Here’s how the web gets ‘conversation-optimized’

Ever since IBM’s Watson beat its first human “Jeopardy” contestants, people have been fascinated with the idea of talking to computers. In recent months, there has been lots of buzz about conversational technology — including Amazon Echo (a.k.a. Alexa), Facebook’s Messenger and Microsoft’s “Conversation-as-a-Platform.” An impressive new entrant in the field of AI-powered assistants, Viv promises to answer even the most complicated queries that include a user’s social graph and contextual information.

The real question is not whether technologies like Alexa, Viv or Messenger will replace the traditional web, but how can the web work better to supply conversational technologies with information. Individuals and companies will continue to create websites for a long time, but the technology behind websites must adapt to a world where people are regularly speaking or texting with computers.

Overall, I’m pretty optimistic about making conversational technologies work on the web. I don’t define “the web” as websites alone, but rather as any user experience that’s delivered across multiple channels and devices. New user experience and distribution platforms only come along every five to 10 years, and when they do, they cause massive shifts in the web’s underlying technology. The last big one was mobile, and the web industry adapted.

The first thing to evolve for mobile was content strategy: People optimized headlines and began designing layouts for smaller screens. Next, the technology had to evolve to keep up, with solutions emerging such as responsive design, push notifications, native application development frameworks and more. The same is true with conversational technologies; it’s first about optimizing content, and then about working on the technology to make these changes second nature.

Web developers and site builders are now contending with experiences across platforms including watches, cars, voice assistants and more. But how do we create a better two-way “conversation” between various platforms and the existing web? Luckily, many devices like Amazon Echo have fairly open developer ecosystems for testing.

My team recently built a demo for Echo based on a hypothetical supermarket chain called Gourmet Market. Gourmet Market wants its customers to not only use the website, but also Echo or push notifications to do business with them. We built a website using the content management system Drupal 8 and connected it to Amazon Echo to have her “answer” questions about which produce items were on sale. In this demo, Alexa also notified a customer via text when a certain requested item went on sale in the future. While this seems like a relatively simple user experience — ask question, get information, set notifications for future — no website offers this capability today, to the best of my knowledge.

In oversimplified terms, we taught Alexa to talk to the Gourmet Market website by programming a specific “Skill,” or custom capability. On the website’s side, a store manager can tag certain items as “on sale,” and Alexa’s voice responses will automatically and instantly reflect those changes. The store manager needs no expertise in programming — Alexa composes its response by talking to Drupal 8 using web service APIs.

Today, hardly anyone questions whether to build a mobile-optimized website. A decade from now, we’ll be saying the same thing about optimizing content for voice or chat commands. The convenience of the customer experience will be a key differentiator. As a result, no one will think twice about optimizing their websites for multiple interaction patterns, including conversational interfaces like voice and chat. Anyone will be able to deliver a continuous user experience across multiple channels, devices and interaction patterns.

Echo and other conversational technologies are proof that the web is undergoing a massive re-architecture to bring relevant content directly to the consumer. It won’t be long until music fans can use voice interfaces to get alerted when their favorite artists are touring through town and purchase tickets. Patients could automatically re-order prescriptions from the pharmacy when their supply was running low. Commuters could be told to bring an umbrella to work before having to ask their virtual assistants anything about the weather. Once we master multichannel content delivery, each new technology will become infinitely more useful to people around the world.

This article originally appeared on Recode.net.