Here's what Windows Phone's rumored digital assistant needs to win you over
Microsoft has packed a wealth of features into the Windows Phone platform. It has live tiles that keep you constantly privy to what’s happening, notifications on the lock screen, and even Office integration. But it still lacks one crucial element that has helped both Android and iOS rise to the top: an all-knowing personal digital assistant.
Let’s face it, Windows Phone 8’s current offering pales in comparison to Siri and Google Now. There’s some light at the end of the tunnel, though: Recent rumors suggest that Windows Phone 8.1 will be unveiled at the Build conference in April, and that a key feature will be a new voice assistant, code-named Cortana. You know, like Master Chief’s AI sidekick in the Halo franchise. In fact, rumors have it that the new assistant will even be voiced by Jen Taylor, the popular voice actress who has played Cortana in all the Halo games.
The service is expected to do more than respond to simple voice commands. And although we don’t have much concrete info to go on, we know the bar Microsoft has to clear. If Cortana is to be more than just Microsoft’s version of what Apple and Google did two years ago, it will need to deliver big in the following six key areas.
Personalized answers to common questions
The first thing I do when I get up every morning is ask Google Now what the weather is going to be like when I go to work. When I need to figure out what’s on the docket for the day, I simply ask Google to bring up my calendar. And then, if I need driving directions home, I can ask Google to “take me home.” Siri provides similar capabilities.
That’s a perfect example of what people want to use their smartphones for. Microsoft’s new voice assistant has to take the data on your phone (appointments, location, contacts), in the cloud (on your SkyDrive account), and from its services (Bing search, weather, traffic) and combine them all to give you simple, plainspoken personal answers.
Microsoft should consider borrowing from Apple’s Siri, too. It’s interactive, and half the fun of using Siri is hoping that it will play along with you. As the fan-made mock-up below shows, personalization doesn’t just mean displaying information that’s relevant to you, but making you feel as if the phone is someone you’re having a conversation with.
Other mock-ups suppose that users want more than just voice commands and search. They want to track diets and get recipes. They want a Wolfram Alpha for their life.
Microsoft could even get a leg up on its competitors by utilizing the Data Sense feature that’s integrated into Windows Phone 8. Imagine if you could just ask your phone, “Hey, how am I doing on data?” or “How many minutes do I have left this month?” without digging for that information in the Settings menus.
Fast-thinking, always-on listening capabilities
Currently, the Android-powered Moto X is one of the few handsets capable of listening for your command from across the room, but in my experience it seems to work best where there isn’t much surrounding noise. It also takes an extra second to launch the Google Now app, translate the message, and then do its duty of processing the query.
Microsoft should take the idea a step further by perfecting the process: Enable the phone to hear a command even in a crowded room, and then allow it to find the answer to the question immediately without launching into another application. Make the process seamless, integrated, and always available, like the voice commands on the Xbox One.
Individual app control
The ability to send text messages, give directions, and launch apps is fine and dandy, but that’s not all a digital assistant should be limited to.
Cortana should include the ability to control individual applications. For instance, if you wanted to play a song, you could simply shout out the name of the app you wanted to launch, and then the command for that specific app. This approach could even work interchangeably with various apps of the same type, such as Xbox Music and Spotify, which theoretically could both understand the command “Play playlist, Katy Perry” with one unified API, making it easy for developers to enable this feature in any app. The possibilities are endless.
A better driving mode
It’s dangerous to text and drive, but it’s also dangerous to reach down and press the button to accept a phone call, even if the call is routed through the Bluetooth-enabled speakers in your car. Although Microsoft already offers a driving mode in the latest Windows Phone update, it could utilize Cortana to let you operate the phone entirely without any finger-to-screen contact.
If you’re stuck in traffic, for example, you could command your phone to read you the last three tweets from your Twitter feed. Your Windows Phone could then dictate those tweets to you, along with the usernames. You could even ask it to find another route if you’re stuck in traffic, without your having to reach over and pan the screen for the route with more green—that’s the most inconvenient thing when you’re trying to maneuver around bumper-to-bumper traffic.
A truly next-level feature would have the phone prompt you in certain situations. If traffic is bad and the phone estimates that you won’t arrive at your next appointment on time, for instance, it could declare: “It looks like you won’t make it to your next appointment. Would you like me to call the associated phone number?” Or how about, “There’s just been an accident along your route. Would you like me to find a way around it?”
When “she” first arrived, half the fun of Siri was engaging “her” in conversations. Sometimes she would answer the most inane questions matter-of-factly, and other times she’d be poignant and aloof. Google, on the other hand, stuck with a generic female voice by default. It’s pleasant, but it doesn’t make you feel as if you’re having a conversation with your Android phone.
Now, imagine if Microsoft fuses Siri’s feminine mystique with Google’s contextual awareness—that would be the perfect personal digital assistant. And with the trademark on the name “Cortana,” the direct reference to the Halo gaming franchise should give that voice its own identity, separate from the smartphone it’s trapped in. Throughout the games, Cortana is witty, sarcastic, loyal, and curious, often wondering aloud at the things she witnesses. A little bit of that would go a long way toward making your Windows Phone feel alive.
If Microsoft really sticks with the Cortana name, it ought to hide some Halo Easter eggs in there for the fans. Ask Cortana about the Pillar of Autumn, for example, and your phone should spit back stats about the fictional ship. Tell her to “wake up the Chief,” and she should give you the release date of the next Halo game. It doesn’t make sense for Microsoft to put a lot of the games’ lore in your face when you’re using its digital assistant—its aspirations are to sell Windows Phones to a much bigger market than Halo fans—but Halo is by far Microsoft’s most important entertainment property. A healthy dose of hidden tie-ins wouldn’t go amiss.