your product remains user friendly and solves actual challenges.
Voice systems are built on different content structures than traditional apps and websites. Content used in voice systems can also be used in chatbots and help pages. Limiting the content length is critical.
Minimize complexity in your content structure to reduce barriers between editors and content.